# Research Papers — 2026-02 · bundle page 188 of 210

> Full-text markdown of papers #9351–9400 of 10493 published in 2026-02, newest first. AI-readable mirrors of the full 10493-paper 2026-02 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-02/page/188
[← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/187.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-02/page/189.md)

### "I'm happy even though it's not real": GenAI Photo Editing as a Remembering Experience

Authors: Yufeng Wu, Qing Li, Elise van den Hoven, A. Baki Kocaballi
Published: 2026-02-03
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2602.03104v2

Generative Artificial Intelligence (GenAI) is increasingly integrated into photo applications on personal devices, making editing photographs easier than ever while potentially influencing the memories they represent. This study explores how and why people use GenAI to edit personal photos and how this shapes their remembering experience. We conducted a two-phase qualitative study with 12 participants: a photo editing session using a GenAI tool guided by the Remembering Experience (RX) dimensions, followed by semi-structured interviews where participants reflected on the editing process and results. Findings show that participants prioritised felt memory over factual accuracy. For different photo elements, environments were modified easily, however, editing was deemed unacceptable if it touched upon a person's identity. Editing processes brought positive and negative impacts, and itself also became a remembering experience. We further discuss potential benefits and risks of GenAI editing for remembering purposes and propose design implications for responsible GenAI.

---

### Task--Specificity Score: Measuring How Much Instructions Really Matter for Supervision

Authors: Pritam Kadasi, Abhishek Upperwal, Mayank Singh
Published: 2026-02-03
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.03103v1

Instruction tuning is now the default way to train and adapt large language models, but many instruction--input--output pairs are only weakly specified: for a given input, the same output can remain plausible under several alternative instructions. This raises a simple question: \emph{does the instruction uniquely determine the target output?} We propose the \textbf{Task--Specificity Score (TSS)} to quantify how much an instruction matters for predicting its output, by contrasting the true instruction against plausible alternatives for the same input. We further introduce \textbf{TSS++}, which uses hard alternatives and a small quality term to mitigate easy-negative effects. Across three instruction datasets (\textsc{Alpaca}, \textsc{Dolly-15k}, \textsc{NI-20}) and three open LLMs (Gemma, Llama, Qwen), we show that selecting task-specific examples improves downstream performance under tight token budgets and complements quality-based filters such as perplexity and IFD.

---

### Consensus Group Relative Policy Optimization for Text Generation

Authors: Yuki Ichihara, Yuu Jinnai, Kaito Ariu, Eiji Uchibe
Published: 2026-02-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.03102v2

Many strong decoding methods for text generation follow a sample-and-rerank paradigm: they draw multiple candidates, score each under a utility (reward) function using consensus across samples, and return the best one. Although effective, these methods incur high computational costs during inference due to repeated sampling and scoring. Prior attempts to amortize inference-time computation typically rely on gold references, teacher labels, or curated preference data, increasing dataset construction effort and the demand for high-fidelity reward models. We propose Consensus Group Relative Policy Optimization (C-GRPO), which distills Minimum Bayes Risk (MBR) decoding into training by formulating the consensus utility as a group-relative objective within GRPO. C-GRPO requires only a utility function and policy samples, without gold references or explicit preference labels. Under ideal conditions, we show that the objective function of C-GRPO is directionally aligned with the gradient of the expected-utility objective underlying MBR decoding, leading to a convergence guarantee. Experiments on machine translation (WMT 2024) and text summarization (XSum) demonstrate that C-GRPO successfully achieves performance comparable to MBR decoding without the associated inference-time overhead, while outperforming reference-free baseline methods.

---

### Consensus Group Relative Policy Optimization for Text Generation

Authors: Yuki Ichihara, Yuu Jinnai, Kaito Ariu, Eiji Uchibe
Published: 2026-02-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.03102v1

Many strong decoding methods for text generation follow a sample-and-rerank paradigm: they draw multiple candidates, score each under a utility (reward) function using consensus across samples, and return the best one. Although effective, these methods incur high computational costs during inference due to repeated sampling and scoring. Prior attempts to amortize inference-time computation typically rely on gold references, teacher labels, or curated preference data, increasing dataset construction effort and the demand for high-fidelity reward models. We propose Consensus Group Relative Policy Optimization (C-GRPO), which distills Minimum Bayes Risk (MBR) decoding into training by formulating the consensus utility as a group-relative objective within GRPO. C-GRPO requires only a utility function and policy samples, without gold references or explicit preference labels. Under ideal conditions, we show that the objective function of C-GRPO is directionally aligned with the gradient of the expected-utility objective underlying MBR decoding, leading to a convergence guarantee. Experiments on machine translation (WMT 2024) and text summarization (XSum) demonstrate that C-GRPO successfully achieves performance comparable to MBR decoding without the associated inference-time overhead, while outperforming reference-free baseline methods.

---

### Risky-Bench: Probing Agentic Safety Risks under Real-World Deployment

Authors: Jingnan Zheng, Yanzhen Luo, Jingjun Xu, Bingnan Liu, Yuxin Chen, Chenhang Cui, Gelei Deng, Chaochao Lu, Xiang Wang, An Zhang, Tat-Seng Chua
Published: 2026-02-03
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.03100v1

Large Language Models (LLMs) are increasingly deployed as agents that operate in real-world environments, introducing safety risks beyond linguistic harm. Existing agent safety evaluations rely on risk-oriented tasks tailored to specific agent settings, resulting in limited coverage of safety risk space and failing to assess agent safety behavior during long-horizon, interactive task execution in complex real-world deployments. Moreover, their specialization to particular agent settings limits adaptability across diverse agent configurations. To address these limitations, we propose Risky-Bench, a framework that enables systematic agent safety evaluation grounded in real-world deployment. Risky-Bench organizes evaluation around domain-agnostic safety principles to derive context-aware safety rubrics that delineate safety space, and systematically evaluates safety risks across this space through realistic task execution under varying threat assumptions. When applied to life-assist agent settings, Risky-Bench uncovers substantial safety risks in state-of-the-art agents under realistic execution conditions. Moreover, as a well-structured evaluation pipeline, Risky-Bench is not confined to life-assist scenarios and can be adapted to other deployment settings to construct environment-specific safety evaluations, providing an extensible methodology for agent safety assessment.

---

### TextME: Bridging Unseen Modalities Through Text Descriptions

Authors: Soyeon Hong, Jinchan Kim, Jaegook You, Seungtaek Choi, Suha Kwak, Hyunsouk Cho
Published: 2026-02-03
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.03098v2

Expanding multimodal representations to novel modalities is constrained by reliance on large-scale paired datasets (e.g., text-image, text-audio, text-3D, text-molecule), which are costly and often infeasible in domains requiring expert annotation such as medical imaging and molecular analysis. We introduce TextME, the first text-only modality expansion framework, to the best of our knowledge, projecting diverse modalities into LLM embedding space as a unified anchor. Our approach exploits the geometric structure of pretrained contrastive encoders to enable zero-shot cross-modal transfer using only text descriptions, without paired supervision. We empirically validate that such consistent modality gaps exist across image, video, audio, 3D, X-ray, and molecular domains, demonstrating that text-only training can preserve substantial performance of pretrained encoders. We further show that our framework enables emergent cross-modal retrieval between modality pairs not explicitly aligned during training (e.g., audio-to-image, 3D-to-image). These results establish text-only training as a practical alternative to paired supervision for modality expansion.

---

### De-conflating Preference and Qualification: Constrained Dual-Perspective Reasoning for Job Recommendation with Large Language Models

Authors: Bryce Kan, Wei Yang, Emily Nguyen, Ganghui Yi, Bowen Yi, Chenxiao Yu, Yan Liu
Published: 2026-02-03
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.03097v1

Professional job recommendation involves a complex bipartite matching process that must reconcile a candidate's subjective preference with an employer's objective qualification. While Large Language Models (LLMs) are well-suited for modeling the rich semantics of resumes and job descriptions, existing paradigms often collapse these two decision dimensions into a single interaction signal, yielding confounded supervision under recruitment-funnel censoring and limiting policy controllability. To address these challenges, We propose JobRec, a generative job recommendation framework for de-conflating preference and qualification via constrained dual-perspective reasoning. JobRec introduces a Unified Semantic Alignment Schema that aligns candidate and job attributes into structured semantic layers, and a Two-Stage Cooperative Training Strategy that learns decoupled experts to separately infer preference and qualification. Building on these experts, a Lagrangian-based Policy Alignment module optimizes recommendations under explicit eligibility requirements, enabling controllable trade-offs. To mitigate data scarcity, we construct a synthetic dataset refined by experts. Experiments show that JobRec consistently outperforms strong baselines and provides improved controllability for strategy-aware professional matching.

