# Research Papers — 2026-01 · bundle page 17 of 189 > Full-text markdown of papers #801–850 of 9403 published in 2026-01, newest first. AI-readable mirrors of the full 9403-paper 2026-01 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-01/page/17 [← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/16.md) [Next bundle →](https://aipod.dev/papers/archive/2026-01/page/18.md) ### PhoStream: Benchmarking Real-World Streaming for Omnimodal Assistants in Mobile Scenarios Authors: Xudong Lu, Huankang Guan, Yang Bo, Jinpeng Chen, Xintong Guo, Shuhan Li, Fang Liu, Peiwen Sun, Xueying Li, Wei Zhang, Xue Yang, Rui Liu et al. Published: 2026-01-30 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2601.22575v1 Multimodal Large Language Models excel at offline audio-visual understanding, but their ability to serve as mobile assistants in continuous real-world streams remains underexplored. In daily phone use, mobile assistants must track streaming audio-visual inputs and respond at the right time, yet existing benchmarks are often restricted to multiple-choice questions or use shorter videos. In this paper, we introduce PhoStream, the first mobile-centric streaming benchmark that unifies on-screen and off-screen scenarios to evaluate video, audio, and temporal reasoning. PhoStream contains 5,572 open-ended QA pairs from 578 videos across 4 scenarios and 10 capabilities. We build it with an Automated Generative Pipeline backed by rigorous human verification, and evaluate models using a realistic Online Inference Pipeline and LLM-as-a-Judge evaluation for open-ended responses. Experiments reveal a temporal asymmetry in LLM-judged scores (0-100): models perform well on Instant and Backward tasks (Gemini 3 Pro exceeds 80), but drop sharply on Forward tasks (16.40), largely due to early responses before the required visual and audio cues appear. This highlights a fundamental limitation: current MLLMs struggle to decide when to speak, not just what to say. Code and datasets used in this work will be made publicly accessible at https://github.com/Lucky-Lance/PhoStream. --- ### Enhancing Video Representations with Spatiotemporal-Semantic Residual to Mitigate Hallucinations in Video Large Multimodal Models Authors: Yuansheng Gao, Jinman Zhao, Tong Zhang, Xingguo Xu, Wenbin Xing, Han Bao, Zonghui Wang, Wenzhi Chen Published: 2026-01-30 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.22574v2 Although Video Large Multimodal Models have achieved strong performance in video understanding, they still suffer from hallucination. Existing inference-time intervention methods usually modify videos under the contrastive decoding framework, but their heuristic designs bring limited improvements and increase inference latency. To address these issues, we propose ViSSRes, an inference-time intervention method that enhances video representations through a lightweight MLP-style network. Specifically, we use a contrastive random walk approach to characterize the spatiotemporal consistency of video representations, and introduce conditional mutual information to associate video representations with the model's semantic understanding. With the model backbone kept frozen, ViSSRes learns residuals for video representations and optimizes them from both spatiotemporal and semantic consistency perspectives. During inference, ViSSRes requires only a single forward pass and introduces no substantial additional inference cost. Experiments show that ViSSRes reduces the hallucination rate of LLaVA-NeXT-Video on EventHallusion by 40.69% and improves video understanding on MMVU by 18.36% under the CoT setting, demonstrating its effectiveness in mitigating hallucinations. --- ### DELNet: Continuous All-in-One Weather Removal via Dynamic Expert Library Authors: Shihong Liu, Kun Zuo, Hanguang Xiao Published: 2026-01-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.22573v1 All-in-one weather image restoration methods are valuable in practice but depend on pre-collected data and require retraining for unseen degradations, leading to high cost. We propose DELNet, a continual learning framework for weather image restoration. DELNet integrates a judging valve that measures task similarity to distinguish new from known tasks, and a dynamic expert library that stores experts trained on different degradations. For new tasks, the valve selects top-k experts for knowledge transfer while adding new experts to capture task-specific features; for known tasks, the corresponding experts are directly reused. This design enables continuous optimization without retraining existing models. Experiments on OTS, Rain100H, and Snow100K demonstrate that DELNet surpasses state-of-the-art continual learning methods, achieving PSNR gains of 16\%, 11\%, and 12\%, respectively. These results highlight the effectiveness, robustness, and efficiency of DELNet, which reduces retraining cost and enables practical deployment in real-world scenarios. --- ### PerfGuard: A Performance-Aware Agent for Visual Content Generation Authors: Zhipeng Chen, Zhongrui Zhang, Chao Zhang, Yifan Xu, Lan Yang, Jun Liu, Ke Li, Yi-Zhe Song Published: 2026-01-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.22571v2 The advancement of Large Language Model (LLM)-powered agents has enabled automated task processing through reasoning and tool invocation capabilities. However, existing frameworks often operate under the idealized assumption that tool executions are invariably successful, relying solely on textual descriptions that fail to distinguish precise performance boundaries and