Peer Revenue Past citations are no guarantee of future returns

Papers

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

Computer Science Artificial Intelligence

cs.AI Watch Artificial Intelligence

Monday 22 June

Artificial Intelligence

ENVS: Environment-Native Verified Search for Long-Horizon GUI Agents

Yincheng Zhou, Athena Zhuoming Zhong, Shijie Zhang et al. (+3 more)

As multimodal agents move from interface understanding to real software control, successful trajectory discovery in live desktop environments becomes a key challenge. GUI tasks require long-horizon sequences of precise mouse and keyboard actions, while feedback is sparse, delayed, and costly to obtain through VM rollouts. We propose Environment-Native Verified Search (ENVS), a training-time search-and-filter pipeline that uses the environment to construct verified supervision before policy optimization: it branches over behaviorally distinct GUI actions in live OSWorld VMs, verifies successful leaves, and trains from globally balanced step-level supervision. To evaluate robustness under realistic desktop interruptions, we also introduce OSWorld-Noisy, a dynamic benchmark for recoverable desktop interruptions that preserves the original tasks while testing whether agents can refocus, dismiss, wait, or recover under live perturbations. On the 300-task OSWorld pool, ENVS reaches 30.3 pass@8 on original evaluations and 29.0 on OSWorld-Noisy, outperforming matched ARPO-style online RL while reducing compute from 184-192 to 138-153 GPU-hours; even with only 30% of its search data, ENVS reaches 27.0 pass@8, exceeding ARPO from the base model. Training from noisy environments also better preserves visual-reasoning abilities on auxiliary benchmarks, including OSWorld-G Refusal (16.7 vs. 1.9) and BLINK Functional Correspondence (26.2 vs. 23.1).
Read the full abstract

All authors Yincheng Zhou, Athena Zhuoming Zhong, Shijie Zhang, Kevin Zhang, Teresa Xiaotao Shang, Shanghang Zhang

Artificial Intelligence · Cross-listed from cs.LG

Provable Benefits of RLVR over SFT for Reasoning Models: Learning to Backtrack Efficiently

Stanley Wei and Juno Kim

Recent advances in large language models (LLMs) have demonstrated that reinforcement fine-tuning of pretrained base models can lead to significant gains in reasoning performance at inference time. In this work, we theoretically analyze why reinforcement fine-tuning induces better reasoning ability than purely supervised fine-tuning (SFT) methods. We model chain-of-thought (CoT) reasoning as a pathfinding problem on graphs and compare the popular method of reinforcement learning with verifiable rewards (RLVR) against traditional SFT. We prove that SFT, when trained on golden shortest paths without negative examples, fails to learn how to efficiently backtrack. In contrast, an RLVR-trained model can learn how to efficiently backtrack from dead ends using only outcome reward. This leads to an exponential separation in inference-time compute between the two methods, and demonstrates that RLVR leads the model to learn the location of difficult decisions in a reasoning chain, ultimately allowing for better allocation of inference-time compute. Finally, we show that the reasoning traces of an RLVR model can be distilled to train a base model to backtrack efficiently as well.
Read the full abstract

Artificial Intelligence

When Agents Commit Too Soon: Diagnosing Premature Commitment in LLM Agents

Aman Mehta and Anupam Datta

Tool-using LLM agents make early choices about what to search for, which evidence to trust, and what to do next. A wrong early choice can steer every later tool call, so an agent may produce a coherent but incorrect result. Existing evaluation does not reveal this process: final-answer scoring comes only after completion, and agreement across runs can be high even when every run is wrong. We ask whether hidden states reveal that repeated runs have already settled into stable behavior. Our contributions are threefold. First, we introduce representational commitment, which measures hidden-state similarity across repeated runs at the same step. On Llama-3.1-70B running ReAct on HotpotQA, we show that higher step-4 similarity is associated with lower whole-trajectory variability (r = -0.35); we find the same pattern in action sequences and replicate it on two other models and StrategyQA. This provides an internal measure for studying when agent behavior stabilizes. Second, we establish the measure's scope. Shared evidence explains much of the observed association, the HotpotQA result disappears on hard questions, and correct and confidently wrong questions overlap. We therefore show that the measure detects stability, not correctness, and cannot by itself establish that commitment was premature. Third, we evaluate monitoring and intervention. A monitor built from three partial runs predicts whole-trajectory variability (mean AUROC 0.81). A commitment prompt reduces variability by 28% relative to a token-matched filler, but not significantly relative to the standard agent after correction, and it does not improve accuracy. Together, these contributions provide a measurement and evaluation framework for studying how agent trajectories stabilize and for testing when additional evidence, sampling, or review may be useful.
Read the full abstract

Artificial Intelligence · Cross-listed from cs.CV

BEV-Denoise: Learning Intrinsic Noise for Accurate Bird's-Eye-View Semantic Segmentation

Dooseop Choi, Kyounghwan An and Kyoung-Wook Min

In this paper, we present a framework dubbed BEV-Denoise that estimates and removes intrinsic noise from learned Bird's-Eye-View (BEV) features to achieve accurate BEV semantic segmentation. Inspired by the noise estimation capability of Denoising Diffusion Probabilistic Models (DDPM), we design a UNet-based noise estimation module that learns to estimate the noise from the learned BEV features. The estimated noise is then subtracted from the BEV features and fed to BEV map decoders for the final prediction results. To facilitate supervision for the noise estimation module, we follow a sequential learning paradigm called Task Decomposition (TD) where a pre-trained BEV map autoencoder is employed to train a view transformation (VT) encoder. We share three key insights learned from our intensive experiments that are critical for improved performance. We apply our framework to four existing models, encompassing the three major VT paradigms. Experimental results on a large-scale real-world dataset, nuScenes, demonstrate the effectiveness of our framework.
Read the full abstract

