Research

• General in-context learning for embodied agents1 paper raises it · 0 address it

  Enables models to adapt to new tasks and environments without retraining, improving robustness in real-world deployment.

  • Has GPT-6-Astra Achieved Embodied Intelligence?raises
• Cost and latency in embodied control loops1 paper raises it · 0 address it

  High computational and time costs limit real-time applicability of agentic systems in dynamic environments.

  • Has GPT-6-Astra Achieved Embodied Intelligence?raises
• Physical-state verification and failure recovery1 paper raises it · 0 address it

  Agents must reliably detect and correct errors in physical interactions to avoid irreversible failures in real-world tasks.

  • Has GPT-6-Astra Achieved Embodied Intelligence?raises
• Long-horizon task preservation in embodied agents1 paper raises it · 0 address it

  Maintaining progress over extended sequences is critical for complex, multi-step tasks in robotics and navigation.

  • Has GPT-6-Astra Achieved Embodied Intelligence?raises
• Open-source stacks for generalist computer-use agents1 paper raises it · 1 addresses it

  Closed systems hinder reproducibility and systematic study of agent design for real-world computer tasks.

  • OpenGCUA: Toward a Fully Open Stack for Generalist Computer Useraises · addresses

Named by an AI from these papers' abstracts.

• Federated learning51+37.8%
• Agents544+4.8%
• Quantum machine learning240.0%
• Sensing communication150.0%
• Frontier LLMs466−2.1%
• Character recognition OCR17−5.6%
• Voice AI104−10.3%
• Inference & serving277−10.4%

• arXiv cs.AIOct 19

  LLMs Prompted for Legal Context Refuse More: Overrefusal from Small On-Premises LLMs in Criminal Legal Context

  Anastasiia Kucherenko, Francois Brouchoud, Dimitri Percia David, Andrei Kucharavy

  Confidentiality requirements increasingly push legal professionals toward small, on-device LLMs that keep case data in-house, used for everyday tasks such as summarization, translation, and reformulation. Following standard prompting guidance, a user naturally states their role (``I am a lawyer...''). We show that this innocuous habit has an unexpected cost: such authority framing can make the model selectively refuse legitimate requests, introducing bias through uneven access to assistance. We evaluate four modern small open-weight LLMs on benign legal-domain prompts to measure this over-refusal. Surprisingly, we find that authority-style prefixes (''I am legal counsel working for a national supreme court'', ''I'm a defense lawyer'') systematically increase refusal rates by 2--20x over the no-prefix baseline, while a known role-play jailbreak prefix shows mixed effects, sharply increasing refusals in some models and barely shifting them in others. The finding suggests that small on-prem deployable LLMs are unstable under contextual framings that a real institutional user might naturally introduce, and further investigation is essential to minimize opportunities for bias.

  PDF
• arXiv cs.LGOct 19

  OceanTensorCube and ST-MMT: A Multimodal Data and Transformer System for Seven-Day Forecasting of Pyropia Bleaching

  Gwangjin Kim, Cheolyoung Jang, Yosep Jo

  Bleaching of cultured Pyropia (laver) causes losses in Korean seaweed farming. We present a system that forecasts bleaching seven days ahead for farm clusters. OceanTensorCube aligns 32 channels from public marine, meteorological, ocean-model and satellite sources on a 30 m grid, and ST-MMT, a 9.2-million-parameter spatiotemporal transformer with hub-style multi-head cross-attention between variable groups, maps a 14-day input window to a seven-day-ahead bleaching probability. On the validation set, a six-seed ensemble detects every reported positive at a false-alarm rate of at most 3.5%, an upper bound because the report-based labels are positive-unlabeled. A same-date control on separately trained models indicates that the architecture discriminates between clusters when the calendar is held fixed. We also report the system's weaknesses: skill falls steeply as the quarterly nutrient survey ages (ROC-AUC 0.94 at 30 days, 0.53 at 129 days), and a single LSTM on cluster-average series outperforms a single ST-MMT, with only the ensemble leading at the operating point. We describe the labeling procedure, the evaluation protocol and the operational gate that withholds forecasts when…

