Computational Complexity
Resilience in labeled real-time automata
Kuize Zhang
In this paper, we characterize resilience for a labeled real-time automaton (LRTA). An LRTA is resilient if whenever a faulty event occurs, after sufficiently many events occur, the LRTA returns to normalcy and the occurrence of the faulty event is not leaked. The notion of resilience reflects the ability of an LRTA recovering from a faulty behavior, and hence can model an intelligent
agent. We formulate one definition of resilience for an LRTA and give verification
algorithms for the definition based on two basic tools — concurrent composition and observer.
Read the full abstract ▾
Computation and Language
A Hyperbolicity Atlas of Large Language Model Hidden States
Zhichao Yang, Yuanze Hu, Gen Li et al. (+7 more)
LLM hidden states are ordinary vectors, but the distances among those vectors may still show hierarchical structure. To our knowledge, this paper is the first systematic study of whether
prompt-
token hidden states in contemporary LLMs exhibit Gromov Hyperbolicity (GH), a distance-based measure of tree-likeness. Using 818,904 sample-layer measurements from ten open-weight models across MATH500, HumanEval, WinoGrande, and TruthfulQA, we build a GH map over four axes: parameter scale, layer depth, model family, and input domain. The clearest pattern is depth, not scale: middle layers usually form a high-relative-hyperbolicity plateau, while final layers often become substantially more tree-like. Scale effects are weak and non-monotonic, matched 7/8B model families differ strongly, and domains interact with model specialization. These findings make GH useful as a practical diagnostic: it shows where hierarchical distance structure appears, how specialization changes it, and which model-layer-domain comparisons deserve closer analysis.
Read the full abstract ▾
All authors Zhichao Yang, Yuanze Hu, Gen Li, Qingchen Yu, Shiying Duan, Xinyu Wang, Ye Qiu, Zeming Liu, Guangxu Chen, Zhaoxin Fan
Machine Learning
TrojanWorld: Backdooring World-Model Agents via Imagination Steering
Wenkai Huang, Siyuan Liang, Gaolei Li et al. (+4 more)
World models increasingly serve as the predictive core of model-based reinforcement learning
agents, enabling them to simulate future dynamics and reason over imagined trajectories before acting. Their substantial training demands make pretrained world models attractive for distribution and reuse, exposing downstream systems to model supply chain threats.
Backdoor attacks offer a targeted and stealthy means of exploiting such supply chains, yet their threat to interactive world-model
agents remains largely unexplored. To fill this gap, we present TrojanWorld, a
backdoor framework for world-model
agents that induces attacker-specified behavior by steering internal imagination. A physical object placed in the scene acts as the trigger, enabling deployment-time activation through the
agent's native observation pipeline without digitally manipulating the observation stream. To achieve effective, stealthy, and persistent control, TrojanWorld combines Decision-Reflective Induction to steer trigger-conditioned imagination toward attacker-specified actions using decision feedback, Clean Behavior Anchoring to preserve trigger-free predictive and behavioral fidelity, and Causal Propagation to sustain the induced preference along subsequent trajectories after the trigger disappears. Together, these mechanisms establish an end-to-end attack chain from physical perception through corrupted imagination to malicious action selection. Experiments with the TD-MPC2, DreamerV3, and R2-Dreamer systems across the DeepMind Control, MetaWorld, MyoSuite, and RoboDesk
benchmarks show that under trigger activation, TrojanWorld achieves a target-action deviation as low as 0.026 while retaining at least 98.8% of the corresponding clean performance. Even after trigger removal, the compromised
agent can remain trapped in the induced behavioral trajectory, continuing to execute attacker-specified actions.
Read the full abstract ▾
All authors Wenkai Huang, Siyuan Liang, Gaolei Li, Yiming Li, Tianhao Peng, Jianhua Li, Dacheng Tao
Artificial Intelligence
Beyond One-Shot Expansion: Contrastive Evidence Exploration for Multi-Hop Retrieval
JungMin Yun and YoungBin Kim
Retrieval-augmented generation (RAG) critically depends on retrieving the evidence necessary for effective
reasoning. However, this remains particularly challenging in multi-hop question answering (QA), where supporting passages are often linked through intermediate entities and relations that must be progressively uncovered. Existing
retrieval approaches typically rely on a single
retrieval intent or one-shot query expansion, limiting their ability to adapt to newly retrieved evidence and potentially introducing noisy or redundant
retrieval signals. To address these limitations, we propose a training-free multi-hop
retrieval framework that integrates evidence-conditioned exploration, passage-specific contrastive refinement, and coverage-aware final ranking. During offline indexing, the framework constructs passage-specific contrastive facets that characterize each passage relative to its semantically similar neighbors, providing fine-grained signals to distinguish closely related candidates. At inference time, the framework iteratively retrieves evidence, generates probes targeting unresolved information needs, refines candidate relevance using the contrastive facets, and selects a complementary set of passages that collectively cover diverse evidence-seeking intents. Experiments on MuSiQue, HotpotQA, and 2WikiMultihopQA demonstrate consistent improvements in
retrieval quality and downstream QA performance over baselines.