Artificial Intelligence · Cross-listed from cs.LG

Hierarchical Reinforcement Learning for Sparse-Reward Search in Commutative Algebra

Giorgi Butbaia, Paul Orland, Coco Huang et al. (+7 more)

Applying machine learning techniques to solving long-standing mathematical conjectures can be particularly challenging due to their extreme reward sparsity. As an illustrative example, we consider Kalai's algebraic Hirsch conjecture and recast the construction of its counterexamples as a sparse-reward reinforcement learning problem on graphs. We propose a constrained options-based HRL framework with an equivariant graph neural network policy, which allows us to learn useful temporal abstractions for this task. We evaluate our approach over a wide range of degrees and demonstrate that it consistently outperforms classical RL algorithms as well as greedy search. By exploiting the hierarchical structure of the problem, we effectively provide a first-of-its-kind application of HRL to a problem in commutative algebra.
Read the full abstract

All authors Giorgi Butbaia, Paul Orland, Coco Huang, Davide Passaro, Lucas Fagan, Michele Tarquini, Hailong Dao, David Eisenbud, Ali Shehper, Sergei Gukov

Artificial Intelligence

Intent-Governed Tool Authorization for AI Agents

Genliang Zhu and Chu Wang

Tool-using AI agents commonly operate under integration credentials whose static permissions exceed a user's current request. We present Intent-Governed Access Control (IGAC), a server-side authorization layer that converts a trusted request into a short-lived intent certificate, narrows the statically authorized tool manifest, and checks proposed tool and payload effects before execution. IGAC cannot grant authority outside static policy; confinement to the request additionally depends on certificate fidelity and sound effect bounds. We evaluate a reusable IGAC path over an OpenPort governance substrate using endpoint tests, 176 runtime-backed synthetic tasks, real-model classifier and planner pilots, 306 end-to-end model-task runtime trials, and a 36-trial benchmark-shaped external subset. In the deterministic runtime comparison, reference-certificate IGAC reduces the archived composite exposure-or-path indicator from 1.0000 to 0. In the end-to-end model runs, the combined IGAC-OpenPort path records no completed unsafe executions, although unsafe accepted authority remains 0.0909-0.2727 and every residual case is a non-executed draft. A trace-backed normalizer counterfactual removes this residual authority at substantial utility cost. The results support static-policy non-expansion and identify certificate precision as the principal remaining bottleneck.
Read the full abstract

Artificial Intelligence · Cross-listed from cs.CV

Intend, Reflect, Refine: An Adaptive Multimodal Reflection Framework for Autonomous Driving

Zisheng Chen, Yuping Qiu, Jianhua Han et al. (+6 more)

Recent Vision-Language-Action (VLA) models have advanced end-to-end autonomous driving by incorporating reasoning for better interpretability and planning quality. However, most existing approaches directly generate the final trajectory without explicitly examining its future consequences, which limits their reliability in complex and dynamic environments. To address this limitation, we propose IRR-Drive (Intend, Reflect, Refine), an adaptive multimodal reflection framework for autonomous driving. Specifically, to tightly couple high-level reasoning with physical constraints, IRR-Drive first generates a preliminary textual intention and anticipates potential interactions by predicting future semantic bird's-eye view (BEV) representations. This dual-modality (Text + BEV) reflection space explicitly models anticipated scene evolution, enabling the model to rigorously self-correct and refine its initial intent before generating the final trajectory. Furthermore, to balance planning performance and computational efficiency, we construct reflection-oriented training data and design an adaptive reflection reward, enabling the model to adaptively select its reasoning mode according to scene complexity. Instead of using reasoning primarily as an auxiliary interpretation, IRR-Drive directly integrates an adaptive reflection mechanism into the planning framework, enabling grounded, decision-aware trajectory correction that is driven by scene complexity. Our method achieves state-of-the-art performance on the NAVSIM benchmark in both PDMS and EPDMS. Extensive experiments demonstrate the effectiveness of our multimodal reflection framework and validate the efficacy of the proposed adaptive reflection strategy.
Read the full abstract

All authors Zisheng Chen, Yuping Qiu, Jianhua Han, Tao Tang, Xiuwei Chen, Likui Zhang, Ying-Cong Chen, Hang Xu, Xiaodan Liang

Artificial Intelligence

ThermoLLM: LLM-Based Multi-Zone HVAC Control with a Spatiotemporal Context

Kirtan Bhatt, Xiachong Lin, Matthew Amos et al. (+2 more)

