Peer Revenue Past citations are no guarantee of future returns

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science

cs Watch Computer Science

Tuesday 29 September

Machine Learning

SemPSG: A Semantic Channel-Aware Foundation Model for Polysomnography Analysis

Junyu Chen, Chenxi Liu, Shiqin Tang et al. (+5 more)

Polysomnography (PSG) integrates multiple physiological signals to provide a comprehensive characterization of human sleep, yet its heterogeneous channel configurations across centers pose substantial challenges for transferable representation learning. Existing foundation models mainly focus on physiological modeling or temporal learning, while channel identity is often treated as a fixed structural index, overlooking the physiological semantics encoded by signal modality and reference configuration. To this end, we propose SemPSG, a Semantic channel-aware foundation model for heterogeneous PSG analysis. SemPSG explicitly represents the physiological semantics of channel identity and incorporates them into both signal representation learning and channel aggregation, enabling flexible modeling across diverse data configurations. Specifically, a semantic-conditioned time-series encoder captures signal-specific temporal dynamics and cross-signal interactions, while a multi-view image encoder extracts complementary time-frequency and morphological patterns from the same physiological recordings. We evaluate SemPSG on sleep and health-related tasks, including sleep staging, sleep-disorder breathing analysis, disease prediction, cognition and emotion recognition, and demographic estimation. Extensive experiments demonstrate consistent improvements over both general-purpose time series foundation models and PSG-specific foundation models, together with generalization across heterogeneous datasets across diverse channel configurations.
Read the full abstract

All authors Junyu Chen, Chenxi Liu, Shiqin Tang, Hao Miao, Wanyun Ling, Ziyue Li, Hongbin Liu, Gaofeng Meng

Human-Computer Interaction

RobotEQ 3.0: Towards Personalized Social Proactive Intelligence in Embodied Agents

Shufan Zhang, Xinyi Che, Kuofei Fang et al. (+8 more)

Social Proactive Intelligence (SPI) is an emerging research area, aiming to shift embodied agents from reactive assistance toward proactively understanding human needs and executing socially desirable actions. Prior work has largely centered on the average user. However, human expectations are inherently diverse, and prior work overlooks individual nuances. To bridge this gap, we introduce RobotEQ 3.0, a benchmark for Personalized SPI. (Dataset) We first profile participants via a structured questionnaire covering factors that are correlated with human expectations of embodied agents, such as basic demographics and personality traits. Participants then select their preferred actions from a set of candidates. Unlike prior SPI benchmarks that focus on assessing behavioral appropriateness, our task centers on predicting the actions preferred by a specific user, thereby capturing human subjectivity. The resulting dataset establishes explicit links between individual traits and behavioral preferences. (Solution) We observe substantial inter-annotator variance, confirming that user preferences over actions are highly individualized. This motivates our exploration of Personalized SPI, in which user traits serve as additional inputs to predict individual preferences. Experimental results show that incorporating user traits can aid personalized prediction. This work aims to shift the research paradigm from developing agents suited for the average user to designing systems tailored to specific individuals.
Read the full abstract

All authors Shufan Zhang, Xinyi Che, Kuofei Fang, Xuehao Wang, Liyi Liu, Junqing Wu, Jiayi Cao, Ziyanghui Wang, Yanhan Huang, Chuyu Wu, Zheng Lian

Computation and Language

Generating Edit-Inducing Questions for AI Research Manuscripts

Sebastian Joseph, Zichao Wang, Jennifer Healey et al. (+3 more)

We study the ability of LLMs to generate edit-inducing questions whose answer will improve a paper draft. On a dataset of paired submission and camera-ready papers from ICLR and NeurIPS, we compare the helpfulness of questions from GPT models with or without full paper context to that of human reviewers. GPT produces more edit-inducing questions and its questions are associated with more extensive edits and cover a broader range of edited content compared to questions from reviewers. However, a much smaller percentage of the GPT questions are edit-inducing. Our analyses confirm that automated questions can be beneficial to authors and highlight an example task where proper attending to long context deteriorates reasoning model ability to produce helpful output.
Read the full abstract

All authors Sebastian Joseph, Zichao Wang, Jennifer Healey, Alexa Siu, Junyi Jessy Li, Ani Nenkova

Computer Vision

CrossTimeEdit: A Decade-Spanning Cross-View Dataset and Reward-Guided Editing for Historical Street-View Generation

Hanwen Lu, Jun He, Mingjia Yang et al. (+4 more)

Historical street-view imagery records urban evolution, but uneven coverage leaves substantial gaps in historical records. Generating plausible past appearances requires restoring changed structures while preserving persistent scene content. We construct VIGOR-his, a decade-spanning cross-view dataset containing 43,653 location-level quadruplets across 11 cities on three continents. Its automated pipeline performs spatial pairing, consistency screening, change classification, and the generation and validation of satellite-based change descriptions and local editing instructions. Based on VIGOR-his, we propose CrossTimeEdit, a model that reformulates historical street-view generation as editing, using recent street views to constrain viewpoint and unchanged appearance and temporal satellite differences as change evidence. Starting from FLUX.2 [Klein] 4B, we train CrossTimeEdit through supervised fine-tuning (SFT) followed by online reinforcement learning (RL). We design three street-view editing criteria, namely Instruction Alignment (IA), Background Preservation (BP), and Quality and Physical Plausibility (QP), as both RL reward dimensions and evaluation metrics. We optimize this multi-reward objective using Within Group Relative Policy Optimization for flow-matching models (Flow-GRPO) with Group reward-Decoupled Normalization Policy Optimization (GDPO), which normalizes each reward dimension before aggregation. CrossTimeEdit improves overall performance across the three editing criteria by 17.12% over the pretrained baseline and outperforms cross-view generation models in scene consistency, visual realism, and perceptual quality. The implementation code, dataset, and model weights are available at https://luhanwen67.github.io/CrossTimeEdit-release/.
Read the full abstract

