# Research Papers — 2026-02 · bundle page 202 of 210

> Full-text markdown of papers #10051–10100 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/202
[← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/201.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-02/page/203.md)

### Restoring Exploration after Post-Training: Latent Exploration Decoding for Large Reasoning Models

Authors: Wenhui Tan, Fiorenzo Parascandolo, Enver Sangineto, Jianzhong Ju, Zhenbo Luo, Qian Cao, Rita Cucchiara, Ruihua Song, Jian Luan
Published: 2026-02-02
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2602.01698v3

Large Reasoning Models (LRMs) have recently achieved strong mathematical and code reasoning performance through Reinforcement Learning (RL) post-training. However, we show that modern reasoning post-training induces an unintended exploration collapse: temperature-based sampling no longer increases pass@$n$ accuracy. Empirically, the final-layer posterior of post-trained LRMs exhibit sharply reduced entropy, while the entropy of intermediate layers remains relatively high. Motivated by this entropy asymmetry, we propose Latent Exploration Decoding (LED), a depth-conditioned decoding strategy. LED aggregates intermediate posteriors via cumulative sum and selects depth configurations with maximal entropy as exploration candidates. Without additional training or parameters, LED consistently improves pass@1 and pass@16 accuracy by 0.61 and 1.03 percentage points across multiple reasoning benchmarks and models. Furthermore, integrating LED into reinforcement learning, e.g., using GRPO as the rollout strategy, yields faster reward improvement and higher final performance, due to the efficient exploration capability of LED. Project page: https://github.com/AlbertTan404/LED.

---

### Cross-Modal Purification and Fusion for Small-Object RGB-D Transmission-Line Defect Detection

Authors: Jiaming Cui, Wenqiang Li, Shuai Zhou, Ruifeng Qin, Feng Shen
Published: 2026-02-02
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.01696v5

Transmission line defect detection remains challenging for automated UAV inspection due to the dominance of small-scale defects, complex backgrounds, and illumination variations. Existing RGB-based detectors, despite recent progress, struggle to distinguish geometrically subtle defects from visually similar background structures under limited chromatic contrast. This paper proposes CMAFNet, a Cross-Modal Alignment and Fusion Network that integrates RGB appearance and depth geometry through a principled purify-then-fuse paradigm. CMAFNet consists of a Semantic Recomposition Module that performs dictionary-based feature purification via a learned codebook to suppress modality-specific noise while preserving defect-discriminative information, and a Contextual Semantic Integration Framework that captures global spatial dependencies using partial-channel attention to enhance structural semantic reasoning. Position-wise normalization within the purification stage enforces explicit reconstruction-driven cross-modal alignment, ensuring statistical compatibility between heterogeneous features prior to fusion. Extensive experiments on the TLRGBD benchmark, where 94.5% of instances are small objects, demonstrate that CMAFNet achieves 32.2% mAP@50 and 12.5% APs, outperforming the strongest baseline by 9.8 and 4.0 percentage points, respectively. A lightweight variant reaches 24.8% mAP50 at 228 FPS with only 4.9M parameters, surpassing all YOLO-based detectors while matching transformer-based methods at substantially lower computational cost.

---

### Beyond Dense States: Sparse Transcoders as Causally Testable Operators for LLM Latent Reasoning

Authors: Yadong Wang, Haodong Chen, Yu Tian, Chuanxing Geng, Dong Liang, Xiang Chen
Published: 2026-02-02
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.01695v2

Latent reasoning reduces the token-generation cost of chain-of-thought reasoning by replacing explicit intermediate tokens with continuous latent transitions. However, existing latent reasoning methods usually rely on dense and entangled transitions, making their reasoning trajectories difficult to inspect or intervene on. We introduce LSTR (Latent Sparse Transcoder Reasoning), a framework that turns sparse transcoders from post-hoc diagnostic tools into in-loop, intervenable transition components for latent reasoning. At each latent step, a Latent Transition Transcoder (LTT) combines a linear skip path with a Top-k sparse innovation path, exposing a small set of active sparse features. Under matched compression settings, LSTR offers a mechanistically inspectable alternative to dense latent reasoning. On GSM8K-Aug, ablating only a few top-active sparse features reduces accuracy by up to 16.5%, whereas analogous interventions have much smaller effects in dense latent baselines. These results indicate that the active sparse features are causally involved in the latent transition process, rather than merely post-hoc descriptors. Additional experiments on mathematical benchmarks and StrategyQA suggest that sparse latent transitions can preserve the compression benefits of latent reasoning while making the resulting trajectories more inspectable and intervenable.

---

### Beyond Dense States: Elevating Sparse Transcoders to Active Operators for Latent Reasoning

Authors: Yadong Wang, Haodong Chen, Yu Tian, Chuanxing Geng, Dong Liang, Xiang Chen
Published: 2026-02-02
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.01695v1

Latent reasoning compresses the chain-of-thought (CoT) into continuous hidden states, yet existing methods rely on dense latent transitions that remain difficult to interpret and control. Meanwhile, sparse representation models uncover human-interpretable semantic features but remain largely confined to post-hoc analysis. We reconcile this tension by proposing LSTR (Latent Sparse Transcoder Reasoning), a latent reasoning framework that elevates functional sparse transcoders into active reasoning operators to perform multi-step computation through sparse semantic transitions. At its core, LSTR employs a Latent Transition Transcoder (LTT) with a residual skip architecture that decouples linear manifold transport from sparse semantic updates, enabling controllable semantic resolution via explicit sparsity constraints. Extensive experiments show that LSTR preserves reasoning accuracy and compression efficiency while substantially improving interpretability over dense latent baselines. Causal interventions and trajectory analyses further demonstrate that these sparse features act as both interpretable and causally effective operators in the reasoning process.

---

### What LLMs Think When You Don't Tell Them What to Think About?

Authors: Yongchan Kwon, James Zou
Published: 2026-02-02
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.01689v1

Characterizing the behavior of large language models (LLMs) across diverse settings is critical for reliable monitoring and AI safety. However, most existing analyses rely on topic- or task-specific prompts, which can substantially limit what can be observed. In this work, we study what LLMs generate from minimal, topic-neutral inputs and probe their near-unconstrained generative behavior. Despite the absence of explicit topics, model outputs cover a broad semantic space, and surprisingly, each model family exhibits strong and systematic topical preferences. GPT-OSS predominantly generates programming (27.1%) and mathematical content (24.6%), whereas Llama most frequently generates literary content (9.1%). DeepSeek often generates religious content, while Qwen frequently generates multiple-choice questions. Beyond topical preferences, we also observe differences in content specialization and depth: GPT-OSS often generates more technically advanced content (e.g., dynamic programming) compared with other models (e.g., basic Python). Furthermore, we find that the near-unconstrained generation often degenerates into repetitive phrases, revealing interesting behaviors unique to each model family. For instance, degenerate outputs from Llama include multiple URLs pointing to personal Facebook and Instagram accounts. We release the complete dataset of 256,000 samples from 16 LLMs, along with a reproducible codebase.

---

### Functional Subspace, where language models can use vector algebra to solve problems

Authors: Jung H. Lee, Sujith Vijayan
Published: 2026-02-02
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.01687v2

Large language models (LLMs) were invented for natural language tasks such as translation, but they have proved that they can perform highly complex functions across domains. Additionally, they have been thought to develop new skills without being trained on them. These learning capabilities lead to LLMs adoption in a wide range of domains. Thus, it is imperative that we understand their operating mechanisms and limitations for proper diagnostics and repair. The earlier studies proposed that high level concepts are encoded as linear directions in LLMs activation space and that the geometry of embeddings have semantic meanings. Inspired by these studies, we hypothesize that LLMs may use subspaces and vector algebra in subspaces to perform tasks. To address this hypothesis, we analyze LLMs' functional modules and residual streams collected from LLMs engaging in in-context learning (ICL), one of the emergent abilities. Our analyses suggest that 1) LLMs can create subspaces, where evidence can be accumulated and 2) ICL tasks can be solved via simple algebraic operations in subspaces.