Multi-zone HVAC control is a spatial decision problem in which indoor thermal evolution and control decisions depend not only on outdoor conditions and internal heat gains but also on zone layout, physical adjacency, and delayed thermal interactions across the building. Recent LLM-based HVAC controllers have shown that prompt-based control is feasible. However, these methods produce inconsistent results, are difficult to generalize, and experience control-latency issues. Their performance also relies heavily on numeric reward values, textual feedback, or unstructured retrieval, which limits their ability to make control decisions that account for zone dynamics and thermodynamics. No existing LLM-based methods have used building semantics and dynamics, together with rolling history, as the centre of the LLM context while testing and comparing HVAC control performance with existing LLM-based HVAC approaches. This paper presents ThermoLLM, an LLM-based HVAC control framework tested in a multi-zone building environment. Spatiotemporal context grounding is a main component of ThermoLLM, which uses a spatial knowledge graph derived from Brick-style building semantics and linked with recent observations from a rolling history. We evaluate ThermoLLM against standard control methods and recent state-of-the-art baselines in a five-zone building environment across six climate-season scenarios. ThermoLLM consistently achieves the best energy-comfort trade-offs and outperforms all evaluated baselines in the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) rankings across all six scenarios.
Read the full abstract

All authors Kirtan Bhatt, Xiachong Lin, Matthew Amos, Flora D. Salim, Wen Hu

Artificial Intelligence · Cross-listed from cs.SD

Cross-lingual Retrieval-Augmented Classification for Dysarthria Severity Assessment

Taeyoung Jeong, Insung Lee, Du-Seong Chang et al. (+1 more)

Automatic dysarthria severity assessment is limited by the scarcity of labeled pathological speech data. To address this, we propose Cross-lingual Retrieval-Augmented Classification (CRAC), which leverages speech from a different language via an align-retrieve-fuse pipeline. Supervised contrastive learning first shapes a severity-focused embedding space, then a vector database is built from the opposite-language corpus. During both training and inference, the classifier retrieves top-k references from the aligned space and fuses them with the input via cross-attention. Evaluated on Korean post-stroke and Italian ALS dysarthria datasets under a speaker-independent three-class protocol, CRAC achieves balanced accuracies of 87.3% on Korean and 86.7% on Italian, improving over monolingual baselines by 8.4 and 20.0 percentage points, respectively.
Read the full abstract

All authors Taeyoung Jeong, Insung Lee, Du-Seong Chang, Myoung-Wan Koo

Artificial Intelligence · Cross-listed from cs.DB

Graph-Enhanced Large Language Models for Spatial Search

Nicole R. Schneider, Kent O'Sullivan and Hanan Samet

There have been many recent improvements in the ability of Large Language Models (LLMs) to perform complex tasks and answer domain-specific questions through techniques like Retrieval Augmented Generation (RAG). However, reasoning abilities of LLMs, including spatial reasoning abilities, are still lacking. Spatial reasoning is a key component required to answer questions in a variety of domains that are grounded in the physical world, including urban planning, civil engineering, travel, and many others. To advance the development of LLMs and facilitate an impact in these domains, new research techniques must be developed to enable LLMs to reason over spatial data, which is commonly stored in the form of a graph. In this paper we outline the challenges associated with spatial reasoning through LLMs and envision a future in which search engines integrate with LLMs to answer complex spatial questions through graph-enhanced reasoning.
Read the full abstract

Artificial Intelligence · Cross-listed from cs.SE

DeepDiscovery: A Location-Inference Framework for Task-Level Repository Understanding

Jiawei He, Weisong Sun, Mengyu Shi et al. (+4 more)

Large language models have shown strong performance on software engineering (SE) tasks, yet understanding large industrial repositories remains challenging. Existing methods often retrieve only local fragments and fail to recover the broader task-relevant context needed for complex repository-level tasks. We present DeepDiscovery, a task-level repository-understanding method for large industrial codebases. DeepDiscovery uses a two-stage Location–Inference framework to localize high-confidence task anchors and recover broader task-relevant context over multi-relational repository structure under budget constraints. Across controlled method-level evaluation, organization-internal industrial repository-understanding scenarios, and end-to-end evaluation on SWE-bench Verified, DeepDiscovery consistently improves task-relevant file recovery and downstream SE performance. On 27 medium-scale tasks, DeepDiscovery achieves the best file recovery quality among five representative baselines without offline preprocessing. On organization-internal industrial tasks from a production-scale integrated codebase ecosystem, including 27 medium-scale tasks and 40 large-scale tasks, DeepDiscovery improves Full Recall Rate across multiple AI coding systems, with absolute gains ranging from 1.6 to 9.2 percentage points on large subprojects and from 2.5 to 7.4 percentage points on medium-scale subprojects. In a controlled end-to-end evaluation on SWE-bench Verified, a system equipped with DeepDiscovery achieves a 78.6% Solve Rate, outperforming the corresponding baseline by 8.2 percentage points. These results suggest that stronger task-level repository understanding can improve coding-agent performance on complex SE tasks.
Read the full abstract

All authors Jiawei He, Weisong Sun, Mengyu Shi, Jie Jia, Tong Bian, Xikai Yang, Dong Sun

Artificial Intelligence

Agent-as-a-Router: Agentic Model Routing for Coding Tasks

Pengfei Zhou, Zhiwei Tang, Yixing Ma et al. (+8 more)

Real-world users typically have access to multiple Large Language Models (LLMs) from different providers, and these LLMs often excel at distinct domains, yet none dominate all. Consequently, routing each task to the most suitable model becomes critical for both performance and cost. Existing routers treat this as a static, one-off classification problem. However, we identify the performance bottleneck for these routers as information deficit: simply augmenting a vanilla LLM router with performance statistics at the task-dimension level yields a 15.3% relative gain, surpassing a heuristic router built on the same dimension-level priors. Motivated by this finding, we propose Agent-as-a-Router, a framework that formalizes routing as a C-A-F loop (Context->Action->Feedback->Context). It closes the information gap by accumulating execution-grounded experience during deployment. We instantiate this framework as ACRouter, composed of an Orchestrator, a Verifier, a Memory module, and introduce CodeRouterBench, an evaluation environment comprising ~10K task instances with verified scores from 8 frontier LLMs, enabling regret-based router comparison on streaming tasks. Experiments show that ACRouter achieves the lowest cumulative regret on in-distribution tasks and generalizes to out-of-distribution agentic-programming tasks, demonstrating that our routing framework actively closes the information gap. Codes and benchmarks are released at https://github.com/LanceZPF/agent-as-a-router.
Read the full abstract