Read the full abstract ▾
Robotics
Large Discrete Policy: Advancing Explicit Behavior Modeling with Stochastic Iterative Scoring
Zhenxin Li, Nadine Chang, Xinglong Sun et al. (+8 more)
Behavior policies are often formulated as continuous generative models, whose iterative denoising processes are expressive but difficult to interpret and prone to producing implausible actions. We propose the Large Discrete Policy (LDiP), a fully discrete behavior modeling framework that selects actions from a large vocabulary of physically plausible candidates. Rather than perturbing actions, LDiP improves expressivity through
stochastic iterative scoring: it progressively re-scores and prunes candidates with score-space stochasticity, enabling fine-grained ranking and exploration among plausible actions while preserving an explicit decision process. Across end-to-end planning, closed-loop driving, robotic manipulation, and
vision-
language-action settings, LDiP consistently outperforms strong discrete and continuous baselines in autonomous driving, and exceeds or matches continuous generative policies in robotic manipulation. These results show that discrete policies, when equipped with effective scoring mechanisms, offer an expressive, plausible, and interpretable alternative for behavior modeling. Project website: https://zhenxinli.net/LargeDiscretePolicy/.
Read the full abstract ▾
All authors Zhenxin Li, Nadine Chang, Xinglong Sun, Jingde Chen, Wenhao Yao, Zi Wang, Maying Shen, Yu-Gang Jiang, Zuxuan Wu, Shiyi Lan, Jose M. Alvarez
Computer Vision
FreqDoor: A Hidden Trojan in the Frequency Domain for Backdoor Attacks on Vision-Language Models
Yasir Arafat Prodhan, Sadad Hasan and Mohammed Imamul Hassan Bhuiyan
Vision-
language models (VLMs) have recently shown excellent progress in open-ended image-to-text generation. However, their
multimodal nature makes them persistently vulnerable to
backdoor attacks. Existing
backdoor triggers for VLMs are either spatial, textual, or bimodal, which may yield localized or recognizable trigger patterns. In this work, we explore a different attack surface and propose \ textsc {FreqDoor}, a training-time
backdoor attack that implants triggers in the frequency domain. \ textsc {FreqDoor} mixes amplitude-spectrum components from a trigger-source image selectively while preserving the phase of a clean image to generate a spatially distributed and visually imperceptible trigger without modifying the textual input. We evaluate the attack on BLIP-2, InstructBLIP, and LLaVA for image captioning and visual question answering. On Flickr8k, \ textsc {FreqDoor} achieves attack success rates of $99.6\%$, $99.8\%$, and $98.4\%$ on the three models, respectively, while preserving the semantic quality of the generated captions. On VQAv2, the corresponding attack success rates are $99.6\%$, $92.4\%$, and $79.6\%$.
Read the full abstract ▾
Robotics
MEMOBench: A Process Level Memory Benchmark for Robotic Manipulation
Haiyang Sun, Haoxiao Wang, Junming Chen et al. (+6 more)
Robotic manipulation often requires acting on information that is no longer visible, yet
Vision-
Language-Action policies are usually evaluated when the current observation largely determines the next action. Existing robotic
memory benchmarks expose this gap, but they still rely mainly on final task success and therefore conflate forgetting with manipulation failure. We present MEMOBench, a
benchmark for process level
memory evaluation in robotic manipulation. MEMOBench includes 30 history dependent tasks, 1{,}500 expert demonstrations, and 4{,}200 executable checkpoint instances from 84 templates. Each checkpoint pairs coarse to fine
language with a simulator predicate and labels one
memory operation: Storage, Update, or Compression. These annotations define
Memory Storage Rate,
Memory Update Rate, and
Memory Compression Rate, which measure
memory fidelity alongside task success. Across standard and
memory augmented VLA policies, the strongest
memory module baseline reaches only 31.9% average success rate, and high storage often coexists with weak update and compression. Checkpoint
language also supervises semantic, contrastive, and framewise
memory alignment objectives, yielding modest gains across different
memory operations. MEMOBench provides a diagnostic evaluation suite and training supervision for
memory grounded robotic policies. The project page is available at https://github.com/Collab-Gen/MEMOBench.
Read the full abstract ▾
All authors Haiyang Sun, Haoxiao Wang, Junming Chen, Weicheng Fang, Zihao Su, Jingkun Yi, Wenyou Yi, Hao Chen, Zhou Zhao
Machine Learning
AI and TCAD for Inverse Design and Defect Discovery: From Simple Machine Learning to LLM
Hiu Yung Wong
AI has revolutionized various engineering domains, but its impact on
semiconductor device design and defect discovery is still limited, due to limited data and the curse of dimensionality. In this paper, we will discuss our work on using the Technology Computer-Aided-Design (TCAD) to generate precise data needed for machine learning (ML) to enable simulation-augmented ML. We demonstrate that with minimal domain expertise, it is possible to create a machine that performs as well as a device engineer on a specific task. We will show that auto-encoder-based machine learning models and noise engineering applied to TCAD data are effective at learning latent physics, and that the models can be seamlessly applied to experimental data. We will demonstrate how to build a device-engineer-level model step by step through various examples, including using only non-destructive electrical data to inverse-engineer the PiN diode layer thickness variations, the Ga2O3 Schottky diode doping and anode workfunction variations, and the transistor contact resistance in an inverter. Examples also include the generation of a FinFET IV/CV prediction model, the mapping between transistor images and IV curves, and the automatic calibration of TCAD parameters for a Ga2O3 Schottky diode, which can only be handled well by experienced TCAD engineers. Finally, to fully realize the potential of AI, large
language models (LLMs) and
multimodal LLMs (MLLMs) are believed to be necessary. We will discuss the application of LLMs to TCAD command file creation and our
vision for MLLMs in automated device design and defect discovery.