---

### PRISM: Structured Optimization via Anisotropic Spectral Shaping

Authors: Yujie Yang
Published: 2026-02-03
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.03096v1

We propose PRISM, an optimizer that enhances first-order spectral descent methods like Muon with partial second-order information. It constructs an efficient, low-rank quasi-second-order preconditioner via innovation-augmented polar decomposition. This mechanism enables PRISM to perform anisotropic spectral shaping, which adaptively suppresses updates in high-variance subspaces while preserving update strength in signal-dominated directions. Crucially, this is achieved with minimal computational overhead and zero additional memory compared to first-order baselines. PRISM demonstrates a practical strategy for integrating curvature-adaptive properties into the spectral optimization paradigm.

---

### Test-time Recursive Thinking: Self-Improvement without External Feedback

Authors: Yufan Zhuang, Chandan Singh, Liyuan Liu, Yelong Shen, Dinghuai Zhang, Jingbo Shang, Jianfeng Gao, Weizhu Chen
Published: 2026-02-03
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.03094v1

Modern Large Language Models (LLMs) have shown rapid improvements in reasoning capabilities, driven largely by reinforcement learning (RL) with verifiable rewards. Here, we ask whether these LLMs can self-improve without the need for additional training. We identify two core challenges for such systems: (i) efficiently generating diverse, high-quality candidate solutions, and (ii) reliably selecting correct answers in the absence of ground-truth supervision. To address these challenges, we propose Test-time Recursive Thinking (TRT), an iterative self-improvement framework that conditions generation on rollout-specific strategies, accumulated knowledge, and self-generated verification signals. Using TRT, open-source models reach 100% accuracy on AIME-25/24, and on LiveCodeBench's most difficult problems, closed-source models improve by 10.4-14.8 percentage points without external feedback.

---

### Training and Simulation of Quadrupedal Robot in Adaptive Stair Climbing and Descending for Indoor Firefighting: An End-to-End Reinforcement Learning Approach

Authors: Baixiao Huang, Baiyu Huang, Yu Hou
Published: 2026-02-03
Categories: cs.RO, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.03087v2

Quadruped robots are used for primary searches during the early stages of indoor fires. A typical primary search involves quickly and thoroughly looking for victims under hazardous conditions and monitoring flammable materials. However, situational awareness in complex indoor environments and rapid stair climbing and descending across different staircases remain the main challenges for robot-assisted primary searches. In this project, we designed a two-stage end-to-end deep reinforcement learning (RL) approach to optimize both navigation and locomotion. In the first stage, the quadrupeds, Unitree Go2, were trained to climb and descend stairs in Isaac Lab's pyramid-stair terrain. In the second stage, the quadrupeds were trained to climb and descend various realistic indoor staircases in the Isaac Lab engine, with the learned policy transferred from the previous stage. These indoor staircases are straight, L-shaped, and spiral, to support climbing and descending tasks in complex environments. This project explores how to balance navigation and locomotion and how end-to-end RL methods can enable quadrupeds to adapt to different stair shapes. Our main contributions are: (1) A two-stage end-to-end RL framework that transfers climbing/descending skills from abstract pyramid terrain to realistic indoor stair topologies. (2) A centerline-based navigation formulation that enables unified learning of navigation and locomotion without hierarchical planning. (3) Demonstration of policy generalization across diverse staircases using only local height-map perception. (4) An empirical analysis of success, efficiency, and failure modes under increasing stair difficulty.

---

### Neural Predictor-Corrector: Solving Homotopy Problems with Reinforcement Learning

Authors: Jiayao Mai, Bangyan Liao, Zhenjun Zhao, Yingping Zeng, Haoang Li, Javier Civera, Tailin Wu, Yi Zhou, Peidong Liu
Published: 2026-02-03
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2602.03086v1

The Homotopy paradigm, a general principle for solving challenging problems, appears across diverse domains such as robust optimization, global optimization, polynomial root-finding, and sampling. Practical solvers for these problems typically follow a predictor-corrector (PC) structure, but rely on hand-crafted heuristics for step sizes and iteration termination, which are often suboptimal and task-specific. To address this, we unify these problems under a single framework, which enables the design of a general neural solver. Building on this unified view, we propose Neural Predictor-Corrector (NPC), which replaces hand-crafted heuristics with automatically learned policies. NPC formulates policy selection as a sequential decision-making problem and leverages reinforcement learning to automatically discover efficient strategies. To further enhance generalization, we introduce an amortized training mechanism, enabling one-time offline training for a class of problems and efficient online inference on new instances. Experiments on four representative homotopy problems demonstrate that our method generalizes effectively to unseen instances. It consistently outperforms classical and specialized baselines in efficiency while demonstrating superior stability across tasks, highlighting the value of unifying homotopy methods into a single neural framework.

---

### The Trigger in the Haystack: Extracting and Reconstructing LLM Backdoor Triggers

Authors: Blake Bullwinkel, Giorgio Severi, Keegan Hines, Amanda Minnich, Ram Shankar Siva Kumar, Yonatan Zunger
Published: 2026-02-03
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2602.03085v1

Detecting whether a model has been poisoned is a longstanding problem in AI security. In this work, we present a practical scanner for identifying sleeper agent-style backdoors in causal language models. Our approach relies on two key findings: first, sleeper agents tend to memorize poisoning data, making it possible to leak backdoor examples using memory extraction techniques. Second, poisoned LLMs exhibit distinctive patterns in their output distributions and attention heads when backdoor triggers are present in the input. Guided by these observations, we develop a scalable backdoor scanning methodology that assumes no prior knowledge of the trigger or target behavior and requires only inference operations. Our scanner integrates naturally into broader defensive strategies and does not alter model performance. We show that our method recovers working triggers across multiple backdoor scenarios and a broad range of models and fine-tuning methods.

---

### AERO: Autonomous Evolutionary Reasoning Optimization via Endogenous Dual-Loop Feedback

Authors: Zhitao Gao, Jie Ma, Xuhong Li, Pengyu Li, Ning Qu, Yaqiang Wu, Hui Liu, Jun Liu
Published: 2026-02-03
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.03084v2

Large Language Models (LLMs) have achieved significant success in complex reasoning but remain bottlenecked by reliance on expert-annotated data and external verifiers. While existing self-evolution paradigms aim to bypass these constraints, they often fail to identify the optimal learning zone and risk reinforcing collective hallucinations and incorrect priors through flawed internal feedback. To address these challenges, we propose \underline{A}utonomous \underline{E}volutionary \underline{R}easoning \underline{O}ptimization (AERO), an unsupervised framework that achieves autonomous reasoning evolution by internalizing self-questioning, answering, and criticism within a synergistic dual-loop system. Inspired by the \textit{Zone of Proximal Development (ZPD)} theory, AERO utilizes entropy-based positioning to target the ``solvability gap'' and employs Independent Counterfactual Correction for robust verification. Furthermore, we introduce a Staggered Training Strategy to synchronize capability growth across functional roles and prevent curriculum collapse. Extensive evaluations across nine benchmarks spanning three domains demonstrate that AERO achieves average performance improvements of 4.57\% on Qwen3-4B-Base and 5.10\% on Qwen3-8B-Base, outperforming competitive baselines. Code is available at https://github.com/mira-ai-lab/AERO.

