Machine Learning
GenLimitLib: A Formal Library for Language Generation in the Limit and AI-Assisted Mathematical Research
Shuangping Li and Peng Zhang
We present GenLimitLib, a source-aligned Lean 4 library for
language generation in the limit. Introduced by Kleinberg and Mullainathan at NeurIPS 2024,
language generation in the limit studies a theoretical question motivated by LLMs: how to generate valid new strings from observed examples. This young and rapidly evolving field offers a natural testbed for studying large-scale formalization. GenLimitLib contains formal developments for 30 papers. It extracts shared definitions and reusable proof components while preserving paper-specific assumptions and statements, and records relationships across papers. In this way, GenLimitLib provides a concrete and structured view of the literature. We show through mathematical case studies and LLM experiments how our library can support both human mathematical research and AI-assisted research. Our Library: https://github.com/pengzhang91/generation-in-the-limit-lib.
Read the full abstract ▾
Machine Learning
AutoLoCo: Communication Efficient Distributed LLM Training via Adaptive Synchronization
Pengyu He, Yan Zhang, Ruien Li et al. (+1 more)
The pre-training of Large
Language Models (LLMs) is increasingly conducted across multiple data centers. As training scales to a larger number of accelerators, the fraction of time spent on computation decreases, while the fraction spent on communication increases. Therefore, frequent synchronization becomes a growing bottleneck. Local update methods reduce this cost by allowing workers to perform several optimizer steps between synchronizations. Most local update methods set the number of local optimizer steps between synchronizations before training and keep this interval fixed throughout the run. However, the best interval can change during the entire train process. If the interval and optimizer are adapted to the current training state, the communication frequency is reduced while maintaining the training performance. In this work, we introduce AutoLoCo, an adaptive training framework to reduce communication in LLM training. It adapts the local interval using scalar training statistics and corrects each outer update. Our method is motivated by two observations: 1) the appropriate local interval varies across training stages, and 2) changing the number of inner steps per interval creates a mismatch with an unchanged outer optimizer, requiring a correction to the outer update. We optimize this mismatch by correction of the outer optimizer for the momentum and the learning rate using the accumulated inner learning rate. Our experiments under communication constraints demonstrate that AutoLoCo reduces communication frequency by 27% relative to DiLoCo while maintaining training performance.
Read the full abstract ▾
All authors Pengyu He, Yan Zhang, Ruien Li, Guangwen Yang
Computer Vision
You Only Reprogram Once: Rethinking Prolonged Training for Visual Reprogramming
Zizhao Li, Mohammed Yaqoob Ansari, Xinyu Su et al. (+3 more)
Visual reprogramming is a parameter-efficient method for adapting pretrained models, yet its training can remain computationally expensive: even with a frozen backbone, visual
prompts are often optimized through the full model for hundreds of epochs. Before changing what the pretrained model sees, we ask whether we are fully using what it already tells us. We find that modeling the full source response can already yield strong downstream predictions without
prompt optimization. Motivated by this observation, we introduce You Only Reprogram Once (YORO), which constructs a downstream predictor from the frozen response space in a single forward-only traversal. Its
Bayesian Discriminant Mapping (BDM) derives a covariance-aware affine mapping from streaming class statistics, requiring no backpropagation, optimizer updates, or repeated visits to the training set. When further input adaptation helps, YORO-FP optionally refines the visual
prompt for 20 epochs. BDM also extends naturally to CLIP by treating attribute-
prompt similarities as source responses. Across three full-data settings, YORO improves average accuracy over the strongest prior gradient-free mapping by 18.4–24.4%. On 16-shot CLIP, it raises the four-backbone average from 71.4% to 77.2%. YORO-FP provides further gains on selected tasks, while validation often retains the one-pass predictor. These results suggest a different default for visual reprogramming: read out the frozen response first, and optimize the input only when needed.
Read the full abstract ▾
All authors Zizhao Li, Mohammed Yaqoob Ansari, Xinyu Su, Jiayang Ao, Joseph West, Kourosh Khoshelham
Machine Learning
Byzantine-Robust Federated Representation Learning
Leonardo F. Toso, James Anderson, Rafael Pinot et al. (+1 more)
We study
federated learning (FL) with
adversarial clients, where the goal is to minimize the average loss of the honest (non-
adversarial) clients without knowing their identity. Under heterogeneity, a single shared model parameter is statistically inappropriate: it cannot capture the distinct data-generating processes across clients, incurring an irreducible model-heterogeneity bias and severely limiting robustness to
adversarial clients (a.k.a. Byzantine-robustness). We address this problem through representation learning, where each client learns a personalized linear head, while collaboratively estimating a shared nonlinear representation through Byzantine-robust aggregation. We demonstrate that the heterogeneity among honest representation gradients is controlled by the representation error and statistical errors that decay either with the number of data samples per client ($\tau$) or the number of iterations ($T$). In particular, our non-asymptotic parameter recovery error bound reveals three terms: (i) an initialization-dependent error that goes away with $T$, (ii) finite-sample noise terms that decreases with $\tau$ and the number of honest clients, and (iii) a
stochastic gradient variance term that also reduces with $T$. Importantly, with no irreducible model-heterogeneity bias in our bounds. We extend the regression analysis to multiclass classification, and empirically validate it on CIFAR-10, FEMNIST, and School Exam Score
datasets.
