Artificial Intelligence
Why Pure Reasoning is Not Enough: Nature as the Source of Mathematical Innovation
Charanjit S. Jutla and Vimal Sharma
We advance the hypothesis that human mathematical
reasoning, constrained by both the undecidability and the computational intractability of even modest logical fragments, relies fundamentally on pattern matching from domains external to pure deduction. The most prolific reservoir of such patterns is the natural world, whose physical laws and biological systems have undergone billions of years of “pre-computation” and already exhibit surprisingly innovative solutions. To ground this claim, we trace the history of the
Fourier transform and relevant mathematics, from the vibrating string controversy to the hear equation and subsequent formalisms prevalent in mathematics. At each critical juncture, a physics problem forced the acceptance or creation of a mathematical tool that pure formal
reasoning failed to anticipate or, worse, human
reasoning had resisted. We further survey the landscape of logical complexity, from NP-hard propositional satisfiability to the non-elementary decision-procedures for monadic second-order theories, to demonstrate that even when a logic is decidable, the resources required for worst-case deduction are astronomically prohibitive. We argue that these barriers make physics-inspired pattern matching not just a historical accident but a cognitive necessity. Finally, we draw the consequence for artificial intelligence: if pure
reasoning is constitutively insufficient, then any system aiming at human-level mathematical creativity must embed a vast store of cross-domain patterns rather than rely on deduction alone. This furnishes a principled justification for the enormous scale of contemporary large
language models.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Two Black Boxes, One Solver: Encoder Probing and Decoder Attribution for Neural Multi-Attribute VRP under Hard-Mask and Recourse Decoders
Sohaib Afifi
Neural autoregressive solvers for the Multi-Attribute Vehicle Routing Problem (MAVRP) reach competitive cost but offer no per-step justification, a problem when dispatchers must validate, accept, or compare them. We open two complementary black boxes in one protocol. On the encoder side, linear probes, spontaneous-organization metrics, rank-based richness measures, and discovered-direction analyses with intervention validation characterize how the latent represents constraint families at the graph, node, and edge level. On the decoder side, three attribution methods (gradient, integrated gradients, DeepLIFT) feed three reading angles: abductive, contrastive against the best feasible alternative, and counterfactual (smallest input change that switches the action or restores feasibility). Explanations are scored on fidelity, concentration, stability, sanity, and actionability. Across six variants combining three encoders (
Attention baseline, Unimp, UnimpMoe) with two decoders (Hard-Mask, Recourse), we find that graph inductive bias improves both representational predictability and decoder sanity, that the Mixture-of-Experts encoder represents constraints in a distributed rather than axis-aligned way, and that the Recourse training regime, not merely its softer mask, produces policies that represent infeasibility usefully, exposing make-feasible counterfactuals that Hard-Mask policies fail to produce even when fed infeasible alternatives externally.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
PulmoSight-XAI: An Explainable Multi-View Attention Ensemble with Gradient Boosting Meta-Learning for Multi-Label Chest X-Ray Classification
Moshiur Rahman, Shafqat Alam and Tasnia Binte Mamun
Automated chest X-ray classification remains challenging due to severe class imbalance, co-occurring pathologies, and the loss of localized features in conventional architectures. To address these, we propose an explainable hierarchical multi-view ensemble framework for the robust classification of 14 thoracic pathologies. The framework employs view-specific training by independently modeling frontal and lateral radiographs using an ensemble of five complementary convolutional neural networks. Replacing global average pooling, a multi-scale feature fusion strategy augmented with Convolutional Block
Attention Modules (CBAM) preserves fine-grained intermediate representations while emphasizing high-level pathology-specific semantic features. To mitigate positive-negative imbalance and varying inter-class difficulty, models are optimized using a novel hybrid objective combining Asymmetric Loss with Adaptive Focal Loss. Beyond simple probability averaging, the framework incorporates a hierarchical meta-learning strategy where test-time augmentation (TTA) predictions and cross-model uncertainty measures are integrated into Level-1 gradient-boosting meta-learners (XGBoost, LightGBM, and CatBoost), followed by Level-2 stacking with optimized alpha blending. Evaluated on a large-scale CheXpert-style
dataset, the framework achieves state-of-the-art macro-average AUROC scores of 0.9319 for frontal and 0.9154 for lateral radiographs. Furthermore, comprehensive explainability analysis using seven post-hoc attribution techniques demonstrates strong anatomical consistency and clinically meaningful decision localization. By integrating architectural diversity, multi-scale
attention, hierarchical meta-learning, and rigorous explainability, the proposed framework provides a transparent, highly accurate, and clinically practical computer-aided diagnosis system for thoracic disease classification.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Regime-Conditional Stabilisation of LLM-Augmented Cooperative Multi-Agent Reinforcement Learning
Faid Keddouri, Sohaib Houhou, Aissa Boulmerka et al. (+1 more)
Large
Language Models (LLMs) offer a natural interface for translating human objectives into reward signals for cooperative multi-
agent reinforcement learning (MARL), yet the training-time dynamics of this integration remain poorly understood. We show that dynamically updating LLM-generated reward weights during off-policy MARL violates the stationarity assumption of Potential-Based Reward Shaping (PBRS) and contaminates the experience replay buffer, whose stored transitions carry reward labels computed under stale shaping weights. We characterise the result as a regime-dependent failure whose severity depends on how competent the unshaped baseline already is. To control it we propose two stabilisation strategies: a Phase-Based Freeze Schedule that enforces strict stationarity within training phases, and Exponential Moving Average (EMA) smoothing that bounds per-episode weight drift. We evaluate across three cooperative environments and five random seeds with QMIX, complemented by an exploratory VDN extension, yielding a three-regime taxonomy. In the augmentative regime (Simple Spread), where the baseline is functional (74.4 %), EMA significantly improves success to 86.7 % ($+12.3$ pp, $p<0.01$) while naive dynamic updates collapse it to 15.2 %. In the essential regime (Level-Based Foraging), where the baseline is broken (0.1 %), any shaping unlocks the task (95.9 % under EMA). In the supplementary regime (SMAC 3m), where the baseline is near-saturated (98.8 %), stabilised shaping preserves performance (99.9 %) while unstabilised shaping adds variance without gain. These findings establish reward-signal stationarity as a necessary design constraint and indicate that regime placement is a practical predictor of whether dynamic LLM shaping helps or harms.