All authors Hanwen Lu, Jun He, Mingjia Yang, Hao Wei, Jinhao Huang, Yi Lin, Xiang Zhang

Numerical Analysis

CI-PINN: Causal Integral Physics-Informed Neural Network for Solving Evolution Equations

Xiaodong Feng, Ziyu Sun, Tao Tang et al. (+2 more)

Physics-informed neural networks (PINNs) solve partial differential equations (PDEs) by incorporating governing physical laws into the training loss. For evolution equations, however, their conventional pointwise space–time representation does not explicitly encode temporal dependence, which can hinder accurate prediction. To mitigate this limitation, this work proposes a novel neural architecture termed a causal integral neural network (CinNet). The core module of CinNet is a Volterra-type causal integral term, which aggregates historical features to encode temporal dependence, thereby incorporating temporal causality at the architectural level rather than through training-level modifications as in many existing methods. Building on CinNet, we further develop a causal integral physics-informed neural network (CI-PINN) for solving evolution equations. Extensive numerical experiments on benchmark evolution equations demonstrate that the presented method outperforms various baseline PINN variants in terms of solution accuracy, with pronounced superiority under sparse-collocation scenarios. Additional empirical analyses show that CI-PINN exhibits low sensitivity to hyperparameter choices, while ablation studies confirm the effectiveness of the proposed network components.
Read the full abstract

All authors Xiaodong Feng, Ziyu Sun, Tao Tang, Xiaoliang Wan, Tao Zhou

Machine Learning

Selective Elicitation as a Commercial Influence Channel: A Reproducible Synthetic Shopping-Agent Stress Test

Jiapeng Li

A commercial incentive need not enter the final ranking algorithm to affect a shopping assistant's recommendation: it may instead influence which preference question the assistant asks. We make this distinction experimentally observable in a deliberately small, synthetic setting. Each task has two products, three verified numerical attributes, a price limit, and a private fixed preference vector. An honest simulated user answers one pairwise question. A separate recommender receives the products and this answer but not the sponsorship assignment. We contrast a neutral question, a soft commercial instruction, and an explicitly adversarial instruction to ask about the sponsor's advantage while omitting the rival's advantage. Across 40 held-out sponsorship-assignment cases (20 distinct catalog-preference contexts), the soft instruction changes no selections. The targeted instruction raises sponsored selection by 0.30 and reduces mean synthetic utility by 0.0547 relative to neutral questioning (95% context-bootstrap interval [-0.0828, -0.0291]) for one language-model recommender. A fixed Bayesian recommender shows a similar effect; a second model makes the same choices on all 120 frozen question-answer inputs. A terminal-answer consistency judge rates all 20 sampled targeted answers consistent, although five have synthetic regret above 0.05; a separate question-coverage dimension flags their one-sided elicitation. A robust partial-preference certificate remains valid under the stipulated synthetic utility but certifies only 16 of 40 targeted cases and is not better than asking a neutral question directly. These results establish neither typical behavior under advertising incentives nor effects on actual consumers.
Read the full abstract

Machine Learning

Do LLMs Really Forget? Hidden-State Leakage in Model Unlearning and How to Fix it

Hadi Reisizadeh, Jiajun Ruan, Sijia Liu et al. (+1 more)

Unlearning in large language models (LLMs) is typically evaluated at the output level, where a model appears to suppress sensitive or undesirable content. In this work, we show that such evaluations can create an illusion of forgetting: even when output-level leakage is eliminated, sensitive information can remain encoded in the model's hidden representations. We first provide a theoretical analysis establishing a fundamental separation between output suppression and representational erasure. Specifically, we show that the decoder can be made arbitrarily insensitive to sensitive directions, driving output-level leakage to zero, while the hidden representations retain the underlying information. To empirically validate this phenomenon, we train generative probe decoders on hidden states across transformer layers, enabling layer-wise measurement of information leakage. Across three widely used benchmarks, TOFU, MUSE, and WMDP, and state-of-the-art unlearning methods, we find that substantial sensitive information remains recoverable from hidden representations, even when standard output-level metrics indicate successful unlearning. To address this gap, we propose Probe-Adversarial Representation Suppression (PARS), an unlearning objective that adversarially minimizes the extractable information from hidden representations. PARS directly targets representational leakage and provides significantly stronger guarantees of erasure under adversarial probing and relearning attacks, outperforming all evaluated baselines. Our results highlight a fundamental limitation of existing unlearning paradigms and suggest that true forgetting in LLMs requires controlling not only model outputs, but also the information encoded in hidden representations. Codes are available at https://github.com/OptimAI-Lab/HiddenStateUnlearning.
Read the full abstract

All authors Hadi Reisizadeh, Jiajun Ruan, Sijia Liu, Mingyi Hong

Artificial Intelligence

Multi-Channel Mitigation of Source-Trust Shortcuts in Fact-Checking RL Agents

Jianchang Su, Yiwei Yang and Wei Zhang

Retrieval-augmented fact-checkers often receive a reliability label, such as HIGH or LOW trust, for each evidence source. These labels should adjust the model's confidence and its decision to search for more evidence, while the verdict should follow the evidence content. We introduce TrustSwap, a counterfactual test that swaps, lowers, or removes source labels while keeping every evidence text fixed, and measures its three output channels (the verdict, the confidence, and the search decision) separately. Across untrained and RL-trained models at two scales, three datasets, and two prompts, confidence and search respond to the labels as intended in 49 of 50 comparisons, yet a label change alone alters 4-23% of confident verdicts for Qwen3 models and up to 50% for an existing RL-trained fact-checker. Standard GRPO fine-tuning amplifies this shortcut at 8B in all six settings. To reduce it, we propose trust-swap augmentation (TSA), which trains GRPO on each claim with both its original and its label-swapped evidence under the same gold verdict. At 4B, TSA lowers the verdict flip rate by 7-35% (relative) in four of six settings, keeps accuracy and the intended confidence and search responses, outperforms reward-based alternatives in the main setting, and carries over to an unseen label-removal perturbation. An added consistency reward helps on the trained-on swap but not on unseen perturbations. At 8B, TSA's effect is not detectable, which makes scale the main open question.
Read the full abstract