All authors Pengfei Zhou, Zhiwei Tang, Yixing Ma, Jiasheng Tang, Yizeng Han, Zhenglin Wan, Fanqing Meng, Wei Wang, Bohan Zhuang, Wangbo Zhao, Yang You

Artificial Intelligence · Cross-listed from eess.AS

Explainable AI in Speaker Recognition – Attention Map Visualisation and Evaluation

Yanze Xu, Mark D. Plumbley and Wenwu Wang

Explaining and understanding the decision-making process of artificial intelligence (AI) systems, particularly those implemented by neural networks, falls within the field of explainable AI (XAI). Analogous to the human attention mechanism, neural networks are assumed to possess their own attention mechanisms that selectively process information during decision-making. This work proposes to study one XAI topic: analysing and visualising the attention mechanisms of neural networks. Our experiments are performed on speaker recognition neural networks that are trained to identify speaker identity from a given utterance. Previous studies have widely used class activation map (CAM)-based methods to analyse and visualise the attention mechanisms of neural networks. Each of these methods produces an attention map for each network input, highlighting which input regions are selectively processed when the speaker recognition network makes decisions. However, the evaluation of attention maps produced by these methods remains largely underexplored. This work systematically reviews an existing attention map evaluation algorithm, establishing key concepts and identifying its shortcomings. On the basis of this existing evaluation algorithm, a new version is then proposed to address the identified shortcomings, called the Modified Randomised Input Sampling for Explanation - Evaluation algorithm (Modified RISE-eval). Using Modified RISE-eval, we evaluate the attention maps produced by two representative CAM-based methods, GradCAM and LayerCAM, applied to a certain speaker recognition network. The evaluation results demonstrate that GradCAM and LayerCAM each exhibit distinct advantages when applied under different experimental conditions in the speaker recognition task.
Read the full abstract

Artificial Intelligence · Cross-listed from cs.CL

Explanation-Guided Medical Named Entity Recognition with Stability and Boundary Awareness for Atopic Dermatitis

Xueguang Li, Di Lin, Xue Jiang et al. (+2 more)

Objective: This study aims to improve the reliability and robustness of medical named entity recognition (NER) in Chinese atopic dermatitis (AD) clinical texts through explanation-guided learning. Methods: We propose a stability and boundary-aware explanation-guided NER framework. Perturbation-based analysis is used to evaluate explanation stability and entity boundary sensitivity. An adaptive fusion strategy dynamically combines local and global explanation to generate more reliable token-level explanations. The fused explanation signals are further incorporated into model training through stability, boundary-aware, and consistency constraints. Results: Experiments on Chinese AD NER datasets show that the proposed framework improves explanation robustness and achieves consistent performance gains across multiple NER models. The adaptive fusion strategy also provides more stable explanations and stronger boundary perception than individual explanation methods. Conclusion: The proposed method effectively integrates reliable explanation signals into medical NER training, improving both recognition performance and explanation reliability. The framework provides a practical and generalizable solution for explainable medical NER and offers reliable support for downstream clinical decision-making and medical knowledge applications.
Read the full abstract

All authors Xueguang Li, Di Lin, Xue Jiang, Yanxi Li, Yugang Chi

Artificial Intelligence

CLI-Universe: Towards Verifiable Task Synthesis Engine for Terminal Agents

Zhanbo Hua, Yifan Yao, Weihao Xie et al. (+14 more)

While recent LLM-based terminal agents have demonstrated promising capabilities, the scarcity of high-quality, executable training data remains a critical bottleneck. Existing synthesis pipelines typically scale by retrofitting surface-level artifacts into tasks, frequently yielding ambiguous instructions, shallow execution paths, and brittle tests that provide weak learning signals. To overcome this, we introduce CLI-Universe, a principled synthesis engine that constructs terminal-agent tasks. CLI-Universe generates candidate tasks by sampling combinations across a multi-dimensional capability taxonomy (domain, skill type, capability, and engineering pillar), then grounds each candidate through evidence-guided deep research over real-world technical materials. To ensure rigorous supervision, validated blueprints are instantiated into Dockerized environments and subjected to a multi-stage executable verification pipeline featuring rubric-gated test construction, hint-conditional filtering, and strict fail-to-pass checking. Across the full pipeline, from candidate generation to verification, approximately two-thirds of candidates are discarded, retaining only those that are genuine, verifiable, and non-trivially challenging. To validate our framework, we instantiate a highly distilled dataset of 6,000 trajectories called CLI-Universe-6K. Remarkably, fine-tuning Qwen3-32B on CLI-Universe-6K achieves 33.4% on Terminal-Bench 2.0. This sets a new state-of-the-art for models trained on open-source data at or below 32B parameters, and outperforms several models an order of magnitude larger, demonstrating the profound data efficiency of structured, high-fidelity synthesis.
Read the full abstract