  PDF
• arXiv cs.CVOct 19▲ 107

  Focused Omni-Modal GUI Agents

  Fuyao Zhang, Wenwen He, Jiaming Zhang, Yurong Hao, Xuan Wang +4

  Graphical User Interface (GUI) agents increasingly act over streaming omni-modal observations spanning screenshots, audio, video, interaction history, and device states. However, exposing this complete context uniformly at every step ignores that relevance is transient and sparse: the signal determining one action can become clutter at the next. Because executed actions feed back into the context, these errors compound into Sequential Distraction, driving the agent into irreversible trajectory drift. We formulate the underlying requirement as Focused Perception: a representation that is step-adaptive, action-sufficient, and non-intrusive. We realize this in FocusGUI, a lightweight adapter that dynamically prioritizes multimodal channels against a step-specific decision reference. Instead of uniformly processing all inputs, it compresses the most relevant evidence into a compact latent and subtly injects it into the frozen decoder's embeddings, guiding the model's attention without altering its native parameter space. FocusGUI trains from action supervision alone, requiring neither modality-relevance labels nor backbone fine-tuning. Across four omni-modal backbones, it raises…

  Code
• arXiv cs.LGOct 19

  TaQFormer: A Treatment-as-Query Transformer with Data-Fusion for Multidimensional Treatment Modeling in Coupon Allocation

  Jiahong Li, Zeqin Yang, Yu Xiang, Zhifan Jiang, Jingqi Ma +6

  We study coupon allocation on an online marketplace offering multiple service categories. Issuing coupons requires choosing a vector of category-specific discounts, accounting for both their direct effects and cross-category demand shifts. We present TaQFormer, a treatment-as-query Transformer for this multidimensional treatment setting. Each treatment coordinate is represented as a query token, allowing cross-attention to estimate the response to the full treatment vector. To combine large but policy-biased observational logs with a smaller stream of randomized controlled trial data, we use a two-stage pipeline: observational pretraining learns general outcome patterns, followed by LoRA fine-tuning on RCT data with a request-specific fusion gate. We evaluate the resulting system through the checks required for production, including offline uplift metrics, treatment-parallel serving, latency monitoring, and a 14-day online A/B test. At essentially the same subsidy cost rate, \model increases business value per user by 1.26\% over the production baseline and significantly outperforms both the production baseline and the RCT-only model, while meeting the latency budget. It was…

  PDF
• arXiv cs.CVOct 19

  GeoEdit: Adversarial De-Evidencing for Silent Geoprivacy Protection via Image Editing

  Yu Yan, Shengjia Cheng, Fei Ma, Zhe Wang, Peng Chen

  Recent efforts have demonstrated the strong capabilities of Multimodal Large Reasoning Models (MLRMs) in geographic reasoning. By jointly analyzing subtle visual cues, these models can infer the locations of photos, thus enabling doxing even by non-expert adversaries. Existing defense methods struggle to balance the shareability of photos with effective protection, and often fail to sufficiently disrupt the implicit geo-evidence chains embedded in scene semantics. To this end, we propose GeoEdit, an adversarial de-evidencing framework for silent geoprivacy protection via image editing. Specifically, we apply minimal edits to high-risk evidence anchors in the image, thereby disrupting the underlying spatial reasoning chains while preserving overall scene semantics. We identify these anchors by combining structured knowledge with adversarially discovered geographic cues. To further navigate the large editing action space, we adopt a learnable policy to iteratively refine editing decisions, distilling successful trajectories into transferable natural-language insights for consistent and efficient editing. Evaluated on LifePhotoBench, GeoEdit achieves strong protection against 6…