Read the full abstract ▾
All authors Faid Keddouri, Sohaib Houhou, Aissa Boulmerka, Nadir Farhi
Artificial Intelligence · Cross-listed from cs.LG
Operator-on-F complements value-equivalence: a planning-time diagnostic for latent world models
Donna Vakalis
World-model evaluation for model-based reinforcement learning typically asks whether the learned model predicts reward and value well, which can leave planning-relevant errors in the model's latent rollouts unmeasured. We introduce a complementary diagnostic, operator-on-F, that compares a model's k-step latent pushforward to the environment's on an observable subset F, using the model's own predictor. On a TD-MPC2 size sweep over cheetah-run, reward-prediction error stays within [0.028, 0.091] for every model size - only about 3x variation - so an unnormalized reward-fit check has narrow resolution to distinguish them; the (unnormalized) Bellman residual and reward error themselves have weak relationships with return (Spearman -0.10 and -0.30). Operator error spans 0.28 to 2.62 over the same sizes. At 317M the operator error is 2.62 - an order of magnitude above the 0.28-0.36 cluster - and the planning return collapses to 0.9, while reward-prediction error (0.091) is the highest of the five but stays within the same small [0.028, 0.091] range as the rest of the sweep. The rank correlation between operator error and return loss is -0.90 (anchor-bootstrap 95% CI [-0.90, -0.70] at n=5 sizes; leave-one-out removal of any single size leaves it at -0.80 or stronger). The operator also returns informative, architecture-discriminating estimates in a cross-architecture comparison between TD-MPC2 and a pure-SSL latent world model. The operator diagnostic complements value-equivalence rather than replacing it.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
Robustness Verification of an Autonomous Underwater Vehicle-based Plankton Classifier
Abdelrahman Sayed Sayed, Pierre-Jean Meyer, Asgeir J. Sørensen et al. (+1 more)
The assessment of planktonic standing stocks and microorganism structures is critical for understanding upper ocean biological processes. Currently, autonomous
underwater vehicles (AUVs) equipped with in-situ optical imaging and artificial intelligence (AI) methods offer a promising solution for persistent surveillance, mapping and monitoring of planktonic life. However, current AI methods often lack robustness in dynamic, unstructured environments, where environmental noise and non-biological artifacts lead to frequent misclassifications. Standard convolutional neural network (CNN) classifiers often struggle with such conditions, leading to misclassifications that require time-consuming manual validation by marine biologists. To address this issue, we propose a novel robustness verification framework for in-situ plankton classifiers based on reachability analysis. We also introduce a continuous-time neural ordinary differential equation (neural ODE) classification model leveraging the high-resolution imaging capabilities of the SilCam particle imager. In this paper, we demonstrate the effectiveness of the proposed framework by formally verifying the robustness of the neural ODE model against environmental perturbations. We demonstrate that our verification framework acts as an automated filter providing formal guarantees of model stability against ambiguous data, thereby improving the reliability of autonomous sampling and reducing the post-processing workload.
Read the full abstract ▾
All authors Abdelrahman Sayed Sayed, Pierre-Jean Meyer, Asgeir J. Sørensen, Mohamed Ghazel
Artificial Intelligence · Cross-listed from cs.LG
A Deep Learning-based surrogate model for Severe Accidents in nuclear reactors using ASTEC
Alessandro Longhi, Danny Lathouwers and Zoltán Perkó
Integral codes like the Accident Source Term Evaluation Code (ASTEC) are powerful tools to study the physics of Severe Accidents (SAs) in
nuclear reactors. Real time SA simulators can also be helpful in training operators of
nuclear plants to react correctly to malfunctions. However, SA simulators can take up to several days per simulation, making their use infeasible for real time applications. In this work we show how to speed up a SA simulator with a fast, Deep Learning based (DL), surrogate model (SM). The SM is built as a combination of a dimensionality reduction stage, via an AutoEncoder, and a time-stepping stage, via a Neural Ordinary Differential Equation. The data on which the SM is trained are obtained from the ASTEC simulator, by sampling a set of operator actions for station blackout (SBO) and loss-of-coolant accidents (LOCA). The objective of the developed SM is to approximate multiple spatio-temporal fields for the thermal-hydraulic physics, core degradation, and fission product release modules in ASTEC's vessel domain. The SM predicts simultaneously around $80$ different physical variables (both scalar and fields), maintaining a stable autoregressive rollout up to $50$ thousand time steps. In addition, the AutoEncoder achieves a dimensionality reduction by a factor of over $300$, which allows the SM to predict up to $40$ hours of simulation in under a minute, both on CPU and GPU. This work is the first study of the capabilities and limits of DL based surrogate modeling in approximating the challenging, highly non-linear physics of ASTEC.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SE
From Regulation to Requirements: An Automated Requirement Derivation and Explanation Pipeline
Pavithra PM Nair and Preethu Rose Anish
Ensuring software compliance with regulations such as the General Data Protection Regulation (GDPR) and the Artificial Intelligence Act (EU AI Act) poses a significant challenge, as requirements engineers must translate complex legal text into actionable software requirements - a process that remains largely manual and error-prone in practice. We present an automated regulation-to-requirements pipeline that identifies requirement-bearing clauses in regulatory documents and derives system-agnostic software requirements, accompanied by plain-
language explanations, traceable to their legal sources. We evaluate the pipeline on the full clause sets of the GDPR (398 clauses) and the EU AI Act (574 clauses). For requirement-bearing clause identification, the approach achieves macro-averaged F1 scores of 0.82 and 0.78, respectively, outperforming a SetFit-based baseline. Human evaluation shows high completeness (4.60 and 4.45) and correctness (3.74 and 3.54) of derived requirements, while explanation clarity scores are near-ceiling (4.92 and 4.94) on a 1-5 scale. We implement the approach in Reg2Req, a publicly released tool that further supports requirement classification, use case seeding, cross-reference analysis, definition indexing, and a traceability
matrix to operationalize regulatory compliance in practice. A user study with 25 practitioners shows that the plain-
language explanations significantly improve comprehension of derived requirements and confidence in acting on them (p < 0.001), and that all participants would use Reg2Req as a starting point for deriving software requirements from a regulation.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Wan-Streamer v0.2: Higher Resolution, Same Latency
Lianghua Huang, Zhi-Fan Wu, Yupeng Shi et al. (+23 more)
We present Wan-Streamer v0.2, a latency-preserving upgrade of the native-streaming, end-to-end audio-visual interaction model. v0.2 keeps the v0.1 modeling formulation, but raises the interactive output stream from 192x336 to 640x368 while preserving approximately 200 ms model-side signal-to-signal latency at 25 FPS. The higher-resolution stream supports scene-grounded mid-shot
agents whose posture, gaze, hands, nearby objects, and local scene layout remain legible during real-time conversation. To support the larger visual stream without adding user-visible delay, v0.2 keeps the thinker as a single-GPU low-latency path for streaming perception, the short
language/state
Transformer pass that builds the generation cache, and final decoding. The performer becomes a multi-GPU Ulysses-style context-parallel group for the expensive next-unit latent generation. Each performer rank writes incoming K/V into a pre-sharded local cache. The long high-resolution latent
video sequence is split across ranks for denoising and gathered through Ulysses communication, while the much shorter audio latent sequence is generated without sequence sharding. In this split, the thinker's
language/state computation reaches the performer only as K/V conditioning, so no separate
language sequence has to be communicated inside the performer group. This concentrates additional hardware on visual generation while preserving the compact thinker-performer boundary, keeping total remote interaction latency at approximately 550 ms when a 350 ms bidirectional network budget is included.