Read the full abstract ▾
Systems and Control · Cross-listed from math.OC
Equivalence Between Continuous-Time Risk-Sensitive Control and Rényi Divergence Minimization
Shinji Kataoka, Kaoru Teranishi and Yasumasa Fujisaki
In this study, we show that a continuous-time risk-sensitive control problem is equivalent to a Rényi divergence minimization problem over trajectory path measures. Reformulating
stochastic optimal control as probabilistic inference via Kullback-Leibler (KL) divergence minimization avoids the computational intractability of the Hamilton-Jacobi-Bellman equation. However, standard KL control is inherently risk-neutral, and recent minimax extensions remain restricted to risk-averse settings. Our equivalence result resolves this limitation by offering a unified probabilistic framework for arbitrary risk attitudes in continuous-time nonlinear systems. Based on Girsanov
theorem, we explicitly map the risk sensitivity to the Rényi divergence order, deriving a noise-dependent control penalty scaled by risk preference. This formulation seamlessly modulates tail-weighting behaviors, interpolating between zero-forcing for risk-averse policies and mass-covering for risk-seeking policies. These findings bridge
stochastic control and information-theoretic inference, providing a foundation for sampling-based control
algorithms.
Read the full abstract ▾
Multimedia
AdoDAS: A Privacy-Preserving Multimodal Challenge for Adolescent Depression, Anxiety, and Stress Assessment
Zhaojie Luo, Junkun Wang, Tianhua Qi et al. (+11 more)
Adolescent depression, anxiety, and stress (D/A/S) call for scalable tools that complement, rather than replace, professional evaluation. Under a
privacy-preserving policy, the AdoDAS Grand Challenge withholds minors' raw recordings and distributes anonymized audio-visual representations and ASR-derived text. Its 6,000 participants provide 24,000 segments across one scripted-reading and three open-response sessions. Two tracks assess multi-task binary D/A/S screening and ordinal prediction of 21 DASS-21 item responses. From 191 registrations, the final leaderboards included 95 eligible screening teams and 64 item-prediction teams. Audio-visual baselines achieved 0.4604 mean F1 and 0.2675 mean Quadratic Weighted Kappa; leading submissions reached 0.5921 and 0.2776. Representative systems emphasize cross-session modelling, temporal
multimodal fusion, psychometric structure, and task-aware calibration.
Read the full abstract ▾
All authors Zhaojie Luo, Junkun Wang, Tianhua Qi, Yuxuan Wu, Xin Zhao, Tetsuya Takiguchi, Tomoko Matsui, Kun Qian, Fei Wang, Shuqiong Wu, Zhengjun Yue, Hiroshi Ishiguro, Xinyuan Qian, Haizhou Li
Machine Learning
Disentangling Steering Vectors
Takeru Hiramatsu, Kyohei Atarashi, Koh Takeuchi et al. (+1 more)
Activation steering has emerged as a lightweight, inference-time approach to control the behavior of Large
Language Models (LLMs). However, traditional steering vectors used to intervene in LLMs' activations, such as those derived from the difference-in-means method, tend to entangle multiple semantic and stylistic concepts into a single composite direction, leading to unpredictable steering effects. Our core objective is to disentangle this composite direction into its constituent concepts. To this end, we propose Steering Vector Dissection, a framework to explicitly isolate individual and semantically consistent features from these composite directions. Specifically, we pair positive and negative activations and take their differences to generate a set of instance-level steering vectors, and train a dedicated Sparse Autoencoder (SAE) directly on them. Quantitative evaluations across two
datasets, two models, and two intervention depths show that our method yields a set of semantically consistent basis vectors whose steering effects are mutually distinguishable. Furthermore, we show that this disentanglement enables precise control over model behaviors.
Read the full abstract ▾
All authors Takeru Hiramatsu, Kyohei Atarashi, Koh Takeuchi, Hisashi Kashima
Computation and Language
Xiaodong Wang and Peixi Peng
We identify the Flow Moment, a
reasoning pattern characterized by sustained, process-confirming verbalizations such as I'm doing, in contrast to the revision- and backtracking-oriented Aha Moment. We refer to their corresponding linguistic expressions as Flow Markers and Aha Markers, respectively. Based on this observation, we construct Flow-CoT by rewriting the discourse markers of original
reasoning traces while preserving their underlying
reasoning content, and use it as auxiliary supervision for on-policy self-
distillation (OPSD). We further propose Aha-Flow
Distillation (AFD), a dual-mode extension of OPSD that pairs different forms of privileged information with corresponding
reasoning instructions. The Aha branch retains concise solution-based supervision, while the Flow branch introduces rewritten Flow-CoT under a direct and confident
reasoning instruction. At inference time, the model uses only the standard reflective instruction, so Flow-style
reasoning serves purely as a training signal. Experiments on AIME25 and HMMT25 show consistent improvements across Qwen3-8B and Qwen3-4B: AFD improves Avg@12 from 60.8 to 61.3 on Qwen3-8B and from 57.5 to 58.6 on Qwen3-4B over our reproduced OPSD baselines. Controlled ablations further show that, with the same Flow-CoT/Aha-CoT composition, dual-mode training improves Avg@12 from 59.5 to 60.1, indicating that the benefit comes not only from introducing heterogeneous
reasoning supervision, but also from how it is organized during self-
distillation. The code is available at https://github.com/Wang-Xiaodong1899/Aha-Flow-
Distillation.