---

### Geometry-Preserving Neural Architectures on Manifolds with Boundary

Authors: Karthik Elamvazhuthi, Shiba Biswal, Kian Rosenblum, Arushi Katyal, Tianli Qu, Grady Ma, Rishi Sonthalia
Published: 2026-02-03
Categories: cs.LG, eess.SY, math.OC
arXiv: https://arxiv.org/abs/2602.03082v2

A growing number of neural architectures have been proposed to enforce geometric constraints, including projection-based networks, exponential-map updates, constrained output layers, and manifold neural ODEs. We provide a unified framework for these geometry-preserving architectures by organizing them according to where and how constraints are enforced, either throughout the intermediate layers or only at the final output. This perspective reveals several gaps in the existing theory. To address these gaps, we prove high-level approximation theorems for projected neural ODEs, intermediate augmented architectures, and final augmented architectures on prox-regular constraint sets, including smooth manifolds with boundary. Numerical experiments on synthetic dynamics over S^2, the disk, SO(3), together with real-world protein backbone data on SE(3), demonstrate exact feasibility for analytic updates and show that the final augmentation have simpler architecture and outperform in most tasks considered. When the constraint set is unknown, we learn projections via small-time heat-kernel limits, showing diffusion/flow-matching can be used as data-based projections. Moreover, we also the demonstrate the usefulness of the architectures that enforce non-convex constraints for path planning on manifolds with boundary.

---

### A generalizable large-scale foundation model for musculoskeletal radiographs

Authors: Shinn Kim, Soobin Lee, Kyoungseob Shin, Han-Soo Kim, Yongsung Kim, Minsu Kim, Juhong Nam, Somang Ko, Daeheon Kwon, Wook Huh, Ilkyu Han, Sunghoon Kwon
Published: 2026-02-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.03076v1

Artificial intelligence (AI) has shown promise in detecting and characterizing musculoskeletal diseases from radiographs. However, most existing models remain task-specific, annotation-dependent, and limited in generalizability across diseases and anatomical regions. Although a generalizable foundation model trained on large-scale musculoskeletal radiographs is clinically needed, publicly available datasets remain limited in size and lack sufficient diversity to enable training across a wide range of musculoskeletal conditions and anatomical sites. Here, we present SKELEX, a large-scale foundation model for musculoskeletal radiographs, trained using self-supervised learning on 1.2 million diverse, condition-rich images. The model was evaluated on 12 downstream diagnostic tasks and generally outperformed baselines in fracture detection, osteoarthritis grading, and bone tumor classification. Furthermore, SKELEX demonstrated zero-shot abnormality localization, producing error maps that identified pathologic regions without task-specific training. Building on this capability, we developed an interpretable, region-guided model for predicting bone tumors, which maintained robust performance on independent external datasets and was deployed as a publicly accessible web application. Overall, SKELEX provides a scalable, label-efficient, and generalizable AI framework for musculoskeletal imaging, establishing a foundation for both clinical translation and data-efficient research in musculoskeletal radiology.

---

### ReMiT: RL-Guided Mid-Training for Iterative LLM Evolution

Authors: Junjie Huang, Jiarui Qin, Di Yin, Weiwen Liu, Yong Yu, Xing Sun, Weinan Zhang
Published: 2026-02-03
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.03075v1

Standard training pipelines for large language models (LLMs) are typically unidirectional, progressing from pre-training to post-training. However, the potential for a bidirectional process--where insights from post-training retroactively improve the pre-trained foundation--remains unexplored. We aim to establish a self-reinforcing flywheel: a cycle in which reinforcement learning (RL)-tuned model strengthens the base model, which in turn enhances subsequent post-training performance, requiring no specially trained teacher or reference model. To realize this, we analyze training dynamics and identify the mid-training (annealing) phase as a critical turning point for model capabilities. This phase typically occurs at the end of pre-training, utilizing high-quality corpora under a rapidly decaying learning rate. Building upon this insight, we introduce ReMiT (Reinforcement Learning-Guided Mid-Training). Specifically, ReMiT leverages the reasoning priors of RL-tuned models to dynamically reweight tokens during the mid-training phase, prioritizing those pivotal for reasoning. Empirically, ReMiT achieves an average improvement of 3\% on 10 pre-training benchmarks, spanning math, code, and general reasoning, and sustains these gains by over 2\% throughout the post-training pipeline. These results validate an iterative feedback loop, enabling continuous and self-reinforcing evolution of LLMs.

---

### TMS: Trajectory-Mixed Supervision for Reward-Free, On-Policy SFT

Authors: Rana Muhammad Shahroz Khan, Zijie Liu, Zhen Tan, Charles Fleming, Tianlong Chen
Published: 2026-02-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.03073v1

Reinforcement Learning (RL) and Supervised Fine-Tuning (SFT) are the two dominant paradigms for enhancing Large Language Model (LLM) performance on downstream tasks. While RL generally preserves broader model capabilities (retention) better than SFT, it comes with significant costs: complex reward engineering, instability, and expensive on-policy sampling. In contrast, SFT is efficient but brittle, often suffering from catastrophic forgetting due to $\textbf{Supervision Mismatch}$: the divergence between the model's evolving policy and static training labels. We address this trade-off with $\textbf{Trajectory-Mixed Supervision (TMS)}$, a reward-free framework that approximates the on-policy benefits of RL by creating a dynamic curriculum from the model's own historical checkpoints. TMS minimizes $\textit{Policy-Label Divergence (PLD)}$, preventing the mode collapse that drives forgetting in standard SFT. Experiments across reasoning (MATH, GSM8K) and instruction-following benchmarks demonstrate that TMS effectively shifts the accuracy--retention Pareto frontier. While RL remains the gold standard for retention, TMS significantly outperforms standard and iterative SFT, bridging the gap to RL without requiring reward models or verifiers. Mechanistic analysis confirms that PLD drift accurately predicts forgetting and that TMS successfully mitigates this drift.

---

### Finding Optimal Video Moment without Training: Gaussian Boundary Optimization for Weakly Supervised Video Grounding

Authors: Sunoh Kim, Kimin Yun, Daeho Um
Published: 2026-02-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.03071v2

Weakly supervised temporal video grounding aims to localize query-relevant segments in untrimmed videos using only video-sentence pairs, without requiring ground-truth segment annotations that specify exact temporal boundaries. Recent approaches tackle this task by utilizing Gaussian-based temporal proposals to represent query-relevant segments. However, their inference strategies rely on heuristic mappings from Gaussian parameters to segment boundaries, resulting in suboptimal localization performance. To address this issue, we propose Gaussian Boundary Optimization (GBO), a novel inference framework that predicts segment boundaries by solving a principled optimization problem that balances proposal coverage and segment compactness. We derive a closed-form solution for this problem and rigorously analyze the optimality conditions under varying penalty regimes. Beyond its theoretical foundations, GBO offers several practical advantages: it is training-free and compatible with both single-Gaussian and mixture-based proposal architectures. Our experiments show that GBO significantly improves localization, achieving state-of-the-art results across standard benchmarks. Extensive experiments demonstrate the efficiency and generalizability of GBO across various proposal schemes. The code is available at https://github.com/sunoh-kim/gbo.

---

### FlashSinkhorn: IO-Aware Entropic Optimal Transport on GPU

Authors: Felix X. -F. Ye, Xingjie Li, An Yu, Ming-Ching Chang, Linsong Chu, Davis Wertheimer
Published: 2026-02-03
Categories: cs.LG, cs.AI, math.NA
arXiv: https://arxiv.org/abs/2602.03067v3

Entropic optimal transport (EOT) via Sinkhorn iterations is widely used in modern machine learning, yet GPU solvers remain inefficient at scale. Tensorized implementations suffer quadratic HBM traffic from dense $n\times m$ interactions, while existing online backends avoid storing dense matrices but still rely on generic tiled map-reduce reduction kernels with limited fusion. We present \textbf{FlashSinkhorn}, an IO-aware EOT solver for squared Euclidean cost that rewrites stabilized log-domain Sinkhorn updates as row-wise LogSumExp reductions of biased dot-product scores, the same normalization as transformer attention. This enables FlashAttention-style fusion and tiling: fused Triton kernels stream tiles through on-chip SRAM and update dual potentials in a single pass, substantially reducing HBM IO per iteration while retaining linear-memory operations. We further provide streaming kernels for transport application, enabling scalable first- and second-order optimization. On A100 GPUs, FlashSinkhorn achieves up to $32\times$ forward-pass and $161\times$ end-to-end speedups over state-of-the-art online baselines on point-cloud OT, improves scalability on OT-based downstream tasks. For reproducibility, we release an open-source implementation at https://github.com/ot-triton-lab/flash-sinkhorn .