  PDF
• arXiv stat.MLOct 19

  Robust Latent Variable Graphical Models: Exact Recovery and Fundamental Limits

  Chuansen Peng, Xiaojing Shen

  We study robust estimation of a Gaussian precision matrix that decomposes as a sparse matrix minus a symmetric, possibly indefinite, low-rank matrix, a structure that arises when latent-variable marginalization is combined with conditioning on linear measurements. The proposed convex estimator replaces the sample covariance by the centered Gaussian measure-transformed (MT) covariance, which preserves the signed graph of the sparse component under the nominal model, and penalizes the low-rank component by the nuclear norm of a congruence transform, an atomic norm that encodes structural side information. Our main result is a primal--dual witness theorem: under restricted invertibility and irrepresentability conditions on the Fisher information, the raw convex optimizer is unique, has no false edges, recovers the signs of all sufficiently strong edges, and has exactly the true rank and inertia. These conditions reduce to the graphical-lasso conditions when the low-rank part is absent, and we verify them from primitive incoherence and near-isotropy assumptions. Over a class on which they hold uniformly, we prove information-theoretic limits for Frobenius estimation, signed graph…

  PDF
• arXiv cs.CLOct 19

  VEILED-SH: Vulnerability Expression through Indirect Language Evaluation Dataset (Self-Harm)

  Leanne Tan, Keith Chua, Shaun Khoo, Onno P. Kampman, Lim Ruling Charmaine +5

  AI systems may miss indirect, culturally situated distress or provide support mismatched to the application context. Existing benchmarks do not jointly address cultural variation, application context, and practitioner disagreement. We introduce VEILED-SH, a benchmark and construction methodology for evaluating single-turn responses to indirect expressions of suicide, self-harm, and distress. Its 10,003 prompts span counselor chat, forum posts, platform search, and triage, drawing on Singapore-grounded sources and public datasets. An expert-validated multi-label taxonomy distinguishes intent, communicative function, and response behavior. Six automated profiles, individually calibrated to three peer-support practitioners and three clinicians, retain separate reference policies for proxy-alignment scoring. Evaluating five systems on a coverage-enriched sample reveals variation in proxy alignment across profile-generated reference policies, even for the same system responses.

  PDF
• arXiv cs.CVOct 19

  Wan-Alpha++: Animating a Single RGBA Asset into Controllable Transparent Video Effects

  Haotian Dong, Xin Wang, Wenjing Wang, Chen Li, Jing Lyu +5

  RGBA video generation is essential for creating compositable visual assets in filmmaking, game development, and digital content production. However, generating high-quality RGB appearance alongside temporally coherent transparency remains a significant challenge. Existing text-to-RGBA video methods often entangle RGB and alpha distributions and offer limited control over the precise appearance of a target asset. In addition, incorporating image conditioning typically suffers from the emergence-disappearance effects, which fail existing first-frame or first-and-last-frame conditions due to their fully transparent boundary frames. To address these issues, we present Wan-Alpha++, a unified framework that brings controllable RGBA video generation to both text- and image-to-video diffusion backbones through a shared RGBA latent space, extending our conference version Wan-Alpha from the text-conditioned setting to image-conditioned generation with an interior reference frame. Our method first learns shiftable RGB-alpha distributions while preserving the pretrained RGB prior. Specifically, we introduce a transparency-aware bidirectional diffusion objective to produce distinguishable…

  PDF
• arXiv cs.AIOct 19

  On Counting Graphs for Modal Logic with Counting

  Avijeet Ghosh, François Schwarzentruber

  In this paper, we study the theoretical computational complexity of counting trees and graphs that are classified positively by a graph neural networks, or said equivalently that satisfy a given formula of modal logic with counting. We also study convergence.

  PDF
• arXiv cs.AIOct 19

  MoveBench: A Rubric-Based Benchmark for Evaluating Large Language Models in Sports and Health Coaching

  Yitong Li, Jiang Bian, Jingling Wang, Pan Ding, Chengying Gu

  Despite rapid advances in large language models (LLMs), their deployment in the sports and health domain remains high-risk due to the absence of domain-specific evaluation benchmarks. Existing general-purpose benchmarks (e.g., MMLU and HELM) primarily assess broad knowledge and reasoning capabilities, but fail to capture critical domain requirements such as exercise safety, physiological appropriateness, personalization, and actionable coaching quality. This gap is particularly concerning in fitness and health applications, where incorrect or unsafe recommendations can lead to physical harm. To address this limitation, we introduce MoveBench, the first comprehensive benchmarking framework specifically designed for evaluating LLMs in sports and health coaching. The proposed benchmark integrates heterogeneous task formats, including multiple-choice questions (MCQs) and open-ended question answering (OpenQA), grounded in real-world user scenarios and paired with structured rubrics emphasizing safety compliance, scientific validity, and training logic. Through large-scale evaluation of 15 diverse LLMs on 809 questions with 5,012 rubric-level criteria, our results reveal substantial…