Read the full abstract ▾
Hardware Architecture · Cross-listed from quant-ph
Capability-Gated Conformance Testing of Quantum Error-Correction Decoder Libraries
Jiachen Shen and Hui Zhong
A
quantum error correction decoder is a library other people's results depend on, judged in one dominant way. Sample errors, decode, and count wrong logical observables. We ask what else can be checked there. Our conformance contract needs no oracle. One check asks that a returned correction explain the syndrome in the caller's index space. The other hands a decoder one instance under two presentations differing only in bookkeeping, where two feasible corrections of different weight prove the heavier is not minimum-weight. Verdicts are gated on what each library declares, so a firing contradicts a published guarantee. Nine configurations from five public libraries give three results. Documentation answers 4 of 54 capability questions. Bounded-distance correctness, the property callers most depend on, has a direct declaration yield of 0.0%, though its hypotheses hold in 62.1% of cases. Presentation sensitivity is real but shallow. One solver moved to a 26% heavier correction under a different numbering, which reaches the logical class at most once in twenty thousand shots. Established evaluation misses corruptions that preserve logical parity, while one summation over the caller's weights catches every one we injected. All 639 certificates ship as bundles a standalone verifier re-derives from first principles.
Read the full abstract ▾
Sound
Frequency Estimation Based on SNR-adaptive Frequency Estimator Under Wide SNR Range
Hee-Yang Jung, Dong-Hee Paek, Woo-Jin Jung et al. (+1 more)
Frequency estimation is the problem of estimating individual tone frequencies from noisy multi-tone sinusoidal signals. Existing frequency estimation methods have difficulty accurately estimating both the number of tone frequencies and the individual tone frequencies in low signal-to-noise ratio (SNR) environments, because weak tone frequency components are buried in noise. In addition, existing methods generally exhibit a trade-off between robustness at low SNR and frequency estimation precision at high SNR, making it difficult to achieve consistently superior frequency estimation performance over a wide SNR range. To overcome these limitations, this paper proposes an SNR-adaptive frequency
estimator (SAFE). SAFE consists of a time-frequency image neural network (TFINet), which enhances weak tone frequency components at low SNR, and an SNR-based frequency selector (SFS), which selects an appropriate frequency
estimator according to the SNR of the estimated tone frequencies. TFINet enhances tone frequency components even in the low-SNR range, while SFS estimates the SNR of each tone frequency and selects either a robust frequency
estimator or a super-resolution frequency
estimator according to the estimated SNR. This enables SAFE to achieve robustness at low SNR while preserving high precision at high SNR. Simulation results show that SAFE achieves an False Negative Rate (FNR) of 13.00% over the SNR range from -10 dB to 0 dB, corresponding to an 13.04% improvement over the state-of-the-art method. In addition, SAFE reduces the Nearest Neighbor-Root Mean Squared Error (NN-RMSE) by 56.67% compared with the state-of-the-art method, demonstrating that SAFE performs more accurate frequency estimation. Furthermore, experiments using real-world data demonstrate that SAFE provides robust frequency estimation performance even in practical environments with clutter.
Read the full abstract ▾
All authors Hee-Yang Jung, Dong-Hee Paek, Woo-Jin Jung, Seung-Hyun Kong
Machine Learning
Efficient Learning and Symmetry Discovery under Exact Invariances
Ashkan Soleymani, Behrooz Tahmasebi, Patrick Jaillet et al. (+1 more)
Learning with group invariances is central to many scientific and
geometric learning problems, yet its computational foundations remain poorly understood. Even for classical supervised regression settings, it has been unclear whether one can efficiently compute a regression function that is exactly invariant to a given group action. Recent work showed that exact invariance can be enforced in
polynomial time when the underlying group is finite and known, but left open the cases of infinite groups and unknown
symmetries. In this paper, we resolve both challenges. First, we present the first
polynomial-time
algorithm for learning with exact group invariances that applies uniformly to finite and infinite groups. The runtime is
polynomial in the data dimension and sample size, and independent of the group, while achieving strong generalization guarantees. This provides a computational explanation for the empirical success of invariant and equivariant methods in
geometric machine learning and partially answers a recent open question in the literature. Second, we study learning in the
symmetry discovery setting, where the invariance group is unknown. Focusing on the subgroup
lattice of a finite group, we show that exact
symmetries can be identified from data and exploited for learning in
polynomial time. For regression over finite-dimensional feature spaces, our
algorithm provably recovers the underlying
symmetry, matches the minimax-optimal sample complexity of the known-
symmetry setting, and runs in time
polynomial in the data dimension and sample size. Our analysis relies on tools from random Cayley graphs and expander theory, which may be of independent interest.