---

### Shortcut Features as Top Eigenfunctions of NTK: A Linear Neural Network Case and More

Authors: Jinwoo Lim, Suhyun Kim, Soo-Mook Moon
Published: 2026-02-03
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.03066v1

One of the chronic problems of deep-learning models is shortcut learning. In a case where the majority of training data are dominated by a certain feature, neural networks prefer to learn such a feature even if the feature is not generalizable outside the training set. Based on the framework of Neural Tangent Kernel (NTK), we analyzed the case of linear neural networks to derive some important properties of shortcut learning. We defined a feature of a neural network as an eigenfunction of NTK. Then, we found that shortcut features correspond to features with larger eigenvalues when the shortcuts stem from the imbalanced number of samples in the clustered distribution. We also showed that the features with larger eigenvalues still have a large influence on the neural network output even after training, due to data variances in the clusters. Such a preference for certain features remains even when a margin of a neural network output is controlled, which shows that the max-margin bias is not the only major reason for shortcut learning. These properties of linear neural networks are empirically extended for more complex neural networks as a two-layer fully-connected ReLU network and a ResNet-18.

---

### JRDB-Pose3D: A Multi-person 3D Human Pose and Shape Estimation Dataset for Robotics

Authors: Sandika Biswas, Kian Izadpanah, Hamid Rezatofighi
Published: 2026-02-03
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.03064v1

Real-world scenes are inherently crowded. Hence, estimating 3D poses of all nearby humans, tracking their movements over time, and understanding their activities within social and environmental contexts are essential for many applications, such as autonomous driving, robot perception, robot navigation, and human-robot interaction. However, most existing 3D human pose estimation datasets primarily focus on single-person scenes or are collected in controlled laboratory environments, which restricts their relevance to real-world applications. To bridge this gap, we introduce JRDB-Pose3D, which captures multi-human indoor and outdoor environments from a mobile robotic platform. JRDB-Pose3D provides rich 3D human pose annotations for such complex and dynamic scenes, including SMPL-based pose annotations with consistent body-shape parameters and track IDs for each individual over time. JRDB-Pose3D contains, on average, 5-10 human poses per frame, with some scenes featuring up to 35 individuals simultaneously. The proposed dataset presents unique challenges, including frequent occlusions, truncated bodies, and out-of-frame body parts, which closely reflect real-world environments. Moreover, JRDB-Pose3D inherits all available annotations from the JRDB dataset, such as 2D pose, information about social grouping, activities, and interactions, full-scene semantic masks with consistent human- and object-level tracking, and detailed annotations for each individual, such as age, gender, and race, making it a holistic dataset for a wide range of downstream perception and human-centric understanding tasks.

---

### Evaluating LLMs When They Do Not Know the Answer: Statistical Evaluation of Mathematical Reasoning via Comparative Signals

Authors: Zihan Dong, Zhixian Zhang, Yang Zhou, Can Jin, Ruijia Wu, Linjun Zhang
Published: 2026-02-03
Categories: cs.LG, cs.AI, math.ST, stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2602.03061v2

Evaluating mathematical reasoning in LLMs is constrained by limited benchmark sizes and inherent model stochasticity, yielding high-variance accuracy estimates and unstable rankings across platforms. On difficult problems, an LLM may fail to produce a correct final answer, yet still provide reliable pairwise comparison signals indicating which of two candidate solutions is better. We leverage this observation to design a statistically efficient evaluation framework that combines standard labeled outcomes with pairwise comparison signals obtained by having models judge auxiliary reasoning chains. Treating these comparison signals as control variates, we develop a semiparametric estimator based on the efficient influence function (EIF) for the setting where auxiliary reasoning chains are observed. This yields a one-step estimator that achieves the semiparametric efficiency bound, guarantees strict variance reduction over naive sample averaging, and admits asymptotic normality for principled uncertainty quantification. Across simulations, our one-step estimator substantially improves ranking accuracy, with gains increasing as model output noise grows. Experiments on GPQA Diamond, AIME 2025, and GSM8K further demonstrate more precise performance estimation and more reliable model rankings, especially in small-sample regimes where conventional evaluation is pretty unstable.

---

### IVC-Prune: Revealing the Implicit Visual Coordinates in LVLMs for Vision Token Pruning

Authors: Zhichao Sun, Yidong Ma, Gang Liu, Yibo Chen, Xu Tang, Yao Hu, Yongchao Xu
Published: 2026-02-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.03060v1

Large Vision-Language Models (LVLMs) achieve impressive performance across multiple tasks. A significant challenge, however, is their prohibitive inference cost when processing high-resolution visual inputs. While visual token pruning has emerged as a promising solution, existing methods that primarily focus on semantic relevance often discard tokens that are crucial for spatial reasoning. We address this gap through a novel insight into \emph{how LVLMs process spatial reasoning}. Specifically, we reveal that LVLMs implicitly establish visual coordinate systems through Rotary Position Embeddings (RoPE), where specific token positions serve as \textbf{implicit visual coordinates} (IVC tokens) that are essential for spatial reasoning. Based on this insight, we propose \textbf{IVC-Prune}, a training-free, prompt-aware pruning strategy that retains both IVC tokens and semantically relevant foreground tokens. IVC tokens are identified by theoretically analyzing the mathematical properties of RoPE, targeting positions at which its rotation matrices approximate identity matrix or the $90^\circ$ rotation matrix. Foreground tokens are identified through a robust two-stage process: semantic seed discovery followed by contextual refinement via value-vector similarity. Extensive evaluations across four representative LVLMs and twenty diverse benchmarks show that IVC-Prune reduces visual tokens by approximately 50\% while maintaining $\geq$ 99\% of the original performance and even achieving improvements on several benchmarks. Source codes are available at https://github.com/FireRedTeam/IVC-Prune.

---

### From Speech-to-Spatial: Grounding Utterances on A Live Shared View with Augmented Reality

Authors: Yoonsang Kim, Divyansh Pradhan, Devshree Jadeja, Arie Kaufman
Published: 2026-02-03
Categories: cs.HC, cs.CL, cs.ET, cs.IR
arXiv: https://arxiv.org/abs/2602.03059v2

We introduce Speech-to-Spatial, a referent disambiguation framework that converts verbal remote-assistance instructions into spatially grounded AR guidance. Unlike prior systems that rely on additional cues (e.g., gesture, gaze) or manual expert annotations, Speech-to-Spatial infers the intended target solely from spoken references (speech input). Motivated by our formative study of speech referencing patterns, we characterize recurring ways people specify targets (Direct Attribute, Relational, Remembrance, and Chained) and ground them to our object-centric relational graph. Given an utterance, referent cues are parsed and rendered as persistent in-situ AR visual guidance, reducing iterative micro-guidance ("a bit more to the right", "now, stop.") during remote guidance. We demonstrate the use cases of our system with remote guided assistance and intent disambiguation scenarios. Our evaluation shows that Speechto-Spatial improves task efficiency, reduces cognitive load, and enhances usability compared to a conventional voice-only baseline, transforming disembodied verbal instruction into visually explainable, actionable guidance on a live shared view.

---

### Stationarity and Spectral Characterization of Random Signals on Simplicial Complexes

Authors: Madeline Navarro, Andrei Buciulea, Santiago Segarra, Antonio Marques
Published: 2026-02-03
Categories: eess.SP, stat.ML
arXiv: https://arxiv.org/abs/2602.03055v1

It is increasingly common for data to possess intricate structure, necessitating new models and analytical tools. Graphs, a prominent type of structure, can encode the relationships between any two entities (nodes). However, graphs neither allow connections that are not dyadic nor permit relationships between sets of nodes. We thus turn to simplicial complexes for connecting more than two nodes as well as modeling relationships between simplices, such as edges and triangles. Our data then consist of signals lying on topological spaces, represented by simplicial complexes. Much recent work explores these topological signals, albeit primarily through deterministic formulations. We propose a probabilistic framework for random signals defined on simplicial complexes. Specifically, we generalize the classical notion of stationarity. By spectral dualities of Hodge and Dirac theory, we define stationary topological signals as the outputs of topological filters given white noise. This definition naturally extends desirable properties of stationarity that hold for both time-series and graph signals. Crucially, we properly define topological power spectral density (PSD) through a clear spectral characterization. We then discuss the advantages of topological stationarity due to spectral properties via the PSD. In addition, we empirically demonstrate the practicality of these benefits through multiple synthetic and real-world simulations.