cannot adapt to iterative tool updates. This gap introduces uncertainty in planning and execution, particularly in domains like visual content generation (AIGC), where nuanced tool performance significantly impacts outcomes. To address this, we propose PerfGuard, a performance-aware agent framework for visual content generation that systematically models tool performance boundaries and integrates them into task planning and scheduling. Our framework introduces three core mechanisms: (1) Performance-Aware Selection Modeling (PASM), which replaces generic tool descriptions with a multi-dimensional scoring system based on fine-grained performance evaluations; (2) Adaptive Preference Update (APU), which dynamically optimizes tool selection by comparing theoretical rankings with actual execution rankings; and (3) Capability-Aligned Planning Optimization (CAPO), which guides the planner to generate subtasks aligned with performance-aware strategies. Experimental comparisons against state-of-the-art methods demonstrate PerfGuard's advantages in tool selection accuracy, execution reliability, and alignment with user intent, validating its robustness and practical utility for complex AIGC tasks. The project code is available at https://github.com/FelixChan9527/PerfGuard. --- ### Leveraging Data to Say No: Memory Augmented Plug-and-Play Selective Prediction Authors: Aditya Sarkar, Yi Li, Jiacheng Cheng, Shlok Mishra, Nuno Vasconcelos Published: 2026-01-30 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2601.22570v1 Selective prediction aims to endow predictors with a reject option, to avoid low confidence predictions. However, existing literature has primarily focused on closed-set tasks, such as visual question answering with predefined options or fixed-category classification. This paper considers selective prediction for visual language foundation models, addressing a taxonomy of tasks ranging from closed to open set and from finite to unbounded vocabularies, as in image captioning. We seek training-free approaches of low-complexity, applicable to any foundation model and consider methods based on external vision-language model embeddings, like CLIP. This is denoted as Plug-and-Play Selective Prediction (PaPSP). We identify two key challenges: (1) instability of the visual-language representations, leading to high variance in image-text embeddings, and (2) poor calibration of similarity scores. To address these issues, we propose a memory augmented PaPSP (MA-PaPSP) model, which augments PaPSP with a retrieval dataset of image-text pairs. This is leveraged to reduce embedding variance by averaging retrieved nearest-neighbor pairs and is complemented by the use of contrastive normalization to improve score calibration. Through extensive experiments on multiple datasets, we show that MA-PaPSP outperforms PaPSP and other selective prediction baselines for selective captioning, image-text matching, and fine-grained classification. Code is publicly available at https://github.com/kingston-aditya/MA-PaPSP. --- ### Whispers of Wealth: Red-Teaming Google's Agent Payments Protocol via Prompt Injection Authors: Tanusree Debi, Wentian Zhu, Pranjol Sen Gupta Published: 2026-01-30 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2601.22569v2 Large language model (LLM) based agents are increasingly used to automate financial transactions, yet their reliance on contextual reasoning exposes payment systems to prompt-driven manipulation. The Agent Payments Protocol (AP2) aims to secure agent-led purchases through cryptographically verifiable mandates, but its practical robustness remains underexplored. In this work, we perform an AI red-teaming evaluation of AP2 and identify vulnerabilities arising from indirect and direct prompt injection. We introduce two attack techniques, the Branded Whisper Attack and the Vault Whisper Attack which manipulate product ranking and extract sensitive user data. Using a functional AP2 based shopping agent built with Gemini-2.5-Flash and the Google ADK framework, we experimentally validate that simple adversarial prompts can reliably subvert agent behavior. Our findings reveal critical weaknesses in current agentic payment architectures and highlight the need for stronger isolation and defensive safeguards in LLM-mediated financial systems. --- ### EUGens: Efficient, Unified, and General Dense Layers Authors: Sang Min Kim, Byeongchan Kim, Arijit Sehanobish, Somnath Basu Roy Chowdhury, Rahul Kidambi, Dongseok Shim, Avinava Dubey, Snigdha Chaturvedi, Min-hwan Oh, Krzysztof Choromanski Published: 2026-01-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.22563v2 Efficient neural networks are essential for scaling machine learning models to real-time applications and resource-constrained environments. Fully-connected feedforward layers (FFLs) introduce computation and parameter count bottlenecks within neural network architectures. To address this challenge, in this work, we propose a new class of dense layers that generalize standard fully-connected feedforward layers, \textbf{E}fficient, \textbf{U}nified and \textbf{Gen}eral dense layers (EUGens). EUGens leverage random features to approximate standard FFLs and go beyond them by incorporating a direct dependence on the input norms in their computations. The proposed layers unify existing efficient FFL extensions and improve efficiency by reducing inference complexity from quadratic to linear time. They also lead to \textbf{the first} unbiased algorithms approximating FFLs with arbitrary polynomial activation functions. Furthermore, EuGens