Machine Learning

Communication-Efficient Agnostic Federated Learning via Faster Convergence and Compression

Haomin Bai, Junyan Sun, Sifan Yang et al. (+2 more)

Agnostic federated learning (AFL) seeks a model that performs reliably across $m$ heterogeneous workers, but communication remains a bottleneck. We improve communication efficiency by reducing the number of synchronization rounds via faster convergence and the communication cost per round via compression. We first propose AFL-BR, which updates the dual weights over workers using online mirror ascent with KL divergence and blockwise restarts. It achieves an $O((\log m)^{1/4}T^{-1/8})$ stationarity rate after $T$ update rounds, reducing the $m$-dependence of the synchronization rounds required for convergence from polynomial to logarithmic order. Building on AFL-BR, we develop AFL-Com by applying bidirectional compression with error feedback (EF). Instead of compressing local gradients, workers apply EF to their dual-weighted gradients, enabling direct control of the aggregated compression error under time-varying weights. We then establish an $O((\delta^{-1}+(\log m)^{1/4})T^{-1/8})$ stationarity rate for AFL-Com under general $\delta$-approximate compressors and improve the $\delta$-dependence from $\delta^{-1}$ to $\delta^{-1/2}$ for additive-and-idempotent compressors with shared randomness (SR). With suitable compression levels, AFL-Com retains the same convergence rate as AFL-BR at a lower per-round communication cost, yielding reductions in total communication complexity by factors of $(\log m)^{1/4}$ with Top-$k$ and $(\log m)^{1/2}$ with Rand-$k$ and SR. Experiments validate the improved synchronization and communication efficiency of our methods.
Read the full abstract

All authors Haomin Bai, Junyan Sun, Sifan Yang, Bo Xue, Lijun Zhang

Machine Learning · Cross-listed from eess.SP

Best Practices in EEG Analysis: Preprocessing, Modeling, and Machine Learning

Parsa Razmara, Woojae Jeong, Aditya Kommineni et al. (+3 more)

Electroencephalography (EEG) analysis requires careful choices in preprocessing, statistical modeling, and machine learning because EEG signals are highly susceptible to artifacts, volume conduction, low signal-to-noise ratio, and substantial inter-subject variability. This chapter provides a practical and methodological guide to modern EEG analysis, spanning EEG preprocessing, artifact removal, filtering, bad-channel detection and interpolation, re-referencing, independent component analysis (ICA), and preprocessing of simultaneous EEG-fMRI recordings. We review major approaches for computational EEG analysis, including event-related potentials (ERPs), time-frequency analysis, functional and effective connectivity, source localization, multivariate decoding, permutation testing, and multiple-comparison correction. We then examine machine-learning methods for EEG, from feature-based classifiers to deep learning and emerging EEG foundation models, with emphasis on cross-subject generalization, limited-data regimes, data leakage, evaluation metrics, and fair benchmarking. Reproducibility is treated as a core requirement throughout, including transparent preprocessing, BIDS-EEG data organization, standardized derivatives, preservation of raw data, and FAIR data practices. The chapter is intended as a practical reference for researchers developing reliable, interpretable, and reproducible EEG analysis and machine-learning pipelines.
Read the full abstract

All authors Parsa Razmara, Woojae Jeong, Aditya Kommineni, Raymundo Cassani, Richard Leahy, Takfarinas Medani

Machine Learning

Act First, Reason Later: Accelerating On-Policy Distillation for Multi-Turn Agents via Reference-Conditioned Inverse Dynamics

Zubin Zheng, Jiahao Wu, Shaofeng Zhang et al. (+3 more)

On-policy distillation (OPD) trains multi-turn language agents with dense teacher supervision on student-generated responses. However, standard think-then-act rollouts require lengthy reasoning before each short action, delaying environment transitions and experience collection. Generating actions directly reduces this delay but can degrade rollout quality. To address this, we propose ActFirst-OPD, an act-first, reason-later training framework that decouples environment interaction from full-response generation. The student infers and executes actions through reference-conditioned inverse dynamics using its current interaction context and a reference next observation, and switches to autonomous next-action prediction when the resulting transition deviates from the reference trajectory. From the collected interaction contexts, the student asynchronously generates full think-then-act responses for token-level teacher supervision. Experiments across 0.6B-, 1.7B-, and 4B-parameter Qwen3 students show that ActFirst-OPD achieves average wall-clock training speedups of $2.3\times$ on ALFWorld, $1.8\times$ on WebShop, and $4.9\times$ on ScienceWorld over Vanilla OPD. It matches or exceeds all compared OPD baselines in mean task success rate across eight of nine benchmark-model settings. These results demonstrate that reasoning need not block acting during multi-turn agent distillation.
Read the full abstract

All authors Zubin Zheng, Jiahao Wu, Shaofeng Zhang, Zhirui Zhang, Yew-Soon Ong, Shengcai Liu

Computer Vision

Pixel-wise Exposure for Highly Robust In-Vehicle Remote-PPG

Jieying Wang, Xinqi Cai, Caifeng Shan et al. (+1 more)