Read the full abstract ▾
All authors Ashkan Soleymani, Behrooz Tahmasebi, Patrick Jaillet, Stefanie Jegelka
Computer Vision
LoGAN: Multilingual Font Localization with Generative Agents
Zhuoning Yuan, Ta-Ying Cheng and Benjamin Klein
Localizing a font into new
languages is a highly intricate task requiring precise design adaptation of glyphs, color/texture, and spacing/kerning, from source to target
languages. Most existing methods focus on single glyph generation with limited capability in handling
multilingual font rendering. In this work, we propose LoGAN, a VLM-based agentic framework for few-shot
multilingual font localization, which takes in a small number of individual glyphs from a font or letters from a logo and uses them to generate complete character sets in other
languages. LoGAN breaks down this task into multiple components: a glyph-level
diffusion model, a style finetuning module, a spacing and kerning transfer
algorithm, and a texture expansion model, with a VLM
agent coordinator. LoGAN achieves broad
language coverage for font localization with various styles, including Chinese/Korean/Japanese (CJK). We evaluate our approach on both font and real-world logo
datasets spanning more than 27
languages and compare it against both specialized font generation and state-of-the-art image editing models with strong text rendering capabilities (e.g., FLUX, Nano-Banana). Our approach yields higher glyph fidelity while maintaining better style, texture, and kerning consistency according to both quantitative and qualitative evaluations.
Read the full abstract ▾
Cryptography and Security
CIPHER: Benchmarking Cross-record Inference over Privacy-Hardened Evidence Records
Suparno Roy Chowdhury, Manan Roy Choudhury, Dhruv Madhwal et al. (+1 more)
Reasoning over
privacy-constrained records requires combining structured attributes with evidence from free-text narratives. We introduce CIPHER (Cross-record Inference over
Privacy-Hardened Evidence Records), a
benchmark of expert-validated questions from consumer-finance, clinical, and law-enforcement records. The questions cover common tabular operations and include executable SQL supervision. We evaluate
retrieval, prompting, table-specialist, and hybrid symbolic-neural systems under native redaction and surrogate-based evidence restoration. All system families exhibit substantial failures even when supporting records are provided. Most errors arise from incorrect record selection and predicate interpretation rather than arithmetic execution.
Privacy transformations have non-uniform effects, sometimes obscuring necessary evidence and sometimes reducing distraction. CIPHER provides a reproducible testbed for diagnosing these failures and assessing how transformations of sensitive text affect
reasoning over hybrid records.
Read the full abstract ▾
All authors Suparno Roy Chowdhury, Manan Roy Choudhury, Dhruv Madhwal, Vivek Gupta
Networking
ASTRA: Low-Overhead Runtime Architecture for STReam Adaptation in Video Analytics
Mahshid Ghasemi, Zoran Kostic, Javad Ghaderi et al. (+1 more)
Real-time
video analytics is crucial for smart city applications and cloud-connected vehicle control. To improve analytics accuracy, it is desirable to process the
video at the highest resolution and frame rate. However, due to limited resources, streaming and processing
video at the highest resolution and frame rate from all cameras is not feasible and adversely affects the analytics latency. Intelligent adaptation of cameras' resolutions and frame rates based on network conditions and the
video content is crucial in order to optimize the performance. In this paper, we present ASTRA, a low-overhead runtime architecture for online adaptation of live camera analytics at the edge. ASTRA can execute various online
algorithms as a black box. We deployed ASTRA in the realistic NSF COSMOS testbed and uniquely assessed its real-time performance using COSMOS' street-level cameras. We further evaluated ASTRA with up to eight emulated cameras by streaming a comprehensive
video dataset under real-world network conditions. We used ASTRA's architecture to evaluate the practical performance of several classes of adaptation
algorithms, including theoretical and empirical methods. The results indicate that ASTRA can provide system reliability (i.e., the probability of meeting accuracy and latency requirements) of more than 90% while maintaining performance within a deviation of less than 10% from optimal offline performance with average GPU utilization overhead of around 2% per camera.
Read the full abstract ▾
All authors Mahshid Ghasemi, Zoran Kostic, Javad Ghaderi, Gil Zussman
Machine Learning
HyperTransfer: Understanding the Equivalence between Base Optimizer and Hyperball
Jinghui Yuan, Hongtao Zhang, Jade Zou et al. (+4 more)
Hyperball optimizers constrain parameter norms and update only their directions, establishing a distinct paradigm for neural network optimization. Although this geometry appears fundamentally different from that of conventional Base Optimizers, which update both parameter norms and directions, we show that the two paradigms are dynamically equivalent for scale-invariant networks. Building on this equivalence, we propose HyperTransfer, which constructs a Hyperball optimizer that reproduces the dynamics of a target Base Optimizer using only its initialization and learning-rate schedule, without running the target optimizer itself. We further derive the inverse mapping and extend the framework to non-scale-invariant networks. Experiments show that both HyperTransfer and the inverse mapping produce loss trajectories nearly identical to those of their targets, suggesting that Hyperball dynamics are governed primarily by the induced effective learning-rate schedule and optimizer state.
Read the full abstract ▾
All authors Jinghui Yuan, Hongtao Zhang, Jade Zou, Tianyu Li, Wenjie Zhou, Tianyu He, Wei Chen
Numerical Analysis · Cross-listed from physics.class-ph
Formation of grain boundaries in ductile single crystals under plane-strain simple shear: a block-coordinate finite element method
Khanh Chau Le and Thanh Danh Nguyen
Large plastic deformation can drive an initially uniform single
crystal to spontaneously subdivide into misoriented grains separated by thin dislocation walls – a pattern-forming instability rooted in the loss of convexity of the
crystal's elastic energy at large strain. We study this phenomenon for a ductile
crystal in plane-strain simple shear within continuum dislocation theory, using a polyconvex (Ciarlet–Geymonat) elastic energy that guarantees existence of minimizers for the coupled deformation–slip problem. Minimizing over the plastic slip yields a condensed energy of double-well form whose non-quasiconvexity favours a lamellar microstructure; the gradient of the geometrically necessary dislocation density regularizes it, giving the grain boundaries a finite thickness and energy as functions of the misorientation angle. A block-coordinate finite element scheme – alternating a convex non-smooth solve for the slip with a Levenberg-regularized Newton solve for the deformation – resolves this microstructure numerically and detects its spontaneous onset, reproducing the lamellar grain structure in agreement with the closed-form analysis.