reduce the parameter count and computational overhead while preserving the expressive power and adaptability of FFLs. We also present a layer-wise knowledge transfer technique that bypasses backpropagation, enabling efficient adaptation of EUGens to pre-trained models. Empirically, we observe that integrating EUGens into Transformers and MLPs yields substantial improvements in inference speed (up to \textbf{27}\%) and memory efficiency (up to \textbf{30}\%) across a range of tasks, including image classification, language model pre-training, and 3D scene reconstruction. Overall, our results highlight the potential of EUGens for the scalable deployment of large-scale neural networks in real-world scenarios. --- ### Hybrid Cross-Device Localization via Neural Metric Learning and Feature Fusion Authors: Meixia Lin, Mingkai Liu, Shuxue Peng, Dikai Fan, Shengyu Gu, Xianliang Huang, Haoyang Ye, Xiao Liu Published: 2026-01-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.22551v1 We present a hybrid cross-device localization pipeline developed for the CroCoDL 2025 Challenge. Our approach integrates a shared retrieval encoder and two complementary localization branches: a classical geometric branch using feature fusion and PnP, and a neural feed-forward branch (MapAnything) for metric localization conditioned on geometric inputs. A neural-guided candidate pruning strategy further filters unreliable map frames based on translation consistency, while depth-conditioned localization refines metric scale and translation precision on Spot scenes. These components jointly lead to significant improvements in recall and accuracy across both HYDRO and SUCCU benchmarks. Our method achieved a final score of 92.62 (R@0.5m, 5°) during the challenge. --- ### Exo-Plore: Exploring Exoskeleton Control Space through Human-aligned Simulation Authors: Geonho Leem, Jaedong Lee, Jehee Lee, Seungmoon Song, Jungdam Won Published: 2026-01-30 Categories: cs.RO, cs.GR, cs.LG arXiv: https://arxiv.org/abs/2601.22550v1 Exoskeletons show great promise for enhancing mobility, but providing appropriate assistance remains challenging due to the complexity of human adaptation to external forces. Current state-of-the-art approaches for optimizing exoskeleton controllers require extensive human experiments in which participants must walk for hours, creating a paradox: those who could benefit most from exoskeleton assistance, such as individuals with mobility impairments, are rarely able to participate in such demanding procedures. We present Exo-plore, a simulation framework that combines neuromechanical simulation with deep reinforcement learning to optimize hip exoskeleton assistance without requiring real human experiments. Exo-plore can (1) generate realistic gait data that captures human adaptation to assistive forces, (2) produce reliable optimization results despite the stochastic nature of human gait, and (3) generalize to pathological gaits, showing strong linear relationships between pathology severity and optimal assistance. --- ### Are LLM Evaluators Really Narcissists? Sanity Checking Self-Preference Evaluations Authors: Dani Roytburg, Matthew Bozoukov, Matthew Nguyen, Jou Barzdukas, Mackenzie Puig-Hall, Narmeen Oozeer Published: 2026-01-30 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.22548v4 Recent research has shown that large language models (LLMs) favor their own outputs when acting as judges, undermining the integrity of automated post-training and evaluation workflows. However, it is difficult to disentangle which behaviors are explained by narcissism versus experimental confounds. Specifically, LLM evaluators may deliver self-preferring verdicts when comparing responses to questions they fail on; these verdicts may not depend on the identity of the author, but on evaluator quality. We correct this by directly comparing the judge's voting distribution in cases where it evaluates itself versus another model. This evaluator quality baseline reveals that only 51% of examples in previous findings retain statistical significance against this null hypothesis, covering 89.6% of total self-preference probability mass. Finally, we compare the entropy of voting distributions, suggesting uncertainty-driven overlap, and show that our procedure enables more careful documentation against the backdrop of judge-bias research. --- ### Towards the Holographic Characteristic of LLMs for Efficient Short-text Generation Authors: Shun Qian, Bingquan Liu, Chengjie Sun, Zhen Xu, Baoxun Wang Published: 2026-01-30 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.22546v2 The recent advancements in Large Language Models (LLMs) have attracted interest in exploring their in-context learning abilities and chain-of-thought capabilities. However, there are few studies investigating the specific traits related to the powerful generation capacity of LLMs. This paper aims to delve into the generation characteristics exhibited by LLMs. Through our investigation, we have discovered that language models tend to capture target-side keywords at the beginning of the generation process. We name this phenomenon the Holographic Characteristic of language models. For the purpose of exploring this characteristic and further improving the inference efficiency of language models, we propose a plugin called HOLO, which leverages the Holographic Characteristic to extract target-side keywords from language models within a limited number of generation steps and complements the sentence with a parallel lexically constrained text generation