---

### Semantic-aware Wasserstein Policy Regularization for Large Language Model Alignment

Authors: Byeonghu Na, Hyungho Na, Yeongmin Kim, Suhyeon Jo, HeeSun Bae, Mina Kang, Il-Chul Moon
Published: 2026-02-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.01685v1

Large language models (LLMs) are commonly aligned with human preferences using reinforcement learning from human feedback (RLHF). In this method, LLM policies are generally optimized through reward maximization with Kullback-Leibler (KL) divergence regularization of the reference policy. However, KL and its $f$-divergence variants only compare token probabilities at identical indices, failing to capture semantic similarity. We propose Wasserstein Policy Regularization (WPR), a semantic-aware regularization for the RLHF framework based on the entropy-regularized Wasserstein distance, which incorporates the geometry of the token space. The dual formulation of the distance expresses the regularization as penalty terms applied to the reward via optimal dual variables, which yield a tractable objective compatible with standard RL algorithms. Empirically, our method outperforms KL- and $f$-divergence-based baselines, demonstrating the benefits of semantic-aware policy distances for alignment. Our code is available at https://github.com/aailab-kaist/WPR.

---

### The Strategic Foresight of LLMs: Evidence from a Fully Prospective Venture Tournament

Authors: Felipe A. Csaszar, Aticus Peterson, Daniel Wilde
Published: 2026-02-02
Categories: econ.GN, cs.AI
arXiv: https://arxiv.org/abs/2602.01684v1

Can artificial intelligence outperform humans at strategic foresight -- the capacity to form accurate judgments about uncertain, high-stakes outcomes before they unfold? We address this question through a fully prospective prediction tournament using live Kickstarter crowdfunding projects. Thirty U.S.-based technology ventures, launched after the training cutoffs of all models studied, were evaluated while fundraising remained in progress and outcomes were unknown. A diverse suite of frontier and open-weight large language models (LLMs) completed 870 pairwise comparisons, producing complete rankings of predicted fundraising success. We benchmarked these forecasts against 346 experienced managers recruited via Prolific and three MBA-trained investors working under monitored conditions. The results are striking: human evaluators achieved rank correlations with actual outcomes between 0.04 and 0.45, while several frontier LLMs exceeded 0.60, with the best (Gemini 2.5 Pro) reaching 0.74 -- correctly ordering nearly four of every five venture pairs. These differences persist across multiple performance metrics and robustness checks. Neither wisdom-of-the-crowd ensembles nor human-AI hybrid teams outperformed the best standalone model.

---

### FreshMem: Brain-Inspired Frequency-Space Hybrid Memory for Streaming Video Understanding

Authors: Kangcong Li, Peng Ye, Lin Zhang, Chao Wang, Huafeng Qin, Tao Chen
Published: 2026-02-02
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.01683v1

Transitioning Multimodal Large Language Models (MLLMs) from offline to online streaming video understanding is essential for continuous perception. However, existing methods lack flexible adaptivity, leading to irreversible detail loss and context fragmentation. To resolve this, we propose FreshMem, a Frequency-Space Hybrid Memory network inspired by the brain's logarithmic perception and memory consolidation. FreshMem reconciles short-term fidelity with long-term coherence through two synergistic modules: Multi-scale Frequency Memory (MFM), which projects overflowing frames into representative frequency coefficients, complemented by residual details to reconstruct a global historical "gist"; and Space Thumbnail Memory (STM), which discretizes the continuous stream into episodic clusters by employing an adaptive compression strategy to distill them into high-density space thumbnails. Extensive experiments show that FreshMem significantly boosts the Qwen2-VL baseline, yielding gains of 5.20%, 4.52%, and 2.34% on StreamingBench, OV-Bench, and OVO-Bench, respectively. As a training-free solution, FreshMem outperforms several fully fine-tuned methods, offering a highly efficient paradigm for long-horizon streaming video understanding.

---

### Finite and Corruption-Robust Regret Bounds in Online Inverse Linear Optimization under M-Convex Action Sets

Authors: Taihei Oki, Shinsaku Sakaue
Published: 2026-02-02
Categories: cs.LG, cs.DS, stat.ML
arXiv: https://arxiv.org/abs/2602.01682v2

We study online inverse linear optimization, also known as contextual recommendation, where a learner sequentially infers an agent's hidden objective vector from observed optimal actions over feasible sets that change over time. The learner aims to recommend actions that perform well under the agent's true objective, and the performance is measured by the regret, defined as the cumulative gap between the agent's optimal values and those achieved by the learner's recommended actions. Prior work has established a regret bound of $O(d\log T)$, as well as a finite but exponentially large bound of $\exp(O(d\log d))$, where $d$ is the dimension of the optimization problem and $T$ is the time horizon, while a regret lower bound of $Ω(d)$ is known (Gollapudi et al. 2021; Sakaue et al. 2025). Whether a finite regret bound polynomial in $d$ is achievable or not has remained an open question. We partially resolve this by showing that when the feasible sets are M-convex -- a broad class that includes matroids -- a finite regret bound of $O(d\log d)$ is possible. We achieve this by combining a structural characterization of optimal solutions on M-convex sets with a geometric volume argument. Moreover, we extend our approach to adversarially corrupted feedback in up to $C$ rounds. We obtain a regret bound of $O((C+1)d\log d)$ without prior knowledge of $C$, by monitoring directed graphs induced by the observed feedback to detect corruptions adaptively.

---

### Hyperspectral Image Fusion with Spectral-Band and Fusion-Scale Agnosticism

Authors: Yu-Jie Liang, Zihan Cao, Liang-Jian Deng, Yang Yang, Malu Zhang
Published: 2026-02-02
Categories: eess.IV, cs.CV, cs.MM
arXiv: https://arxiv.org/abs/2602.01681v1

Current deep learning models for Multispectral and Hyperspectral Image Fusion (MS/HS fusion) are typically designed for fixed spectral bands and spatial scales, which limits their transferability across diverse sensors. To address this, we propose SSA, a universal framework for MS/HS fusion with spectral-band and fusion-scale agnosticism. Specifically, we introduce Matryoshka Kernel (MK), a novel operator that enables a single model to adapt to arbitrary numbers of spectral channels. Meanwhile, we build SSA upon an Implicit Neural Representation (INR) backbone that models the HS signal as a continuous function, enabling reconstruction at arbitrary spatial resolutions. Together, these two forms of agnosticism enable a single MS/HS fusion model that generalizes effectively to unseen sensors and spatial scales. Extensive experiments demonstrate that our single model achieves state-of-the-art performance while generalizing well to unseen sensors and scales, paving the way toward future HS foundation models.

---

### Towards Autonomous Instrument Tray Assembly for Sterile Processing Applications

Authors: Raghavasimhan Sankaranarayanan, Paul Stuart, Nicholas Ahn, Arno Sungarian, Yash Chitalia
Published: 2026-02-02
Categories: cs.RO, cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.01679v1

The Sterile Processing and Distribution (SPD) department is responsible for cleaning, disinfecting, inspecting, and assembling surgical instruments between surgeries. Manual inspection and preparation of instrument trays is a time-consuming, error-prone task, often prone to contamination and instrument breakage. In this work, we present a fully automated robotic system that sorts and structurally packs surgical instruments into sterile trays, focusing on automation of the SPD assembly stage. A custom dataset comprising 31 surgical instruments and 6,975 annotated images was collected to train a hybrid perception pipeline using YOLO12 for detection and a cascaded ResNet-based model for fine-grained classification. The system integrates a calibrated vision module, a 6-DOF Staubli TX2-60L robotic arm with a custom dual electromagnetic gripper, and a rule-based packing algorithm that reduces instrument collisions during transport. The packing framework uses 3D printed dividers and holders to physically isolate instruments, reducing collision and friction during transport. Experimental evaluations show high perception accuracy and statistically significant reduction in tool-to-tool collisions compared to human-assembled trays. This work serves as the scalable first step toward automating SPD workflows, improving safety, and consistency of surgical preparation while reducing SPD processing times.

---

### SMTrack: State-Aware Mamba for Efficient Temporal Modeling in Visual Tracking

Authors: Yinchao Ma, Dengqing Yang, Zhangyu He, Wenfei Yang, Tianzhu Zhang
Published: 2026-02-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.01677v1

Visual tracking aims to automatically estimate the state of a target object in a video sequence, which is challenging especially in dynamic scenarios. Thus, numerous methods are proposed to introduce temporal cues to enhance tracking robustness. However, conventional CNN and Transformer architectures exhibit inherent limitations in modeling long-range temporal dependencies in visual tracking, often necessitating either complex customized modules or substantial computational costs to integrate temporal cues. Inspired by the success of the state space model, we propose a novel temporal modeling paradigm for visual tracking, termed State-aware Mamba Tracker (SMTrack), providing a neat pipeline for training and tracking without needing customized modules or substantial computational costs to build long-range temporal dependencies. It enjoys several merits. First, we propose a novel selective state-aware space model with state-wise parameters to capture more diverse temporal cues for robust tracking. Second, SMTrack facilitates long-range temporal interactions with linear computational complexity during training. Third, SMTrack enables each frame to interact with previously tracked frames via hidden state propagation and updating, which releases computational costs of handling temporal cues during tracking. Extensive experimental results demonstrate that SMTrack achieves promising performance with low computational costs.