Read the full abstract ▾
All authors Leonardo F. Toso, James Anderson, Rafael Pinot, Nirupam Gupta
Machine Learning
On-Policy Parameter Update Direction Underlies Generalization in LLM Post-Training
Shufan Shen, Zhongni Hou, Junshu Sun et al. (+5 more)
The strong generalization performance of on-policy post-training paradigms has motivated studies of their parameter update behaviors. However, these studies treat the observed behaviors only as byproducts in on-policy training, overlooking their potential to serve as optimization principles for improving the generalization of other paradigms such as supervised fine-tuning (SFT). To address this limitation, we investigate whether there exists a specific on-policy update behavior that can achieve such improvements. First, our analyses reveal that SFT updates parameters along consistent directions, while the on-policy paradigm continuously adjusts the direction during training. This difference inspires us to focus on the cumulative update direction of each parameter as a promising behavior. Then, we evaluate its effectiveness for improving generalization by proposing On-Policy direction-constrained Supervised Fine-Tuning (OPSFT), which constrains SFT updates to the direction identified by on-policy paradigms. The strong performance of OPSFT indicates that the generalization advantage of on-policy paradigms can be transferred to SFT through the parameter update direction. Once such a direction is identified, even SFT can generalize with its updates constrained to this direction. This finding offers two practical benefits by combining the strong generalization of on-policy paradigms with the advantages of SFT, including the high training efficiency and ability to leverage high-quality trajectories. For efficiency, we identify update directions that support strong generalization using a few on-policy training steps, and subsequently apply OPSFT to achieve high training efficiency. For leveraging high-quality trajectories, OPSFT can utilize these trajectories to continue improving a post-trained model along its update direction without disrupting the ability learned from on-policy training.
Read the full abstract ▾
All authors Shufan Shen, Zhongni Hou, Junshu Sun, Yufei Zhang, Wei Lin, Guojun Yin, Qingming Huang, Shuhui Wang
Machine Learning
Constitutional adapters: Inference-time interventions for misalignment and misuse
Adam S. Lowet and Mark Kurzeja
Training models to act in accordance with an explicitly defined set of principles, or "constitution," has shown promise as a robust and transparent mechanism for AI
alignment. However, the generality and flexibility of such methods remain unclear. Here, we show that constitution-consistent behavior can be distilled from synthetic corpora into lightweight objects (low-rank adapters and steering vectors). Despite never seeing a harmful request or jailbreak during training, such objects increase jailbreak defense success and measured
alignment – particularly at long context lengths and against multi-turn attacks, where they outperform both prompted and steered baselines. Subtracting control-trained from constitution-trained objects further accentuates these effects, yielding defenses we call "constitutional adapters" (CAs). CAs can be trained on a base model, transferred zero-shot to its post-trained checkpoint, and scaled at inference time to predictably trade off defense for benign compliance. Taken together, these results recommend CAs as a lightweight, portable, and tunable lever for mitigating misalignment and misuse in API deployments.
Read the full abstract ▾
Computer Vision
Not Every Correction Helps: Gain-Guided Continual Test-Time Adaptation
Youjia Zhang, Huiling Liu, Soyun Choi et al. (+2 more)
Continual test-time adaptation (CTTA) adapts a source model to an unlabeled test stream whose distribution may change over time. Existing TTA methods often assess prediction reliability using confidence or
entropy, which primarily reflect the model's self-certainty for the current sample. In CTTA, accumulated target observations can provide complementary evidence for correcting the source prediction, but this history may become misaligned as the target distribution changes. The key question is therefore not how much the correction differs from the source prediction, but whether and how strongly it should be applied. This paper proposes Gain-Aware INtervention (GAIN), a backpropagation-free CTTA framework guided by a simple principle: history proposes, gain decides. GAIN maintains compact target statistics to form a correction proposal and a posterior-predictive evaluator that accounts for estimation uncertainty. The resulting source-relative gain estimates the proposal's benefit and determines a sample-specific intervention strength along a continuous path through efficient one-dimensional optimization. Gain-controlled predictions then update the target statistics online, limiting the propagation of unreliable corrections, all without backpropagation, sample storage, or replay. Across five
benchmarks, our method achieves strong predictive performance, with favorable accuracy–calibration–efficiency trade-offs in continual adaptation. On ImageNet-C, for example, GAIN achieves 61.9% accuracy with near-source calibration. It remains stable under diverse and challenging continual shifts while running 15.9x faster than a representative optimization-based CTTA baseline.
Read the full abstract ▾
All authors Youjia Zhang, Huiling Liu, Soyun Choi, Jaehong Yoon, Sungeun Hong
Machine Learning
Replay the Curvature: Accurate and Scalable NVFP4 Quantization for Large Language Model Inference
Ruiyi Ding, Jie Li, Kang He et al. (+4 more)
Large
language models make weight storage and
memory traffic major inference costs, motivating low-precision formats that represent each weight with only a few bits. Such formats use a scale to map floating-point values into a small codebook; NVFP4 improves local range utilization by letting every 16 E2M1 weights share an E4M3 block scale. Choosing that scale is difficult in GPTQ because quantizing one column updates those that follow, so evaluating a block independently can misestimate its final reconstruction error. Large models pose a second challenge: full-precision weights, calibration activations, and second-order state cannot all remain on one accelerator, while assigning complete layers to devices leaves each time-consuming layer solve serial. We introduce Schur Replay, a scale-selection
algorithm that reproduces the GPTQ updates caused by each block scale and scores the resulting block error after accounting for compensation from unquantized columns. Separately, our execution infrastructure keeps only the active layer resident, tiers activations across device, host, and disk, retires full-precision layers after export, and distributes independent output rows across tensor-parallel ranks. Together, the
algorithm and infrastructure attain $99.35\%$ and $100.84\%$ question-weighted recovery from BF16 across seven
benchmarks on Qwen3.5-397B-A17B and Llama-3.3-70B-Instruct. On the 397B model, the infrastructure reduces measured per-layer time by $15.17\times$ over ModelOpt and $23.14\times$ over LLM Compressor, with lower
memory used per GPU.