method. To verify the effectiveness of HOLO, we conduct massive experiments on language models of varying architectures and scales in the short-text generation scenario. The results demonstrate that HOLO achieves comparable performance to the baselines in terms of both automatic and human-like evaluation metrics and highlight the potential of the Holographic Characteristic. --- ### Adapting Reinforcement Learning for Path Planning in Constrained Parking Scenarios Authors: Feng Tao, Luca Paparusso, Chenyi Gu, Robin Koehler, Chenxu Wu, Xinyu Huang, Christian Juette, David Paz, Ren Liu Published: 2026-01-30 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2601.22545v1 Real-time path planning in constrained environments remains a fundamental challenge for autonomous systems. Traditional classical planners, while effective under perfect perception assumptions, are often sensitive to real-world perception constraints and rely on online search procedures that incur high computational costs. In complex surroundings, this renders real-time deployment prohibitive. To overcome these limitations, we introduce a Deep Reinforcement Learning (DRL) framework for real-time path planning in parking scenarios. In particular, we focus on challenging scenes with tight spaces that require a high number of reversal maneuvers and adjustments. Unlike classical planners, our solution does not require ideal and structured perception, and in principle, could avoid the need for additional modules such as localization and tracking, resulting in a simpler and more practical implementation. Also, at test time, the policy generates actions through a single forward pass at each step, which is lightweight enough for real-time deployment. The task is formulated as a sequential decision-making problem grounded in a bicycle model dynamics, enabling the agent to directly learn navigation policies that respect vehicle kinematics and environmental constraints in the closed-loop setting. A new benchmark is developed to support both training and evaluation, capturing diverse and challenging scenarios. Our approach achieves state-of-the-art success rates and efficiency, surpassing classical planner baselines by +96% in success rate and +52% in efficiency. Furthermore, we release our benchmark as an open-source resource for the community to foster future research in autonomous systems. The benchmark and accompanying tools are available at https://github.com/dqm5rtfg9b-collab/Constrained_Parking_Scenarios. --- ### Detect and Act: Automated Dynamic Optimizer through Meta-Black-Box Optimization Authors: Zijian Gao, Yuanting Zhong, Zeyuan Ma, Yue-Jiao Gong, Hongshu Guo Published: 2026-01-30 Categories: cs.NE, cs.LG arXiv: https://arxiv.org/abs/2601.22542v1 Dynamic Optimization Problems (DOPs) are challenging to address due to their complex nature, i.e., dynamic environment variation. Evolutionary Computation methods are generally advantaged in solving DOPs since they resemble dynamic biological evolution. However, existing evolutionary dynamic optimization methods rely heavily on human-crafted adaptive strategy to detect environment variation in DOPs, and then adapt the searching strategy accordingly. These hand-crafted strategies may perform ineffectively at out-of-box scenarios. In this paper, we propose a reinforcement learning-assisted approach to enable automated variation detection and self-adaption in evolutionary algorithms. This is achieved by borrowing the bi-level learning-to-optimize idea from recent Meta-Black-Box Optimization works. We use a deep Q-network as optimization dynamics detector and searching strategy adapter: It is fed as input with current-step optimization state and then dictates desired control parameters to underlying evolutionary algorithms for next-step optimization. The learning objective is to maximize the expected performance gain across a problem distribution. Once trained, our approach could generalize toward unseen DOPs with automated environment variation detection and self-adaption. To facilitate comprehensive validation, we further construct an easy-to-difficult DOPs testbed with diverse synthetic instances. Extensive benchmark results demonstrate flexible searching behavior and superior performance of our approach in solving DOPs, compared to state-of-the-art baselines. --- ### Benchmarking Long Roll-outs of Auto-regressive Neural Operators for the Compressible Navier-Stokes Equations with Conserved Quantity Correction Authors: Sean Current, Chandan Kumar, Datta Gaitonde, Srinivasan Parthasarathy Published: 2026-01-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.22541v1 Deep learning has been proposed as an efficient alternative for the numerical approximation of PDE solutions, offering fast, iterative simulation of PDEs through the approximation of solution operators. However, deep learning solutions have struggle to perform well over long prediction durations due to the accumulation of auto-regressive error, which is compounded by the inability of models to conserve physical quantities. In this work, we present conserved quantity correction, a model-agnostic technique for incorporation physical conservation criteria within deep learning models. Our results demonstrate consistent improvement in the long-term stability of auto-regressive neural operator models, regardless of the model architecture. Furthermore, we analyze the performance of neural operators from the spectral domain, highlighting significant limitations of present architectures. These results highlight the need for future work to