Read the full abstract ▾
Computer Vision
ARNAI: Artifact Removal Network based on Autoencoding and Inpainting for Robust Spinal Image Segmentation and Measurement
Sang-Jin Park, Jinyoung Choi, Seokwon Kim et al. (+13 more)
Purpose: This study aims to develop an AI framework applicable for postoperative imaging for automated measurement of spinopelvic parameters on radiographs with robustness to the presence of spinal implants. Materials and Methods: We retrospectively reviewed lateral lumbar spine radiographs from two institutions (Internal: January 2017–December 2024; External: October 2021–September 2025). We developed the Restore, Segment, and Measure (RSM) framework, incorporating a novel Artifact Removal Network based on Autoencoding and Inpainting (ARNAI) to mitigate implant-related artifacts in postoperative radiographs.
Segmentation and spinopelvic parameter (PT, LL, SS, SCA) measurement performance were assessed using Wilcoxon signed-rank tests and intraclass correlation coefficients. Results: When ARNAI was added to a recent
Transformer-based
segmentation model, FCBFormer, the mean DSC increased to 0.870 from 0.814, with marked gains at L3–L5 and smaller improvements at L1–L2. On 91 radiographs with implants, the mean L4–L5 segmental Cobb angle error decreased to 4.7 {\deg} from 15.6–16.2 {\deg}, an average error reduction of 70%. The ICC for L4–L5 segmental Cobb angle improved to 0.54 (Rater 1) and 0.59 (Rater 2) from 0.18, and ICCs for pelvic tilt, lumbar lordosis, and sacral slope all exceeded 0.70. The improvement in L4–L5 segmental Cobb angle error was statistically significant in the internal implant-containing cohort after correction for multiple comparisons. Conclusion: The proposed RSM framework improved automated spinopelvic parameter measurement in implant-containing postoperative radiographs. By mitigating implant-related artifacts, ARNAI improved
segmentation and downstream measurement accuracy, with the greatest benefit observed for L4–L5 segmental Cobb angle estimation, where the mean error was reduced by approximately 70%.
Read the full abstract ▾
All authors Sang-Jin Park, Jinyoung Choi, Seokwon Kim, Seungeon Song, Insu Park, Dougho Park, Taeyeon Kim, Youjin Lee, Donghoon Yang, Jaeman Cho, Joongwon Yang, Mansu Kim, Heumdai Kwon, Hong Gyu Baek, Dae Chul Cho, Injung Kim
Computer Vision · Cross-listed from eess.IV
AstraMoE-SR: Trajectory-Guided Diffusion for Blind Satellite Jitter Deblurring and Super-Resolution
Yi-Chung Lai, Chin-Tien Wu and Yu-Chih Chen
Pushbroom satellite imaging couples limited spatial resolution with platform attitude instability. Platform jitter produces spatially varying motion blur because each scan line is acquired under a different instantaneous attitude, while perspective geometry causes the same perturbation to induce different pixel displacements across the field of view. Existing blind restoration methods that assume a spatially invariant kernel and satellite jitter correction methods that rely on auxiliary observations are therefore not directly applicable. We present AstraMoE-SR, a single-image framework that jointly restores motion blur and spatial resolution without auxiliary measurements. Rather than estimating a blur kernel, we infer how the camera moved by reparameterizing degradation as a local exposure trajectory under pushbroom geometry. A conditional
diffusion model estimates the trajectory distribution, mitigating the over-smoothing of high-frequency jitter by deterministic point estimation. The predicted trajectory conditions a pretrained latent
diffusion backbone through trajectory-guided
geometric alignment and spatially adaptive reconstruction. We further show that the remaining point-wise trajectory error is consistent with intrinsic jitter-phase ambiguity that is not resolved by increasing
estimator capacity. On all 1,411 DOTA-v1.0 images degraded using our physically motivated forward model, AstraMoE-SR is the only evaluated method to outperform the no-restoration baseline across every fidelity metric, improving on StableSR by 0.64 dB PSNR, 15.2% LPIPS, and 0.091 DINO feature similarity. Reconstructions conditioned on predicted trajectories differ negligibly from those using ground-truth trajectories, indicating that the estimates retain the degradation information required for effective restoration.
Read the full abstract ▾
Computer Vision
Fine-Grained Visual Preprocessing and Dual-Stream Temporal Modeling for Multimodal Sentiment Analysis on Social Media
Su Li, Yigong Zhang, Lei Xiong et al. (+1 more)
Multimodal sentiment analysis often remains text-dominant due to raw-
video noise and insufficient temporal modeling. Using CH-SIMS v2.0S, this study proposes three improvements: the NAPS pipeline—a seven-stage system integrating face tracking,identity
embedding, and normalized lip-motion analysis to reduce visual noise;DS-TANet, combining an EfficientNetB2 static stream, RAFT optical-flow motion stream, motion-guided
attention, and Bi-GRU temporal modeling; and DS-TAFNet, fusing visual and MacBERT-Base textual representations via concatenation fusion. With NAPS, the static visual baseline achieves 80.98% Macro F1, comparable to the text baseline of 80.55%; DS-TANet improves visual Macro F1 to 82.58%;and DS-TAFNet achieves 87.49% accuracy and 87.48% Macro F1. These results demonstrate that improving visual input quality and temporal representation is more effective than increasing fusion complexity under limited-data conditions.