Read the full abstract ▾
All authors Ruiyi Ding, Jie Li, Kang He, Ziyan Liu, Chengru Song, Yuedong Xu, Yuan Cheng
Machine Learning
Boyuan Wang, Chengyao Yu, Jiaxi Ren et al. (+3 more)
Recurrent
reasoning models have attracted growing
attention for scaling test-time computation, typically by iteratively refining latent states with shared parameters. However, these models apply each learned update with a fixed unit scale, which can be conservative when updates make persistent progress and overly aggressive when they fluctuate, limiting the benefit of additional loops. To understand how the scale should vary along the trajectory, we first analyze the sensitivity of terminal loss to recurrent update scale. We show that its temporal average admits an exact decomposition into persistent-progress and centered-fluctuation contributions. Based on this, we introduce the Trajectory Adaptive Progress-Fluctuation Scheduler (TAPS), which tracks their balance across recurrent updates and adapts the step size online. Theoretically, we establish sufficient conditions under which TAPS reduces expected terminal loss and reaches a target quality in fewer recurrent loops. Empirically, we show that TAPS improves terminal accuracy across structured
reasoning tasks without retraining. By further incorporating the progress-fluctuation principle into training, TAPS yields additional accuracy gains with up to 1.56 times wall-clock speedup at matched baseline accuracy. The broad applicability of TAPS is supported by its effectiveness across diverse recurrent architectures and inference strategies. Together, these results establish update scale as complementary control axis of recurrent inference alongside architecture and depth.
Read the full abstract ▾
All authors Boyuan Wang, Chengyao Yu, Jiaxi Ren, Hongxin Wei, Bingyi Jing, Yuxin Tao
Artificial Intelligence
RankBuffer: Efficient Ranking-Based Rewards for Open-Ended Generation
Zixuan Yang, Yiqun Chen, Qi Liu et al. (+6 more)
Open-ended generation lacks canonical answers, making pointwise rewards difficult to calibrate for group-based reinforcement learning. Directly ranking same-query rollouts provides a more suitable relative reward signal, but existing ranking-based reward methods can incur substantial judging cost. We introduce RankBuffer, which maintains an ordered, query-specific buffer of previously judged responses as a reusable quality scale. Each rollout is first inserted into an anchor interval through an independent coarse judgment, after which only rollouts assigned to the same interval undergo local fine ranking. The resulting complete order is converted into bounded rank rewards, while boundary expansion, local refinement, and inactive-anchor
pruning adapt the buffer as the policy evolves. Across four open-ended
benchmarks, RankBuffer consistently outperforms all pointwise baselines. It also achieves nearly on-par performance with the strongest ranking-based reward baseline while substantially reducing judging cost. Ablations demonstrate the importance of both local fine ranking and anchor response content, while buffer analyses show that rollout-derived anchors progressively extend and refine the covered quality scale. These results establish response reuse as an effective approach to efficient relative reward construction.
Read the full abstract ▾
All authors Zixuan Yang, Yiqun Chen, Qi Liu, Wei Yang, Erhan Zhang, Liyi Chen, Qimeng Wang, Yan Gao, Jiaxin Mao
Computer Vision
FocusVTC: Efficient and High-Performance Visual Text Compression with Adaptive Resolution
FangZhi Zhong, Xuerui Qiu, Yuqi Pan et al. (+4 more)
Long-context
reasoning in large
language models incurs substantial computation and
memory costs. Visual text compression (VTC) reduces input length by rendering text as images, but fixed-resolution rendering creates a compression-performance trade-off: low DPI saves
tokens at the expense of legibility, whereas high DPI spends
tokens on irrelevant content. We introduce FocusVTC, which breaks this trade-off through adaptive resolution while preserving general
multimodal capabilities. It combines compressed low-DPI global views with selective region enhancement, integrating enhanced views into ongoing
reasoning. We construct 29.4K high-quality
Reasoning-Evidence Localization (REL) chain-of-thought examples (REL-CoT) that link
reasoning traces to page indices and bounding boxes. Multi-resolution REL supervised fine-tuning (REL-SFT) teaches the model to localize relevant regions, and Group Relative Policy Optimization learns when to enhance resolution and how to use the resulting observations, without a separate continual-pretraining stage. At 72 DPI on RULER v1, FocusVTC scores 87.4 at $2.9\times$ input compression, including tool observations, versus 57.5 for Glyph at $3.0\times$ input compression. It surpasses its text-input backbone on LongBench (56.40 versus 55.86), improves the MRCR macro-average by 13.91 points, and achieves a 51.19 macro-average on VTCBench. The MRCR latency evaluation also shows a $2.79\times$ online end-to-end speedup over Text. General
multimodal capabilities are preserved, with MMMU increasing from 65.12 to 66.73 and MME from 2424.02 to 2457.62.