---

### TRIP-Bench: A Benchmark for Long-Horizon Interactive Agents in Real-World Scenarios

Authors: Yuanzhe Shen, Zisu Huang, Zhengyuan Wang, Muzhao Tian, Zhengkang Guo, Chenyang Zhang, Shuaiyu Zhou, Zengjie Hu, Dailin Li, Jingwen Xu, Kaimin Wang, Wenhao Liu et al.
Published: 2026-02-02
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.01675v1

As LLM-based agents are deployed in increasingly complex real-world settings, existing benchmarks underrepresent key challenges such as enforcing global constraints, coordinating multi-tool reasoning, and adapting to evolving user behavior over long, multi-turn interactions. To bridge this gap, we introduce \textbf{TRIP-Bench}, a long-horizon benchmark grounded in realistic travel-planning scenarios. TRIP-Bench leverages real-world data, offers 18 curated tools and 40+ travel requirements, and supports automated evaluation. It includes splits of varying difficulty; the hard split emphasizes long and ambiguous interactions, style shifts, feasibility changes, and iterative version revision. Dialogues span up to 15 user turns, can involve 150+ tool calls, and may exceed 200k tokens of context. Experiments show that even advanced models achieve at most 50\% success on the easy split, with performance dropping below 10\% on hard subsets. We further propose \textbf{GTPO}, an online multi-turn reinforcement learning method with specialized reward normalization and reward differencing. Applied to Qwen2.5-32B-Instruct, GTPO improves constraint satisfaction and interaction robustness, outperforming Gemini-3-Pro in our evaluation. We expect TRIP-Bench to advance practical long-horizon interactive agents, and GTPO to provide an effective online RL recipe for robust long-horizon training.

---

### VRGaussianAvatar: Integrating 3D Gaussian Avatars into VR

Authors: Hail Song, Boram Yoon, Seokhwan Yang, Seoyoung Kang, Hyunjeong Kim, Henning Metzmacher, Woontack Woo
Published: 2026-02-02
Categories: cs.CV, cs.GR
arXiv: https://arxiv.org/abs/2602.01674v2

We present VRGaussianAvatar, an integrated system that enables real-time full-body 3D Gaussian Splatting (3DGS) avatars in virtual reality using only head-mounted display (HMD) tracking signals. The system adopts a parallel pipeline with a VR Frontend and a GA Backend. The VR Frontend uses inverse kinematics to estimate full-body pose and streams the resulting pose along with stereo camera parameters to the backend. The GA Backend stereoscopically renders a 3DGS avatar reconstructed from a single image. To improve stereo rendering efficiency, we introduce Binocular Batching, which jointly processes left and right eye views in a single batched pass to reduce redundant computation and support high-resolution VR displays. We evaluate VRGaussianAvatar with quantitative performance tests and a within-subject user study against image- and video-based mesh avatar baselines. Results show that VRGaussianAvatar sustains interactive VR performance and yields higher perceived appearance similarity, embodiment, and plausibility. Project page and source code are available at https://vrgaussianavatar.github.io.

---

### Real-Time Loop Closure Detection in Visual SLAM via NetVLAD and Faiss

Authors: Enguang Fan
Published: 2026-02-02
Categories: cs.CV, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2602.01673v1

Loop closure detection (LCD) is a core component of simultaneous localization and mapping (SLAM): it identifies revisited places and enables pose-graph constraints that correct accumulated drift. Classic bag-of-words approaches such as DBoW are efficient but often degrade under appearance change and perceptual aliasing. In parallel, deep learning-based visual place recognition (VPR) descriptors (e.g., NetVLAD and Transformer-based models) offer stronger robustness, but their computational cost is often viewed as a barrier to real-time SLAM. In this paper, we empirically evaluate NetVLAD as an LCD module and compare it against DBoW on the KITTI dataset. We introduce a Fine-Grained Top-K precision-recall curve that better reflects LCD settings where a query may have zero or multiple valid matches. With Faiss-accelerated nearestneighbor search, NetVLAD achieves real-time query speed while improving accuracy and robustness over DBoW, making it a practical drop-in alternative for LCD in SLAM.

---

### Adaptive Information Control for Search-Augmented LLM Reasoning

Authors: Siheng Xiong, Oguzhan Gungordu, James C. Kerce, Faramarz Fekri
Published: 2026-02-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.01672v2

Search-augmented reasoning agents interleave multi-step reasoning with external retrieval, but uncontrolled retrieval can introduce redundant evidence, saturate the context, and destabilize reinforcement learning (RL). Existing outcome-based RL methods provide only sparse terminal rewards, offering limited guidance for intermediate information-acquisition decisions. We propose DeepControl, an adaptive information-control framework based on information utility, a state-dependent estimate of the marginal value of retrieved evidence. The framework regulates information acquisition along two axes: extent, i.e., whether retrieval should continue, and resolution, i.e., how much retrieved detail should be exposed. It implements these controls through retrieval-continuation guidance, hierarchical granularity control, and an annealed control-forcing scheme. This enables the policy to internalize effective acquisition behavior during training and operate without external control at test time. Across seven benchmarks, DeepControl consistently outperforms strong RL and retrieval baselines without explicit information control; compared with Search-R1, it improves average performance by +9.4 and +8.6 points on Qwen2.5-7B and Qwen2.5-3B, respectively. Additional analyses show improved search effectiveness, training stability, and evidence utilization.

---

### AI-Assisted Adaptive Rendering for High-Frequency Security Telemetry in Web Interfaces

Authors: Mona Rajhans
Published: 2026-02-02
Categories: cs.HC, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2602.01671v1

Modern cybersecurity platforms must process and display high-frequency telemetry such as network logs, endpoint events, alerts, and policy changes in real time. Traditional rendering techniques based on static pagination or fixed polling intervals fail under volume conditions exceeding hundreds of thousands of events per second, leading to UI freezes, dropped frames, or stale data. This paper presents an AI-assisted adaptive rendering framework that dynamically regulates visual update frequency, prioritizes semantically relevant events, and selectively aggregates lower-priority data using behavior-driven heuristics and lightweight on-device machine learning models. Experimental validation demonstrates a 45-60 percent reduction in rendering overhead while maintaining analyst perception of real-time responsiveness.

---

### ASGMamba: Adaptive Spectral Gating Mamba for Multivariate Time Series Forecasting

Authors: Qianyang Li, Xingjun Zhang, Shaoxun Wang, Jia Wei, Yueqi Xing
Published: 2026-02-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.01668v1

Long-term multivariate time series forecasting (LTSF) plays a crucial role in various high-performance computing applications, including real-time energy grid management and large-scale traffic flow simulation. However, existing solutions face a dilemma: Transformer-based models suffer from quadratic complexity, limiting their scalability on long sequences, while linear State Space Models (SSMs) often struggle to distinguish valuable signals from high-frequency noise, leading to wasted state capacity. To bridge this gap, we propose ASGMamba, an efficient forecasting framework designed for resource-constrained supercomputing environments. ASGMamba integrates a lightweight Adaptive Spectral Gating (ASG) mechanism that dynamically filters noise based on local spectral energy, enabling the Mamba backbone to focus its state evolution on robust temporal dynamics. Furthermore, we introduce a hierarchical multi-scale architecture with variable-specific Node Embeddings to capture diverse physical characteristics. Extensive experiments on nine benchmarks demonstrate that ASGMamba achieves state-of-the-art accuracy. While keeping strictly $$\mathcal{O}(L)$$ complexity we significantly reduce the memory usage on long-horizon tasks, thus establishing ASGMamba as a scalable solution for high-throughput forecasting in resource limited environments.The code is available at https://github.com/hit636/ASGMamba

---

### Quantifying Epistemic Predictive Uncertainty in Conformal Prediction

Authors: Siu Lun Chau, Soroush H. Zargarbashi, Yusuf Sale, Michele Caprio
Published: 2026-02-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.01667v1

We study the problem of quantifying epistemic predictive uncertainty (EPU) -- that is, uncertainty faced at prediction time due to the existence of multiple plausible predictive models -- within the framework of conformal prediction (CP). To expose the implicit model multiplicity underlying CP, we build on recent results showing that, under a mild assumption, any full CP procedure induces a set of closed and convex predictive distributions, commonly referred to as a credal set. Importantly, the conformal prediction region (CPR) coincides exactly with the set of labels to which all distributions in the induced credal set assign probability at least $1-α$. As our first contribution, we prove that this characterisation also holds in split CP. Building on this connection, we then propose a computationally efficient and analytically tractable uncertainty measure, based on \emph{Maximum Mean Imprecision}, to quantify the EPU by measuring the degree of conflicting information within the induced credal set. Experiments on active learning and selective classification demonstrate that the quantified EPU provides substantially more informative and fine-grained uncertainty assessments than reliance on CPR size alone. More broadly, this work highlights the potential of CP serving as a principled basis for decision-making under epistemic uncertainty.