Read the full abstract ▾
All authors Lianghua Huang, Zhi-Fan Wu, Yupeng Shi, Wei Wang, Mengyang Feng, Junjie He, Chen-Wei Xie, Yu Liu, Jingren Zhou, Ang Wang, Bang Zhang, Baole Ai, Chen Liang, Cheng Yu, Chongyang Zhong, Jinwei Qi, Kai Zhu, Pandeng Li, Peng Zhang, Wenyuan Zhang, Xinhua Cheng, Yitong Huang, Yun Zheng, Yuxiang Bao, Yuzheng Wang, Zoubin Bi
Artificial Intelligence · Cross-listed from physics.geo-ph
Generative wave propagator
Shijun Cheng and Tariq Alkhalifah
Seismic wavefield simulation is fundamental to seismology, but conventional finite-difference (FD) methods remain limited by numerical dispersion and stability constraints, which often require dense spatial grids and small time steps and thereby severely limit the effectiveness of iterative inversion workflows. We introduce a conditional
diffusion-based wavefield propagator that advances seismic wavefields recursively from one time step to the next. Instead of learning an unconditional data distribution of wavefield
evolution, the model is conditioned by a short history of recent wavefield time steps (snapshots), the velocity model, and the wavefield time step index, allowing it to represent the conditional transition between adjacent physical states. By training the network to directly predict the clean next wavefield snapshot, this strong physical conditioning makes it possible to replace the iterative reverse
diffusion process with a single network evaluation for each predicted snapshot. To improve stability over long recursive rollouts, we further introduce a causal time-weighted loss, in which adaptive weights, accumulated as exponential moving averages of per-snapshot training errors, emphasize training directions that are consistent with the forward propagation sequence and reduce the amplification of one-step prediction errors. Because the learned propagator is tied to the temporal spacing of the training snapshots rather than to the FD stability limit, it can advance the wavefield using a physical time step ten times larger than that required by the underlying solver. Experiments on the Overthrust, SEG/EAGE, and Marmousi models show that the proposed method accurately reproduces wavefield snapshots and shot gathers and achieves an end-to-end speedup of 2.17 x over a GPU-accelerated tenth-order staggered-grid FD implementation under matched hardware conditions.
Read the full abstract ▾
Artificial Intelligence
ResearchStudio-Idea: An Evidence-Grounded Research-Ideation Skill Suite from ML Conference Outcomes
Qihao Zhao, Yangyu Huang, Yalun Dai et al. (+8 more)
Large
language models have made research ideation increasingly accessible, yet effective idea development requires more than generating candidate directions. Researchers must ground a problem in current literature, identify meaningful bottlenecks, differentiate from existing solutions, and evaluate risks before committing to implementation. We present ResearchStudio-Idea as a reusable skill suite for this first mile of research ideation. The suite includes Paper-Search, a standalone multi-source literature search skill; Scoop-Check, a standalone prior-art collision checker for novelty claims; and IdeaSpark, the end-to-end skill that composes evidence grounding, pattern-guided generation, collision
retrieval, audit, and idea-card rendering into one workflow. IdeaSpark is constructed from a corpus of 1,947 machine learning conference papers collected from ICLR, ICML, and NeurIPS between 2021 and 2025, including Oral papers, a separately tracked high-citation subset, and rejected submissions. Analysis of these outcomes reveals 31 recurring ideation sub-patterns, consolidated into 15 reusable ideation patterns. Each pattern is operationalized as a structured card containing research contexts, bottleneck types, differentiation strategies, supporting precedents, and common failure modes. Given a research problem and an evidence bundle, IdeaSpark evaluates evidence readiness, reconstructs the surrounding research context, identifies unresolved bottlenecks, selects relevant patterns, instantiates one candidate direction, retrieves potentially conflicting prior work, and performs outcome-informed
auditing. This workflow transforms reusable ideation patterns into traceable research proposals. Blind automated-judge evaluations show that IdeaSpark consistently produces stronger research proposals than no-skill and generic-skill baselines while maintaining competitive novelty.