---

### Towards Considerate Embodied AI: Co-Designing Situated Multi-Site Healthcare Robots from Abstract Concepts to High-Fidelity Prototypes

Authors: Yuanchen Bai, Ruixiang Han, Niti Parikh, Wendy Ju, Angelique Taylor
Published: 2026-02-03
Categories: cs.HC, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2602.03054v1

Co-design is essential for grounding embodied artificial intelligence (AI) systems in real-world contexts, especially high-stakes domains such as healthcare. While prior work has explored multidisciplinary collaboration, iterative prototyping, and support for non-technical participants, few have interwoven these into a sustained co-design process. Such efforts often target one context and low-fidelity stages, limiting the generalizability of findings and obscuring how participants' ideas evolve. To address these limitations, we conducted a 14-week workshop with a multidisciplinary team of 22 participants, centered around how embodied AI can reduce non-value-added task burdens in three healthcare settings: emergency departments, long-term rehabilitation facilities, and sleep disorder clinics. We found that the iterative progression from abstract brainstorming to high-fidelity prototypes, supported by educational scaffolds, enabled participants to understand real-world trade-offs and generate more deployable solutions. We propose eight guidelines for co-designing more considerate embodied AI: attuned to context, responsive to social dynamics, mindful of expectations, and grounded in deployment. Project Page: https://byc-sophie.github.io/Towards-Considerate-Embodied-AI/

---

### MAS-ProVe: Understanding the Process Verification of Multi-Agent Systems

Authors: Vishal Venkataramani, Haizhou Shi, Zixuan Ke, Austin Xu, Xiaoxiao He, Yingbo Zhou, Semih Yavuz, Hao Wang, Shafiq Joty
Published: 2026-02-03
Categories: cs.AI, cs.CL, cs.MA
arXiv: https://arxiv.org/abs/2602.03053v2

Multi-Agent Systems (MAS) built on Large Language Models (LLMs) often exhibit high variance in their reasoning trajectories. Process verification, which evaluates intermediate steps in trajectories, has shown promise in general reasoning settings, and has been suggested as a potential tool for guiding coordination of MAS; however, its actual effectiveness in MAS remains unclear. To fill this gap, we present MAS-ProVe, a systematic empirical study of process verification for multi-agent systems (MAS). Our study spans three verification paradigms (LLM-as-a-Judge, reward models, and process reward models), evaluated across two levels of verification granularity (agent-level and iteration-level). We further examine five representative verifiers and four context management strategies, and conduct experiments over six diverse MAS frameworks on multiple reasoning benchmarks. We find that process-level verification does not consistently improve performance and frequently exhibits high variance, highlighting the difficulty of reliably evaluating partial multi-agent trajectories. Among the methods studied, LLM-as-a-Judge generally outperforms reward-based approaches, with trained judges surpassing general-purpose LLMs. We further observe a small performance gap between LLMs acting as judges and as single agents, and identify a context-length-performance trade-off in verification. Overall, our results suggest that effective and robust process verification for MAS remains an open challenge, requiring further advances beyond current paradigms. Code is available at https://github.com/Wang-ML-Lab/MAS-ProVe.

---

### MAS-ProVe: Understanding the Process Verification of Multi-Agent Systems

Authors: Vishal Venkataramani, Haizhou Shi, Zixuan Ke, Austin Xu, Xiaoxiao He, Yingbo Zhou, Semih Yavuz, Hao Wang, Shafiq Joty
Published: 2026-02-03
Categories: cs.AI, cs.CL, cs.MA
arXiv: https://arxiv.org/abs/2602.03053v1

Multi-Agent Systems (MAS) built on Large Language Models (LLMs) often exhibit high variance in their reasoning trajectories. Process verification, which evaluates intermediate steps in trajectories, has shown promise in general reasoning settings, and has been suggested as a potential tool for guiding coordination of MAS; however, its actual effectiveness in MAS remains unclear. To fill this gap, we present MAS-ProVe, a systematic empirical study of process verification for multi-agent systems (MAS). Our study spans three verification paradigms (LLM-as-a-Judge, reward models, and process reward models), evaluated across two levels of verification granularity (agent-level and iteration-level). We further examine five representative verifiers and four context management strategies, and conduct experiments over six diverse MAS frameworks on multiple reasoning benchmarks. We find that process-level verification does not consistently improve performance and frequently exhibits high variance, highlighting the difficulty of reliably evaluating partial multi-agent trajectories. Among the methods studied, LLM-as-a-Judge generally outperforms reward-based approaches, with trained judges surpassing general-purpose LLMs. We further observe a small performance gap between LLMs acting as judges and as single agents, and identify a context-length-performance trade-off in verification. Overall, our results suggest that effective and robust process verification for MAS remains an open challenge, requiring further advances beyond current paradigms. Code is available at https://github.com/Wang-ML-Lab/MAS-ProVe.

---

### Fedcompass: Federated Clustered and Periodic Aggregation Framework for Hybrid Classical-Quantum Models

Authors: Yueheng Wang, Xing He, Zinuo Cai, Rui Zhang, Ruhui Ma, Yuan Liu, Rajkumar Buyya
Published: 2026-02-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.03052v1

Federated learning enables collaborative model training across decentralized clients under privacy constraints. Quantum computing offers potential for alleviating computational and communication burdens in federated learning, yet hybrid classical-quantum federated learning remains susceptible to performance degradation under non-IID data. To address this,we propose FEDCOMPASS, a layered aggregation framework for hybrid classical-quantum federated learning. FEDCOMPASS employs spectral clustering to group clients by class distribution similarity and performs cluster-wise aggregation for classical feature extractors. For quantum parameters, it uses circular mean aggregation combined with adaptive optimization to ensure stable global updates. Experiments on three benchmark datasets show that FEDCOMPASS improves test accuracy by up to 10.22% and enhances convergence stability under non-IID settings, outperforming six strong federated learning baselines.

---

### SAES-SVD: Self-Adaptive Suppression of Accumulated and Local Errors for SVD-based LLM Compression

Authors: Xing Hu, Dawei Yang, Yuan Cheng, Zhixuan Chen, Zukang Xu
Published: 2026-02-03
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.03051v1

The rapid growth in the parameter scale of large language models (LLMs) has created a high demand for efficient compression techniques. As a hardware-agnostic and highly compatible technique, low-rank compression has been widely adopted. However, existing methods typically compress each layer independently by minimizing per-layer reconstruction error, overlooking a critical limitation: the reconstruction error propagates and accumulates through the network, which leads to amplified global deviations from the full-precision baseline. To address this, we propose Self-Adaptive Error Suppression SVD (SAES-SVD), a LLMs compression framework that jointly optimizes intra-layer reconstruction and inter-layer error compensation. SAES-SVD is composed of two novel components: (1) Cumulative Error-Aware Layer Compression (CEALC), which formulates the compression objective as a combination of local reconstruction and weighted cumulative error compensation. Based on it, we derive a closed-form low-rank solution relied on second-order activation statistics, which explicitly aligns each layer's output with its full-precision counterpart to compensate for accumulated errors. (2) Adaptive Collaborative Error Suppression (ACES), which automatically adjusts the weighting coefficient to enhance the low-rank structure of the compression objective in CEALC. Specifically, the coefficient is optimized to maximize the ratio between the Frobenius norm of the compressed layer's output and that of the compression objective under a fixed rank, thus ensuring that the rank budget is utilized effectively. Extensive experiments across multiple LLM architectures and tasks show that, without fine-tuning or mixed-rank strategies, SAES-SVD consistently improves post-compression performance.

---

### Unified Inference Framework for Single and Multi-Player Performative Prediction: Method and Asymptotic Optimality

Authors: Zhixian Zhang, Xiaotian Hou, Linjun Zhang
Published: 2026-02-03
Categories: stat.ML, cs.LG, math.ST, stat.ME
arXiv: https://arxiv.org/abs/2602.03049v1

Performative prediction characterizes environments where predictive models alter the very data distributions they aim to forecast, triggering complex feedback loops. While prior research treats single-agent and multi-agent performativity as distinct phenomena, this paper introduces a unified statistical inference framework that bridges these contexts, treating the former as a special case of the latter. Our contribution is two-fold. First, we put forward the Repeated Risk Minimization (RRM) procedure for estimating the performative stability, and establish a rigorous inferential theory for admitting its asymptotic normality and confirming its asymptotic efficiency. Second, for the performative optimality, we introduce a novel two-step plug-in estimator that integrates the idea of Recalibrated Prediction Powered Inference (RePPI) with Importance Sampling, and further provide formal derivations for the Central Limit Theorems of both the underlying distributional parameters and the plug-in results. The theoretical analysis demonstrates that our estimator achieves the semiparametric efficiency bound and maintains robustness under mild distributional misspecification. This work provides a principled toolkit for reliable estimation and decision-making in dynamic, performative environments.