consider architectures that place specific emphasis on high frequency components, which are integral to the understanding and modeling of turbulent flows. --- ### Neural-Inspired Posterior Approximation (NIPA) Authors: Babak Shahbaba, Zahra Moslemi Published: 2026-01-30 Categories: cs.LG, stat.CO, stat.ML arXiv: https://arxiv.org/abs/2601.22539v1 Humans learn efficiently from their environment by engaging multiple interacting neural systems that support distinct yet complementary forms of control, including model-based (goal-directed) planning, model-free (habitual) responding, and episodic memory-based learning. Model-based mechanisms compute prospective action values using an internal model of the environment, supporting flexible but computationally costly planning; model-free mechanisms cache value estimates and build heuristics that enable fast, efficient habitual responding; and memory-based mechanisms allow rapid adaptation from individual experience. In this work, we aim to elucidate the computational principles underlying this biological efficiency and translate them into a sampling algorithm for scalable Bayesian inference through effective exploration of the posterior distribution. More specifically, our proposed algorithm comprises three components: a model-based module that uses the target distribution for guided but computationally slow sampling; a model-free module that uses previous samples to learn patterns in the parameter space, enabling fast, reflexive sampling without directly evaluating the expensive target distribution; and an episodic-control module that supports rapid sampling by recalling specific past events (i.e., samples). We show that this approach advances Bayesian methods and facilitates their application to large-scale statistical machine learning problems. In particular, we apply our proposed framework to Bayesian deep learning, with an emphasis on proper and principled uncertainty quantification. --- ### Learning-to-Defer in Non-Stationary Time Series via Switching State-Space Models Authors: Yannis Montreuil, Letian Yu, Axel Carlier, Lai Xing Ng, Wei Tsang Ooi Published: 2026-01-30 Categories: cs.LG, stat.AP arXiv: https://arxiv.org/abs/2601.22538v3 Learning-to-defer (L2D) routes each decision to a system's own predictor or to an external expert. Streaming time-series settings break the offline-L2D assumptions: the data are non-stationary, expert availability shifts over time, and the internal predictor is trained online. We propose L2D-SLDS, a one-stage online L2D framework based on a factorized switching linear-Gaussian state-space model over all potential residuals: a discrete regime, a shared global factor, and per-expert idiosyncratic states. The always-observed internal residual continuously updates beliefs about every unqueried expert through the shared factor, and a learner-aware query score balances immediate cost against latent-state information gain and one-step learner improvement. We prove an oracle inequality against a time-varying learn-and-defer comparator, decomposing regret into a query-bonus budget, an SLDS predictive-cost-error term~$\mathcal{E}_{\mathrm{SLDS}}$, and the internal learner's interval dynamic regret. On synthetic, Melbourne, Jena, and 24-expert Delhi benchmarks, L2D-SLDS is competitive with or improves on contextual- and non-stationary-bandit baselines while deferring on ${<}2\%$ of real-data rounds. --- ### EndoCaver: Handling Fog, Blur and Glare in Endoscopic Images via Joint Deblurring-Segmentation Authors: Zhuoyu Wu, Wenhui Ou, Pei-Sze Tan, Jiayan Yang, Wenqi Fang, Zheng Wang, Raphaël C. -W. Phan Published: 2026-01-30 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2601.22537v1 Endoscopic image analysis is vital for colorectal cancer screening, yet real-world conditions often suffer from lens fogging, motion blur, and specular highlights, which severely compromise automated polyp detection. We propose EndoCaver, a lightweight transformer with a unidirectional-guided dual-decoder architecture, enabling joint multi-task capability for image deblurring and segmentation while significantly reducing computational complexity and model parameters. Specifically, it integrates a Global Attention Module (GAM) for cross-scale aggregation, a Deblurring-Segmentation Aligner (DSA) to transfer restoration cues, and a cosine-based scheduler (LoCoS) for stable multi-task optimisation. Experiments on the Kvasir-SEG dataset show that EndoCaver achieves 0.922 Dice on clean data and 0.889 under severe image degradation, surpassing state-of-the-art methods while reducing model parameters by 90%. These results demonstrate its efficiency and robustness, making it well-suited for on-device clinical deployment. Code is available at https://github.com/ReaganWu/EndoCaver. --- ### Decoding in Geometry: Alleviating Embedding-Space Crowding for Complex Reasoning Authors: Yixin Yang, Qingxiu Dong, Zhifang Sui Published: 2026-01-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.22536v1 Sampling-based decoding underlies complex reasoning in large language models (LLMs), where decoding strategies critically shape model behavior. Temperature- and truncation-based methods reshape the next-token distribution through global probability reweighting or thresholding to balance the quality-diversity tradeoff. However, they operate solely on token probabilities, ignoring fine-grained relationships among tokens in the embedding space. We uncover a novel phenomenon, embedding-space crowding, where the next-token distribution concentrates its probability mass on