Read the full abstract ▾
All authors Qihao Zhao, Yangyu Huang, Yalun Dai, Lingao Xiao, Jianjun Gao, Xin Zhang, Wenshan Wu, Scarlett Li, Yang He, Yan Lu, Yap Kim Hui
Artificial Intelligence · Cross-listed from cs.CV
ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog
Lingao Xiao, Yalun Dai, Yangyu Huang et al. (+17 more)
Despite growing automation, turning a paper into a coherent poster, talk
video, and blog piece often remains a labor-intensive last mile. Recent systems increasingly generate multiple dissemination formats, but a practical workflow must also keep the outputs editable in native tools and bound into one navigable deliverable for revision and reuse. We present ResearchStudio-Reel, a native-editable dissemination workspace that binds its three artifacts into one interactive deliverable at the experience level, implemented as five skills executable in Claude Code and Codex: one shared extractor, three editable artifact generators, and one interactive convergence layer. A shared asset bundle feeds a PowerPoint poster and
video deck, plus a bilingual Word blog; rather than re-rendering the paper into a fourth format, Paper2Reel converges these already-produced artifacts at the experience level, binding poster regions,
video segments, and blog passages into one interactive viewer. Artifact-specific release checks make this delivery contract testable, and Paper2Poster additionally uses a measured-fill loop. On the Paper2Poster
benchmark, our Claude Code configuration achieves the best scores among automated systems on all three aesthetic sub-criteria and the best or tied-best scores on two of three information sub-criteria. Under two VLMjudges, it exceeds the authors' posters in average aesthetics (3.56 vs. 3.03) and wins on overall quality on 74 and 95 of the 100 papers under the two judges. The full pipeline additionally packages the native-editable source artifacts and their aligned viewer. Project is available at https://aka.ms/ResearchStudio
Read the full abstract ▾
All authors Lingao Xiao, Yalun Dai, Yangyu Huang, Qihao Zhao, Wenshan Wu, Hugo He, Ruishuo Chen, Jin Jiang, Qianli Ma, Jiahuan Zhang, Xin Zhang, Ying Xin, Yang Ou, Yan Xia, Scarlett Li, Longbo Huang, Zhipeng Zhang, Yang He, Yap Kim Hui, Yan Lu
Artificial Intelligence · Cross-listed from cs.SE
A Retrieval-Augmented Framework for Detecting and Resolving Pragmatic Ambiguities in Natural Language Requirements
Pavithra PM Nair and Preethu Rose Anish
Natural
language requirements (NLRs) are essential for bridging communication gaps among diverse stakeholders in software development. However, the inherent ambiguity in NLRs can pose significant challenges. In particular, some requirements may be misinterpreted due to varying contextual knowledge and domain-specific expectations of the stakeholders, a phenomenon known as pragmatic ambiguity. This paper presents an approach for detecting and resolving pragmatic ambiguities in NLRs. The approach leverages
retrieval-augmented generation techniques with novice, intermediate, and expert domain knowledge bases to simulate stakeholders with varying domain expertise and detect discrepancies in requirement interpretation. Candidate disambiguated requirements are generated using the expert domain knowledge base, with final validation by a requirements analyst required to ensure
alignment with the intended functionality. We evaluate the approach on two requirements specification documents from the PUblic REquirements
dataset, using four large
language models: GPT-4o-mini, Mistral-7B, Llama-3.1-8B, and Qwen2.5-7B. Detection performance is assessed using macro-averaged accuracy, precision, recall, F1, and F2 scores. The resolution quality of the candidate disambiguated requirements is measured through human evaluation of relevance, clarity, and consistency. In this initial evaluation, results show that the proposed approach can detect pragmatic ambiguities and produce candidate disambiguated requirements that are relevant, clear, and consistent with the intended system functionality. Among the evaluated models, GPT-4o-mini achieved the highest macro-averaged recall (0.75) and F2 score (0.75) for pragmatic ambiguity detection. In the resolution task, GPT-4o-mini received the highest relevance scores from human evaluators, while Mistral-7B achieved the highest scores for clarity and consistency.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies
Tianxing Chen, Yue Chen, Zixuan Li et al. (+41 more)
Generalist
robot manipulation policies have advanced rapidly, yet existing
benchmarks remain limited in systematically evaluating their capabilities. Many rely on simple, short-horizon, or skill-narrow tasks with limited capability coverage, and are often conducted only in simulation or only in the real world. Simulation enables scalable feedback but misses physical deployment challenges, while real-world evaluation is costly, time-consuming, and difficult to reproduce. We introduce RoboDojo, a unified sim-and-real
benchmark for comprehensive evaluation of generalist
robot manipulation policies. RoboDojo includes 42 simulation tasks and 18 real-world tasks covering diverse and complementary manipulation capabilities. The simulation
benchmark evaluates five dimensions: generalization,
memory, precision, long-horizon execution, and open-vocabulary instruction following, while the real-world
benchmark exposes policies to challenging physical-world deployment conditions. RoboDojo supports scalable evaluation through heterogeneous parallel simulation in Isaac Sim and provides RoboDojo-RealEval, a reproducible real-world evaluation system with remote cloud access, standardized hardware, scene reset, evaluation protocol, and deployment interface. Together with XPolicyLab, policies can be integrated once and evaluated across simulation and real-world settings with minimal adaptation. We integrate 30 policies into XPolicyLab and evaluate them on RoboDojo, establishing a public leaderboard and systematic analysis of current policy performance. The website is available at http://robodojo-
benchmark.com/.