---

### CoBA-RL: Capability-Oriented Budget Allocation for Reinforcement Learning in LLMs

Authors: Zhiyuan Yao, Yi-Kai Zhang, Yuxin Chen, Yueqing Sun, Zishan Xu, Yu Yang, Tianhao Hu, Qi Gu, Hui Su, Xunliang Cai
Published: 2026-02-03
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.03048v3

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a key approach for enhancing LLM reasoning. However, standard frameworks like Group Relative Policy Optimization (GRPO) typically employ a uniform rollout budget, leading to resource inefficiency. Moreover, existing adaptive methods often rely on instance-level metrics, such as task pass rates, failing to capture the model's dynamic learning state. To address these limitations, we propose CoBA-RL, a reinforcement learning algorithm designed to adaptively allocate rollout budgets based on the model's evolving capability. Specifically, CoBA-RL utilizes a Capability-Oriented Value function to map tasks to their potential training gains and employs a heap-based greedy strategy to efficiently self-calibrate the distribution of computational resources to samples with high training value. Extensive experiments demonstrate that our approach effectively orchestrates the trade-off between exploration and exploitation, delivering consistent generalization improvements across multiple challenging benchmarks. These findings underscore that quantifying sample training value and optimizing budget allocation are pivotal for advancing LLM post-training efficiency.

---

### Clarify Before You Draw: Proactive Agents for Robust Text-to-CAD Generation

Authors: Bo Yuan, Zelin Zhao, Petr Molodyk, Bin Hu, Yongxin Chen
Published: 2026-02-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.03045v2

Large language models have recently enabled text-to-CAD systems that synthesize parametric CAD programs (e.g., CadQuery) from natural-language prompts. In practice, however, geometric descriptions can be under-specified or internally inconsistent: critical dimensions may be missing and constraints may conflict. However, existing fine-tuned models tend to reactively follow the user instructions and hallucinate dimensions when the text is ambiguous. To address this, we propose a proactive agentic framework for text-to-CadQuery generation, named as ProCAD, that resolves specification issues before code synthesis. Our framework pairs a proactive clarifying agent, which audits the prompt and asks targeted clarification questions only when necessary to produce a self-consistent specification, with a CAD coding agent that translates the specification into an executable CadQuery program. We fine-tune the coding agent based on a curated high-quality text-to-CadQuery dataset and train the clarifying agent via agentic SFT on clarification trajectories. Experiments show that proactive clarification significantly improves robustness to ambiguous prompts while keeping interaction overhead low. ProCAD outperforms frontier closed-source models, including Claude Sonnet 4.5, reducing the mean Chamfer distance by 79.9% and lowering the invalidity ratio from 4.8% to 0.9%. Our code and datasets are made publicly available on https://github.com/BoYuanVisionary/Pro-CAD.

---

### SAFE-KD: Risk-Controlled Early-Exit Distillation for Vision Backbones

Authors: Salim Khazem
Published: 2026-02-03
Categories: cs.LG, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2602.03043v1

Early-exit networks reduce inference cost by allowing ``easy'' inputs to stop early, but practical deployment hinges on knowing \emph{when} early exit is safe. We introduce SAFE-KD, a universal multi-exit wrapper for modern vision backbones that couples hierarchical distillation with \emph{conformal risk control}. SAFE-KD attaches lightweight exit heads at intermediate depths, distills a strong teacher into all exits via Decoupled Knowledge Distillation (DKD), and enforces deep-to-shallow consistency between exits. At inference, we calibrate per-exit stopping thresholds on a held-out set using conformal risk control (CRC) to guarantee a user-specified \emph{selective} misclassification risk (among the samples that exit early) under exchangeability. Across multiple datasets and architectures, SAFE-KD yields improved accuracy compute trade-offs, stronger calibration, and robust performance under corruption while providing finite-sample risk guarantees.

---

### HP-GAN: Harnessing pretrained networks for GAN improvement with FakeTwins and discriminator consistency

Authors: Geonhui Son, Jeong Ryong Lee, Dosik Hwang
Published: 2026-02-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.03039v2

Generative Adversarial Networks (GANs) have made significant progress in enhancing the quality of image synthesis. Recent methods frequently leverage pretrained networks to calculate perceptual losses or utilize pretrained feature spaces. In this paper, we extend the capabilities of pretrained networks by incorporating innovative self-supervised learning techniques and enforcing consistency between discriminators during GAN training. Our proposed method, named HP-GAN, effectively exploits neural network priors through two primary strategies: FakeTwins and discriminator consistency. FakeTwins leverages pretrained networks as encoders to compute a self-supervised loss and applies this through the generated images to train the generator, thereby enabling the generation of more diverse and high quality images. Additionally, we introduce a consistency mechanism between discriminators that evaluate feature maps extracted from Convolutional Neural Network (CNN) and Vision Transformer (ViT) feature networks. Discriminator consistency promotes coherent learning among discriminators and enhances training robustness by aligning their assessments of image quality. Our extensive evaluation across seventeen datasets-including scenarios with large, small, and limited data, and covering a variety of image domains-demonstrates that HP-GAN consistently outperforms current state-of-the-art methods in terms of Fréchet Inception Distance (FID), achieving significant improvements in image diversity and quality. Code is available at: https://github.com/higun2/HP-GAN.

---

### Bongards at the Boundary of Perception and Reasoning: Programs or Language?

Authors: Cassidy Langenfeld, Claas Beger, Gloria Geng, Wasu Top Piriyakulkij, Keya Hu, Yewen Pu, Kevin Ellis
Published: 2026-02-03
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.03038v1

Vision-Language Models (VLMs) have made great strides in everyday visual tasks, such as captioning a natural image, or answering commonsense questions about such images. But humans possess the puzzling ability to deploy their visual reasoning abilities in radically new situations, a skill rigorously tested by the classic set of visual reasoning challenges known as the Bongard problems. We present a neurosymbolic approach to solving these problems: given a hypothesized solution rule for a Bongard problem, we leverage LLMs to generate parameterized programmatic representations for the rule and perform parameter fitting using Bayesian optimization. We evaluate our method on classifying Bongard problem images given the ground truth rule, as well as on solving the problems from scratch.

---

### LatentMem: Customizing Latent Memory for Multi-Agent Systems

Authors: Muxin Fu, Xiangyuan Xue, Yafu Li, Zefeng He, Siyuan Huang, Xiaoye Qu, Yu Cheng, Yang Yang
Published: 2026-02-03
Categories: cs.CL, cs.LG, cs.MA
arXiv: https://arxiv.org/abs/2602.03036v2

Large language model (LLM)-powered multi-agent systems (MAS) demonstrate remarkable collective intelligence, wherein multi-agent memory serves as a pivotal mechanism for continual adaptation. However, existing multi-agent memory designs remain constrained by two fundamental bottlenecks: (i) memory homogenization arising from the absence of role-aware customization, and (ii) information overload induced by excessively fine-grained memory entries. To address these limitations, we propose LatentMem, a learnable multi-agent memory framework designed to customize agent-specific memories in a token-efficient manner. Specifically, LatentMem comprises an experience bank that stores raw interaction trajectories in a lightweight form, and a memory composer that synthesizes compact latent memories conditioned on retrieved experience and agent-specific contexts. Further, we introduce Latent Memory Policy Optimization (LMPO), which propagates task-level optimization signals through latent memories to the composer, encouraging it to produce compact and high-utility representations. Extensive experiments across diverse benchmarks and mainstream MAS frameworks show that LatentMem achieves a performance gain of up to $19.36$% over vanilla settings and consistently outperforms existing memory architectures, without requiring any modifications to the underlying frameworks.

