Research

Open problems for this view are being prepared; they appear within a day.

• arXiv cs.AISep 29

  Distilling Agentic Systems: A Roadmap across Models, Artifacts, and Harnesses

  Ziluowen Luo, Senzhang Wang, Chaozhuo Li, Jun Yin, Hao Yan +7

  Modern agents increasingly rely on memories, tools, and execution logic, so their competence extends beyond model parameters. This shift exposes a limitation of conventional knowledge distillation, which asks how a student model imitates a teacher model. We define Agent Distillation as the persistent transfer of task-solving knowledge from a teacher agent to a student agent. Our study organizes the field by where transferred knowledge is retained: within the model, as artifacts, through the execution harness, or across substrates. This perspective separates transfer evidence from its outcome and clarifies how knowledge moves between agent components. We develop an evaluation framework that relates retention to causal contribution and deployed utility. Together, these contributions establish a foundation for the reliable, maintainable, and safe development of increasingly complex agentic systems.

  PDF

  Summarize this
• arXiv cs.CVSep 29

  Beyond Binary Preferences: Graded Preference Optimization for Limb-Motion Captioning

  Yanan Wang, Tingsong Li, Kaixun Jiang, Chongyang Zhong, Chenwei Xoe +1

  Vision-Language Models (VLMs) can generate rich video captions, yet often misidentify which person performs an action or which limb is involved, particularly across camera cuts. Improving these details requires evaluation and training that distinguish missing information from incorrect assertions. We introduce FlexBench, a benchmark spanning 3,105 shots and 18,161 evaluation queries, with human-verified identities and systematic per-person coverage of fine-grained limb actions and states. Its reference-derived checklists support automated assessment of complete captions in their person and shot contexts. Our Graded Physical Alignment score (GPA) awards credit for correct content and deducts points for incorrect or fabricated actions, making these errors explicit in the aggregate score. Building on this rubric, we propose Graded Margin Direct Preference Optimization (GM-DPO), which assigns stronger preference margins and greater training weight to more severe action errors. Across three VLM backbones, GM-DPO achieves the highest substantive-action and GPA scores among the evaluated preference objectives, improving GPA over DPO by 2.02-3.40 points. On Qwen3-8B, it reduces the…

  PDF

  Summarize this
• arXiv cs.AISep 29

  Semantic Projection for Continual Self-Evolution of Language Agents

  Ziyu Liu, Jun Chen, Lixu Wang

  Language-model agents increasingly rely on persistent natural-language skills to adapt beyond their frozen model parameters. When a shared skill is repeatedly revised from a non-stationary, heterogeneous task stream, however, improvements for new tasks can overwrite procedures needed for earlier ones. In continual learning, Orthogonal Gradient Descent (OGD) addresses analogous interference by projecting a new-task gradient onto a subspace that locally preserves prior predictions. Natural-language skill revisions, however, have neither gradients nor a canonical vector space in which such a projection can be performed. We introduce \emph{Semantic-Scope Projected Evolution} (SSPE), which transfers the functional principle of gradient projection from parameter space to behavior space. SSPE treats an unconstrained skill revision as a proposed update, identifies acquired capabilities with which it may interfere, and uses the observed gains and regressions to construct a compatible revision rather than merely rejecting the update. This enables one shared skill to evolve across latent and recurring task contexts without exposing semantic domain identities to the evolution model. Across…

  PDF

  Summarize this
• arXiv cs.AISep 29

  DualTrack: Synchronized speech-gesture generation via symmetric coupling of pretrained priors

  Yuanzhuo Hu, Zehan Liu, Xiaoyi Qin, Ming Li

  Joint speech-gesture synthesis must coordinate two modalities despite limited paired data. Existing approaches often lack bidirectional interaction, have limited language coverage, or simplify body and finger representations. We present DualTrack, which couples pretrained speech and motion priors on a shared 12.5 Hz timeline. Causal adapters exchange previous-packet information, while current-state fusion coordinates the streams before they separately complete sixteen-codebook packets. We evaluate 43 BEAT2 recordings in four languages, with speakers held out from joint training and validation. On the shared English/Spanish inputs, without speech or motion prefixes, DualTrack achieves lower word error rate and full-motion Fréchet Gesture Distance, higher beat consistency and speech naturalness than the evaluated GELINA baseline.