All authors Zhanbo Hua, Yifan Yao, Weihao Xie, Yongchi Zhao, Minghao Liu, Ruizhi Qiu, Zhewei Huang, Zun Wang, Yiyan Ji, Yunhai Ye, Letian Zhu, Xinping Lei, Han Li, Zhiyuan Ma, Zili Wang, Zhaoxiang Zhang, Jiaheng Liu

Artificial Intelligence · Cross-listed from cs.LG

Priority-Aware Learning-Unlearning Correction for Dynamic Decentralized LoRA Fine-Tuning

Nuocheng Yang, Yechen He, Sihua Wang et al. (+3 more)

As large language models (LLMs) are increasingly deployed at the network edge to provide pervasive generative AI services, decentralized federated learning (DFL) provides a vital mechanism for privacy-preserving, domain-specific fine-tuning through peer-to-peer exchanges of parameter-efficient updates. However, the dynamic nature of practical decentralized edge networks, where devices may dynamically join or leave the collaborative training process, requires the system to continuously adapt to new data while selectively removing prior contributions. This correction process remains a significant bottleneck, as individual device updates become deeply entangled within the global fine-tuned parameters. To address this challenge, we propose a priority-aware learning-unlearning correction framework based on orthogonal LoRA that can enhance the knowledge evaluation through topology adjustment. Specifically, we first design an orthogonal LoRA mechanism that yields post-training contribution coordinates, enabling history-free projection addition and deletion in response to membership changes. We then analyze the correction bottleneck and develop a priority-aware policy that selects among topology refinement, local correction, proximal damping, and synchronization scheduling according to the dominant residual term. A resource allocation algorithm is further developed to allocate limited communication across layer groups, prioritizing the primary bottlenecks within per-round wireless constraints. Experiments demonstrate that the proposed framework achieves robust post-event correction for both device join and leave events and validate that different residual regimes necessitate distinct correction actions.
Read the full abstract

All authors Nuocheng Yang, Yechen He, Sihua Wang, Zihan Chen, Tony Q. S. Quek, Changchuan Yin

Artificial Intelligence · Cross-listed from cs.LG

SpotAttention: Plug-In Block-Sparse Routing for Pretrained Long-Context Transformers

Huzama Ahmad and Se-Young Yun

Long contexts have become standard in pretrained LLMs, yet they remain expensive to run: prefill compute grows quadratically with sequence length, and every decode step re-reads a key-value cache that grows linearly with it. Sparse attention cuts these costs by attending only to a relevant subset of past tokens, but selecting that subset is itself expensive. We present SpotAttention, a lightweight selector that attaches to a frozen pretrained transformer and learns by KL distillation to estimate its attention distribution. The selector picks the top-K keys each query attends to, and because its estimate is a calibrated distribution, a dual top-p rule reads the per-query, per-layer budget directly from it. Across Qwen3 (dense, 4B-32B) and Qwen3.5 (hybrid linear/full attention, 4B-9B), SpotAttention matches dense accuracy at contexts up to 128K tokens, eight times the training length. Decode at L=128K runs 3.9x faster than FlashAttention and 1.8x faster than Twilight, the strongest training-free baseline. Quantizing the selector's K-cache to INT4 or FP4 microscale shrinks it 3.5x at no accuracy cost.
Read the full abstract

Artificial Intelligence · Cross-listed from cs.CV

VideoLatent: Video-Language Learning via Latent Self-Forcing

Zi-Yuan Hu, Zicong Tang, Shijia Huang et al. (+3 more)

Recent advancements in chain-of-thought (CoT) reasoning have shown promise in enhancing video understanding and reasoning capabilities of multimodal large language models (MLLMs). However, existing CoT-based MLLMs require labor-intensive CoT annotations and incur substantial training and inference overhead. While visual latent reasoning has emerged as a more efficient alternative, existing methods primarily focus on image tasks and heavily rely on additional supervision signals for visual latent generation (e.g., CoT traces, auxiliary images, or fine-grained annotations), limiting their scalability and transferability to video tasks. To bridge this gap, we introduce VideoLatent, a novel MLLM equipped with a latent injection module tailored for video understanding and reasoning. Specifically, VideoLatent learns to perform visual latent reasoning using a new latent self-forcing training paradigm, which comprises latent alignment and latent diversity objectives, and relies solely on standard video-question-answer triplets. Extensive experiments across 14 benchmarks demonstrate that our model consistently outperforms existing standard and latent MLLMs on general video understanding and complex video reasoning. Compared with Video-R1, our VideoLatent achieves superior computational efficiency, reducing training/inference overhead by $\sim$6$\times$/$\sim$68$\times$. Moreover, experiments demonstrate that our method has strong generalizability to different MLLM backbones and different model scales.
Read the full abstract

All authors Zi-Yuan Hu, Zicong Tang, Shijia Huang, Yanyang Li, Michael R. Lyu, Liwei Wang