Read the full abstract ▾
All authors Su Li, Yigong Zhang, Lei Xiong, Chune Li
Machine Learning
NeuCME: Toward Dynamic Multimodal Continual Learning via Neural Combinatorics of Multiple Experts
Kai Guo, Chuanbin Liu, Peng Hu et al. (+2 more)
Multimodal continual learning has recently shown great potential for developing
agents with human-like intelligence by continuously learning new tasks across multiple modalities. However, existing methods typically assume that the set of modalities per task is predefined and fixed. In this paper, we investigate a more realistic learning setting, referred to as dynamic
multimodal continual learning, in which the set of modalities may vary across tasks rather than remaining fixed. This setting involves two primary challenges: (i) spatio-temporal catastrophic forgetting and (ii) adaptive
multimodal fusion. To address these challenges, we propose NeuCME (as shorthand for Neural Combinatorics of Multiple Experts), a novel framework designed to effectively learn and integrate knowledge across tasks with varying modalities. The proposed NeuCME model comprises three key components, namely modality-combinational rehearsal, multi-gated mixture-of-experts, and task relevance-guided
distillation. Furthermore, we formulate an evaluation metric to quantify the dynamism of task sequences and then set up a comprehensive
benchmark with different degrees of dynamism. Extensive experiments using four real-world
datasets demonstrate that the proposed NeuCME outperforms state-of-the-art methods markedly.
Read the full abstract ▾
All authors Kai Guo, Chuanbin Liu, Peng Hu, Hao Wang, Xi Peng
Artificial Intelligence
RedKnot-MLA: Multi-Head Offline-Online Reuse for DeepSeek-V4 Long-Context Serving
Yang Liu, Zhaokai Luo, Huayi Jin et al. (+10 more)
Multi-head latent
attention (MLA) exposes many logical query heads through one packed latent KV stream. This representation is
memory efficient, but it removes the physical per-head cache boundary assumed by conventional head-wise reuse. We present our system, a DeepSeek-V4 realization of RedKnot's head-aware reuse principle. Each immutable document is processed offline at canonical position zero; certified Local-head contributions are retained as MLA-Off. At serving time, query-side RoPE relocation restores the document's request position, a small Global-head set and protected Local
token rows are recomputed as MLA-Online, and the two paths are merged before a single shared output projection. The packed MLA latent is never split. DeepSeek-V4-Flash uses 37 reusable layers and a 56/8 Local/Global partition, giving a 75.29% analytic logical head-row ceiling; the Pro-0813 profile uses 55 layers and 112/16 heads, giving 78.89%. Frozen Flash operating points show hot-artifact TTFT speedups of 2.02-3.84x. At 256K, the archived three-
dataset study reports an aggregate F1 change of +3.24 percentage points, an EM change of +4.16 points, and a 78.7-79.5% analytic major-operator arithmetic saving, while one
dataset decreases by 2.81 F1 points. A separate author-reported 256K hot-artifact QPS measurement is approximately 2.0x; because its raw concurrency trace is not included in this bundle, we mark it as preliminary rather than archived evidence. We describe the factorization, position repair,
token-row closure, sparse-MoE support, TP8 integration, and the measurement boundaries needed to interpret these results.
Read the full abstract ▾
All authors Yang Liu, Zhaokai Luo, Huayi Jin, Ruozhou He, Chenchen Hong, Mingxiao Ma, Biao Zhang, Zhiyong Wang, Boyu Wang, Guanjie Chen, Yifei Liu, Tao Xie, Junhao Hu
Computer Vision
GIFT: Goal-Injected Fine-Tuning for Efficient Manipulation Policy Adaptation
Xiaoyuan Fang, Shuo Feng, Yuxuan Wang et al. (+3 more)
Compared with relying solely on initial observations and
language instructions, predicting goal images with generative models as high-level visual guidance can significantly enhance the robustness of
Vision-
Language-Action (VLA) models. However, most existing foundation models have not systematically incorporated goal image conditioning due to the high computational training cost. To this end, we propose Goal-Injected Fine-Tuning (GIFT), a lightweight and efficient fine-tuning framework that seamlessly integrates generated goal images into multiple representative pretrained VLA models. Our approach introduces goal image features into observations via a zero-initialized convolution which progressively grows parameters from zero and prevents harmful noise from disrupting the pretrained policy during fine-tuning. As training proceeds, goal information is gradually incorporated, enabling efficient goal understanding without disrupting model stability. We further introduce a refined image editing method to generate semantically and visually consistent goal images from initial observations and task instructions. Experiments show that goal-aware VLA models achieve substantial performance gains across tasks: with only a single epoch of fine-tuning, GIFT outperforms the base model by 6.0% and 13.4% on two SIMPLER settings, and by 4.7% on LIBERO, demonstrating both efficiency and effectiveness.