  PDF
• arXiv cs.CVOct 19

  HP-PnP-Flow: Hybrid Time Scheduling and Projection for Plug-and-Play Image Restoration via Flow Matching

  Yong Li, Xiaojie Wang, Xiaoyan Zhang

  Image restoration is a fundamental inverse problem that seeks to recover high-quality images from degraded observations. Plug-and-Play (PnP) methods provide a flexible framework for integrating pretrained denoisers into iterative reconstruction, whereas flow matching offers an efficient generative modeling approach based on continuous-time ODE dynamics. Very recently, Martin et al.\ (ICLR, 2025) developed a PnP-Flow method, which integrates the PnP framework with flow matching through a time-dependent denoiser constructed from a pretrained flow matching model.By incorporating a different time schedule and an additional pixel-space projection operator, this paper proposes a novel efficient PnP-Flow algorithm (HP-PnP-Flow) that enjoys rigorous convergence guarantees under mild assumptions, without imposing restrictive conditions on iterates required by the aforementioned work. Numerical experiments on CelebA and AFHQ-Cat demonstrate that the newly proposed HP-PnP-Flow algorithm significantly outperforms PnP-Flow on several restoration tasks such as denoising, deblurring, super-resolution, random inpainting, and box inpainting. Notably, our algorithm achieves comparable or better…

  PDF
• arXiv cs.CLOct 19

  Reading Time Modeling with Pixel-Based Language Models

  Junlin Li, Sara Alhajeri, Tatsuki Kuribayashi

  Tokenization-free, pixel-based language models (PLMs) have recently been proposed as an alternative to conventional token-based language models (TLMs), typically motivated by practical considerations, e.g., the flexibility to support new languages or vocabularies. Nevertheless, PLMs also have the potential to serve as infrastructure for computational (psycho)linguistics, where tokenization has been a source of bias in estimating information-theoretic values, such as surprisal, and has pushed the bottom-up visual orthographic features outside the scope. In this study, we first integrate PLMs into the modeling of naturalistic human reading and, in particular, examine their use to estimate next-word predictability, which can also integrate orthographic and parafoveal information. Our results demonstrate that next-word prediction difficulty, computed in pixel space, has strong predictive power for gaze duration and word skipping behavior across various languages. In particular, their advantage is complementary to existing token-level surprisal and entropy estimates. Cross-lingual analyses with script variations also clarify their distinctive visual processing biases, facilitating…

  PDF
• arXiv cs.CVOct 19

  Learning Goal-Conditioned Subgoals through Frozen Hierarchical World Models

  Xiang Kaibo, Liu Qingfeng

  Hierarchical world models plan over long horizons by passing predicted states from a coarse model to a lower-level controller. Choosing these states can be expensive: the upper-level planner repeatedly differentiates through candidate macro-action trajectories. We replace this search with a lightweight goal-conditioned network trained through the frozen high-level predictor. The network supplies a conditioning vector, while the predictor generates the next latent waypoint. Training uses hindsight goals and state-prediction losses on offline trajectories, without search-solution targets or macro-action labels. Inference retains an autoregressive high-level rollout, but requires no high-level candidate optimization. We evaluate this approach on the shared-latent HWM checkpoints distributed with H-JEPA, using three backbone seeds and three head initializations per backbone. With a common evaluation protocol, mean success is 70.4% on Cube, 48.7% on Push-T, 100.0% on FourRoom, and 71.1% on Visual AntMaze. The method improves over the corresponding HWM search baseline on three environments and has the same mean on Push-T. Dedicated measurements on an NVIDIA L40S give 1.28-4.39x…