geometrically close tokens in the embedding space. We quantify crowding at multiple granularities and find a statistical association with reasoning success in mathematical problem solving. Motivated by this finding, we propose CraEG, a plug-and-play sampling method that mitigates crowding through geometry-guided reweighting. CraEG is training-free, single-pass, and compatible with standard sampling strategies. Experiments on multiple models and benchmarks demonstrate improved generation performance, with gains in robustness and diversity metrics. --- ### Demystifying Design Choices of Reinforcement Fine-tuning: A Batched Contextual Bandit Learning Perspective Authors: Hong Xie, Xiao Hu, Tao Tan, Haoran Gu, Xin Li, Jianyu Han, Defu Lian, Enhong Chen Published: 2026-01-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.22532v1 The reinforcement fine-tuning area is undergoing an explosion papers largely on optimizing design choices. Though performance gains are often claimed, inconsistent conclusions also arise from time to time, making the progress illusive. Reflecting on this illusion, we still lack principled answers to two fundamental questions: 1) what is the role of each design choice? 2) which ones are critical? This paper aims to shed light on them. The underlying challenge is that design choices are entangled together, making their contribution to learning and generalization difficult to attribute. To address this challenge, we first construct a minimalist baseline for disentangling factors: one rollout per query in each round, the outcome reward serving as the training signal without any advantage trick, and a batch size of thirty-two. This baseline connects to batched contextual bandit learning, which facilitates experimental analysis. Centering around this baseline, we design an experiment pipeline, examining the marginal gains of factors like advantage, number of rollouts, etc. Experiments on three base models and two datasets, not only reveal new understanding on the role of various design choices on learning and generalization dynamics, but also identify critical ones that deserve more effort. --- ### Learn from A Rationalist: Distilling Intermediate Interpretable Rationales Authors: Jiayi Dai, Randy Goebel Published: 2026-01-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.22531v2 Because of the pervasive use of deep neural networks (DNNs), especially in high-stakes domains, the interpretability of DNNs has received increased attention. The general idea of rationale extraction (RE) is to provide an interpretable-by-design framework for DNNs via a select-predict architecture where two neural networks learn jointly to perform feature selection and prediction, respectively. Given only the remote supervision from the final task prediction, the process of learning to select subsets of features (or rationales) requires searching in the space of all possible feature combinations, which is computationally challenging and even harder when the base neural networks are not sufficiently capable. To improve the predictive performance of RE models that are based on less capable or smaller neural networks (i.e., the students), we propose REKD (Rationale Extraction with Knowledge Distillation) where a student RE model learns from the rationales and predictions of a teacher (i.e., a rationalist) in addition to the student's own RE optimization. This structural adjustment to RE aligns well with how humans could learn effectively from interpretable and verifiable knowledge. Because of the neural-model agnostic nature of the method, any black-box neural network could be integrated as a backbone model. To demonstrate the viability of REKD, we conduct experiments with multiple variants of BERT and vision transformer (ViT) models. Our experiments across language and vision classification datasets (i.e., IMDB movie reviews, CIFAR 10 and CIFAR 100) show that REKD significantly improves the predictive performance of the student RE models. --- ### Enhancing Table Reasoning with Deterministic Table-State Rewards Authors: Tung Sum Thomas Kwok, Xinyu Wang, Hengzhi He, Xiaofeng Lin, Peng Lu, Liheng Ma, Chunhe Wang, Chun Ho Mak, Yuyu Luo, Ying Nian Wu, Lei Ding, Guang Cheng Published: 2026-01-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.22530v2 Large Language Models (LLMs) struggle with multi-step reasoning over structured tables. The primary reason is the lack of explicit supervision for intermediate reasoning states. Existing learned reward models or executor-based verifiers are either unscalable or rely on answer-checking environments unavailable for many tabular tasks. This leaves no signal that is scalable and grounded in the query. To address this, we introduce TABROUGE, a training-free and deterministic state reward. By adapting the Longest Common Subsequence (LCS) metric from text summarization to evaluate tabular states, TABROUGE assesses the lexical coverage and structural integrity of intermediate tables against the query without requiring learned models or external executors. Built upon this metric, we propose RE-TAB, a plug-and-play, training-free framework. RE-TAB reframes table reasoning as deterministic control over intermediate states, utilizing TABROUGE for stepwise feedback and trajectory-level test-time scaling (TTS) signals. Across six backbones and three benchmarks, RE-TAB improves accuracy by an average of 26.7 pp over no-reward baselines. It also reduces TTS samples by up to 33%. Preliminary GRPO experiments further indicate TABROUGE's viability as a scalable post-training