Read the full abstract ▾
All authors Xiaoyuan Fang, Shuo Feng, Yuxuan Wang, Enhua Cheng, Peng Zhou, Piji Li
Numerical Analysis
Limiter-based fully-discrete entropy stable explicit DG schemes for ideal MHD equations
Yuchang Liu, Yan Jiang and Zheng Sun
We propose a class of high-order fully-discrete
entropy stable (ES) explicit discontinuous Galerkin (DG) solvers for the compressible ideal magnetohydrodynamics (MHD) equations. Our main theoretical contribution is the introduction of a novel generalized-path-decomposition framework for MHD equations in Godunov's symmetric form. By innovatively interpreting the interior volume integral of the non-conservative source term as a path integral along a generalized path constructed by the solution
polynomial, we establish the weak
cell entropy inequality for the fully-discrete DG schemes. This overarching framework also accommodates other existing DG solvers based on the symmetric form. Combined with a carefully designed ES limiter, the proposed scheme satisfies the genuine fully-discrete
cell entropy inequality. With this property, a Lax–Wendroff-type
theorem can be obtained to show that the solution limit satisfies the
entropy condition. Finally, the scheme is naturally compatible with the locally divergence-free space. Extensive numerical experiments demonstrate the scheme's low numerical dissipation and strong robustness.
Read the full abstract ▾
Computer Vision
CGSM: Concept-Guided Segmentation Model for Precise Pulmonary Lesion Delineation
Changheng Lin, Wenjie Zhang, Yushan Lu et al. (+3 more)
Accurate
segmentation of pulmonary lesions is essential for effective clinical diagnosis and treatment strategies. Existing
segmentation approaches often lack task-specific semantic guidance, as text-based annotations typically offer coarse localization of lesions, leading to inadequate delineation of lesion boundaries and poor performance on small-scale lesions. To address this, we propose CGSM, a Concept-Guided
Segmentation Model that integrates LLM-generated and clinically reviewed concepts into the
segmentation process. Specifically, we design a Concept-Visual
Alignment Module (CVAM) to activate relevant
tokens within the concepts that align with visual features, enhancing the interaction between textual and visual information. In addition, we introduce a Concept Modulated Decoder (CM-Decoder), which uses concepts from CVAM as modulation signals to facilitate the adaptive fusion of image and text features, improving the
segmentation accuracy. Extensive experiments on two public
datasets show that CGSM achieves state-of-the-art performance, with results of 91.59% Dice and 84.49% mIoU on the QaTa-COV19
dataset, demonstrating its effectiveness in pulmonary lesion
segmentation.
Read the full abstract ▾
All authors Changheng Lin, Wenjie Zhang, Yushan Lu, Xinyue Yan, Xiao Jia, Wei Zhang
Robotics
WM-Craftnet: World Synesthesia Model for Generalizable and Robust Dexterous In-Hand Manipulation
Jie Yin, Zeyuan Zhao, Xiaojing Tan et al. (+3 more)
Generalizable and robust dexterous in-hand manipulation requires a policy to infer object pose, geometry, contact, and potential slip from partial and noisy observations. Although recent tactile and visuotactile RL methods achieve strong in-hand rotation in controlled settings, their robustness often degrades under pose shifts, force disturbances, and object variation. We propose WM-Craftnet, a world-model-conditioned framework that learns compact action-conditioned latent dynamics from proprioception, depth, tactile sensing, and actions, supervised by
multimodal reconstruction and reward prediction. Rather than using the world model for latent imagination or policy optimization, WM-Craftnet uses the learned World Synesthesia Model (WSM) as recurrent task context for an asymmetric actor–critic policy. Importantly, WSM is trained to reconstruct clean depth targets from noisy depth inputs, providing a denoised
geometric state for real-
robot deployment. Ablations over recurrent baselines, auxiliary heads, tactile masking, and WSM modality heads show that predictive world modeling, clean-depth supervision, and tactile contact cues all shape the learned state. A WSM pretrained on nine \(z\)-axis objects serves as a reusable prior for \(49\)-object downstream policy learning. This context improves multi-object rotation, with quantitative and qualitative evidence for unseen-object, perturbation-recovery, and sim-to-real transfer.
Read the full abstract ▾
All authors Jie Yin, Zeyuan Zhao, Xiaojing Tan, Yang Liu, Chiyu Wang, Xinyang Gu
Human-Computer Interaction
Adaptive Complementarity in Human-AI Systems: Architecture as a State-Shaping Choice
Babak Heydari
Human-AI interaction can improve current performance while changing the capabilities and relationships on which future performance depends. We develop adaptive complementarity, a framework for choosing interaction architecture with these state consequences in view. Access, information exposure, task allocation, timing, and communication can alter which arrangement will be valuable later; their settings can often be reset faster than the capabilities, search patterns, or conventions they create. Three mechanisms organize the argument: information exposure and collective search, delegation and capability
evolution, and strategic interdependence and information governance. Their integration yields cross-mechanism implications, including conditions under which a loss of expertise heterogeneity increases the information differentiation required to preserve independent search. We distinguish strong human-AI complementarity from advantage over another workflow and from advantage over an evolving reference policy. A computational illustration examines scarce human review in a workflow whose success requires several specialized stages. Review develops human expertise and AI capabilities, changing where subsequent review is most valuable. Adaptive allocation improves net output over untailored procedures and the optimal predetermined calendar. An understandable priority rule derived from the adaptive solution retains essentially all of its gain: the procedure stays fixed while assignments respond to the capabilities that interaction creates. The framework directs evaluation toward the states present interaction creates, their consequences for later architectural fit, and the conditions under which observing and responding to them is worthwhile.
Read the full abstract ▾