Read the full abstract ▾
All authors Tianxing Chen, Yue Chen, Zixuan Li, Junyuan Tang, Kailun Su, Haoran Lu, Weijie Wan, Baijun Chen, Songling Liu, Haowen Yan, Honghao Su, Zhiyang Dou, Kaixuan Wang, Dandan Zhang, Yunze Liu, Yan Qin, Qiwei Liang, Qiwei Wu, Zijian Lin, Wenwei Lin, Yuran Wang, Minghua He, Tianshu Wu, Ruihai Wu, Jingquan Zhou, Kai-Chong Lei, Haibao Yu, Yuanfeng Ji, Weiyang Jin, Guanyu Lin, Xiaofan Li, Qi Xiong, Renjing Xu, Zhongyu Li, Wenhao Chai, Enze Xie, Ziwei Wang, Yao Mu, Hao Dong, Wojciech Matusik, Mingyu Ding, Wenbo Ding, Ping Luo, Masayoshi Tomizuka
Artificial Intelligence · Cross-listed from cs.LG
Covert Trait Propagation Is Representation Alignment: Mechanistic Evidence from Hidden-Channel Distillation
Kargi Chauhan and Aditya Shah
A student model trained on pure uniform noise can still inherit its teacher's digit-classification ability, provided the two share initialization. Previous work proves this transfer is guaranteed when the teacher's learning rate is small enough, but does not explain where in the network the channel lives or what sets its capacity. Working in an MLP
distillation setting on MNIST, we show these channels are not purely informational:
geometric alignment gates access to the information the channel carries. Shared initialization makes the output projection W_2 a common coordinate key, and KL gradients reshape the student's input projection W_0 until its hidden representations align with the teacher's. We call this covert trait propagation (CTP). Five experiments support this mechanism: channel closure tracks weight drift, not teacher accuracy; freezing W_0 destroys transfer while freezing W_2 leaves it intact; multi-teacher ensembles cancel out despite each teacher carrying comparable label information; and linear centered kernel
alignment (CKA) tracks student accuracy at r=0.98 across a continuous initialization sweep. Applying the same
geometric lens to cross-
token behavioral
entanglement (CTBE) in instruction-tuned LLMs, we find the effect appears to be activated by
alignment training, acting on an inherited substrate, and that the standard log-ratio metric produces an apparent frequency bias that is largely a circularity artifact.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from stat.ML
On Pairwise Quantile Regression - Statistical Guarantees and Applications
Romain Thérézien, Stephan Clémençon, Fantin Girard et al. (+1 more)
Quantile regression provides a powerful tool for summarizing the conditional distribution of a real-valued random variable (r.v.) of interest $Y$ as a function of
covariates $Z$ in cases where it shows a large dispersion with high probability, going beyond the situation where standard least square regression is informative/predictive. This article aims to extend this methodology to the pairwise setting, where the variable to be explained is a similarity score between two independent observations (e.g., pixelated ID photos used as input to biometric systems), and the explanatory variables consist of the pair of
covariates attached to these observations, such as age or hair color. We establish theoretical guarantees for solutions of this statistical learning problem, considered here as empirical minimizers of a pairwise version of the pinball loss. Leveraging sharp concentration results for $U$-processes, we prove generalization bounds and identify mild conditions under which fast learning rates can be achieved. Confirming the probabilistic analysis, experiments based on simulation data also provide solid empirical evidence of the validity of the methodology promoted here for pairwise
quantile regression. Finally, its usefulness from an application perspective is demonstrated by a detailed study aimed at analyzing errors in similarity scoring for facial recognition.
Read the full abstract ▾
All authors Romain Thérézien, Stephan Clémençon, Fantin Girard, Hamza El-Abdouni
Artificial Intelligence · Cross-listed from cs.CL
evalci: A Python Library for Statistically Rigorous Comparison of Language Model Evaluations
Shreyas K Chandrahas
The dominant practice in
language model evaluation is to report a single accuracy number per model and declare the higher one better, without testing whether the gap could plausibly be sampling noise. On
benchmarks of a few thousand items, and under temperature sampling where a model can differ from itself run to run by more than the reported gap between models, this practice routinely overstates confidence in headline claims. The statistical machinery to fix this – confidence intervals, paired significance tests, power analysis, clustered standard errors, multiple-comparison correction – is well established, but no standard, pip-installable tool packages it in the shape an evaluation actually takes: a per-item results table. We present evalci, a pure-Python library (numpy/scipy/pandas only) that turns a per-item results table into a publication-ready claim – e.g., "Model A beats Model B, $\Delta=3.1$ pts, 95% CI [1.2, 5.0], paired permutation $p=0.002$, $n=1{,}319$" – in one function call, with adapters for lm-evaluation-harness and HELM output. Every routine is validated against an independent reference (statsmodels, or brute-force exact enumeration) rather than only against itself. As a case study, we re-analyze a public comparison of nine
language models' MMLU accuracy and find that 3 of the 8 adjacent leaderboard-rank gaps are not statistically significant after correcting for the 36 pairwise comparisons the ranking implies. evalci is available at https://pypi.org/project/evalci/ (source: https://github.com/Shreyaskc/evalci, DOI: https://doi.org/10.5281/zenodo.21201815)
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Phuong Tuan Dat, Qi Li and Xinchao Wang
Diffusion large
language models (dLLMs) generate text by iteratively denoising a masked sequence, offering a parallel alternative to autoregressive models, but eliciting strong
reasoning through post-training remains difficult: supervised fine-tuning is off-policy and suffers from exposure bias, while reinforcement learning gives only sparse, sequence-level rewards and is hard to apply without tractable sequence likelihoods. On-policy self-
distillation (OPSD) offers a promising alternative, using one model as both student and teacher to provide dense,
token-level, on-policy supervision, but its effectiveness hinges on giving the teacher privileged information (PI) - typically an instance-specific ground-truth reference unavailable at inference - so the student ends up distilling a weak PI-free consensus policy that yields little improvement on dLLM
reasoning. We introduce dOPSD, which instead derives the teacher's privilege directly from the student's own denoising trajectory, evaluating masked positions using later, more-decoded steps of that same trajectory rather than an external label, so the teacher's advantage emerges from the model's own decoding process; on Dream and LLaDA, dOPSD improves both in-domain math
reasoning and out-of-domain code generation, outperforming supervised and on-policy baselines.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
UI-MOPD: Multi-Platform On-Policy Distillation for Unified GUI Agents
Niu Lian, Tongbo Chen, Zhehao Yu et al. (+8 more)
Recent advances in
multimodal foundation models and
agent systems have driven GUI
agents from single-platform task execution toward cross-platform interaction. However, unified multi-platform GUI learning remains challenging: high-quality cross-platform trajectories remain scarce, while platforms share transferable capabilities but differ in action semantics and interaction conventions. Naively mixing supervision or merging specialized models can blur native behaviors and produce imbalanced performance. To address these challenges, we construct Uni-GUI, a high-quality
dataset containing nearly 10K executable cross-platform interaction trajectories collected through a unified desktop-mobile harness. Building on Uni-GUI, we propose UI-MOPD, the first framework to introduce multi-teacher on-policy
distillation (MOPD) into unified multi-platform GUI
agent training. UI-MOPD trains a shared student on its own rollouts and dynamically routes each rollout to the corresponding platform-specialized teacher. At student-visited states, teacher guidance serves as a platform-conditioned behavioral anchor, enabling the integration of complementary desktop and mobile expertise without averaging their distinct interaction conventions. On OSWorld and MobileWorld, UI-MOPD achieves task success rates of 38.2% and 12.0%, respectively, outperforming parameter-matched integration strategies while preserving general GUI grounding. These results demonstrate that multi-teacher on-policy
distillation provides an effective approach to building unified cross-platform GUI
agents. Project page: https://elispectre.github.io/UI-MOPD/.