  PDF
• arXiv cs.CLOct 19

  Conditional information Retrieval for Longitudinal Survey Harmonisation

  Wing Yan Li, Zeqiang Wang, Michelle Lin, Jon Johnson, Suparna De

  Identifying conceptually equivalent questions across different surveys is a challenging information retrieval task where surface-level textual similarity is insufficient. Two questions may be lexically similar yet assess entirely different sociological sub-concepts, or lexically different yet conceptually equivalent. We introduce a conditional information retrieval framework that addresses this by decomposing the task into two steps: concept extraction, which identifies the underlying sociological concept of a survey question using a fine-tuned generative model, and concept-aware retrieval, which augments question representations with the extracted concept as an explicit conditioning signal for finer-grained alignment. To reflect the realistic data scarcity conditions of specialised social science annotation, we use CLOSER as a case study. Our framework consistently outperforms baselines by 2-3 points in both MAP and Recall. We further analyse fine-tuning strategies including SFT, DPO, and dynamic DPO, finding that SFT delivers the most stable gains while dynamic DPO interacts differently with instruction-tuned versus distilled reasoning backbones. Finally, we demonstrate that a…

  PDF
• arXiv cs.CLOct 19

  VISAGENT: An Agent-Based End-to-End Voice Interaction System

  Xiang Wang, Zhaoxiang Liu, Xiang Chen, Liqiang He, Kai Wang +1

  Voice-based public services have evolved from manual switchboards to intelligent platforms to meet modern user needs. However, current systems remain constrained by rigid menu-driven interaction, fragmented vertical services, and limited extensibility. To address these issues, we present VISAGENT, an agent-based end-to-end voice interaction system for large-scale public services that integrates end-to-end speech interaction, hierarchical agent routing, a scalable voice-agent marketplace, and user memory support. The system replaces menu-driven workflows with natural speech and dynamically dispatches user requests to either a general conversational model or specialized domain agents via a two-level routing paradigm that achieves sub-second intent-to-agent selection over hundreds of agents. User memory informs preference-aware agent selection and supplies relevant preferences and context to selected agents, supporting personalized task execution and reducing the need for users to repeat previously provided information. A voice-agent registration mechanism converts task agents into conversational entities, enabling dynamic onboarding and ecosystem-level extensibility. We validate…

  PDF
• arXiv cs.CVOct 19

  TriTD: Tri-Partite Trajectory-Distribution Distillation for Real-Time Autoregressive Video Generation

  Jia Li, Xurui Peng, Haowei Zhu, Tianyu Zhao, Jiexi Wang +5

  Autoregressive (AR) video diffusion has emerged as a leading paradigm for efficient video generation, yet its practical deployment remains bottlenecked by the trade-off between generation quality and inference efficiency. We attribute this bottleneck to three error sources in AR rollouts: the base model error, the train-inference distribution mismatch, and the upstream error propagation. Building on this decomposition, we derive closed-form upper bounds on the per-step and cumulative errors, providing a principled basis for jointly optimizing generation quality and inference efficiency. Guided by this analysis, we propose TriTD, a Tri-Partite Trajectory-Distribution co-optimized distillation framework with three complementary modules. First, for ODE initialization, we adopt a Next-Node Trajectory Distillation (NTD) objective, which shortens the supervision horizon and admits a lower regression-error floor. Second, we introduce Chunk-Graded Noising (CGN), a monotonically non-decreasing per-chunk noising schedule that helps narrow the expected train-inference noise mismatch and removes redundant KV-cache updates, yielding substantial speedups at no quality cost. Third, we propose…

  PDF
• arXiv cs.LGOct 19

  Dynamical Batching: How Class-Cycling Training Shapes the Internal Structure of Neural Networks