Remote photoplethysmography (rPPG) offers a promising non-contact solution for heart rate monitoring, yet its real-world robustness is fundamentally limited by an inherent hardware limitation: existing camera exposure control paradigms, whether fixed or auto-exposure, impose a uniform exposure time across all pixels within a frame. In high-dynamic-range scenes such as automotive cabins with strong directional sunlight, this spatially invariant exposure constraint inevitably leads to localized facial overexposure or underexposure, irreversibly corrupting the subtle pulsatile signals essential for rPPG at the point of capture, a physical degradation that no downstream algorithm can recover. To overcome this bottleneck, we propose PixExpo (Pixel-wise Exposure), a "temporal-for-spatial" framework that sequentially captures frames under a predefined cyclic exposure schedule and performs non-iterative pixel-wise fusion. At each pixel location, PixExpo selects the observation closest to an rPPG-motivated target intensity. This criterion seeks to reduce local saturation and severe underexposure rather than optimize perceptual appearance. PixExpo requires no sensor modification but assumes programmable frame-level exposure control. We validate the proposed PixExpo framework using our newly introduced MEX-Drive dataset, comprising 48 participants under real-world driving conditions. Experimental results demonstrate that PixExpo outperforms manufacture-default auto-exposure methods, reducing the mean absolute error (MAE) by 7.21 bpm (from 13.94 to 6.73 bpm) and increasing the success rate by 37.29 percentage points (from 25.95% to 63.24%) across challenging driving scenarios.
Read the full abstract

All authors Jieying Wang, Xinqi Cai, Caifeng Shan, Wenjin Wang

Robotics

RoboChrono: A Real Robot Benchmark for Streaming Task Understanding

Yuzhou Wu, Longteng Fan, Zimeng Li et al. (+22 more)

Understanding ongoing robot manipulation requires models to interpret visual observations in relation to interaction history and task progress. We introduce RoboChrono, a benchmark for streaming task understanding comprising 39 scenarios and 34,713 evaluation instances, constructed from real robot executions and complementary bare-hand human recordings. The benchmark evaluates seven tasks grouped into recognition, alignment, and temporal grounding, covering action understanding and anticipation, visual correspondence, temporal ordering, and action localization. Zero-shot evaluation of 18 vision-language models reveals substantial differences across tasks. GPT-6-Astra achieves 98.3% accuracy on Frame Matching but 68.3% on Frame Ordering, while RynnBrain1.1-122B-A10B exhibits a larger gap, reaching 95.4% and 32.9%, respectively. Input ablations on matched questions with five open-weight models further reveal distinct dependencies on visual evidence: removing visual observations reduces Current Action Recognition accuracy by 22.1 percentage points, whereas Next Action Prediction decreases by only 0.7 points. These findings show that strong visual matching does not consistently coincide with strong temporal ordering, and suggest that next-action prediction can be supported by task and action priors even when visual evidence is unavailable. RoboChrono provides a diagnostic setting for examining these differences, highlighting the need for capability-specific evaluation beyond aggregate scores when assessing task understanding in robot manipulation.
Read the full abstract

All authors Yuzhou Wu, Longteng Fan, Zimeng Li, Yu Wanchan, Ting Zhang, Yiyang Ma, Shihao Li, Wei Ying, Jianbin Qin, Jiajian Jing, Fangwen Chen, Yifan Wu, Zichen Zhang, Ruiqi Yang, Weibin Kong, Yihang Xu, Haoran Liu, Zonghang He, Xuyang Liu, YiFan Xiong, Siteng Huang, Tao Xu, Zhuo Xu, Long Chen, Ruoxiang Li

Cryptography and Security

Self-Evolving Defense: Continual Security Policy Learning for LLM Agents

Minh Nhat Le, Nisarga Gondi, Yibo Peng et al. (+4 more)

Large language models (LLMs) increasingly power agents that access sensitive information, use external tools, and modify software repositories. Although these capabilities offer substantial benefits, they also create security risks such as jailbreaks, prompt injection, and vulnerable code generation. Existing defenses often require retraining, fail to adapt to evolving attacks, or address only a single threat pattern. To address these limitations, we propose Self-Evolving Defense (SED), a training-free framework that distills harmful agent trajectories into reusable security policies without updating model weights. By retrieving relevant policies for future tasks, SED continually adapts to new attacks while retaining knowledge across attack scenarios. To evaluate the effectiveness of SED, we test it with three open-source models (DeepSeek V4 Flash, GLM 5.2, and Kimi K3) on eight benchmarks that span jailbreaks, prompt injection, and insecure code generation. SED lowers targeted prompt-injection success on AGENTDOJO to 0.42%, compared with 3.7% for the best baseline defense, and holds adaptive X-TEAMING attack success on HARMBENCH to 7.8%, more than four times lower than the best baseline at 35.2%, while preserving benign task utility.
Read the full abstract

All authors Minh Nhat Le, Nisarga Gondi, Yibo Peng, Ronghao Ni, Limin Jia, Beidi Chen, Haizhong Zheng

Robotics

OTRetarget: Joint Robot and Object Motion Retargeting via Optimal Transport

Guillaume Besset, Erwann Carn, Timothée Carecchio et al. (+5 more)

Transferring human motion to humanoid robots requires adapting the demonstrated motion to the robot morphology while preserving interactions with the environment. This is particularly challenging for loco-manipulation tasks, where contacts with the ground and manipulated objects must remain consistent despite differences in body proportions. Yet, skeletal motion alone does not fully describe these interactions, and fixing object trajectories limits the adaptation to a new embodiment. In this paper, we introduce OTR ETARGET, a unified approach to jointly retarget robot and multi-object motion from human demonstrations. Our approach represents surface interactions through signed distances, closest surface points, and relative directions, and uses entropic optimal transport to transfer these quantities across human, robot, and object geometries. We incorporate the resulting interaction targets into a constrained inverse kinematics formulation that balances contact preservation with motion style and jointly optimizes robot and object poses at each frame. This formulation accommodates robot-object and object-object interactions without rescaling the scene or the demonstration. We validate the proposed approach on OMOMO, where it achieves a robot- object interaction Jaccard score of 87% and a depth error of 8.7 mm, compared with 28% and 29.3 mm for OmniRetarget. Finally, we demonstrate transfer to a physical G1 humanoid using whole-body policies trained with reinforcement learning on the retargeted references, across motions including two-handed box pick-and-place onto a table.
Read the full abstract