Read the full abstract ▾
All authors FangZhi Zhong, Xuerui Qiu, Yuqi Pan, Ya Liu, Shaowei Gu, Bo Xu, Guoqi Li
Computer Vision
VLM4Cluster: Benchmarking Deep Clustering In the Era of Vision-Language Pre-training
Yuanwei Hu, Bo Peng, Yuheng Jia et al. (+3 more)
Vision-
language pre-training has reshaped image clustering, giving rise to
language-assisted image clustering (LaIC), which leverages textual semantics to complement visual representations. Despite the rapid proliferation of LaIC methods, it remains unclear how much LaIC has actually advanced image clustering, as existing studies generally suffer from major limitations, including inconsistent experimental settings, inadequate
dataset selection, and limited evaluation dimensions. To address this gap, we introduce VLM4Cluster, a comprehensive
benchmark for image clustering in the era of pre-trained
vision-
language models (VLMs). VLM4Cluster implements 17 representative methods spanning classical, deep, and
language-assisted image clustering, and evaluates them on 20
datasets covering classical, challenging, fine-grained, large-scale, and out-of-distribution settings. Beyond effectiveness, VLM4Cluster systematically investigates image clustering along three complementary dimensions: robustness to
adversarial perturbations, generalization under distribution shifts, and computational efficiency. Our study shows that LaIC substantially advances the clustering performance frontier on many semantically demanding
benchmarks, generally exhibits stronger generalization under distribution shifts, and achieves a more favorable effectiveness-efficiency trade-off. However, its gains become less consistent on large-scale and fine-grained
datasets, while
language assistance does not systematically reduce sensitivity to
adversarial perturbations. VLM4Cluster is released at https://github.com/YuanweiHuu/VLM4Cluster.
Read the full abstract ▾
All authors Yuanwei Hu, Bo Peng, Yuheng Jia, Xinting Hu, Yadan Luo, Wenjie Zhu
Software Engineering
CTE-Bench: Counterfactual Trace Evaluation for Stateful Software Simulators
Xinran Zhang
Coding
agents change running software: they patch a service's code or overwrite its stored state, and then act on their own expectation of how the service will respond afterwards. A wrong expectation may surface only several calls later. Function-level code-execution
benchmarks omit persistent service state, and
agent benchmarks score the actions an
agent takes or the final state it reaches. We introduce CTE-Bench, which measures whether a model can predict how an intervention changes a stateful service's future behavior, without asking it to choose actions. Each scenario gives the model Python service code, the calls and responses observed before the intervention, the intervention itself (a source edit or a state overwrite), and 40 fixed future calls; the model predicts every future response, and predictions are checked by executing the service. Three
memory protocols control whether the model sees the correct earlier responses, none of them, or its own earlier predictions. CTE-Bench-Core-v1 contains 255 scenarios over six deterministic Python services, giving 10,200 predictions per model. The main score is effect-step value match (VM): exact response equality on the 2,476 future calls whose response the intervention changes. With correct earlier responses revealed, four API-hosted models (DeepSeek V4-Flash, Kimi K2.5, Qwen3.6-35B-A3B, and Claude Sonnet 4.6) reach 54.3%-61.7% effect-step VM. Hiding those responses lowers effect-step VM to 23.2%-29.0%; conditioning on self-generated predictions gives 24.8%-33.2%, and at most 1.2% of scenarios are predicted exactly end to end. Current models thus track intervention effects mainly when correct feedback is supplied, and their errors compound over a rollout. We release CTE-Bench-Core-v1 with its executable oracle, evaluation scripts, and an evaluation card mapping each claim to its protocol.
Read the full abstract ▾
Robotics
Where Predictive Supervision Goes Shapes What VLA Policies Learn
Hanseul Kim, Jewon Yeom, Youngjoon Jeong et al. (+2 more)
Future prediction is increasingly used to improve
vision-
language-action (VLA) policies, based on the premise that anticipating scene
evolution encourages representations useful for control. However, forecast quality alone does not establish that a policy has learned a better representation for action. This distinction matters under distribution shift, where successful control depends on preserving spatial state and likely scene change beyond familiar configurations. We study what determines whether predictive supervision improves the visual representation used by a VLA policy. Through controlled comparisons with matched target constructions, prediction horizons, and training conditions, we find that different prediction interfaces produce markedly different forecasts and visual representations, including in the spatial, dynamics, and action information that transfers beyond familiar scenes. We trace these differences to how predictive errors shape the policy's visual stream. Consistent with this controlled finding, VLA policies trained with more direct, scene-matched future supervision show stronger robustness under simulated and physical distribution shifts. Together, our results frame future prediction as a representation-learning design problem whose value for control depends on whether its supervision reaches the representations through which the policy acts.