Artificial Intelligence · Cross-listed from cs.LG

Discovering Crystal Structure Prediction Algorithms with an AI Co-Scientist

Kiyoung Seong, Nayoung Kim and Sungsoo Ahn

We introduce Human-AI Co-discovery system (HACO) for scientific algorithm discovery through cross-domain search and sparse human steering. Starting from the goal of generating crystal structures from chemical compositions, HACO searched across generative modeling methodologies from multiple fields and identified MaskGIT, a masked generative model from vision, as a promising framework for crystal structure prediction (CSP). HACO instantiated this masked formulation as a discrete token model of crystal structure; guided by sparse high-level human objectives, it then added crystallographic symmetry tokens, space group stratified sampling for polymorph coverage, and sub-bin coordinate refinement, yielding the Masked Generative Crystal Transformer (MaskGXT). On the MP-20 polymorph split, MaskGXT reaches 79.06% match-everyone-to-reference (METRe) accuracy, compared with 70.87% for the strongest evaluated baseline. MaskGXT also attains the best match rate on standard MP-20 and MPTS-52 CSP benchmarks. These results provide evidence that, in domains offering cheap, fast, and well-aligned validation, transfer-guided interactive AI co-scientists can contribute to scientific algorithm discovery by identifying transferable modeling principles and combining them with targeted human domain guidance.
Read the full abstract

Artificial Intelligence

AI Scientists as Engines of Discovery: A Case for Development within Reformed Institutions

Raul Jimenez, Boris Bolliet, Francisco Villaescusa-Navarro et al. (+7 more)

Agentic artificial intelligence (AI) systems are beginning to assist, accelerate, and partially automate scientific discovery, performing tasks that span literature synthesis, code generation, data analysis, hypothesis proposal, and model criticism. We argue that this transition is qualitative rather than incremental, and that suitably designed multi-agent systems may evolve from passive computational tools into “AI scientists” that can expand the hypothesis-generating and verification capacity of science. Such systems must be developed and deployed within a scientific ecosystem fit for purpose: institutions must be redesigned for verification, accountability, interpretability, and dual-use safety. We sketch how multi-agent architectures, illustrated by the prototype framework Denario, accelerate the discovery cycle and traverse model spaces beyond human reach; examine what this implies for authorship, peer review, and the enduring role of human scientists; and close with recommendations for governing AI as an epistemic actor rather than a mere instrument.
Read the full abstract

All authors Raul Jimenez, Boris Bolliet, Francisco Villaescusa-Navarro, Rabih Zbib, Benjamin Wandelt, David N. Spergel, Thomas Meier, Jessica Montgomery, Hana Aliee, Licia Verde

Artificial Intelligence · Cross-listed from cs.LG

The Unseen Hand: Manipulating Model Fairness and SHAP with Targeted Identity Re-Association Attacks

Sannaan Khan and Muhammad U. S. Khan

As machine learning models grow more influential and opaque, algorithmic fairness and explainability are critical for ensuring accountability. However, we demonstrate that these auditing mechanisms are themselves vulnerable to subtle manipulation, camouflaging the influence of protected features. While prior work on data-agnostic attacks has exposed this vulnerability, they leave behind detectable artifacts that compromise their stealth. We introduce Targeted Identity Re-Association (TIRA) attacks, a novel family of attacks that iteratively and probabilistically manipulate a model's outputs without requiring access to the model's internals or feature representations. We formalize two algorithms: Probabilistic Micro-Shuffling (PMiS), which applies localized adjacent swaps, and Probabilistic Rank-Shift Micro-Perturbation (PRSMP), which introduces small, randomized rank shifts. We empirically demonstrate that TIRA attacks are highly effective at pushing fairness metrics towards ideal values. Crucially, TIRA attacks successfully confound SHAP-based explanations, leaving effectively zero residual attribution for protected features, a major improvement over prior work.
Read the full abstract

Artificial Intelligence

RaMem: Contextual Reinstatement for Long-term Agentic Memory

Wei Yang, Bryce Kan, Shixuan Li et al. (+5 more)

Long-term memory has become increasingly important for LLM agents that operate across extended interactions and evolving task contexts. Recent memory systems have made past experiences more persistent, compact, and retrievable, but retrieval alone does not ensure that a memory provides valid evidence for the current query. When experiences are compressed into reusable fragments, memories from different situations may appear equally relevant if they involve recurring entities or user states. We refer to this failure as context collapse: memories lose the surrounding context needed to judge whether they provide valid evidence for the current query. To address this problem, we propose Contextual Reinstatement for Agentic Memory (RaMem), a framework that turns retrieved memory fragments into contextually verifiable evidence. RaMem operates through four coordinated stages: (i) evidence anchoring grounds each memory in its original episodic conditions, especially event time, mention time, session span, and participants; (ii) recall condition induction derives the evidence conditions implied by the query; (iii) validity-aware retrieval uses these conditions to prioritize context-compatible memories while retaining content-relevant candidates as fallback evidence; and (iv) context-preserved synthesis keeps the selected memories' structured context available to the generator. Experiments on long-term memory benchmarks show that RaMem consistently improves performance over strong memory baselines, with average F1 gains of more than 10% across several backbones.
Read the full abstract

All authors Wei Yang, Bryce Kan, Shixuan Li, Li Li, Yuehan Qin, Jiate Li, Paul Bogdan, Jesse Thomason

Artificial Intelligence · Cross-listed from cs.LG

CLIP-guided Diffusion Model for Backdoor Generation in Sensor-based Human Activity Recognition

Toby Briston, Illya Kosyk and Kuniyih S

Sensors are critical components of modern intelligent devices. The proliferation of the Internet of Things (IoT) and wearable mobile devices has enabled the integration of such sensors to monitor the environment and enable users to take predictive actions. Human activity recognition (HAR) is a popular application in which Inertial Measurement Unit (IMU)-based sensors, such as accelerometers and gyroscopes, are used to provide insights into health, training, and medical diagnosis. However, the accuracy of such a model is hindered by the lack of data. The diffusion model-based technique has proven successful in generating synthetic data for training HAR models. In this paper, we propose a backdoor training technique, IMU-DM-CLIP, that leverages a diffusion model to enable trigger-based attacks on HAR models. Our empirical analysis shows that the attack is successful even with a very small backdoor injection rate of 10% and 10% of the data guided for the diffusion model.
Read the full abstract