All authors Guillaume Besset, Erwann Carn, Timothée Carecchio, Valentin Tordjman-Levavasseur, Fabian Schramm, Yann de Mont-Marin, Justin Carpentier, Ajay Suresha Sathya

Artificial Intelligence

SAKI: Maximal-Coupling-Routed Teacher Supervision for On-Policy Distillation

Miteto Wei, Xiaohan Wang, Zehao Chen et al. (+7 more)

On-policy distillation (OPD) reduces train-test state mismatch by training a student on its own generated trajectories, but weak students may visit teacher-misaligned prefixes where supervision is less representative. We introduce SAKI (Supervision Allocation with KL-constrained Interpolation), which combines a KL-constrained teacher-guided rollout with maximal coupling and reuses realized accept/correction events to route token-level supervision. Accepted positions retain sampled-token reverse-KL supervision, while correction positions receive direct supervision on the teacher's highest-probability token. Under maximal coupling, the correction probability is exactly TV(p_t, q_t), so the same trust-region radius controls rollout deviation and upper-bounds intervention and specialized-supervision frequency. We further implement an engine-resident speculative verifier that preserves the exact-q trajectory distribution and coupling semantics while improving matched-workload rollout throughput by 4.22x. Across seven mathematical reasoning benchmarks, SAKI improves the matched teacher-guided baseline in Mean@8 and Pass@8 for both 1.7B and 0.6B students. Placement controls and fixed-prefix analysis further support correction-triggered routing as a conflict-adaptive supervision signal.
Read the full abstract

All authors Miteto Wei, Xiaohan Wang, Zehao Chen, Jiajun Chai, Sichao Liu, Li Wang, Haoyuan Xu, Zhaoyu Hu, Wei Lin, Guojun Yin

Artificial Intelligence · Cross-listed from math.OC

Second-Moment Stochastic Approximation Methods

Tao Jiang and Lin Xiao

Classical stochastic approximation methods rely on estimators of the first moment (mean) of a random regression function. We study methods that employ estimators of both the first and the second moments, which include modern deep-learning optimizers such as Adam and Muon as special cases. We derive second-moment stochastic approximation methods through the lens of optimal preconditioning for solving matrix equations, and develop a two-stage framework for their convergence analysis. The first stage focuses on the analysis of conceptual (impractical) methods that rely on the exact first and second moments. In the second stage, we replace the exact moments with their respective estimators, and invoke Dvoretzky's theorem to show that the resulting practical methods converge almost surely to a neighborhood of the target solution. The size of the neighborhood depends on the biases and variances of the first- and second-moment estimators. We derive concrete bounds for Muon and a spectral variant of Adam that determine the radius of their neighborhood of convergence.
Read the full abstract

Computer Vision

Scaling Video Generation for Reasoning: At What Cost?

Weihang Guo, Xiaoyu Wu, Yifei Wang et al. (+2 more)

We study whether scaling video generation enables models to reason about hidden information from the past frames, and at what computational cost. Our controlled benchmark requires predicting nine prescribed moves of an initially solved 2x2x2 Rubik's Cube from a fixed view of three faces. Correct predictions require inferring how actions change hidden states, and the simulator provides exact ground truth for evaluation. Models learn plausible cube geometry early, while correct sticker configurations require substantially more training. Although validation MSE follows approximate power-law scaling, lower MSE loss does not reliably indicate downstream reasoning capabilities. Smaller autoregressive models achieve higher state accuracy with limited compute, while larger models reach higher accuracy after more training. At roughly 0.1 PF-days, the 70M-parameter model correctly predicts the visible sticker configuration in 44.6% of post-action frames, compared with 0.3% for the 1B model, which reaches 83.7% at 3.14 PF-days. Symbolic state supervision raises the 20M model's frame accuracy from 31.1% to 67.3% at the same training-data budget, suggesting that learning representations of state changes can complement scaling.
Read the full abstract

All authors Weihang Guo, Xiaoyu Wu, Yifei Wang, Niloofar Mireshghallah, Lydia E. Kavraki

Computer Vision

Beyond Legibility: Benchmarking Visual Text Rendering and In-Place Editing in Unified Video Generation

Ziying Zhang, Litao Li, Junchao Liao et al. (+4 more)

A video can exhibit convincing motion and photorealism yet fail immediately when visual text collapses. Unlike generic scene content, visual text is unforgiving in video generation: minor stroke corruption, temporal instability, or editing errors instantly break legibility and realism. Existing benchmarks overlook this challenge by treating text as incidental or using static OCR metrics that ignore temporal dynamics. We introduce VidScribe, a unified diagnostic benchmark spanning four generation regimes: writing from language (T2V), transferring text identity from a reference (R2V), sustaining text under dynamics (I2V), and localized text editing (V2V). VidScribe contains 803 human-verified samples across a 12-axis conditionally orthogonal factor space covering Intrinsic Text Properties, Physical Imaging Conditions, and Temporal Behavior. For reliable evaluation, we build a track-grounded, gated suite with 11 shared metrics and 2 task-specific probes under strict measurability conditions. Benchmarking 11 commercial and open-source systems shows that video text capability is non-monolithic, with content recognition decoupled from stroke-level glyph correctness. Performance is highly task-asymmetric: I2V sustains text most reliably, whereas V2V editing is the primary bottleneck. Counter-intuitively, degradation concentrates on a small subset of text-centric structural and temporal factors rather than adverse imaging conditions. Further probes show that visual references improve glyph and typographic fidelity rather than content accuracy, while localized editing fails to isolate target text without corrupting undeclared source text. Beyond evaluation, VidScribe also provides an actionable training signal, where benchmark-aligned preference optimization measurably improves visual text generation. https://huggingface.co/datasets/Vicky0720/VidScribe.
Read the full abstract