Read the full abstract ▾
All authors Hanseul Kim, Jewon Yeom, Youngjoon Jeong, Minsoo Jo, Taesup Kim
Computer Vision
OCA: ODE-Driven Cross-Attention for Image-to-Point-Cloud Registration
Pei An, Jiaqi Yang, Yulong Wang et al. (+2 more)
Cross-
attention is a crucial component in learning-based image-to-point-cloud (I2P) registration. Although existing cross-
attention mechanisms have achieved promising progress,
attention ambiguity remains a fundamental challenge that hinders the learning of discriminative 2D-3D correspondences. To address this problem, we revisit cross-
attention and establish ordinary differential equations (ODEs) to model the ideal I2P feature interaction. Based on this formulation, we develop an ODE-driven cross-
attention (OCA) module that refines feature representations and
attention matrices through ODEs. In practice, OCA can be seamlessly integrated into existing I2P registration frameworks. To validate its effectiveness, we incorporate OCA into five state-of-the-art baselines and evaluate on four public
benchmark datasets. Experimental results demonstrate that OCA improves registration recall by up to 5%, 9%, and 15% under the standard, fine-tuning, and zero-shot settings, respectively.
Read the full abstract ▾
All authors Pei An, Jiaqi Yang, Yulong Wang, Siwen Quan, Liangliang Nan
Machine Learning
PR-OPD: Privileged Representation On-policy Self-Distillation for Agentic Reinforcement Learning
Muyang Li, Jie Yang, Zhengyu Fang et al. (+5 more)
Language-model
agents are usually trained by reinforcement learning from one reward per episode, and privileged self-
distillation enriches it by letting the same policy, given a skill, teach its skill-free self through
token probabilities. However, we identify two phenomena that question this channel. Invisible Advantage: a skill in context lifts WebShop success from 42.2% to 56.2%, yet changes the probabilities of fewer than a quarter of the sampled
tokens. Much to Align: a skill changes the hidden states of over 80% of response
tokens, in a way that linear probes can trace back to the specific skill. To exploit this, we propose Privileged Representation On-policy Self-
Distillation (PR-OPD). After a GRPO warm start, the policy writes a hindsight skill for each trajectory, re-reads its own responses with that skill as a stop-gradient teacher, and aligns its projected hidden states to the teacher's at every layer alongside the reward objective, with no external skill library, separate teacher, or inference overhead. On ALFWorld and WebShop with two backbones, PR-OPD achieves the best overall results in every setting, improving over GRPO by up to 4.7 points in ALFWorld success and 14.0 points in WebShop accuracy. Code is available at https://github.com/balibata/PR-OPD.
Read the full abstract ▾
All authors Muyang Li, Jie Yang, Zhengyu Fang, Junchao Zhu, Zhengkun Xiao, Ruining Deng, Zhe Jiang, Shigang Chen
Machine Learning
Inducing Process Supervision from Outcome-Only Reinforcement Learning
Shengda Fan, Xin Cong, Zhong Zhang et al. (+2 more)
Process reward models (PRMs) have become a key component for LLMs, as their step-level feedback supports both post-training and test-time
reasoning. However, training strong PRMs remains costly: human step annotation is difficult to scale, while Monte Carlo estimation is computationally expensive and can drift from the intrinsic correctness of steps. To get effective PRMs at low cost, we introduce TIPS (Thinking-Induced Process Supervision), an outcome-only reinforcement learning (RL) framework for training generative PRMs. In TIPS, the model generates a chain-of-thought (CoT) followed by step-level labels and an outcome label. The reward depends solely on whether the predicted outcome matches the ground truth, and the resulting group-relative advantage is used to optimize the entire generated response. Intuitively, when checking intermediate steps helps determine the outcome, more accurate checks can lead to better outcome judgments and higher rewards. Outcome-only RL can therefore reinforce step-level verification without explicit process supervision. We validate the effectiveness of TIPS across math and
agent benchmarks and four backbone families. Notably, TIPS-Qwen3-4B-Thinking-2507 reaches 85.2 F1 on ProcessBench with only 3.2K outcome-labeled trajectories, surpassing all evaluated trained PRMs and strong
prompt-only judges such as GPT-5.4-Instruct and Claude-4.7-Opus, while still trailing o1-mini. Code and data are available at https://github.com/RUCBM/TIPS.
Read the full abstract ▾
All authors Shengda Fan, Xin Cong, Zhong Zhang, Haotian Chen, Yankai Lin
Robotics
Foundation-Model-Guided Topology-Aware Semantic Risk Fields for Manipulation
Giung Lee, Weihang Guo and Lydia E. Kavraki
Robot motion planning in everyday environments must satisfy hard
geometric constraints while accounting for context-dependent semantic risk. We present a foundation-model-guided,
topology-aware semantic risk field that extends manipulation safety beyond collision avoidance. For each manipulated-object/scene-object pair, a foundation model provides six directional risk weights and a pair-specific spatial decay scale. The method combines these priors with voxelized 3D scene geometry using
topology-aware shielding and geodesic spatial decay. A GPU-parallel backend batches object-level distance and risk computations to construct a dense 3D field that serves as a modular cost for downstream motion planning. We evaluate the field's shielding behavior under full and partial barriers and compare its 3D workspace representation with a pixel-wise semantic-prior baseline. Across three household simulation scenarios, trajectories optimized with the proposed field have lower semantic exposure than collision-only trajectories under the same
geometric constraints. We also evaluate the computational practicality and reliability of the supporting pipeline. Together, these results support the proposed field as a practical
topology-aware semantic cost representation for manipulation planning beyond collision avoidance.