Read the full abstract ▾
All authors Niu Lian, Tongbo Chen, Zhehao Yu, Chengzhen Duan, Fazhan Liu, Hui Liu, Pei Fu, Jian Luan, Heng Qu, Shu-Tao Xia, Jinpeng Wang
Artificial Intelligence · Cross-listed from cs.CV
Transferability Between Understanding and Generation in Unified Multimodal Models
Jiwon Kang, Heeji Yoon, Jaewoo Jung et al. (+5 more)
Unified
Multimodal Models (UMMs) integrate image understanding and generation within a single architecture, yet how the two tasks interact remains understudied. We investigate $\boldsymbol{\mathsf{transferability}}$ in UMMs: whether training a capability on one task improves the same capability on the other without explicit supervision. Through controlled experiments, we empirically find that transferability depends on architecture-models with fully shared
transformer backbone and a unified visual encoder exhibit consistent cross-task transfer, while loosely coupled designs show little or none. Leveraging this transferability, we propose a practical training strategy. The most straightforward way to improve a target generative capability (e.g., counting) is to fine-tune generation directly, but this can degrade visual quality due to distribution shift. Instead, we train the corresponding understanding task and let it transfer into generation, which improves capability-specific generative performance while minimizing distribution shift. We validate this across three capabilities-counting, spatial relation, and text recognition/generation-showing that cross-task transferability can be systematically exploited in UMMs.
Read the full abstract ▾
All authors Jiwon Kang, Heeji Yoon, Jaewoo Jung, Jaewon Min, Minkyeong Jeon, Biyeon Hwang, Sangwon Jung, Seungryong Kim
Artificial Intelligence · Cross-listed from cs.LG
Full-Stack FP4: Stable LLM Pretraining with Quantized Projections, Optimizers, and Attention
Siyu Ding, Mingchuan Ma, Jiabo Tong et al. (+3 more)
Recent NVFP4 pretraining work has primarily optimized
Transformer linear projections, leaving persistent optimizer states, optimizer computation, and low-precision
attention forward–backward paths less explored. We present Full-Stack FP4, a modular NVFP4 framework with separate recipes for projections, AdamW states, Root/
Muon computation, and
attention. LoRA-SVD protects a compact projection subspace in BF16 while retaining full-shape NVFP4 computation, reducing the linear-only loss gap from 1.40% to 0.61%. An ordered square-root, tile-mean, and Hadamard pipeline enables stable NVFP4 AdamW momentum storage; shape-dependent coefficients and clipping stabilize direct NVFP4 Root iterations; and mixed-precision
attention retains softmax-sensitive operations in BF16. On 3B pretraining with 64B
tokens, BF16 and Full-Stack FP4 reach losses of 2.267 and 2.286, a 0.838% gap. Their average zero-shot perplexities are 26.675 and 26.665, respectively, with Full-Stack FP4 averaging 0.10 percentage points lower in accuracy. Native four-block measurements on one RTX 5090 show 2.50–2.83$\times$ Root speedups over optimized BF16 and 37.9–42.5% lower AdamW peak
memory.
Read the full abstract ▾
All authors Siyu Ding, Mingchuan Ma, Jiabo Tong, Xingrun Xing, Ziming Wang, Guoqi Li
Artificial Intelligence
Agent Step Value: Auditing Evaluation-Channel Sensitivity in Black-Box Agent Traces
Andrew Zhang and Chengzhan Li
Reusing evaluator-derived step rewards across evaluation channels raises a measurement question: does the assigned direction remain stable? We define
Agent Step Value (ASV) as a channel-indexed before/after target-margin gain and identify the state-by-channel interaction from a matched 2x2 design. Across frozen PubMed question-answering transitions, cross-channel gain signs disagree on 48.3% of comparisons, compared with 0.3% for same-channel retries. Transition interactions are nearly balanced in sign (median +0.014; 10% trimmed mean -0.033), but asymmetric negative magnitudes produce a positive direct mean and a negative generated-view mean under the empirical target mixture. Equal-target weighting preserves a negative mean interaction but not this strict mean reversal. Matched
retrieval designs localize the negative component to the generated-view coordinate and retain its direction across three sign checks that vary readout and evaluator stack. In a matched 512-
token source-contract follow-up, source-only generation restores the positive mean direction on artifact-bearing
retrievals and removes parser-detected support claims from artifact-free before-state views. These results support an explanation in which generated support inflates the pre-
retrieval baseline. The resulting audit can localize channel sensitivity and test an intervention before step rewards are reused.
Read the full abstract ▾
Artificial Intelligence
LLM-as-a-Tutor: Policy-Aware Prompt Adaptation for Non-Verifiable RL
Yujin Kim, Namgyu Ho, Sangmin Hwang et al. (+7 more)
Reinforcement learning (RL) for non-verifiable instruction following increasingly relies on LLM judges with
prompt-specific rubrics as reward signals. While recent methods adapt these rubrics to the evolving policy during training, the training
prompts themselves remain static, drawn from fixed corpora. This static approach often results in a critical misalignment between
prompt difficulty and policy capability, leaving the judge unable to recover a discriminative reward signal when
prompts fail to elicit quality variance among rollouts. To address this misalignment, we introduce LLM-as-a-Tutor, a framework that extends the LLM's role from judge to tutor: a single model serves as an examiner that pairwise-compares policy rollouts to detect non-challenging
prompts, and as a generator that appends atomic constraints to them. This append-only design monotonically raises difficulty in step with the policy's capability, producing a self-calibrating training signal without external difficulty schedules. On three complex instruction-following
benchmarks, our method consistently outperforms both policy-unaware baselines and prior policy-adaptive methods that adapt rubrics or rewrite
prompts, suggesting
prompt adaptation as a missing axis of policy-awareness in non-verifiable RL.