---

### Generalizable and Interpretable RF Fingerprinting with Shapelet-Enhanced Large Language Models

Authors: Tianya Zhao, Junqing Zhang, Haowen Xu, Xiaoyan Sun, Jun Dai, Xuyu Wang
Published: 2026-02-03
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2602.03035v1

Deep neural networks (DNNs) have achieved remarkable success in radio frequency (RF) fingerprinting for wireless device authentication. However, their practical deployment faces two major limitations: domain shift, where models trained in one environment struggle to generalize to others, and the black-box nature of DNNs, which limits interpretability. To address these issues, we propose a novel framework that integrates a group of variable-length two-dimensional (2D) shapelets with a pre-trained large language model (LLM) to achieve efficient, interpretable, and generalizable RF fingerprinting. The 2D shapelets explicitly capture diverse local temporal patterns across the in-phase and quadrature (I/Q) components, providing compact and interpretable representations. Complementarily, the pre-trained LLM captures more long-range dependencies and global contextual information, enabling strong generalization with minimal training overhead. Moreover, our framework also supports prototype generation for few-shot inference, enhancing cross-domain performance without additional retraining. To evaluate the effectiveness of our proposed method, we conduct extensive experiments on six datasets across various protocols and domains. The results show that our method achieves superior standard and few-shot performance across both source and unseen domains.

---

### KANFIS: A Neuro-Symbolic Framework for Interpretable and Uncertainty-Aware Learning

Authors: Binbin Yong, Haoran Pei, Jun Shen, Haoran Li, Qingguo Zhou, Zhao Su
Published: 2026-02-03
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.03034v3

Adaptive Neuro-Fuzzy Inference System (ANFIS) was designed to combine the learning capabilities of neural network with the reasoning transparency of fuzzy logic. However, conventional ANFIS architectures suffer from structural complexity, where the product-based inference mechanism causes an exponential explosion of rules in high-dimensional spaces. We herein propose the Kolmogorov-Arnold Neuro-Fuzzy Inference System (KANFIS), a compact neuro-symbolic architecture that unifies fuzzy reasoning with additive function decomposition. KANFIS employs an additive aggregation mechanism, under which both model parameters and rule complexity scale linearly with input dimensionality rather than exponentially. Furthermore, KANFIS is compatible with both Type-1 (T1) and Interval Type-2 (IT2) fuzzy logic systems, enabling explicit modeling of uncertainty and ambiguity in fuzzy representations. By using sparse masking mechanisms, KANFIS generates compact and structured rule sets, resulting in an intrinsically interpretable model with clear rule semantics and transparent inference processes. Empirical results demonstrate that KANFIS achieves competitive performance against representative neural and neuro-fuzzy baselines.

---

### KANFIS: A Neuro-Symbolic Framework for Interpretable and Uncertainty-Aware Learning

Authors: Binbin Yong, Haoran Pei, Jun Shen, Haoran Li, Qingguo Zhou, Zhao Su
Published: 2026-02-03
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.03034v2

Adaptive Neuro-Fuzzy Inference System (ANFIS) was designed to combine the learning capabilities of neural network with the reasoning transparency of fuzzy logic. However, conventional ANFIS architectures suffer from structural complexity, where the product-based inference mechanism causes an exponential explosion of rules in high-dimensional spaces. We herein propose the Kolmogorov-Arnold Neuro-Fuzzy Inference System (KANFIS), a compact neuro-symbolic architecture that unifies fuzzy reasoning with additive function decomposition. KANFIS employs an additive aggregation mechanism, under which both model parameters and rule complexity scale linearly with input dimensionality rather than exponentially. Furthermore, KANFIS is compatible with both Type-1 (T1) and Interval Type-2 (IT2) fuzzy logic systems, enabling explicit modeling of uncertainty and ambiguity in fuzzy representations. By using sparse masking mechanisms, KANFIS generates compact and structured rule sets, resulting in an intrinsically interpretable model with clear rule semantics and transparent inference processes. Empirical results demonstrate that KANFIS achieves competitive performance against representative neural and neuro-fuzzy baselines.

---

### Physics-inspired transformer quantum states via latent imaginary-time evolution

Authors: Kimihiro Yamazaki, Itsushi Sakata, Takuya Konishi, Yoshinobu Kawahara
Published: 2026-02-03
Categories: cond-mat.dis-nn, cs.LG, quant-ph
arXiv: https://arxiv.org/abs/2602.03031v1

Neural quantum states (NQS) are powerful ansätze in the variational Monte Carlo framework, yet their architectures are often treated as black boxes. We propose a physically transparent framework in which NQS are treated as neural approximations to latent imaginary-time evolution. This viewpoint suggests that standard Transformer-based NQS (TQS) architectures correspond to physically unmotivated effective Hamiltonians dependent on imaginary time in a latent space. Building on this interpretation, we introduce physics-inspired transformer quantum states (PITQS), which enforce a static effective Hamiltonian by sharing weights across layers and improve propagation accuracy via Trotter-Suzuki decompositions without increasing the number of variational parameters. For the frustrated $J_1$-$J_2$ Heisenberg model, our ansätze achieve accuracies comparable to or exceeding state-of-the-art TQS while using substantially fewer variational parameters. This study demonstrates that reinterpreting the deep network structure as a latent cooling process enables a more physically grounded, systematic, and compact design, thereby bridging the gap between black-box expressivity and physically transparent construction.

---

### MUSE: A Multi-agent Framework for Unconstrained Story Envisioning via Closed-Loop Cognitive Orchestration

Authors: Wenzhang Sun, Zhenyu Wang, Zhangchi Hu, Chunfeng Wang, Hao Li, Wei Chen
Published: 2026-02-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.03028v1

Generating long-form audio-visual stories from a short user prompt remains challenging due to an intent-execution gap, where high-level narrative intent must be preserved across coherent, shot-level multimodal generation over long horizons. Existing approaches typically rely on feed-forward pipelines or prompt-only refinement, which often leads to semantic drift and identity inconsistency as sequences grow longer. We address this challenge by formulating storytelling as a closed-loop constraint enforcement problem and propose MUSE, a multi-agent framework that coordinates generation through an iterative plan-execute-verify-revise loop. MUSE translates narrative intent into explicit, machine-executable controls over identity, spatial composition, and temporal continuity, and applies targeted multimodal feedback to correct violations during generation. To evaluate open-ended storytelling without ground-truth references, we introduce MUSEBench, a reference-free evaluation protocol validated by human judgments. Experiments demonstrate that MUSE substantially improves long-horizon narrative coherence, cross-modal identity consistency, and cinematic quality compared with representative baselines.

---

### Visual Reasoning over Time Series via Multi-Agent System

Authors: Weilin Ruan, Yuxuan Liang
Published: 2026-02-03
Categories: cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2602.03026v1

Time series analysis underpins many real-world applications, yet existing time-series-specific methods and pretrained large-model-based approaches remain limited in integrating intuitive visual reasoning and generalizing across tasks with adaptive tool usage. To address these limitations, we propose MAS4TS, a tool-driven multi-agent system for general time series tasks, built upon an Analyzer-Reasoner-Executor paradigm that integrates agent communication, visual reasoning, and latent reconstruction within a unified framework. MAS4TS first performs visual reasoning over time series plots with structured priors using a Vision-Language Model to extract temporal structures, and subsequently reconstructs predictive trajectories in latent space. Three specialized agents coordinate via shared memory and gated communication, while a router selects task-specific tool chains for execution. Extensive experiments on multiple benchmarks demonstrate that MAS4TS achieves state-of-the-art performance across a wide range of time series tasks, while exhibiting strong generalization and efficient inference.