Read the full abstract ▾
Machine Learning
A Digital Simulation Toolkit for Physics-Based Generation of Realistic Experimental Scanning Tunneling Microscopy Images
Huanhuan Zhao, Laxmi Bhurtel, Connor Vernachio et al. (+3 more)
Scanning Tunneling Microscopy (STM) is a widely used tool for characterizing surfaces of materials at the atomic scale, playing a crucial role in discoveries across condensed matter physics and materials science. Despite its extreme spatial resolution, STM is one of the most sensitive microscopy techniques and is highly prone to noise. While existing unsupervised denoising methods are very cheap to train, these are primarily focused on removing the noise with minimal recovery of key physical information. While supervised methods can offer superior performance, the major bottleneck is that a large amount of paired clean-noisy experimental images is required which are impractical to obtain. Thus, we developed a low-cost physics-driven digital toolkit to rapidly generate large volume of realistic STM images. Firstly, we simulate clean images from a chosen material system. Then, with prior knowledge of the physical characteristics of the artifacts and noise present in STM experiments, we formulate several artifact-noise functions such as Gaussian electronic noise, 1/f flicker noise, scan-line noise, background tilt and mechanical drift. These physically informed noise components are then added to the simulated clean images to generate realistic STM images. We demonstrated the capability of the proposed digital toolkit to generate AI-ready data for denoising images of the (111) surfaces of copper and lead, while preserving atoms, defects, and electron waves. We also validated the quality of the downstream image analysis of learning electron wave patterns induced by
quantum interference from Cu(111) images. Results show that the supervised models trained on digitally generated AI-ready data can more effectively denoise and learn electron wave patterns on Cu(111) images than benchmarked unsupervised approaches, indicating that the proposed toolkit facilitate scientific discovery.
Read the full abstract ▾
All authors Huanhuan Zhao, Laxmi Bhurtel, Connor Vernachio, Fahmy Paiziah, Wonhee Ko, Arpan Biswas
Machine Learning
PE-OPSD: Internalizing Prompt Enhancement into Flow-matching Models via On-Policy Self-Distillation
Mingfeng Lin, Chengfei Cai, Lin Xu et al. (+3 more)
Text-to-image users often provide concise and underspecified
prompts, whereas generative models benefit from detailed textual conditions for reliable instruction following. Existing systems bridge this gap with
Prompt Enhancers (PEs) that rewrite raw
prompts at inference time, introducing additional latency and leaving
prompt elaboration external to the generator. We instead view enhanced
prompts as privileged training information and ask whether their benefits can be internalized. We propose
Prompt-Enhanced On-Policy Self-
Distillation (PE-OPSD) for text-to-image flow-matching models. During training, a raw-
prompt student follows its own generation trajectory, while an enhanced-
prompt teacher provides vector-field targets at the states visited by the student. This on-policy supervision distills the behavior induced by enhanced
prompts into the raw-
prompt student without requiring additional text–image pairs. At inference, both the PE and teacher are removed, and the student generates directly from raw
prompts. Across multiple model families, PEs, and
benchmarks, PE-OPSD achieves the strongest aggregate
prompt fidelity among the evaluated baselines, yields positive aggregate visual appeal gains, and retains the base-model inference efficiency.
Read the full abstract ▾
All authors Mingfeng Lin, Chengfei Cai, Lin Xu, Chengqian Ma, Yuxiang Wei, Liang Han
Computational Engineering
Decompose Dynamics Before Learning Dependencies in Spatiotemporal Systems
Ziqi Wang, Daojiang Hu, Cheng Bao et al. (+4 more)
Relations in networked spatiotemporal systems are often learned from observations that entangle dynamics governed by different mechanisms, obscuring what evolves locally and how it propagates across nodes. We introduce Component-Aware Network Dynamics with Ordered Relations (CANDOR), which decomposes local dynamics before learning their dependencies. CANDOR represents each trajectory through a persistent background, gradual accumulation and release, and sparse shocks. Conditioned on these components, a delay-aware physical branch models edge and sample-dependent propagation over directed
topology, while a
topology-unconstrained functional branch discovers latent dependencies from background dynamics. Context-adaptive fusion combines functional, forward-propagation, and reverse-support forecasts, with training objectives encouraging specialized and semantically consistent representations. Experiments on two traffic
benchmarks and three long-horizon water-quality
datasets span two distinct spatiotemporal systems: human-driven urban traffic and naturally evolving river water quality. CANDOR consistently outperforms the strongest baselines, reducing MAE by up to 4.31% for traffic and MSE by up to 5.47% for water-quality
forecasting. These results establish decomposition before dependency learning as an effective principle for spatiotemporal representation learning.
Read the full abstract ▾
All authors Ziqi Wang, Daojiang Hu, Cheng Bao, Zhiwei Ling, Wenzhuo Qian, Jiahui Zhai, Hailiang Zhao
Machine Learning
What Makes Recurrence Effective in Looped Language Models?
Xinlin Zhuang, Siyuan Wang, Imran Razzak et al. (+1 more)
Looped
language models (LoopLMs) increase computational depth through parameter sharing, offering a path to scale inference computation without adding parameters. However, it remains unclear when additional recurrence is beneficial and how architectural choices affect its effectiveness. Through controlled experiments, we systematically examine (1) when recurrence helps, (2) where it should be applied, and (3) how its conditioning affects performance. Our evaluation covers inference budgets below, within, and beyond the training horizon under knowledge and
reasoning tasks. (1) We find that recurrence can improve
reasoning beyond the training horizon while degrading knowledge performance, but harder
reasoning instances do not consistently benefit more. (2) Performance also depends on how distinct layers and recurrent iterations are allocated, showing that effective depth alone is insufficient to predict behavior. Non-recurrent output layers improve robustness to under-unrolling, while the preferred placement of input and output layers varies with inference budget. (3) Finally, we find that conventional initial-state injection offers limited robustness to varying recurrence depth. We therefore propose history-state injection as an alternative, and show that channel-wise history-state injection combined with timestep conditioning offers a low-cost and more effective design, better preserving knowledge under extended unrolling while improving robustness across inference budgets. Overall, our results clarify when recurrent computation helps, where it fails, and offer practical guidelines for designing LoopLMs across variable inference budgets.