reward, increasing gains by 8.34 pp. We further analyze failure modes of TABROUGE, including paraphrase under-rewarding and echo-column hacking, and identify when structure-aware lexical rewards remain reliable. --- ### SHED Light on Segmentation for Dense Prediction Authors: Seung Hyun Lee, Sangwoo Mo, Stella X. Yu Published: 2026-01-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.22529v1 Dense prediction infers per-pixel values from a single image and is fundamental to 3D perception and robotics. Although real-world scenes exhibit strong structure, existing methods treat it as an independent pixel-wise prediction, often resulting in structural inconsistencies. We propose SHED, a novel encoder-decoder architecture that enforces geometric prior explicitly by incorporating segmentation into dense prediction. By bidirectional hierarchical reasoning, segment tokens are hierarchically pooled in the encoder and unpooled in the decoder to reverse the hierarchy. The model is supervised only at the final output, allowing the segment hierarchy to emerge without explicit segmentation supervision. SHED improves depth boundary sharpness and segment coherence, while demonstrating strong cross-domain generalization from synthetic to the real-world environments. Its hierarchy-aware decoder better captures global 3D scene layouts, leading to improved semantic segmentation performance. Moreover, SHED enhances 3D reconstruction quality and reveals interpretable part-level structures that are often missed by conventional pixel-wise methods. --- ### Darwinian Memory: A Training-Free Self-Regulating Memory System for GUI Agent Evolution Authors: Hongze Mi, Yibo Feng, WenJie Lu, Song Cao, Jinyuan Li, Yanming Li, Xuelin Zhang, Haotian Luo, Songyang Peng, He Cui, Tengfei Tian, Jun Fang et al. Published: 2026-01-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.22528v1 Multimodal Large Language Model (MLLM) agents facilitate Graphical User Interface (GUI) automation but struggle with long-horizon, cross-application tasks due to limited context windows. While memory systems provide a viable solution, existing paradigms struggle to adapt to dynamic GUI environments, suffering from a granularity mismatch between high-level intent and low-level execution, and context pollution where the static accumulation of outdated experiences drives agents into hallucination. To address these bottlenecks, we propose the Darwinian Memory System (DMS), a self-evolving architecture that constructs memory as a dynamic ecosystem governed by the law of survival of the fittest. DMS decomposes complex trajectories into independent, reusable units for compositional flexibility, and implements Utility-driven Natural Selection to track survival value, actively pruning suboptimal paths and inhibiting high-risk plans. This evolutionary pressure compels the agent to derive superior strategies. Extensive experiments on real-world multi-app benchmarks validate that DMS boosts general-purpose MLLMs without training costs or architectural overhead, achieving average gains of 18.0% in success rate and 33.9% in execution stability, while reducing task latency, establishing it as an effective self-evolving memory system for GUI tasks. --- ### $ρ$-$\texttt{EOS}$: Training-free Bidirectional Variable-Length Control for Masked Diffusion LLMs Authors: Jingyi Yang, Yuxian Jiang, Jing Shao Published: 2026-01-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.22527v2 Beyond parallel generation and global context modeling, current masked diffusion large language models (masked dLLMs, i.e., LLaDA) suffer from a fundamental limitation: they require a predefined, fixed generation length, which lacks flexibility and forces an inevitable trade-off between output quality and computational efficiency. To address this, we study the denoising dynamics and find that the implicit density ($ρ$) of end-of-sequence ($\texttt{EOS}$) tokens serves as a reliable signal of generation sufficiency. In particular, the evolving implicit $\texttt{EOS}$ density during denoising reveals whether the current masked space is excessive or insufficient, thereby guiding the adjustment direction for generation length. Building on this insight, we propose $\textbf{$ρ$-$\texttt{EOS}$}$, a training-free, single-stage strategy that enables bidirectional variable-length generation for masked dLLMs. Unlike prior two-stage approaches--which require separate length adjustment and iterative mask insertion phases while supporting only unidirectional expansion--$\textbf{$ρ$-$\texttt{EOS}$}$ achieves bidirectional length adjustment within a unified denoising process by continuously estimating the implicit $\texttt{EOS}$ density: excessively high density triggers $\texttt{MASK}$ token contraction, while insufficient density induces expansion. Extensive experiments on mathematics and code benchmarks demonstrate that $\textbf{$ρ$-$\texttt{EOS}$}$ achieves comparable performance while substantially improving inference efficiency and token utilization. Code is available at https://github.com/yjyddq/rho-EOS. --- ### Variational Bayesian Flow Network for Graph Generation Authors: Yida Xiong, Jiameng Chen, Xiuwen Gong, Jia Wu, Shirui Pan, Wenbin Hu Published: 2026-01-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.22524v2 Graph generation aims to sample discrete node and edge attributes while satisfying coupled structural constraints. Diffusion models for graphs often adopt largely factorized forward-noising, and many flow-matching methods start from factorized reference noise and coordinate-wise