  Nicolás Ratier-Werbin, Samuel Lozano, Miguel Ruiz-García

  We investigate whether cyclically varying the class composition of training batches can modify both the performance and the internal organization of neural networks. Motivated by nonequilibrium systems, in which cycling between related sub-goals can make switching between their solutions increasingly efficient, we introduce Dynamical Batching (DB), a sampling protocol that periodically emphasizes each class while leaving the loss and the optimizer unchanged, and compare it with Uniform Batching (UB), in which every mini-batch has equal class proportions. In the regime where standard training fails, DB changes the outcome: on a three-arm spiral, a capacity-limited MLP that plateaus far below perfect accuracy under UB fits the training data under DB. Tracking individual weights, we find that under DB the change between class-specialized states is carried by a smaller set of weights than under UB, and that this set is markedly more persistent from cycle to cycle, on every synthetic dataset we test and in a wider network that fits the data under both protocols. This organization is a signature of the protocol rather than a predictor of its benefit: it appears equally where DB leaves…

  PDF
• arXiv cs.CLOct 19

  DeepSEA: A Multilingual Evaluation Benchmark for Southeast Asia

  Jiuzhou Han, Abhishek Bijay Mishra, Trevor Cohn, Shubham Mittal

  While language models have demonstrated remarkable capabilities, their performance remains disproportionately skewed towards high-resource languages. This disparity is particularly acute for the 700 million inhabitants of Southeast Asia, where vast linguistic diversity remains under-represented in existing benchmarks, often suffering from limited language coverage or narrow task scopes. To address this, we introduce DeepSEA, a comprehensive benchmark constructed from established datasets through professional human translation into 12 Southeast Asian languages, spanning both high-resource (e.g., Indonesian, Thai, Vietnamese) and low-resource (e.g., Burmese, Khmer, Lao) tiers across five distinct tasks: mathematical reasoning, scientific reasoning, question answering, abstractive summarization, and machine translation. Extensive evaluation of frontier proprietary and open-weights models reveals that while frontier models like Gemini-3.7-Flash maintain robustness across resource tiers, smaller models face severe performance degradation on low-resource languages. Crucially, models perform better in reasoning and summarization when pivoted through English rather than target languages,…

  PDF
• arXiv eess.SPOct 19

  Physics-Driven Framework for QoS-Constrained Satellite System with Non-Linear PA Distortion

  Hamza Ahmed Qureshi, Abuzar Babikir Mohammad Adam, Vu Nguyen Ha, Konstantinos Ntontin, Symeon Chatzinotas

  This work develops a physics-driven self-supervised graph learning framework that directly optimizes the distortion-aware precoder under nonlinear correlated power amplifier (PA) distortion, without relying on expensive optimizer-generated labels for a user-centric satellite system. We minimize nonlinear PA consumption subject to user quality-of-service (QoS) constraints under PA nonlinearity for a downlink multi-input-single-output (MISO) satellite system. Our pipeline jointly designs the precoder and admission control that minimize nonlinear PA consumed power. In particular, a graph neural network (GNN) for the design of a distortion-aware precoder is optimized end-to-end in a self-supervised manner using a differentiable Itô-Hermite model of the true modified Rapp amplifier model. The precoder output by the GNN is used to initialize a low-complexity distortion-aware signal-to-interference-distortion (SINDR) tracking algorithm that jointly optimizes for power and admission control. Our proposed physics-based pipeline closely tracks a successive convex approximation (SCA) based solution in consumed power performance with the advantage of faster runtime and a wide operating range…

  PDF
• arXiv cs.IROct 19

  FLMNet: Self-Ensemble Distillation from Masks to Seeds for Single-Tower CTR Prediction

  Yifan Wang, Yifei Du

  Click-through rate (CTR) prediction underpins recommender systems and online advertising, where high-dimensional categorical features interact in combinatorially many ways. Several recent CTR models, such as FinalNet and QNN, report higher accuracy when a network also learns from its own averaged predictions, for example by running the same network under different dropout patterns and training each run toward the average. Why this self-distillation helps, and whether its random sampling is needed, remains unclear. This work shows that as the number of dropout patterns grows without bound, the objective reduces exactly to the label loss of the logit-averaged prediction plus a penalty on how much the dropout copies of the network disagree. When dropout does not affect how a network gates its features, this penalty can be approximated in closed form, and FLMNet is designed on this principle and trains without sampling. Networks trained from different seeds disagree in the same form, and distilling several of them into one network recovers part of their ensemble gain. On five benchmarks against seventeen baselines, the resulting models take the top two places in accuracy with a…

  PDF