Read the full abstract ▾
All authors Xinlin Zhuang, Siyuan Wang, Imran Razzak, Weiyang Liu
Software Engineering
WitnessGym: Benchmarking Coding Agents on the Construction of Bug Witnesses
Haomin Qi, Xiangzhe Xu, Yiming Huang et al. (+2 more)
Bug validation asks a coding
agent to produce an executable witness for a reported bug. The witness combines a concrete input with a testing harness and exposes faulty behavior during execution. Such evidence makes audit findings actionable, yet
benchmark evaluation is difficult when cases reuse public historical bugs and witnesses or require manual construction. We present WitnessGym, an automated framework for constructing bug-validation
benchmarks through bug injection. It injects bugs into test-reached paths of real projects, rebuilds each project, and retains cases exposed by a construction-time witness. Bug specifications and execution adapters allow extension to additional bug types and
languages. Bug-preserving transformations vary the surrounding structure while preserving the witness behavior. Based on real-world Java projects with test suites, WitnessGym automatically constructs 1,300
benchmark cases. The injected patches resemble historical bug patches and are difficult for the two evaluated models to distinguish in blinded comparisons. We evaluate four coding
agent frameworks in six framework/model pairings across bug types, execution contexts, and transformation depths. Witness construction remains difficult even when the bug pattern is known. Our framework,
benchmark cases, and evaluation scripts are available.
Read the full abstract ▾
All authors Haomin Qi, Xiangzhe Xu, Yiming Huang, Jingbo Shang, Chengpeng Wang
Hardware Architecture
Lossless Compression of Lookup Tables for Hardware Applications
Alireza Khataei and Kia Bazargan
Large lookup tables are widely used in hardware to store constant-valued arrays for applications ranging from elementary mathematical operations, such as constant-coefficient multiplication and nonlinear function evaluation, to emerging machine learning models, including table-based neural networks (NNs) and Kolmogorov-Arnold networks (KANs). However, storing extensive tables of constant values can lead to excessive hardware costs in resource-constrained edge devices such as FPGAs. In this paper, we propose CompressedLUT, a lossless compression scheme and its decoder hardware architecture for the efficient storage and
retrieval of arbitrary data in hardware. Our method combines decomposition, self-similarities, higher-bit compression, and multilevel compression techniques to maximize table size savings without accuracy loss. Its hardware decoder primarily uses addition, arithmetic right shift, and several small lookup tables, ensuring low area and high throughput. We evaluated CompressedLUT on FPGAs by implementing multiple nonlinear functions, constant-coefficient multipliers (CCMs), and KANs at 12-bit resolution. CompressedLUT is available as an open-source tool.
Read the full abstract ▾
Machine Learning
Physics-Aware Machine Unlearning for Cyber-Physical Systems
Mohammad Zakaria Haider, Muhammad Nadeem and Mohammad Ashiqur Rahman
This paper proposes a physics-guided gradient-ascent-based machine unlearning method that couples the forgetting signal with the physical residual of the target cyber-physical systems, ensuring that weight updates during unlearning are steered toward physically feasible regions of the weight space. The physics residual acts as a safety fence during gradient ascent: the model is steered away from the poisoned behavioral basin and simultaneously toward physics-compliant territory, rather than toward an arbitrary alternative that may still violate domain constraints. We evaluate the proposed method against four baselines: naive gradient ascent, exact unlearning, SISA, and full retraining on an IEEE 34-bus distribution system, driven by two physics-informed neural network-based distribution energy resource controllers and validated through high-fidelity OpenDSS power-flow co-simulation. From the evaluation, we found that our proposed physics-guided model simultaneously removes poison and restores physical compliance, which are essential for the safe deployment of safety-critical cyber-physical systems
Read the full abstract ▾
Artificial Intelligence
Distilling Agentic Systems: A Roadmap across Models, Artifacts, and Harnesses
Ziluowen Luo, Senzhang Wang, Chaozhuo Li et al. (+9 more)
Modern
agents increasingly rely on
memories, tools, and execution logic, so their competence extends beyond model parameters. This shift exposes a limitation of conventional knowledge
distillation, which asks how a student model imitates a teacher model. We define
Agent Distillation as the persistent transfer of task-solving knowledge from a teacher
agent to a student
agent. Our study organizes the field by where transferred knowledge is retained: within the model, as artifacts, through the execution harness, or across substrates. This perspective separates transfer evidence from its outcome and clarifies how knowledge moves between
agent components. We develop an evaluation framework that relates retention to causal contribution and deployed utility. Together, these contributions establish a foundation for the reliable, maintainable, and safe development of increasingly complex agentic systems.