---

### Moonworks Lunara Aesthetic II: An Image Variation Dataset

Authors: Yan Wang, Partho Hassan, Samiha Sadeka, Nada Soliman, Sayeef Abdullah, Sabit Hassan
Published: 2026-02-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.01666v3

We introduce Lunara Aesthetic II, a publicly released, ethically sourced image dataset designed to support controlled evaluation and learning of contextual consistency in modern image generation and editing systems. The dataset comprises 2,854 anchor-linked variation pairs derived from original art and photographs created by Moonworks. Each variation pair applies contextual transformations, such as illumination, weather, viewpoint, scene composition, color tone, or mood; while preserving a stable underlying identity. Lunara Aesthetic II operationalizes identity-preserving contextual variation as a supervision signal while also retaining Lunara's signature high aesthetic scores. Results show high identity stability, strong target attribute realization, and a robust aesthetic profile that exceeds large-scale web datasets. Released under the Apache 2.0 license, Lunara Aesthetic II is intended for benchmarking, fine-tuning, and analysis of contextual generalization, identity preservation, and edit robustness in image generation and image-to-image systems with interpretable, relational supervision. The dataset is publicly available at: https://huggingface.co/datasets/moonworks/lunara-aesthetic-image-variations.

---

### TABX: A High-Throughput Sandbox Battle Simulator for Multi-Agent Reinforcement Learning

Authors: Hayeong Lee, JunHyeok Oh, Byung-Jun Lee
Published: 2026-02-02
Categories: cs.MA, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.01665v4

The design of environments plays a critical role in shaping the development and evaluation of cooperative multi-agent reinforcement learning (MARL) algorithms. While existing benchmarks highlight critical challenges, they often lack the modularity required to design custom evaluation scenarios. We introduce the Totally Accelerated Battle Simulator in JAX (TABX), a high-throughput sandbox designed for reconfigurable multi-agent tasks. TABX provides granular control over environmental parameters, permitting a systematic investigation into emergent agent behaviors and algorithmic trade-offs across a diverse spectrum of task complexities. Leveraging JAX for hardware-accelerated execution on GPUs, TABX enables massive parallelization and significantly reduces computational overhead. By providing a fast, extensible, and easily customized framework, TABX facilitates the study of MARL agents in complex structured domains and serves as a scalable foundation for future research. Our code is available at: https://github.com/ku-dmlab/TABX.

---

### FlowSteer: Towards Agents Designing Agentic Workflows via Reinforced Progressive Canvas Editing

Authors: Mingda Zhang, Wenjin Liu, Tiesunlong Shen, Qika Lin, Rui Mao, Erik Cambria, Xiaoying Tang, Haoran Luo
Published: 2026-02-02
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.01664v4

In recent years, agentic workflows have been widely applied to solve complex human tasks. However, existing workflow construction still faces key challenges, including human-dependent workflow construction, the lack of graph-level execution feedback, and the inability to repair errors in-loop during long-horizon construction. To address these challenges, we propose FlowSteer, a new paradigm of Agent Designing Agentic Workflows - a single agent itself end-to-end designs the workflow that a downstream executor runs. To support this paradigm, we introduce the Workflow Canvas, a novel executable graph-state environment that returns syntax-checked execution feedback for every atomic edit. Built on the canvas, we further propose Reinforced Progressive Canvas Editing, in which a lightweight policy agent issues one atomic edit per turn conditioned on real canvas feedback, and is trained end-to-end via reinforcement learning. Moreover, FlowSteer provides a plug-and-play framework that supports diverse operator libraries and interchangeable LLM backends. Experimental results on twelve datasets show that FlowSteer significantly outperforms baselines across various tasks. Our code is available at https://anonymous.4open.science/r/FlowSteer-9B2E.

---

### From Frames to Sequences: Temporally Consistent Human-Centric Dense Prediction

Authors: Xingyu Miao, Junting Dong, Qin Zhao, Yuhang Yang, Junhao Chen, Yang Long
Published: 2026-02-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.01661v2

In this work, we focus on the challenge of temporally consistent human-centric dense prediction across video sequences. Existing models achieve strong per-frame accuracy but often flicker under motion, occlusion, and lighting changes, and they rarely have paired human video supervision for multiple dense tasks. We address this gap with a scalable synthetic data pipeline that generates photorealistic human frames and motion-aligned sequences with pixel-accurate depth, normals, and masks. Unlike prior static data synthetic pipelines, our pipeline provides both frame-level labels for spatial learning and sequence-level supervision for temporal learning. Building on this, we train a unified ViT-based dense predictor that (i) injects an explicit human geometric prior via CSE embeddings and (ii) improves geometry-feature reliability with a lightweight channel reweighting module after feature fusion. Our two-stage training strategy, combining static pretraining with dynamic sequence supervision, enables the model first to acquire robust spatial representations and then refine temporal consistency across motion-aligned sequences. Extensive experiments show that we achieve state-of-the-art performance on THuman2.1 and Hi4D and generalize effectively to in-the-wild videos.

---

### CoDiQ: Test-Time Scaling for Controllable Difficult Question Generation

Authors: Zhongyuan Peng, Caijun Xu, Changyi Xiao, Shibo Hong, Eli Zhang, Stephen Huang, Yixin Cao
Published: 2026-02-02
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.01660v1

Large Reasoning Models (LRMs) benefit substantially from training on challenging competition-level questions. However, existing automated question synthesis methods lack precise difficulty control, incur high computational costs, and struggle to generate competition-level questions at scale. In this paper, we propose CoDiQ (Controllable Difficult Question Generation), a novel framework enabling fine-grained difficulty control via test-time scaling while ensuring question solvability. Specifically, first, we identify a test-time scaling tendency (extended reasoning token budget boosts difficulty but reduces solvability) and the intrinsic properties defining the upper bound of a model's ability to generate valid, high-difficulty questions. Then, we develop CoDiQ-Generator from Qwen3-8B, which improves the upper bound of difficult question generation, making it particularly well-suited for challenging question construction. Building on the CoDiQ framework, we build CoDiQ-Corpus (44K competition-grade question sequences). Human evaluations show these questions are significantly more challenging than LiveCodeBench/AIME with over 82% solvability. Training LRMs on CoDiQ-Corpus substantially improves reasoning performance, verifying that scaling controlled-difficulty training questions enhances reasoning capabilities. We open-source CoDiQ-Corpus, CoDiQ-Generator, and implementations to support related research.