All authors Ziying Zhang, Litao Li, Junchao Liao, Tianyi Zeng, Siyu Zhu, Long Qin, Zhenghao Zhang

Robotics

Executor-aware Candidate Selection via a Feasibility Certificate

Sooin Choi, Soonwoong Hwang and Wansoo Kim

Modular robotic systems often separate motion planning from a downstream executor that enforces state-dependent hard constraints. A candidate that is geometrically valid may therefore be incompatible with the executor's available command set. We present a certificate-based candidate-selection framework that constructs a command witness from the executor hard set at predicted rollout states and verifies it against the original constraints, without changing candidate generation, ranking, or the executor. Across 5,085 geometry-valid numerical evaluations on two robot models, 795 admitted no executor-feasible command. The certificate is sufficient but conservative: none of the 795 was certified, while 7.09% of reference-feasible cases remained uncertified. In controlled FR3 and fixed-base RB-Y1 simulations, certificate admission frequently changed candidate selection, and a post-hoc exact linear-programming (LP) admission baseline revealed platform-dependent conservatism. Relative to geometry-based selection, certificate admission was associated with lower planner-command coverage and higher nominal tracking error, without a consistent advantage in reached-state interaction reserve. A planner-generated MoveIt/OMPL study further evaluates the same admission rule on externally generated candidate pools.
Read the full abstract

Robotics

HACo: Learning Haptic Active Compliance for Force-Aware Dexterous Manipulation

Naisheng Ye, Yinzhe Zhou, Junkai Zhao et al. (+5 more)

Contact-rich dexterous manipulation requires policies that translate physical feedback into motion commands while regulating interaction loads across evolving multi-contact interactions. This requires haptic observations of contact state and action supervision showing how commands should adapt. Existing policies often overlook complementary fingertip tactile and joint-torque feedback, while common action targets either encode excessive loading or omit motion constrained by the object. We introduce HACo, a Haptic Active Compliance policy that learns force-regulating actions directly from haptic feedback. Compliance-regulated teleoperation converts operator inputs into controller-executable compliant actions that preserve motion intent while regulating loads. HACo learns these actions directly, using command-state discrepancy as auxiliary compliant-intent supervision. It combines local fingertip tactile responses with joint-torque feedback capturing load transmission through the articulated hand, including contacts beyond tactile coverage. A Compliance Grounding Module uses gated haptic cross-attention to ground action generation in the evolving haptic state, enabling closed-loop force regulation without explicit online contact modeling. We evaluate HACo on a real-world benchmark covering multi-contact friction, tangential interaction, fragile curved-surface contact, rotational torque, and deformable-object manipulation. Across 20 trials per task, HACo achieves an 83% mean success rate, compared with 35% for the strongest evaluated baseline. These results demonstrate active compliance across diverse force-sensitive dexterous manipulation tasks.
Read the full abstract

All authors Naisheng Ye, Yinzhe Zhou, Junkai Zhao, Yuhang Lu, Checheng Yu, Zhenjie Yang, Pengwei Wang, Hongyang Li

Robotics

Simple Agentic Memory for Generalist Robot Policies

Yuyou Zhang, Yunbei Zhang, Miao Li et al. (+4 more)

Visual-memory systems commonly retain or compress past observations. Robot control additionally requires interaction-derived state that no individual frame may explicitly represent, such as persistent identity relations, accumulated progress, or ordered procedures. We introduce Simple Agentic Robot Memory (SimpleARM), a training-free memory layer for frozen generalist robot policies. From the task instruction, SimpleARM specifies what to monitor; frozen perceptual tools maintain compact typed state online; structured access retrieves that state only when a proposed subgoal depends on history; and current-view grounding resolves recalled entities before execution. We evaluate SimpleARM on RoboMME, a benchmark of memory-dependent robot manipulation tasks that require history information no longer available in the current observation. Across all 16 tasks and three policy seeds, SimpleARM achieves 67.17% mean success, compared with 44.51% for the strongest non-oracle baseline. Matched ablations show mechanism specificity: removing relation, reference, progress, or route state produces large losses where the affected state is retrieved for control, while largely sparing other tasks. These results support a state-based view of robot memory: effective memory for control is not simply retained visual history, but compact task-relevant state derived from the interaction history.
Read the full abstract

All authors Yuyou Zhang, Yunbei Zhang, Miao Li, Janet Wang, Zijian Jin, Shilong Liu, Ding Zhao

Graphics

Text2Sim: Agentic Physics-Based Simulation Generation with Distilled Expertise

Xiaoyu Xiong, Tsun-Hsuan Wang, Yi-Ling Qiao et al. (+2 more)

Creating diverse physical simulations remains labor-intensive because assets, layout, physical parameters, motion, control, and rendering must be designed and debugged jointly. We present Text2Sim, a simulation-specialized agentic pipeline that converts a text-only request into an executable, editable dynamic case. Built on Genesis, Text2Sim uses a hierarchical agentic structure that combines a Planner with specialized Writers, asset-generation tools, and an independent Critic. Compact skills (Debug Cards) distilled from graphics demonstrations provide role-specific physical guidance for execution-based repair. We evaluate physical quality, visual quality, and human preference on 42 held-out prompts spanning rigid, articulated, deformable, and cloth phenomena, with a paper-level split between experience construction and evaluation. We design automatic physical and visual scorers to evaluate the quality of the results, and Text2Sim achieves higher scores than all four state-of-the-art baselines on both metrics. In blinded user studies with these baselines, significantly more participants prefer Text2Sim than prefer the baselines, which is consistent with the results from our automatic scorers. The pipeline also supports a broad range of downstream applications; we select dataset construction and extension to multimodal input as two representative examples. We will release the code, the Debug Card library, and a dataset of generated cases, each pairing the text prompt and rendered video with the executable program, assets, physical parameters, controls, and recorded states.
Read the full abstract