Read the full abstract ▾
All authors Ziluowen Luo, Senzhang Wang, Chaozhuo Li, Jun Yin, Hao Yan, Ming Cheng, Chenxu Wang, Songyang Liu, Litian Zhang, Qiwei Ye, Zheng Liu, Philip S. Yu
Computer Vision
Beyond Binary Preferences: Graded Preference Optimization for Limb-Motion Captioning
Yanan Wang, Tingsong Li, Kaixun Jiang et al. (+3 more)
Vision-
Language Models (VLMs) can generate rich
video captions, yet often misidentify which person performs an action or which limb is involved, particularly across camera cuts. Improving these details requires evaluation and training that distinguish missing information from incorrect assertions. We introduce FlexBench, a
benchmark spanning 3,105 shots and 18,161 evaluation queries, with human-verified identities and systematic per-person coverage of fine-grained limb actions and states. Its reference-derived checklists support automated assessment of complete captions in their person and shot contexts. Our Graded Physical
Alignment score (GPA) awards credit for correct content and deducts points for incorrect or fabricated actions, making these errors explicit in the aggregate score. Building on this rubric, we propose Graded Margin Direct Preference Optimization (GM-DPO), which assigns stronger preference margins and greater training weight to more severe action errors. Across three VLM backbones, GM-DPO achieves the highest substantive-action and GPA scores among the evaluated preference objectives, improving GPA over DPO by 2.02-3.40 points. On Qwen3-8B, it reduces the weighted
hallucination rate by 21.3% relative to DPO. These gains accompany sustained long-form output, improved shot structure, and competitive performance on three additional
multimodal benchmarks.
Read the full abstract ▾
All authors Yanan Wang, Tingsong Li, Kaixun Jiang, Chongyang Zhong, Chenwei Xoe, Zhaohe Liao
Artificial Intelligence
Ziyu Liu, Jun Chen and Lixu Wang
Language-model
agents increasingly rely on persistent natural-
language skills to adapt beyond their frozen model parameters. When a shared skill is repeatedly revised from a non-stationary, heterogeneous task stream, however, improvements for new tasks can overwrite procedures needed for earlier ones. In continual learning, Orthogonal Gradient Descent (OGD) addresses analogous interference by projecting a new-task gradient onto a subspace that locally preserves prior predictions. Natural-
language skill revisions, however, have neither gradients nor a canonical vector space in which such a projection can be performed. We introduce Semantic-Scope Projected
Evolution (SSPE), which transfers the functional principle of gradient projection from parameter space to behavior space. SSPE treats an unconstrained skill revision as a proposed update, identifies acquired capabilities with which it may interfere, and uses the observed gains and regressions to construct a compatible revision rather than merely rejecting the update. This enables one shared skill to evolve across latent and recurring task contexts without exposing semantic domain identities to the
evolution model. Across controlled synthetic streams and heterogeneous real-
agent benchmarks, SSPE improves final cross-domain competence and mitigates forgetting relative to strong skill-
evolution baselines. The evolved skill also retains the strongest average performance after transfer to a different executor model. These results establish semantic projection as a promising principle for stable and adaptive self
evolution of
language agents.
Read the full abstract ▾
Artificial Intelligence
DualTrack: Synchronized speech-gesture generation via symmetric coupling of pretrained priors
Yuanzhuo Hu, Zehan Liu, Xiaoyi Qin et al. (+1 more)
Joint
speech-gesture synthesis must coordinate two modalities despite limited paired data. Existing approaches often lack bidirectional interaction, have limited
language coverage, or simplify body and finger representations. We present DualTrack, which couples pretrained
speech and motion priors on a shared 12.5 Hz timeline. Causal adapters exchange previous-packet information, while current-state fusion coordinates the streams before they separately complete sixteen-codebook packets. We evaluate 43 BEAT2 recordings in four
languages, with speakers held out from joint training and validation. On the shared English/Spanish inputs, without
speech or motion prefixes, DualTrack achieves lower word error rate and full-motion Fréchet Gesture Distance, higher beat consistency and
speech naturalness than the evaluated GELINA baseline.
Read the full abstract ▾
All authors Yuanzhuo Hu, Zehan Liu, Xiaoyi Qin, Ming Li
Artificial Intelligence
Neural Structural Reasoner: A Brain-inspired Architecture for Reasoning over Structured Knowledge
Zixing Jia, Yuhang Pan and Ni Ji
Structural
reasoning, the ability to recognize and make inferences over the relational structure between objects and concepts, is a hallmark of human cognition, yet prevailing methods often collapse relational
topology into flat
embeddings, cannot discover hidden structure and lack interpretability. We introduce Neural Structural Reasoner (NSR), a
brain-inspired network that preserves relational structure directly in the connectivity and dynamics of coupled neuronal populations. NSR draws inspiration from three biological mechanisms: multi-layered architecture for encoding hierarchical knowledge, stable representations of entity and concepts, and path integration for input-driven state inference. At query time, NSR parallelizes computation over candidate relational structures and leverages confidence-weighted scores to perform link prediction. Across standard knowledge-graph
benchmarks, NSR achieves competitive accuracy without leading on every
dataset, and has lower reported training times than several neural baselines. Because
reasoning is implemented through sequences of human-readable
neuron activations, NSR affords native interpretability by tracking intermediate inference steps. The model further extracts latent relational hierarchies and compositional rules, demonstrating the
brain-inspired architecture as an effective, efficient, and highly interpretable substrate for structural
reasoning.
Read the full abstract ▾