---

### Efficient Adversarial Attacks on High-dimensional Offline Bandits

Authors: Seyed Mohammad Hadi Hosseini, Amir Najafi, Mahdieh Soleymani Baghshah
Published: 2026-02-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.01658v2

Bandit algorithms have recently emerged as a powerful tool for evaluating machine learning models, including generative image models and large language models, by efficiently identifying top-performing candidates without exhaustive comparisons. These methods typically rely on a reward model, often distributed with public weights on platforms such as Hugging Face, to provide feedback to the bandit. While online evaluation is expensive and requires repeated trials, offline evaluation with logged data has become an attractive alternative. However, the adversarial robustness of offline bandit evaluation remains largely unexplored, particularly when an attacker perturbs the reward model (rather than the training data) prior to bandit training. In this work, we fill this gap by investigating, both theoretically and empirically, the vulnerability of offline bandit training to adversarial manipulations of the reward model. We introduce a novel threat model in which an attacker exploits offline data in high-dimensional settings to hijack the bandit's behavior. Starting with linear reward functions and extending to nonlinear models such as ReLU neural networks, we study attacks on two Hugging Face evaluators used for generative model assessment: one measuring aesthetic quality and the other assessing compositional alignment. Our results show that even small, imperceptible perturbations to the reward model's weights can drastically alter the bandit's behavior. From a theoretical perspective, we prove a striking high-dimensional effect: as input dimensionality increases, the perturbation norm required for a successful attack decreases, making modern applications such as image evaluation especially vulnerable. Extensive experiments confirm that naive random perturbations are ineffective, whereas carefully targeted perturbations achieve near-perfect attack success rates ...

---

### ProjDevBench: Benchmarking AI Coding Agents on End-to-End Project Development

Authors: Pengrui Lu, Shiqi Zhang, Yunzhong Hou, Lyumanshan Ye, Chaoyi Huang, Zixi Chen, Ji Zeng, Hantao Jiang, Pengfei Liu, Yiwei Wang, Ming-Hsuan Yang
Published: 2026-02-02
Categories: cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2602.01655v2

Recent coding agents can generate complete codebases from simple prompts, yet existing evaluations focus on issue-level bug fixing and lag behind end-to-end development. We introduce ProjDevBench, an end-to-end benchmark that provides project requirements to coding agents and evaluates the resulting repositories. Combining Online Judge (OJ) testing with LLM-assisted code review, the benchmark evaluates agents on (1) system architecture design, (2) functional correctness, and (3) iterative solution refinement. We curate 20 programming problems across 8 categories, covering both concept-oriented tasks and real-world application scenarios, and evaluate six coding agents built on different LLM backends. Our evaluation reports an overall acceptance rate of 27.38%: agents handle basic functionality and data structures but struggle with complex system design, time complexity optimization, and resource management. Our benchmark is available at https://github.com/zsworld6/projdevbench.

---

### Steering Vector Fields for Context-Aware Inference-Time Control in Large Language Models

Authors: Jiaqian Li, Yanshu Li, Kuan-Hao Huang
Published: 2026-02-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.01654v2

Steering vectors (SVs) offer a lightweight way to control large language models (LLMs) at inference time by shifting hidden activations, providing a practical middle ground between prompting and fine-tuning. Yet SVs can be unreliable in practice. Some concepts are unsteerable, and even when steering helps on average it can backfire for a non-trivial fraction of inputs. Reliability also degrades in long-form generation and multi-attribute steering. We take a geometric view of these failures. A static SV applies the same update vector everywhere in representation space, implicitly assuming that the concept-improving direction is constant across contexts. When the locally effective direction varies with the current activation, a single global vector can become misaligned, which yields weak or reversed effects. Guided by this perspective, we propose Steering Vector Fields (SVF), which learns a differentiable concept scoring function whose local gradient defines the steering direction at each activation, making interventions explicitly context-dependent. This formulation supports coordinated multi-layer interventions in a shared, aligned concept space, and enables efficient long-form and multi-attribute control within a unified framework. Across multiple LLMs and steering tasks, SVF delivers stronger and more reliable control, improving the practicality of inference-time steering.

---

### Steering Vector Fields for Context-Aware Inference-Time Control in Large Language Models

Authors: Jiaqian Li, Yanshu Li, Kuan-Hao Huang
Published: 2026-02-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.01654v1

Steering vectors (SVs) offer a lightweight way to control large language models (LLMs) at inference time by shifting hidden activations, providing a practical middle ground between prompting and fine-tuning. Yet SVs can be unreliable in practice. Some concepts are unsteerable, and even when steering helps on average it can backfire for a non-trivial fraction of inputs. Reliability also degrades in long-form generation and multi-attribute steering. We take a geometric view of these failures. A static SV applies the same update vector everywhere in representation space, implicitly assuming that the concept-improving direction is constant across contexts. When the locally effective direction varies with the current activation, a single global vector can become misaligned, which yields weak or reversed effects. Guided by this perspective, we propose Steering Vector Fields (SVF), which learns a differentiable concept scoring function whose local gradient defines the steering direction at each activation, making interventions explicitly context-dependent. This formulation supports coordinated multi-layer interventions in a shared, aligned concept space, and enables efficient long-form and multi-attribute control within a unified framework. Across multiple LLMs and steering tasks, SVF delivers stronger and more reliable control, improving the practicality of inference-time steering.

---

### On the Spatiotemporal Dynamics of Generalization in Neural Networks

Authors: Zichao Wei
Published: 2026-02-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.01651v2

Why do neural networks fail to generalize addition from 16-digit to 32-digit numbers, while a child who learns the rule can apply it to arbitrarily long sequences? We argue that this failure is not an engineering problem but a violation of physical postulates. Drawing inspiration from physics, we identify three constraints that any generalizing system must satisfy: (1) Locality -- information propagates at finite speed; (2) Symmetry -- the laws of computation are invariant across space and time; (3) Stability -- the system converges to discrete attractors that resist noise accumulation. From these postulates, we derive -- rather than design -- the Spatiotemporal Evolution with Attractor Dynamics (SEAD) architecture: a neural cellular automaton where local convolutional rules are iterated until convergence. Experiments on three tasks validate our theory: (1) Parity -- demonstrating perfect length generalization via light-cone propagation; (2) Addition -- achieving scale-invariant inference from L=16 to L=1 million with 100% accuracy, exhibiting input-adaptive computation; (3) Rule 110 -- learning a Turing-complete cellular automaton without trajectory divergence. Our results suggest that the gap between statistical learning and logical reasoning can be bridged -- not by scaling parameters, but by respecting the physics of computation.

---

### Contribution-aware Token Compression for Efficient Video Understanding via Reinforcement Learning

Authors: Yinchao Ma, Qiang Zhou, Zhibin Wang, Xianing Chen, Hanqing Yang, Jun Song, Bo Zheng
Published: 2026-02-02
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.01649v2

Video large language models have demonstrated remarkable capabilities in video understanding tasks. However, the redundancy of video tokens introduces significant computational overhead during inference, limiting their practical deployment. Many compression algorithms are proposed to prioritize retaining features with the highest attention scores to minimize perturbations in attention computations. However, the correlation between attention scores and their actual contribution to correct answers remains ambiguous. To address the above limitation, we propose a novel \textbf{C}ontribution-\textbf{a}ware token \textbf{Co}mpression algorithm for \textbf{VID}eo understanding (\textbf{CaCoVID}) that explicitly optimizes the token selection policy based on the contribution of tokens to correct predictions. First, we introduce a reinforcement learning-based framework that optimizes a policy network to select video token combinations with the greatest contribution to correct predictions. This paradigm shifts the focus from passive token preservation to active discovery of optimal compressed token combinations. Secondly, we propose a combinatorial policy optimization algorithm with online combination space sampling, which dramatically reduces the exploration space for video token combinations and accelerates the convergence speed of policy optimization. Extensive experiments on diverse video understanding benchmarks demonstrate the effectiveness of CaCoVID. Codes are available at https://github.com/LivingFutureLab/CaCoVID.

---

### From Perception to Action: Spatial AI Agents and World Models

Authors: Gloria Felicia, Nolan Bryant, Handi Putra, Ayaan Gazali, Eliel Lobo, Esteban Rojas
Published: 2026-02-02
Categories: cs.LG, cs.AI, cs.CV, cs.MA, cs.RO
arXiv: https://arxiv.org/abs/2602.01644v1

While large language models have become the prevailing approach for agentic reasoning and planning, their success in symbolic domains does not readily translate to the physical world. Spatial intelligence, the ability to perceive 3D structure, reason about object relationships, and act under physical constraints, is an orthogonal capability that proves important for embodied agents. Existing surveys address either agentic architectures or spatial domains in isolation. None provide a unified framework connecting these complementary capabilities. This paper bridges that gap. Through a thorough review of over 2,000 papers, citing 742 works from top-tier venues, we introduce a unified three-axis taxonomy connecting agentic capabilities with spatial tasks across scales. Crucially, we distinguish spatial grounding (metric understanding of geometry and physics) from symbolic grounding (associating images with text), arguing that perception alone does not confer agency. Our analysis reveals three key findings mapped to these axes: (1) hierarchical memory systems (Capability axis) are important for long-horizon spatial tasks. (2) GNN-LLM integration (Task axis) is a promising approach for structured spatial reasoning. (3) World models (Scale axis) are essential for safe deployment across micro-to-macro spatial scales. We conclude by identifying six grand challenges and outlining directions for future research, including the need for unified evaluation frameworks to standardize cross-domain assessment. This taxonomy provides a foundation for unifying fragmented research efforts and enabling the next generation of spatially-aware autonomous systems in robotics, autonomous vehicles, and geospatial intelligence.