All authors Xiaoyu Xiong, Tsun-Hsuan Wang, Yi-Ling Qiao, Tao Du, Minchen Li

Computation and Language

SEED: Self-Speculative Decoding via Implicit Encoder-Decoder

Hankun Lin, Patrick Pynadath and Ruqi Zhang

Self-speculative decoding accelerates large language model (LLM) inference by drafting tokens from the target model itself, but faces a sharp tradeoff between the quality and cost of the draft. Early-exit methods produce drafts cheaply by terminating computation at intermediate layers, but forgo the deeper representations that later layers provide and thus suffer in draft quality. Multi-token prediction preserves draft quality by emitting from the model's final hidden states, but pays for a full forward pass to produce those states at every drafting step. We propose self-speculative encoder-decoder (SEED), a self-speculative method that obtains high-quality drafts cheaply by reusing the deep contextual representations already computed during verification. We reinterpret the standard decoder-only transformer as an implicit encoder-decoder: the first layers (encoder) build deep contextual representations, and the last few layers (decoder) emit tokens from them. Encoding and verification are merged into a single step: verification is performed by the full encoder-decoder, and the contextual representations of the verified prefix are cached for reuse during drafting. Drafting is therefore very fast: between verifications, the lightweight decoder drafts multiple tokens autoregressively, each conditioned on the cached representations and on preceding drafts. Experiments across multiple benchmarks show that SEED achieves up to 2.7$\times$ average speedup on 4B-scale models, outperforming both early-exit and MTP-style self-speculative baselines and running 28% faster than the state-of-the-art EAGLE-3, while preserving or even improving the generation quality of standard autoregressive fine-tuning. Code is available at https://github.com/lhk2004/SEED.
Read the full abstract

Game Theory

Non-Linear Pricing Restores Tractability for a Data Seller

Bhaskar Ray Chaudhury, Jugal Garg, Eklavya Sharma et al. (+1 more)

We consider a data seller who designs pricing mechanisms over multiple datasets to maximize revenue from budget-constrained buyers. The seller offers multiple datasets and assigns each a pricing function that maps the quantity purchased to a total payment. The goal is to design these pricing functions to maximize revenue, anticipating that buyers—who trade off accuracy gains against cost—choose bundles optimally subject to their budget constraints. Prior work [Chaudhury et al., 2026] studies such optimal pricing under the restriction that each dataset is assigned a linear price, and shows that computing optimal linear prices is computationally intractable. In contrast, we allow each dataset to be priced via a general function and show that this additional flexibility can not only increase the revenue but also restore tractability, yielding a surprising simultaneous improvement in economic performance and computational efficiency. Even when pricing functions are only required to be monotone and lower-continuous, optimal pricing admits a highly structured and simple form: each pricing function is piecewise linear and convex (PLC), and the optimal solution can be computed in polynomial time. Moreover, the total number of kinks across all pricing functions is bounded by the number of buyers. Consequently, when datasets significantly outnumber buyers, most pricing functions are effectively linear. We further empirically study the structure of optimal pricing by analyzing the number of kinks and the revenue gap between optimal nonlinear pricing and optimal linear pricing on simulations generated from a real dataset.
Read the full abstract

All authors Bhaskar Ray Chaudhury, Jugal Garg, Eklavya Sharma, Jiaxin Song

Robotics

Cooperative Multi-Agent Vision-Language-Action Models via Reinforced Fine Tuning

Ruixiao Xu, Wong Lik Hang Kenny, Zhiqian Liu et al. (+12 more)

We study reinforcement learning (RL) methods for cooperative multi-agent Vision-Language-Action (VLA) models. This problem is challenging because VLAs are pretrained on large-scale single-agent data and therefore lack the fine-grained coordination skills required for inter-robot collaboration. Supervised fine-tuning (SFT) on multi-robot demonstrations partially bridges this gap, but its performance is bounded by the demonstration data and cannot improve from its own experience. We present a three-stage reinforced fine-tuning (RFT) pipeline for multi-agent VLAs. First, initialization-aware data collection sweeps over initial configurations and invokes human demonstrations only when the pretrained VLA repeatedly fails, yielding robustness to initialization shift with reduced human cost. Second, offline credit-filtered tuning assigns credit to individual agents and fine-tunes on per-agent trajectories with positive advantage rather than on entire joint rollouts. Third, we find existing online RL for VLAs are less effective for hard multi-agent tasks, which we attribute to noisy co-exploration and unstable updates. We instead use online latent-space fine tuning, which freeze the VLA and perform RL in its latent noise space. We evaluate our multi-agent VLA with both $\pi_0$ and $\pi_{0.5}$ backbones across 11 tasks in RoboTwin, RoboFactory and real-world manipulation with two Franka robots. Our multi-agent VLA improves the average success rate by $+23.1\%$, $+16.4\%$, and $+44\%$ on RoboTwin, RoboFactory, and real-world tasks, respectively. Code available at https://anonymous.4open.science/r/mavla_rft-2BC0/.
Read the full abstract

All authors Ruixiao Xu, Wong Lik Hang Kenny, Zhiqian Liu, Jianing Guo, Hanxiao Li, Kejian Shi, Shuning Zhang, Pu Feng, Yongjia Ma, Yuqing Ma, Kai Chen, Qi Dou, Yaodong Yang, Xianglong Liu, Simin Li