Read the full abstract ▾
All authors Yujin Kim, Namgyu Ho, Sangmin Hwang, Joonkee Kim, Yongjin Yang, Sangmin Bae, Seungone Kim, Jaehun Jung, Se-Young Yun, Hwanjun Song
Artificial Intelligence
MechMath Agent Team: LLM Driven Agents for Mathematical Research
Yichuan Cao, Ruichen Qiu, Junqi Liu et al. (+5 more)
AI
reasoning has become a central focus in contemporary artificial intelligence, largely driven by the success of large
language models. However, mathematical research, which is characterized by non-linear derivation paths, rigorous logical requirements, and protracted exploration cycles, poses severe challenges for existing
reasoning systems. To overcome these limitations, we present the MechMath
Agent Team (MMAT), which is a large
language model driven
agent designed to serve as a co-pilot throughout the full cycle of mathematical research. We design a tripartite Harness Architecture that decouples system responsibilities into Control, Execution, and Augmentation planes, thereby reconciling rigorous logical control with the agility demanded by open-ended research. Building upon this framework, we instantiate three specialized
agents: a Knowledge Base Manager, a Natural
Language Prover, and a Formal
Language Prover, all operating in a closed loop to produce formally certified mathematical proofs. We evaluate MMAT on open problems in Number Theory, Algebraic Complexity Theory, Differential
Algebra, Operator
Algebra, and Inequalities. Across a two-month deployment, 11 problems have been solved, demonstrating its capacity to act as a co-pilot throughout the entire research cycle. The contributions are threefold: a general decoupled Harness Architecture for multi-
agent mathematical
reasoning, its concrete instantiation in the MMAT system, and empirical validation on a diverse suite of open problems.
Read the full abstract ▾
All authors Yichuan Cao, Ruichen Qiu, Junqi Liu, Jiaqi Wang, Dakai Guo, Ruyong Feng, Lihong Zhi, Xiao-Shan Gao
Artificial Intelligence
Decentralized Aggregation of LLM Predictions via Wagering Mechanisms
Yuhong Luo, David M. Pennock and Xintong Wang
It is increasingly common to aggregate predictions from multiple LLMs, each with domain expertise or access to private tools and data, to improve collective prediction performance. In decentralized settings, aggregation weights need to be determined without access to models' private information and should remain robust to strategic reporting. We propose a family of advantage-aligned wagering mechanisms for LLM aggregation (WALLA), in which each model reports a prediction and a learned wager, and predictions are aggregated using wagers as weights. WALLA introduces a leave-one-out baseline into the net payout function, yielding three desirable properties: (1) dominant-strategy incentive compatibility of prediction under arbitrary belief structure, (2) advantage–wager
alignment, where the optimal wager is proportional to the model's expected score advantage, and (3) prediction-agnostic wager optimization, enabling decentralized learning of wager policies without requiring optimal predictions. We further instantiate two mechanism variants that trade off normality and no-arbitrage while maintaining a bounded worst-case deficit for the mechanism. Experiments on question-answering and
forecasting benchmarks across heterogeneous models and private-information settings show that WALLA matches centralized aggregation methods in predictive performance, while simultaneously achieving decentralized learning, advantage-aligned aggregation weights, uncertainty awareness, and incentive-compatible prediction.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SD
Auto-AEG: Scalable Data Construction for Open-Vocabulary Audio Event Grounding
Zihan Zhang, Xize Cheng, Wenhao Yan et al. (+9 more)
Large Audio-
Language Models (LALMs) reason fluently about sound yet struggle to localize precisely when events occur, while classical Sound Event Detection (SED) attains frame-level precision only over a closed label set. At the intersection of these paradigms lies the task of Open-Vocabulary Audio Event Grounding: predicting all time intervals of a target sound event described by an arbitrary natural
language query. Progress is bottlenecked by data scarcity: no large-scale resource provides open-vocabulary onset/offset supervision, and manual temporal annotation is prohibitively expensive. To address this, we introduce Auto-AEG, a scalable pipeline that constructs such supervision by automatic data construction and model fine-tuning. It pairs programmatically synthesized clips, which carry placement-exact ground-truth intervals for supervised cold-start, with multi-model pseudo-labels on real-world audio that supply the reward signal for reinforcement learning. Training with this pipeline yields large temporal-localization gains on AEGBench, an independent difficulty-stratified
benchmark whose annotations we release, and these gains generalize to various held-out SED and audio grounding
benchmarks. Our results show that automatically constructed data, coupled with interval-aware reward design, provides an effective data-side route to expanding the temporal localization capability of LALMs.
Read the full abstract ▾
All authors Zihan Zhang, Xize Cheng, Wenhao Yan, Tong Zhang, Dongjie Fu, Wenxu Jia, Boyun Zhang, Yongbo He, Qifei Zhang, Linjun Li, Wenshi Chen, Tao Jin
Artificial Intelligence
Nemotron-Labs-3-Puzzle-75B-A9B: Compressing Hybrid MoE LLMs
Akhiad Bercovich, Talor Abramovich, Daniel Afrimi et al. (+67 more)
We present Nemotron-Labs-3-Puzzle-75B-A9B, a compressed variant of Nemotron-3-Super optimized for interactive deployment. We designed the model to maximize server throughput under high user throughput constraints. In interactive serving workloads on a single 8xB200 node, Puzzle-75B-A9B achieves approximately 2x higher server throughput than Nemotron-3-Super at matched user throughput constraints. In ultra-long-context deployment on a single H100 GPU, the compressed model increases 1M-
token concurrency from 1 request to 8 requests. Puzzle-75B-A9B is constructed using a multi-stage pipeline that combines the Iterative Puzzle compression framework with knowledge
distillation, reinforcement learning, quantization, and a Multi-
Token Prediction head. The compression process jointly optimizes heterogeneous MoE
pruning, active parameter budget, and Mamba
pruning to improve inference efficiency while preserving model quality. We evaluate Puzzle-75B-A9B on a broad suite of
reasoning, coding,
multilingual, long-context, and agentic
benchmarks. Despite substantial compression, the model retains strong downstream accuracy relative to the parent model across a wide range of tasks. These results demonstrate that large hybrid MoE models can be substantially optimized for deployment efficiency while maintaining strong downstream capability. Our model is publicly available on Hugging Face.