Artificial Intelligence · Cross-listed from cs.CV

OrthoMotion:Disentangling Camera and Subject Motion via Geometry Semantics Orthogonal Attention

Zijie Meng

Controllable video generation demands independent command of the camera and the subject, yet 2D conditioning entangles them: camera- and object-induced optical flow share the same inverse-depth (1/Z) scaling and cannot be separated from image evidence alone. We first prove that this entanglement is representational, not architectural – the 2D camera/object split is a non-identifiable inverse problem – and therefore reframe decoupling as a question of operator design. We resolve it at the level of the attention operator. OrthoMotion routes camera motion into a geometric channel, a norm-preserving rotation of the rotary position embedding (RoPE) phase, and subject motion into a semantic channel, a gated value injection in cross-attention. Because these sub-operators are algebraically complementary – a rotation versus a translation of the affine action on tokens – a lightweight decoupling regularizer provably drives their response subspaces to orthogonality, so the two controls stop interfering. To our knowledge OrthoMotion is the first method to guarantee disentanglement by construction rather than hope for it to emerge. It attains state-of-the-art camera and subject accuracy at once while minimizing cross-talk, which we quantify with a new Cross-Talk Error (CTE) metric, cutting cross-talk by more than 2.4x with no loss in fidelity and generalizing across backbones.
Read the full abstract

Artificial Intelligence

Finding the Evidence: Discovering Decision-Supporting Tokens for On-Policy Reasoning Distillation

Jinwei Xiao, Zhuowen Han, Yueqing Sun et al. (+6 more)

On-policy distillation transfers reasoning ability through dense token-level supervision, yet the nature of the transferable signal remains unclear. We discover that reasoning chains contain two types of knowledge that require different discovery mechanisms: decisions (where to branch), which surface through student uncertainty, and evidence (intermediate steps that justify decisions), which hides in positions where the student is confident yet wrong. Current methods capture only decisions; the substantive knowledge in evidence tokens remains untransferred. We propose DEAR(Decision-Evidence Aware Reasoning Distillation), which first identifies decisions via student entropy, then discovers their supporting evidence through hidden-state cosine similarity to decision anchors, boosted by teacher-student divergence to prioritize the largest knowledge gaps. Across three student-teacher configurations on math and code benchmarks, DEAR consistently outperforms standard OPD, with up to +2.5pp on competition math and +5.7pp on code generation.
Read the full abstract

All authors Jinwei Xiao, Zhuowen Han, Yueqing Sun, Zhengxi Lu, Yuxin Liu, Zhiyuan Yao, Wentao Chen, Qi Gu, Xunliang Cai

Artificial Intelligence · Cross-listed from cs.CV

DBT-Bleed: Dual-Branch Temporal Modeling with Key-Frame Selection for Surgical Bleeding Detection

Sudhanshu Mishra, Jialang Xu, Jensen Ang et al. (+3 more)

Intraoperative Adverse Events (IAEs) detection is critical for improving surgical safety, with bleeding being among the most frequent events across many surgery types. Existing methods struggle to distinguish bleeding IAE from visually similar residual blood due to limited temporal reasoning. Moreover, modeling long surgical videos while preserving fine-grained temporal dynamics remains computationally challenging. We propose DBT-Bleed, a dual-branch multi-scale temporal modeling framework disentangling bleeding and normal representations using layer-wise temporal adapters for short- and long-term bleeding progression. To efficiently process long surgical videos without sacrificing fine-grained temporal information, we introduce HiRED, a Hierarchical Entropy-Driven frame selection strategy that retains temporally informative segments while removing redundancy. Experiments on the MultiBypass dataset demonstrate gains of 6.53% in F1, 5.62% in Recall and 9% in MCC values for bleeding IAE detection, consistently outperforming video-level baselines. Additionally, we evaluate cross-procedure generalization on a newly curated dataset from a different surgical procedure type, where DBT-Bleed demonstrates robust transferability by achieving gain of 6% in F1 and 8% in MCC under zero-shot setting. To support this evaluation, we introduce EndoPit-IAE, an Endonasal Pituitary Surgery dataset annotated for IAEs, representing the first IAE-annotated dataset in neurosurgery. Code will be made publicly available upon acceptance.
Read the full abstract

All authors Sudhanshu Mishra, Jialang Xu, Jensen Ang, Evangelos B. Mazomenos, Beng Ti Ang, Yueming Jin

Artificial Intelligence

MINCE: Shrinking LLM Evaluation Datasets via Few-Model Monte Carlo Calibration

Devleena Das, Rajeev Patwari, Vikram Kumar Bukka et al. (+3 more)