  PDF

  Summarize this
• arXiv cs.AISep 29

  Neural Structural Reasoner: A Brain-inspired Architecture for Reasoning over Structured Knowledge

  Zixing Jia, Yuhang Pan, Ni Ji

  Structural reasoning, the ability to recognize and make inferences over the relational structure between objects and concepts, is a hallmark of human cognition, yet prevailing methods often collapse relational topology into flat embeddings, cannot discover hidden structure and lack interpretability. We introduce Neural Structural Reasoner (NSR), a brain-inspired network that preserves relational structure directly in the connectivity and dynamics of coupled neuronal populations. NSR draws inspiration from three biological mechanisms: multi-layered architecture for encoding hierarchical knowledge, stable representations of entity and concepts, and path integration for input-driven state inference. At query time, NSR parallelizes computation over candidate relational structures and leverages confidence-weighted scores to perform link prediction. Across standard knowledge-graph benchmarks, NSR achieves competitive accuracy without leading on every dataset, and has lower reported training times than several neural baselines. Because reasoning is implemented through sequences of human-readable neuron activations, NSR affords native interpretability by tracking intermediate inference…

  PDF

  Summarize this
• arXiv cs.LGSep 29

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

  Junyu Chen, Chenxi Liu, Shiqin Tang, Hao Miao, Wanyun Ling +3

  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,…

  PDF

  Summarize this
• arXiv cs.CLSep 29

  Generating Edit-Inducing Questions for AI Research Manuscripts

  Sebastian Joseph, Zichao Wang, Jennifer Healey, Alexa Siu, Junyi Jessy Li +1

  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.

  PDF

  Summarize this
• arXiv cs.CVSep 29▲ 33

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

  Hanwen Lu, Jun He, Mingjia Yang, Hao Wei, Jinhao Huang +2

  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…

  Code
• arXiv math.NASep 29

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

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

  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…

  PDF

  Summarize this
• arXiv cs.LGSep 29

  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…

  PDF

  Summarize this
• arXiv cs.LGSep 29

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

  Hadi Reisizadeh, Jiajun Ruan, Sijia Liu, Mingyi Hong

  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…

  PDF

  Summarize this
• arXiv cs.AISep 29

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

  Jianchang Su, Yiwei Yang, 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…

  PDF

  Summarize this
• arXiv cs.LGSep 29

  Communication-Efficient Agnostic Federated Learning via Faster Convergence and Compression

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

  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 $O((δ^{-1}+(\log m)^{1/4})T^{-1/8})$ stationarity rate for AFL-Com under general $δ$-approximate compressors and improve the $δ$-dependence from $δ^{-1}$ to $δ^{-1/2}$ for additive-and-idempotent compressors with shared randomness (SR). With…

  PDF

  Summarize this
• arXiv eess.SPSep 29

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

  Parsa Razmara, Woojae Jeong, Aditya Kommineni, Raymundo Cassani, Richard Leahy +1

  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…

  PDF

  Summarize this
• arXiv cs.LGSep 29

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

  Zubin Zheng, Jiahao Wu, Shaofeng Zhang, Zhirui Zhang, Yew-Soon Ong +1

  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…

  PDF

  Summarize this
• arXiv cs.CVSep 29

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

  Jieying Wang, Xinqi Cai, Caifeng Shan, Wenjin Wang

  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…

  PDF

  Summarize this
• arXiv cs.AISep 29

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

  Miteto Wei, Xiaohan Wang, Zehao Chen, Jiajun Chai, Sichao Liu +5

  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…

  PDF

  Summarize this
• arXiv math.OCSep 29

  Second-Moment Stochastic Approximation Methods

  Tao Jiang, 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.

  PDF

  Summarize this
• arXiv cs.CVSep 29

  Scaling Video Generation for Reasoning: At What Cost?

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

  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…

  PDF

  Summarize this
• arXiv cs.CVSep 29

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

  Ziying Zhang, Litao Li, Junchao Liao, Tianyi Zeng, Siyu Zhu +2

  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…

  PDF

  Summarize this

• Character recognition OCR38+2.7%
• Spiking neural networks70.0%
• Voice AI62−11.4%
• Diffusion priors20−13.0%
• Quantum machine learning25−13.8%
• Molecular property prediction37−26.0%
• Robotics149−27.0%
• Forecasting time100−31.5%