---

### De Novo Molecular Generation from Mass Spectra via Many-Body Enhanced Diffusion

Authors: Xichen Sun, Wentao Wei, Jiahua Rao, Jiancong Xie, Yuedong Yang
Published: 2026-02-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.01643v1

Molecular structure generation from mass spectrometry is fundamental for understanding cellular metabolism and discovering novel compounds. Although tandem mass spectrometry (MS/MS) enables the high-throughput acquisition of fragment fingerprints, these spectra often reflect higher-order interactions involving the concerted cleavage of multiple atoms and bonds-crucial for resolving complex isomers and non-local fragmentation mechanisms. However, most existing methods adopt atom-centric and pairwise interaction modeling, overlooking higher-order edge interactions and lacking the capacity to systematically capture essential many-body characteristics for structure generation. To overcome these limitations, we present MBGen, a Many-Body enhanced diffusion framework for de novo molecular structure Generation from mass spectra. By integrating a many-body attention mechanism and higher-order edge modeling, MBGen comprehensively leverages the rich structural information encoded in MS/MS spectra, enabling accurate de novo generation and isomer differentiation for novel molecules. Experimental results on the NPLIB1 and MassSpecGym benchmarks demonstrate that MBGen achieves superior performance, with improvements of up to 230% over state-of-the-art methods, highlighting the scientific value and practical utility of many-body modeling for mass spectrometry-based molecular generation. Further analysis and ablation studies show that our approach effectively captures higher-order interactions and exhibits enhanced sensitivity to complex isomeric and non-local fragmentation information.

---

### The Effect of Mini-Batch Noise on the Implicit Bias of Adam

Authors: Matias D. Cattaneo, Boris Shigida
Published: 2026-02-02
Categories: cs.LG, cs.AI, math.OC, stat.CO, stat.ML
arXiv: https://arxiv.org/abs/2602.01642v2

With limited high-quality data and growing compute, multi-epoch training is gaining back its importance across sub-areas of deep learning. Adam(W), versions of which are go-to optimizers for many tasks such as next token prediction, has two momentum hyperparameters $(β_1, β_2)$ controlling memory and one very important hyperparameter, batch size, controlling (in particular) the amount mini-batch noise. We introduce a theoretical framework to understand how mini-batch noise influences the implicit bias of memory in Adam (depending on $β_1$, $β_2$) towards sharper or flatter regions of the loss landscape, which is commonly observed to correlate with the generalization gap in multi-epoch training. We find that in the case of large batch sizes, higher $β_2$ increases the magnitude of anti-regularization by memory (hurting generalization), but as the batch size becomes smaller, the dependence of (anti-)regulariation on $β_2$ is reversed. A similar monotonicity shift (in the opposite direction) happens in $β_1$. In particular, the commonly "default" pair $(β_1, β_2) = (0.9, 0.999)$ is a good choice if batches are small; for larger batches, in many settings moving $β_1$ closer to $β_2$ is much better in terms of validation accuracy in multi-epoch training. Moreover, our theoretical derivations connect the scale of the batch size at which the shift happens to the scale of the critical batch size. We illustrate this effect in experiments with small-scale data in the about-to-overfit regime.

---

### A2Eval: Agentic and Automated Evaluation for Embodied Brain

Authors: Shuai Zhang, Jiayu Hu, Zijie Chen, Zeyuan Ding, Yi Zhang, Yingji Zhang, Ziyi Zhou, Junwei Liao, Shengjie Zhou, Yong Dai, Zhenzhong Lan, Xiaozhu Ju
Published: 2026-02-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.01640v1

Current embodied VLM evaluation relies on static, expert-defined, manually annotated benchmarks that exhibit severe redundancy and coverage imbalance. This labor intensive paradigm drains computational and annotation resources, inflates costs, and distorts model rankings, ultimately stifling iterative development. To address this, we propose Agentic Automatic Evaluation (A2Eval), the first agentic framework that automates benchmark curation and evaluation through two collaborative agents. The Data Agent autonomously induces capability dimensions and assembles a balanced, compact evaluation suite, while the Eval Agent synthesizes and validates executable evaluation pipelines, enabling fully autonomous, high-fidelity assessment. Evaluated across 10 benchmarks and 13 models, A2Eval compresses evaluation suites by 85%, reduces overall computational costs by 77%, and delivers a 4.6x speedup while preserving evaluation quality. Crucially, A2Eval corrects systematic ranking biases, improves human alignment to Spearman's rho=0.85, and maintains high ranking fidelity (Kendall's tau=0.81), establishing a new standard for high-fidelity, low-cost embodied assessment. Our code and data will be public soon.

---

### ReCALL: Recalibrating Capability Degradation for MLLM-based Composed Image Retrieval

Authors: Tianyu Yang, Chenwei He, Xiangzhao Hao, Tianyue Wang, Jiarui Guo, Haiyun Guo, Leigang Qu, Jinqiao Wang, Tat-Seng Chua
Published: 2026-02-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.01639v2

Composed Image Retrieval (CIR) aims to retrieve target images based on a hybrid query comprising a reference image and a modification text. Early dual-tower Vision-Language Models (VLMs) struggle with cross-modality compositional reasoning required for this task. While adapting generative Multimodal Large Language Models (MLLMs) for retrieval offers a promising direction, we identify that this strategy overlooks a fundamental issue: compressing a generative MLLM into a single-embedding discriminative retriever triggers a paradigm conflict, which leads to Capability Degradation - the deterioration of native fine-grained reasoning after retrieval adaptation. To address this challenge, we propose ReCALL, a model-agnostic framework that follows a diagnose-generate-refine pipeline: First, we diagnose cognitive blind spots of the retriever via self-guided informative instance mining. Next, we generate corrective instructions and triplets by prompting the foundation MLLM and conduct quality control with VQA-based consistency filtering. Finally, we refine the retriever through continual training on these triplets with a grouped contrastive scheme, thereby internalizing fine-grained visual-semantic distinctions and realigning the discriminative embedding space of retriever with intrinsic compositional reasoning within the MLLM. Extensive experiments on CIRR and FashionIQ show that ReCALL consistently recalibrates degraded capabilities and achieves state-of-the-art performance. Code is available at https://github.com/RemRico/Recall.

---

### Chance-Constrained Inference for Hallucination Risk Control in Large Language Models

Authors: Sreenivasan Mohandas
Published: 2026-02-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.01637v1

Large language models generate outputs stochastically and may produce fluent but invalid responses, including factual hallucinations. Existing mitigation strategies reduce average error rates but do not provide explicit control over the \emph{frequency} of such failures under repeated use. We formulate inference as a deployment-time risk control problem and introduce \emph{chance-constrained inference}, which directly bounds the probability of hallucinations among accepted generations. Hallucinations are modeled as stochastic constraint violations, and we show that confidence-based selective prediction does not, in general, imply probabilistic risk guarantees. To enforce chance constraints efficiently, we propose a sequential, anytime-valid inference procedure that adaptively certifies feasibility or infeasibility using finite samples, avoiding conservative fixed-sample bounds. Experiments on questions inspired by NaturalQuestions and controlled multi-hop question answering demonstrate reliable risk control, early detection of intrinsically infeasible inputs, and safe composition under repeated use, while confidence-based baselines fail to provide consistent guarantees.