Evaluating LLMs across many model variants—quantized, fine-tuned, or deployment-specific—requires running large benchmarks repeatedly, a process that can take tens of hours per model on edge hardware such as NPUs. Existing subset selection methods reduce this cost but depend on large calibration pools or learned prediction layers. We introduce MINCE (Monte Carlo Informed N-sizing for Compact Evaluation), which uses Monte Carlo simulation over per-item logs from a small set of calibration models to find the minimum subset size that bounds accuracy drift and then fixes a randomly sampled subset at that size, with no prediction layer needed. MINCE reduces IFEVAL by 54%, MMLU by 89%, GSM8K by 70%, and MMLU-Pro by 88% with maximum drift $\leq$2.62\,pp on BF16 calibration models. The frozen subsets generalize to held-out GPU models with mean drift $\leq$1.40\,pp and to INT4 NPU models with mean drift of 0.77–3.59\,pp, while delivering evaluation speedups of up to 8.1$\times$ on the GPU models and evaluation speedups of 1.7–3.4$\times$ on the NPU models. The method is robust to calibration pool size and achieves lower drift than tinyBenchmarks (12$\times$ lower on MMLU, 3.3$\times$ on GSM8K) while using 42$\times$ fewer calibration models.
Read the full abstract

All authors Devleena Das, Rajeev Patwari, Vikram Kumar Bukka, Nithin Kumar Guggilla, Elliott Delaye, Ashish Sirasao

Artificial Intelligence

Active Inference as the Test-Time Scaling Law for Physical AI Agents

Omar Hashash, Christo Kurisummoottil Thomas, Walid Saad et al. (+3 more)

In this paper, a novel test-time scaling law for physical artificial intelligence (AI) agents is introduced. This scaling law enables physical AI agents to reason with their world models to generalize in unforeseen scenarios at test time. The derived scaling law is grounded in the first principle of active inference, which equips agents with the general objective to survive in the real world, under which their specific task objectives are subsumed. Active inference achieves this by providing the reasoning to resolve prediction errors that arise when the agent encounters unforeseen situations outside its training distribution, enabling generalization in non-stationary environments. The proposed scaling law captures this by dynamically updating the agent's policy with this reasoning at test time. This policy update is modeled as a soft Bayesian inference process in which beliefs about the policy are updated using the reasoning that reduces expected prediction errors under allowable policies as a likelihood. The resulting posterior policy admits a biological interpretation, recovering the scaling mechanism that engages the brain's basal ganglia and prefrontal cortex at test time. To solve this analytically intractable problem, a variational inference solution minimizing free energy bounds is developed. This solution extends to enable learning beyond training by reinforcing new instances, resolved at test time, in both the policy and world model. Unlike existing scaling laws constrained by model size and training data, the derived solution scales with the continuous real-world experience of a physical AI agent. Simulation results on an autonomous driving task demonstrate that the proposed solution outperforms model-free Q-learning and model-based Bayesian reinforcement learning, achieving robust generalization to unforeseen scenarios while improving inference efficiency by over 36%.
Read the full abstract

All authors Omar Hashash, Christo Kurisummoottil Thomas, Walid Saad, Merouane Debbah, Karl Friston, Adeel Razi

Artificial Intelligence · Cross-listed from cs.CL

Bagpiper-TTS: Natural Language Guided Universal Speech Synthesis

Jinchuan Tian, Haoran Wang, Siddhant Arora et al. (+6 more)

Classical TTS systems typically rely on rigid input formats and predefined metadata slots, limiting their ability to fulfill flexible user requirements. This paper introduces Bagpiper-TTS, a universal speech synthesis system that deals with diverse natural language user requests. Given a natural language prompt, Bagpiper-TTS first reasons over the users' intent to derive a rich caption, i.e., a comprehensive textual blueprint encompassing both transcription and nuanced metadata. Subsequently, this caption guides the synthesis of the target speech. Our model inherently supports a broad spectrum of tasks besides classical TTS applications, including multi-talker, intent-to-speech, role-play synthesis, singing voice synthesis, and more. Experimental results demonstrate that Bagpiper-TTS achieves an 1.7% Word Error Rate (WER) on the Seed-TTS-Eval benchmark and match the performance of dedicated models in both LLM-as-a-judge and human subjective evaluations across multiple applications.
Read the full abstract

All authors Jinchuan Tian, Haoran Wang, Siddhant Arora, Takashi Maekaku, Keita Goto, Jin Sakuma, Yusuke Shinohara, Chao-Han Huck Yang, Shinji Watanabe

Artificial Intelligence

AI-Assisted Help-Seeking Trajectories in Programming Education from an SRL-Informed Perspective

Boxuan Ma, Huiyong Li, Gen Li et al. (+3 more)

Generative AI tools provide novice programmers with instant, personalized support, but also raise concerns about whether AI use supports or bypasses students' regulation of problem-solving. Existing work has largely focused on correctness, usability, or overall usage frequency, with less attention to how student–AI help-seeking unfolds. This study addresses this gap by analyzing AI-assisted help-seeking trajectories in university-level programming. Using an SRL-informed analytical framework that links prompt-level help-seeking codes to conceptual, implementation, debugging, and reflective forms of support, we analyzed 1,290 task-specific student prompts linked to 17,190 code submissions from 71 students in introductory Python programming courses. Specifically, we examined how help-seeking interactions were structured across turns and attempts, and how trajectory patterns related to task scores and the number of code submissions. Results indicate that many students primarily used AI for reactive troubleshooting rather than for planned, self-regulated problem-solving. Although trajectory patterns were not associated with significant differences in task scores, they differed substantially in the number of code submissions required. These findings suggest that the educational significance of AI support lies not only in whether students use AI, but in how their help-seeking trajectories develop during programming problem-solving.
Read the full abstract

All authors Boxuan Ma, Huiyong Li, Gen Li, Li Chen, Atsushi Shimada, Shin'ichi Konomi