Machine Learning

Learned Reporting Preferences in RLVR Can Conflict with the Current Request

Yupeng Chang, Wenxuan Zhang and Yuan Wu

Reinforcement learning with verifiable rewards (RLVR) has become a prominent approach for improving language-model performance on reasoning tasks using automatically checked answers. Yet convention-matched evaluation cannot reveal whether reinforcing one reporting convention reduces adherence to a different request that the initial policy already follows. To test this, we train matched policies under two reporting conventions and evaluate each policy under both current requests, using the same initial policy as a shared reference. We complement this crossed design with controlled interventions and independent human calibration. On GSM8K, boxed-format RLVR reduces the fraction of Qwen2.5-7B responses containing the requested hash-format payload by 35.33–74.37 percentage points relative to a 95.45% initial baseline in four of five training seeds; the fifth improves by 2.50 points. In the four deteriorating runs, almost every response that omits the requested payload instead retains the trained boxed convention, and the same four seeds deteriorate under two fixed paraphrases. Changing only the final-answer marker in supervised targets reverses which reporting convention the model prefers across three seeds, providing controlled evidence that this preference is learnable. Across three settings with independent human calibration, gains under a convention-sensitive scorer exceed the corresponding gains in committed-answer correctness, i.e., the correctness of the answer the model actually commits to. Together, these results separate three distinct post-training outcomes: learned reporting preference, current-request adherence, and committed-answer correctness. They show that convention-matched accuracy alone does not fully characterize post-training behavior and motivate evaluating current-request adherence alongside convention-matched task accuracy.
Read the full abstract

Information Theory

Surrogate-Enhanced Fractional Programming for MIMO Device-to-Device Interference Networks

Zihan Jiao, Xinping Yi, Shi Jin et al. (+1 more)

Interference management in multi-stream multi-input multi-output (MIMO) device-to-device (D2D) networks often leads to weighted sum-rate maximization with sum-log-determinant involving matrix-valued signal-to-interference-plus-noise ratios (SINRs). The state-of-the-art paradigms, including weighted minimum mean-square error (WMMSE) and fractional programming (FP), have achieved tremendous success in link scheduling, power control, and beamforming problems. Recently, an upgraded FP approach, named surrogate-enhanced FP (SEFP) in a scalar form, has attained improved performance in joint uplink scheduling and power control in coordinated multicell SISO networks. The proposed SEFP improves the surrogate construction of the classical Lagrangian dual transform plus quadratic transform for logarithmic fractional objectives with a novel reciprocal-inverse transform (RIT), yet its extension to the matrix form for MIMO settings does not seem straightforward because the matrix ratio and the auxiliary matrix generally do not commute. In this paper, by leveraging mathematical tools from Hermitian functional calculus, we extend RIT to matrix ratios by lifting the scalar RIT along the eigendirections of an auxiliary matrix and recasting the resulting directional construction in an operator form. Following, we develop a matrix SEFP framework for weighted sum-log-determinant maximization. Further, we establish a unified view of SEFP and the recently proposed XMMSE method, specify when the two algorithms attribute to identical minorization-maximization (MM) surrogates and variable update trajectories, and prove XMMSE can be considered as a special case of SEFP under the algorithmic family perspective. Inspired by the unified view, we develop SEFPLinQ for the joint scheduling and beamforming optimization in flexible-association MIMO D2D networks. Numerical results demonstrate consistent performance gains.
Read the full abstract

All authors Zihan Jiao, Xinping Yi, Shi Jin, Giuseppe Caire

Artificial Intelligence

Transformers Stop Thinking Too Early, and a Tiny LoRA Fixes It

Zehao Jin, Ruixuan Deng and Junran Wang

Pretrained transformers use little of their depth to follow references in context. Thirteen base models reliably follow only 1.4-3.6 lines, and extra pretrained loops add little. A task-trained rank-8 LoRA at one early layer extends this computation with all model weights frozen. Qwen3-8B improves from 15.5% to 99% exact accuracy on 24-line chains; a longer-trained LoRA reaches 50 lines. Ouro-1.4B reaches 60 lines after four loops and at least 160 after eight. The LoRA starts a relay: program lines pass on their chain identity through a short range of middle layers. Frozen heads read progressively further up the chain, and removing parent-line attention stops the relay. A frozen-model measurement locates the last useful intervention layer within tolerance in three of four held-out models. Task-specific LoRAs also improve MuSiQue. Default answers therefore understate the computation accessible through a tiny edit. Code and an interactive demo are available at https://lunamos.github.io/stop-thinking-too-early/
Read the full abstract

Machine Learning

Making Analog Training Scale: Co-Designing Mapping, Optimizer, and Converters

Zhaoxian Wu, Tayfun Gokmen, Omobayode Fagbohungbe et al. (+2 more)

Analog in-memory computing (AIMC) offers an alternative for model training by executing matrix operations directly where weights are stored. However, scaling AIMC to train modern deep models remains an open challenge due to severe hardware non-idealities, including physical weights with finite dynamic range and write granularity, analog-digital converters with finite resolution, and noisy and asymmetric updates. Guided by the insight that gradient accumulation is sensitive to precision and rounding errors, we adopt a mixed-precision training paradigm: executing forward and backward matrix multiplications in the analog domain while computing weight gradients in the digital domain. To enable scalable training, we present a holistic system-algorithm co-design that co-optimizes weight mapping to ensure well-conditioned physical and logical weight profiles, couples a preconditioned optimizer with threshold-triggered open-loop pulsing to stabilize training trajectories, and aligns converter dynamic ranges to suppress quantization errors. Evaluated via hardware-calibrated architectural simulations calibrated with electrochemical RAM measurements, our framework scales Transformer training up to $123\text{M}$ parameters with validation loss scaling as $L\propto N^{-0.231}$, where $N$ is the parameter count, comparable to $L\propto N^{-0.238}$ for digital training.
Read the full abstract

All authors Zhaoxian Wu, Tayfun Gokmen, Omobayode Fagbohungbe, T. Patrick Xiao, Tianyi Chen