Read the full abstract ▾
All authors Akhiad Bercovich, Talor Abramovich, Daniel Afrimi, Shay Aharon, Nir Ailon, Vladimir Anisimov, Omer Ullman Argov, Maor Ashkenazi, Tomer Asida, Nave Assaf, Tomer Bar Natan, Alexander Bukharin, Grzegorz Chlebus, Marcin Chochowski, Eric Chung, Mohammad Dabbah, Carlo del Mundo, Ewa Dobrowolska, Ido Galil, Yaniv Galron, Amnon Geifman, Yonatan Geifman, Izik Golan, Alex Gronskiy, Tomasz Grzegorzek, Netanel Haber, Lior Kadoch, Grzegorz Karch, Tomer Keren, Abhinav Khattar, Amir Klein, Tugrul Konuk, Roi Koren, Daniel Korzekwa, Shaun Kotek, Konstantinos Krommydas, Itay Levy, Ofri Masad, Yoav Miron, Pavlo Molchanov, Shahar Mor, Zach Moshe, Saurav Muralidharan, Najeeb Nabwani, Besmira Nushi, Mostofa Patwary, Omri Puny, Johannes Rausch, Tomer Ronen, Sepehr Sameni, Itamar Schen, Elad Segal, Daniel Serebrenik, Ido Shahaf, Soumye Singhal, Daniil Sorokin, Sharath Turuvekere Sreenivas, Marta Stepniewska-Dziubinska, Ali Taghibakhshi, Nima Tajbakhsh, Oren Tropp, Dor Tzur, Anna Warno, Yi-Fu Wu, Michal Zawalski, Jiaqi Zeng, Yian Zhang, Ran Zilberstein, Amit Zuker, Ran El-Yaniv
Artificial Intelligence · Cross-listed from cs.CV
HASSL: Hierarchy-Aware Self-Supervised Learning Framework for Single Cell Microscopy
Julius Riel, Vishwa Mohan Singh, Sai Anirudh Aryasomayajula et al. (+10 more)
Hierarchical structure is common in image data, where fine-grained clusters often merge into larger, coarser semantic groups. In biological
cell images, current self-supervised learning models often suppress this hierarchy, as coarse factors such as imaging modality can obscure finer morphological attributes in the latent space. We propose a hierarchy-aware self-supervised training framework to address this problem. Our method combines two components: a
distillation framework with a
segmentation teacher to improve morphological awareness in the latent space, and a hierarchy-aware contrastive loss based on HDBSCAN to improve decision boundaries between closely related subtypes at different hierarchical levels. Together, these components reduce the tendency of self-supervised learning to overemphasize coarse factors and instead align
embeddings with semantic and morphological cues. This yields biologically meaningful sub-clusters driven by fine morphological detail. We train and evaluate our method on a curated corpus of 2.3 million single
cells aggregated from 20 microscopy
datasets, both labeled and unlabeled, covering 208
cell classes. Our method improves over baseline and counterpart methods, increasing average top-K accuracy by 2.8%, top-9
retrieval on the
dataset with the deepest hierarchy by 6.3%, and downstream F1-score for biologically relevant drug classification from perturbed
cell morphology by 7.8%.
Read the full abstract ▾
All authors Julius Riel, Vishwa Mohan Singh, Sai Anirudh Aryasomayajula, Anuun Chinbat, Hannes Leonhard, Moritz Ladenburger, Frederik Alexander, Vishisht Choudhary, Fabio Laredo, Giacomo Masserdotti, Thorben Prein, Carsten Marr, Amirhossein Kardoost
Artificial Intelligence · Cross-listed from cs.CV
IRIS: An Intelligent Vision-Language System for Ocular Surface Diseases via Topic Tree and Scene-Driven VQA Generation
Hao Wei, Wenjin Qi, Dasen Dai et al. (+2 more)
While Large
Vision-
Language Models (VLMs) demonstrate remarkable generic capabilities, their clinical
reasoning in specialized domains like ocular surface diseases (OSDs) is severely hindered by a paucity of high-fidelity,
multimodal instruction-tuning data. To dismantle this data bottleneck, we introduce IRIS, an Intelligent Recognition and Interaction System tailored for fine-grained OSD understanding via external eye photography. First, we curate IRIS-120K, the largest and most comprehensive OSD visual question-answering (VQA)
dataset to date. Crucially, to overcome the semantic shallowness of conventional image-caption pairs, we propose a synergistic data generation paradigm to explicitly inject clinical priors. Our data engine operates via a dual-branch framework: 1) a Topic Finding Tree (TFT) that hierarchically anchors visual features to precise anatomical and pathological concepts, enforcing rigorous medical deduction logic; and 2) a Scene-driven strategy that synthesizes role-adaptive clinical dialogues to ensure pragmatic generalization. By explicitly aligning a compact 4B-parameter VLM on this structurally enriched corpus, IRIS achieves state-of-the-art performance, comprehensively outperforming both generalist and specialized medical VLMs with up to 34B parameters. Our findings underscore that structured knowledge injection profoundly prevails over sheer parameter scaling, unlocking the potential for resource-efficient, expert-level AI deployment on mobile edge devices for scalable OSD screening. Code,
datasets, and model weights will be publicly released by this repo.
Read the full abstract ▾
All authors Hao Wei, Wenjin Qi, Dasen Dai, Minqing Zhang, Wu Yuan
Artificial Intelligence · Cross-listed from cs.LG
One Framework for All: Cross-Modal Membership Inference for Generative Models
Dayong Ye, Tainqing Zhu, Kun Gao et al. (+6 more)
Large generative models across text-to-text, text-to-image, and image-to-text modalities have been shown to pose significant
privacy risks. One fundamental threat is membership inference attacks (MIA), which aim to determine whether a given data point was used in a model's training set. Although prior work has investigated MIAs against these three classes of generative models, existing approaches treat them in isolation and are not cross-applicable, thereby limiting their real-world utility. To address this limitation, we present the first comprehensive study of a unified membership inference framework that applies across text-to-text, text-to-image, and image-to-text modalities. Our approach is grounded in a key modality-agnostic observation: the output distribution of a generative model can approximate its training data distribution. Leveraging this property, we model the distributions of model-generated outputs and auxiliary non-member samples in a shared
embedding space, and perform membership inference via likelihood ratio testing. We conduct extensive experiments in a strict black-box setting under both partial-knowledge and zero-knowledge threat models, and evaluate membership inference against both fine-tuning and pre-training data. Experimental results demonstrate our approach's superior performance in comparison to existing state-of-the-art methods, which are typically optimized for a single model class.
Read the full abstract ▾
All authors Dayong Ye, Tainqing Zhu, Kun Gao, Junhao Liu, Yichuan Chen, Shuai Zhou, Hengzhu Liu, Bo Liu, Wanlei Zhou