---

### RC-GRPO: Reward-Conditioned Group Relative Policy Optimization for Multi-Turn Tool Calling Agents

Authors: Haitian Zhong, Jixiu Zhai, Lei Song, Jiang Bian, Qiang Liu, Tieniu Tan
Published: 2026-02-03
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.03025v1

Multi-turn tool calling is challenging for Large Language Models (LLMs) because rewards are sparse and exploration is expensive. A common recipe, SFT followed by GRPO, can stall when within-group reward variation is low (e.g., more rollouts in a group receive the all 0 or all 1 reward), making the group-normalized advantage uninformative and yielding vanishing updates. To address this problem, we propose RC-GRPO (Reward-Conditioned Group Relative Policy Optimization), which treats exploration as a controllable steering problem via discrete reward tokens. We first fine-tune a Reward-Conditioned Trajectory Policy (RCTP) on mixed-quality trajectories with reward goal special tokens (e.g., <|high_reward|>, <|low_reward|>) injected into the prompts, enabling the model to learn how to generate distinct quality trajectories on demand. Then during RL, we sample diverse reward tokens within each GRPO group and condition rollouts on the sampled token to improve within-group diversity, improving advantage gains. On the Berkeley Function Calling Leaderboard v4 (BFCLv4) multi-turn benchmark, our method yields consistently improved performance than baselines, and the performance on Qwen-2.5-7B-Instruct even surpasses all closed-source API models.

---

### Consistency Deep Equilibrium Models

Authors: Junchao Lin, Zenan Ling, Jingwen Xu, Robert C. Qiu
Published: 2026-02-03
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.03024v2

Deep Equilibrium Models (DEQs) have emerged as a powerful paradigm in deep learning, offering the ability to model infinite-depth networks with constant memory usage. However, DEQs incur significant inference latency due to the iterative nature of fixed-point solvers. In this work, we introduce the Consistency Deep Equilibrium Model (C-DEQ), a novel framework that leverages consistency distillation to accelerate DEQ inference. We cast the DEQ iterative inference process as evolution along a fixed ODE trajectory toward the equilibrium. Along this trajectory, we train C-DEQs to consistently map intermediate states directly to the fixed point, enabling few-step inference while preserving the performance of the teacher DEQ. At the same time, it facilitates multi-step evaluation to flexibly trade computation for performance gains. Extensive experiments across various domain tasks demonstrate that C-DEQs achieve consistent 2-20$\times$ accuracy improvements over implicit DEQs under the same few-step inference budget. Our code is available at https://github.com/landrarwolf/CDEQ.

---

### Rethinking Music Captioning with Music Metadata LLMs

Authors: Irmak Bukey, Zhepei Wang, Chris Donahue, Nicholas J. Bryan
Published: 2026-02-03
Categories: cs.SD, cs.LG
arXiv: https://arxiv.org/abs/2602.03023v1

Music captioning, or the task of generating a natural language description of music, is useful for both music understanding and controllable music generation. Training captioning models, however, typically requires high-quality music caption data which is scarce compared to metadata (e.g., genre, mood, etc.). As a result, it is common to use large language models (LLMs) to synthesize captions from metadata to generate training data for captioning models, though this process imposes a fixed stylization and entangles factual information with natural language style. As a more direct approach, we propose metadata-based captioning. We train a metadata prediction model to infer detailed music metadata from audio and then convert it into expressive captions via pre-trained LLMs at inference time. Compared to a strong end-to-end baseline trained on LLM-generated captions derived from metadata, our method: (1) achieves comparable performance in less training time over end-to-end captioners, (2) offers flexibility to easily change stylization post-training, enabling output captions to be tailored to specific stylistic and quality requirements, and (3) can be prompted with audio and partial metadata to enable powerful metadata imputation or in-filling--a common task for organizing music data.

---

### STAR: Similarity-guided Teacher-Assisted Refinement for Super-Tiny Function Calling Models

Authors: Jiliang Ni, Jiachen Pu, Zhongyi Yang, Jingfeng Luo, Conggang Hu
Published: 2026-02-03
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.03022v2

The proliferation of Large Language Models (LLMs) in function calling is pivotal for creating advanced AI agents, yet their large scale hinders widespread adoption, necessitating transferring their capabilities into smaller ones. However, existing paradigms are often plagued by overfitting, training instability, ineffective binary rewards for multi-solution tasks, and the difficulty of synergizing techniques. We introduce STAR: Similarity-guided Teacher-Assisted Refinement, a novel holistic framework that effectively transfers LLMs' capabilities to super-tiny models. STAR consists of two core technical innovations: (1) Constrained Knowledge Distillation (CKD), a training objective that augments top-k forward KL divergence to suppress confidently incorrect predictions, ensuring training stability while preserving exploration capacity for downstream RL. STAR holistically synergizes these strategies within a cohesive training curriculum, enabling super-tiny models to achieve exceptional performance on complex function calling tasks; (2) Similarity-guided RL (Sim-RL), a RL mechanism that introduces a fine-grained, similarity-based reward. This provides a robust, continuous, and rich signal for better policy optimization by evaluating the similarity between generated outputs and the ground truth. Extensive experiments on challenging and renowned benchmarks demonstrate the effectiveness of our method. Our STAR models establish SOTA in their size classes, significantly outperforming baselines. Remarkably, our 0.6B STAR model achieves the best performance among all open models under 1B, surpassing even several well-known open models at a larger scale. STAR demonstrates a training framework that distills capabilities of LLMs into super-tiny models, paving the way for powerful, accessible, and efficient AI agents.

---

### FedKRSO: Communication and Memory Efficient Federated Fine-Tuning of Large Language Models

Authors: Guohao Yang, Tongle Wu, Yuanxiong Guo, Ying Sun, Yanmin Gong
Published: 2026-02-03
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.03019v1

Fine-tuning is essential to adapt general-purpose large language models (LLMs) to domain-specific tasks. As a privacy-preserving framework to leverage decentralized data for collaborative model training, Federated Learning (FL) is gaining popularity in LLM fine-tuning, but remains challenging due to the high cost of transmitting full model parameters and computing full gradients on resource-constrained clients. While Parameter-Efficient Fine-Tuning (PEFT) methods are widely used in FL to reduce communication and memory costs, they often sacrifice model performance compared to FFT. This paper proposes FedKRSO (Federated $K$-Seed Random Subspace Optimization), a novel method that enables communication and memory efficient FFT of LLMs in federated settings. In FedKRSO, clients update the model within a shared set of random low-dimension subspaces generated by the server to save memory usage. Furthermore, instead of transmitting full model parameters in each FL round, clients send only the model update accumulators along the subspaces to the server, enabling efficient global model aggregation and dissemination. By using these strategies, FedKRSO can substantially reduce communication and memory overhead while overcoming the performance limitations of PEFT, closely approximating the performance of federated FFT. The convergence properties of FedKRSO are analyzed rigorously under general FL settings. Extensive experiments on the GLUE benchmark across diverse FL scenarios demonstrate that FedKRSO achieves both superior performance and low communication and memory overhead, paving the way towards on federated LLM fine-tuning at the resource-constrained edge.

---

### From Zero to Hero: Advancing Zero-Shot Foundation Models for Tabular Outlier Detection

Authors: Xueying Ding, Haomin Wen, Simon Klüttermann, Leman Akoglu
Published: 2026-02-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.03018v2

Outlier detection (OD) is widely used in practice; but its effective deployment on new tasks is hindered by lack of labeled outliers, which makes algorithm and hyperparameter selection notoriously hard. Foundation models (FMs) have transformed ML, and OD is no exception: Shen et. al. (2025) introduced FoMo-0D, the first FM for OD, achieving remarkable performance against numerous baselines. This work introduces OUTFORMER, which advances FoMo-0D with (1) a mixture of synthetic priors and (2) self-evolving curriculum training. OUTFORMER is pretrained solely on synthetic labeled datasets and infers test labels of a new task by using its training data as in-context input. Inference is fast and zero-shot, requiring merely forward pass and no labeled outliers. Thanks to in-context learning, it requires zero additional work-no OD model training or bespoke model selection-enabling truly plug-and-play deployment. OUTFORMER achieves state-of-the-art performance on the prominent AdBench, as well as two new large-scale OD benchmarks that we introduce, comprising over 1,500 datasets, while maintaining speedy inference.

---

### A Vision-Based Analysis of Congestion Pricing in New York City

Authors: Mehmet Kerem Turkcan, Jhonatan Tavori, Javad Ghaderi, Gil Zussman, Zoran Kostic, Andrew Smyth
Published: 2026-02-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.03015v1

We examine the impact of New York City's congestion pricing program through automated analysis of traffic camera data. Our computer vision pipeline processes footage from over 900 cameras distributed throughout Manhattan and New York, comparing traffic patterns from November 2024 through the program's implementation in January 2025 until January 2026. We establish baseline traffic patterns and identify systematic changes in vehicle density across the monitored region.

---