---

### COMET: Codebook-based Online-adaptive Multi-scale Embedding for Time-series Anomaly Detection

Authors: Jinwoo Park, Hyeongwon Kang, Seung Hun Han, Pilsung Kang
Published: 2026-02-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.01635v2

Time series anomaly detection is a critical task across various industrial domains. However, capturing temporal dependencies and multivariate correlations within patch-level representation learning remains underexplored, and reliance on single-scale patterns limits the detection of anomalies across different temporal ranges. Furthermore, focusing on normal data representations makes models vulnerable to distribution shifts at inference time. To address these limitations, we propose Codebook-based Online-adaptive Multi-scale Embedding for Time-series anomaly detection (COMET), which consists of three key components: (1) Multi-scale Patch Encoding captures temporal dependencies and inter-variable correlations across multiple patch scales. (2) Vector-Quantized Coreset learns representative normal patterns via codebook and detects anomalies with a dual-score combining quantization error and memory distance. (3) Online Codebook Adaptation generates pseudo-labels based on codebook entries and dynamically adapts the model at inference through contrastive learning. Experiments on five benchmark datasets demonstrate that COMET achieves the best performance in 36 out of 45 evaluation metrics, validating its effectiveness across diverse environments.

---

### HuPER: A Human-Inspired Framework for Phonetic Perception

Authors: Chenxu Guo, Jiachen Lian, Yisi Liu, Baihe Huang, Shriyaa Narayanan, Bixing Wu, Zoe Ezzes, Jet Vonk, Zachary Miller, Cheol Jun Cho, Maria Gorno-Tempini, Gopala Anumanchipalli
Published: 2026-02-02
Categories: eess.AS, cs.AI
arXiv: https://arxiv.org/abs/2602.01634v2

We propose HuPER, a human-inspired framework that models phonetic perception as adaptive inference over acoustic-phonetics evidence and linguistic knowledge. With only 100 hours of training data, HuPER achieves state-of-the-art phonetic error rates on five English benchmarks and strong zero-shot transfer to 95 unseen languages. HuPER is also the first framework to enable adaptive, multi-path phonetic perception under diverse acoustic conditions. All training data, models, and code are open-sourced. Code and demo avaliable at https://github.com/Berkeley-Speech-Group/HuPER.

---

### HuPER: A Human-Inspired Framework for Phonetic Perception

Authors: Chenxu Guo, Jiachen Lian, Yisi Liu, Baihe Huang, Shriyaa Narayanan, Cheol Jun Cho, Gopala Anumanchipalli
Published: 2026-02-02
Categories: eess.AS, cs.AI
arXiv: https://arxiv.org/abs/2602.01634v1

We propose HuPER, a human-inspired framework that models phonetic perception as adaptive inference over acoustic-phonetics evidence and linguistic knowledge. With only 100 hours of training data, HuPER achieves state-of-the-art phonetic error rates on five English benchmarks and strong zero-shot transfer to 95 unseen languages. HuPER is also the first framework to enable adaptive, multi-path phonetic perception under diverse acoustic conditions. All training data, models, and code are open-sourced. Code and demo avaliable at https://github.com/HuPER29/HuPER.

---

### Federated Vision Transformer with Adaptive Focal Loss for Medical Image Classification

Authors: Xinyuan Zhao, Yihang Wu, Ahmad Chaddad, Tareef Daqqaq, Reem Kateb
Published: 2026-02-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.01633v1

While deep learning models like Vision Transformer (ViT) have achieved significant advances, they typically require large datasets. With data privacy regulations, access to many original datasets is restricted, especially medical images. Federated learning (FL) addresses this challenge by enabling global model aggregation without data exchange. However, the heterogeneity of the data and the class imbalance that exist in local clients pose challenges for the generalization of the model. This study proposes a FL framework leveraging a dynamic adaptive focal loss (DAFL) and a client-aware aggregation strategy for local training. Specifically, we design a dynamic class imbalance coefficient that adjusts based on each client's sample distribution and class data distribution, ensuring minority classes receive sufficient attention and preventing sparse data from being ignored. To address client heterogeneity, a weighted aggregation strategy is adopted, which adapts to data size and characteristics to better capture inter-client variations. The classification results on three public datasets (ISIC, Ocular Disease and RSNA-ICH) show that the proposed framework outperforms DenseNet121, ResNet50, ViT-S/16, ViT-L/32, FedCLIP, Swin Transformer, CoAtNet, and MixNet in most cases, with accuracy improvements ranging from 0.98\% to 41.69\%. Ablation studies on the imbalanced ISIC dataset validate the effectiveness of the proposed loss function and aggregation strategy compared to traditional loss functions and other FL approaches. The codes can be found at: https://github.com/AIPMLab/ViT-FLDAF.

---

### Research on World Models Is Not Merely Injecting World Knowledge into Specific Tasks

Authors: Bohan Zeng, Kaixin Zhu, Daili Hua, Bozhou Li, Chengzhuo Tong, Yuran Wang, Xinyi Huang, Yifan Dai, Zixiang Zhang, Yifan Yang, Zhou Liu, Hao Liang et al.
Published: 2026-02-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.01630v1

World models have emerged as a critical frontier in AI research, aiming to enhance large models by infusing them with physical dynamics and world knowledge. The core objective is to enable agents to understand, predict, and interact with complex environments. However, current research landscape remains fragmented, with approaches predominantly focused on injecting world knowledge into isolated tasks, such as visual prediction, 3D estimation, or symbol grounding, rather than establishing a unified definition or framework. While these task-specific integrations yield performance gains, they often lack the systematic coherence required for holistic world understanding. In this paper, we analyze the limitations of such fragmented approaches and propose a unified design specification for world models. We suggest that a robust world model should not be a loose collection of capabilities but a normative framework that integrally incorporates interaction, perception, symbolic reasoning, and spatial representation. This work aims to provide a structured perspective to guide future research toward more general, robust, and principled models of the world.

---

### AdaptNC: Adaptive Nonconformity Scores for Conformal Prediction under Distribution Shift

Authors: Renukanandan Tumu, Aditya Singh, Rahul Mangharam
Published: 2026-02-02
Categories: cs.LG, cs.RO, eess.SY
arXiv: https://arxiv.org/abs/2602.01629v2

Rigorous uncertainty quantification is essential for the safe deployment of autonomous systems in unconstrained environments. Conformal Prediction (CP) provides a distribution-free framework for this task, yet its standard formulations rely on exchangeability assumptions that are violated by the distribution shifts inherent in real-world robotics. Existing online CP methods maintain target coverage by adaptively scaling the conformal threshold, but typically employ a static nonconformity score function. We show that this fixed geometry leads to highly conservative, volume-inefficient prediction regions when environments undergo structural shifts. To address this, we propose $\textbf{AdaptNC}$, a framework for the joint online adaptation of both the nonconformity score parameters and the conformal threshold. AdaptNC leverages an adaptive reweighting scheme to optimize score functions, and introduces a replay buffer mechanism to mitigate the coverage instability that occurs during score transitions. We evaluate AdaptNC on diverse robotic benchmarks involving multi-agent policy changes, environmental changes and sensor degradation. Our results demonstrate that AdaptNC significantly reduces prediction region volume compared to state-of-the-art threshold-only baselines while maintaining target coverage levels.

---

### Toward Enhancing Representation Learning in Federated Multi-Task Settings

Authors: Mehdi Setayesh, Mahdi Beitollahi, Yasser H. Khalil, Hongliang Li
Published: 2026-02-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.01626v1

Federated multi-task learning (FMTL) seeks to collaboratively train customized models for users with different tasks while preserving data privacy. Most existing approaches assume model congruity (i.e., the use of fully or partially homogeneous models) across users, which limits their applicability in realistic settings. To overcome this limitation, we aim to learn a shared representation space across tasks rather than shared model parameters. To this end, we propose Muscle loss, a novel contrastive learning objective that simultaneously aligns representations from all participating models. Unlike existing multi-view or multi-model contrastive methods, which typically align models pairwise, Muscle loss can effectively capture dependencies across tasks because its minimization is equivalent to the maximization of mutual information among all the models' representations. Building on this principle, we develop FedMuscle, a practical and communication-efficient FMTL algorithm that naturally handles both model and task heterogeneity. Experiments on diverse image and language tasks demonstrate that FedMuscle consistently outperforms state-of-the-art baselines, delivering substantial improvements and robust performance across heterogeneous settings.

---

### PISCES: Annotation-free Text-to-Video Post-Training via Optimal Transport-Aligned Rewards

Authors: Minh-Quan Le, Gaurav Mittal, Cheng Zhao, David Gu, Dimitris Samaras, Mei Chen
Published: 2026-02-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.01624v2

Text-to-video (T2V) generation aims to synthesize videos with high visual quality and temporal consistency that are semantically aligned with input text. Reward-based post-training has emerged as a promising direction to improve the quality and semantic alignment of generated videos. However, recent methods either rely on large-scale human preference annotations or operate on misaligned embeddings from pre-trained vision-language models, leading to limited scalability or suboptimal supervision. We present $\texttt{PISCES}$, an annotation-free post-training algorithm that addresses these limitations via a novel Dual Optimal Transport (OT)-aligned Rewards module. To align reward signals with human judgment, $\texttt{PISCES}$ uses OT to bridge text and video embeddings at both distributional and discrete token levels, enabling reward supervision to fulfill two objectives: (i) a Distributional OT-aligned Quality Reward that captures overall visual quality and temporal coherence; and (ii) a Discrete Token-level OT-aligned Semantic Reward that enforces semantic, spatio-temporal correspondence between text and video tokens. To our knowledge, $\texttt{PISCES}$ is the first to improve annotation-free reward supervision in generative post-training through the lens of OT. Experiments on both short- and long-video generation show that $\texttt{PISCES}$ outperforms both annotation-based and annotation-free methods on VBench across Quality and Semantic scores, with human preference studies further validating its effectiveness. We show that the Dual OT-aligned Rewards module is compatible with multiple optimization paradigms, including direct backpropagation and reinforcement learning fine-tuning. Project page: https://roar-ai.github.io/pisces

---

### Omni-Judge: Can Omni-LLMs Serve as Human-Aligned Judges for Text-Conditioned Audio-Video Generation?

Authors: Susan Liang, Chao Huang, Filippos Bellos, Yolo Yunlong Tang, Qianxiang Shen, Jing Bi, Luchuan Song, Zeliang Zhang, Jason Corso, Chenliang Xu
Published: 2026-02-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.01623v1

State-of-the-art text-to-video generation models such as Sora 2 and Veo 3 can now produce high-fidelity videos with synchronized audio directly from a textual prompt, marking a new milestone in multi-modal generation. However, evaluating such tri-modal outputs remains an unsolved challenge. Human evaluation is reliable but costly and difficult to scale, while traditional automatic metrics, such as FVD, CLAP, and ViCLIP, focus on isolated modality pairs, struggle with complex prompts, and provide limited interpretability. Omni-modal large language models (omni-LLMs) present a promising alternative: they naturally process audio, video, and text, support rich reasoning, and offer interpretable chain-of-thought feedback. Driven by this, we introduce Omni-Judge, a study assessing whether omni-LLMs can serve as human-aligned judges for text-conditioned audio-video generation. Across nine perceptual and alignment metrics, Omni-Judge achieves correlation comparable to traditional metrics and excels on semantically demanding tasks such as audio-text alignment, video-text alignment, and audio-video-text coherence. It underperforms on high-FPS perceptual metrics, including video quality and audio-video synchronization, due to limited temporal resolution. Omni-Judge provides interpretable explanations that expose semantic or physical inconsistencies, enabling practical downstream uses such as feedback-based refinement. Our findings highlight both the potential and current limitations of omni-LLMs as unified evaluators for multi-modal generation.

---

### CGF-Softmax: A Cumulant-Based Softmax Reformulation for Efficient Inference under Homomorphic Encryption

Authors: Hanjun Park, Byeongseo Min, Jiheon Woo, Min-Wook Jeong, Jongho Shin, Yongwoo Lee, Young-Sik Kim, Yongjune Kim
Published: 2026-02-02
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2602.01621v3

Homomorphic encryption (HE) is a prominent framework for privacy-preserving machine learning, enabling inference directly on encrypted data. However, evaluating softmax, a core component of transformer architectures, remains particularly challenging in HE due to its multivariate structure, the large dynamic range induced by exponential functions, and the costly division operation. In this paper, we propose CGF-softmax, which reformulates the softmax denominator through the cumulant generating function (CGF). By eliminating both homomorphic division and explicit maximum subtraction, this reformulation substantially reduces multiplicative depth while preserving key properties of softmax. Extensive experiments on Vision Transformers and large language models show that CGF-softmax provides an efficient and accurate approximation of softmax in encrypted inference. In particular, it achieves inference accuracy close to that of high-depth exact methods, while requiring substantially lower computational cost through reduced multiplicative depth.

---

### SUSD: Structured Unsupervised Skill Discovery through State Factorization

Authors: Seyed Mohammad Hadi Hosseini, Mahdieh Soleymani Baghshah
Published: 2026-02-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.01619v2

Unsupervised Skill Discovery (USD) aims to autonomously learn a diverse set of skills without relying on extrinsic rewards. One of the most common USD approaches is to maximize the Mutual Information (MI) between skill latent variables and states. However, MI-based methods tend to favor simple, static skills due to their invariance properties, limiting the discovery of dynamic, task-relevant behaviors. Distance-Maximizing Skill Discovery (DSD) promotes more dynamic skills by leveraging state-space distances, yet still fall short in encouraging comprehensive skill sets that engage all controllable factors or entities in the environment. In this work, we introduce SUSD, a novel framework that harnesses the compositional structure of environments by factorizing the state space into independent components (e.g., objects or controllable entities). SUSD allocates distinct skill variables to different factors, enabling more fine-grained control on the skill discovery process. A dynamic model also tracks learning across factors, adaptively steering the agent's focus toward underexplored factors. This structured approach not only promotes the discovery of richer and more diverse skills, but also yields a factorized skill representation that enables fine-grained and disentangled control over individual entities which facilitates efficient training of compositional downstream tasks via Hierarchical Reinforcement Learning (HRL). Our experimental results across three environments, with factors ranging from 1 to 10, demonstrate that our method can discover diverse and complex skills without supervision, significantly outperforming existing unsupervised skill discovery methods in factorized and complex environments. Code is publicly available at: https://github.com/hadi-hosseini/SUSD.

---

### SEA-Guard: Culturally Grounded Multilingual Safeguard for Southeast Asia

Authors: Panuthep Tasawong, Jian Gang Ngui, Alham Fikri Aji, Trevor Cohn, Peerat Limkonchotiwat
Published: 2026-02-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.01618v1

Culturally aware safeguards are crucial for AI alignment in real-world settings, where safety extends beyond common sense and encompasses diverse local values, norms, and region-specific regulations. However, building large-scale, culturally grounded datasets is challenging due to limited resources and a scarcity of native annotators. Consequently, many safeguard models rely on machine translation of English datasets, often missing regional and cultural nuances. We present a novel agentic data-generation framework to scalably create authentic, region-specific safety datasets for Southeast Asia (SEA). On this foundation, we introduce the SEA-Guard family, the first multilingual safeguard models grounded in SEA cultural contexts. Evaluated across multiple benchmarks and cultural variants, SEA-Guard consistently outperforms existing safeguards at detecting regionally sensitive or harmful content while maintaining strong general safety performance.

---

### AgroFlux: A Spatial-Temporal Benchmark for Carbon and Nitrogen Flux Prediction in Agricultural Ecosystems

Authors: Qi Cheng, Licheng Liu, Yao Zhang, Mu Hong, Yiqun Xie, Xiaowei Jia
Published: 2026-02-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.01614v1

Agroecosystem, which heavily influenced by human actions and accounts for a quarter of global greenhouse gas emissions (GHGs), plays a crucial role in mitigating global climate change and securing environmental sustainability. However, we can't manage what we can't measure. Accurately quantifying the pools and fluxes in the carbon, nutrient, and water nexus of the agroecosystem is therefore essential for understanding the underlying drivers of GHG and developing effective mitigation strategies. Conventional approaches like soil sampling, process-based models, and black-box machine learning models are facing challenges such as data sparsity, high spatiotemporal heterogeneity, and complex subsurface biogeochemical and physical processes. Developing new trustworthy approaches such as AI-empowered models, will require the AI-ready benchmark dataset and outlined protocols, which unfortunately do not exist. In this work, we introduce a first-of-its-kind spatial-temporal agroecosystem GHG benchmark dataset that integrates physics-based model simulations from Ecosys and DayCent with real-world observations from eddy covariance flux towers and controlled-environment facilities. We evaluate the performance of various sequential deep learning models on carbon and nitrogen flux prediction, including LSTM-based models, temporal CNN-based model, and Transformer-based models. Furthermore, we explored transfer learning to leverage simulated data to improve the generalization of deep learning models on real-world observations. Our benchmark dataset and evaluation framework contribute to the development of more accurate and scalable AI-driven agroecosystem models, advancing our understanding of ecosystem-climate interactions.

---