interpolation, so node-edge coupling is not encoded by the generative geometry and must be recovered implicitly by the core network, which can be brittle after discrete decoding. Bayesian Flow Networks (BFNs) evolve distribution parameters and naturally support discrete generation. But classical BFNs typically rely on factorized beliefs and independent channels, which limit geometric evidence fusion. We propose Variational Bayesian Flow Network (VBFN), which performs a variational lifting to a tractable joint Gaussian variational belief family governed by structured precisions. Each Bayesian update reduces to solving a symmetric positive definite linear system, enabling coupled node and edge updates within a single fusion step. We construct sample-agnostic sparse precisions from a representation-induced dependency graph, thereby avoiding label leakage while enforcing node-edge consistency. On synthetic and molecular graph datasets, VBFN improves fidelity and diversity, and surpasses baseline methods. The reproducible code is available at https://github.com/Cello2195/VBFN. --- ### Can 3D point cloud data improve automated body condition score prediction in dairy cattle? Authors: Zhou Tang, Jin Wang, Angelo De Castro, Yuxi Zhang, Victoria Bastos Primo, Ana Beatriz Montevecchio Bernardino, Gota Morota, Xu Wang, Ricardo C Chebel, Haipeng Yu Published: 2026-01-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.22522v2 Body condition score (BCS) is a widely used indicator of body energy status and is closely associated with metabolic status, reproductive performance, and health in dairy cattle; however, conventional visual scoring is subjective and labor-intensive. Computer vision approaches have been applied to BCS prediction, with depth images widely used because they capture geometric information independent of coat color and texture. More recently, three-dimensional point cloud data have attracted increasing interest due to their ability to represent richer geometric characteristics of animal morphology, but direct head-to-head comparisons with depth image-based approaches remain limited. In this study, we compared top-view depth image and point cloud data for BCS prediction under four settings: 1) unsegmented raw data, 2) segmented full-body data, 3) segmented hindquarter data, and 4) handcrafted feature data. Prediction models were evaluated using data from 1,020 dairy cows collected on a commercial farm, with cow-level cross-validation to prevent data leakage. Depth image-based models consistently achieved higher accuracy than point cloud-based models when unsegmented raw data and segmented full-body data were used, whereas comparable performance was observed when segmented hindquarter data were used. Both depth image and point cloud approaches showed reduced accuracy when handcrafted feature data were employed compared with the other settings. Overall, point cloud-based predictions were more sensitive to noise and model architecture than depth image-based predictions. Taken together, these results indicate that three-dimensional point clouds do not provide a consistent advantage over depth images for BCS prediction in dairy cattle under the evaluated conditions. --- ### One Ring to Rule Them All: Unifying Group-Based RL via Dynamic Power-Mean Geometry Authors: Weisong Zhao, Tong Wang, Zichang Tan, Te Yang, Siran Peng, Haoyuan Zhang, Tianshuo Zhang, Haichao Shi, Meng Meng, Yang Yang, Xiangyu Zhu, Zhen Lei et al. Published: 2026-01-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.22521v1 Group-based reinforcement learning has evolved from the arithmetic mean of GRPO to the geometric mean of GMPO. While GMPO improves stability by constraining a conservative objective, it shares a fundamental limitation with GRPO: reliance on a fixed aggregation geometry that ignores the evolving and heterogeneous nature of each trajectory. In this work, we unify these approaches under Power-Mean Policy Optimization (PMPO), a generalized framework that parameterizes the aggregation geometry via the power-mean geometry exponent p. Within this framework, GRPO and GMPO are recovered as special cases. Theoretically, we demonstrate that adjusting p modulates the concentration of gradient updates, effectively reweighting tokens based on their advantage contribution. To determine p adaptively, we introduce a Clip-aware Effective Sample Size (ESS) mechanism. Specifically, we propose a deterministic rule that maps a trajectory clipping fraction to a target ESS. Then, we solve for the specific p to align the trajectory induced ESS with this target one. This allows PMPO to dynamically transition between the aggressive arithmetic mean for reliable trajectories and the conservative geometric mean for unstable ones. Experiments on multiple mathematical reasoning benchmarks demonstrate that PMPO outperforms strong baselines. --- ### Corrected Samplers for Discrete Flow Models Authors: Zhengyan Wan, Yidong Ouyang, Liyan Xie, Hongyuan Zha, Fang Fang, Guang Cheng Published: 2026-01-30 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2601.22519v3 Discrete flow models (DFMs) have been proposed to learn the data distribution on finite state space, offering a flexible framework as an alternative to discrete diffusion models. A line of recent work has studied samplers for discrete diffusion models, such as tau-leaping and Euler solver. However, these samplers require a large number of iterations to control discretization error, since the transition rates are frozen in time and evaluated at the initial state within each time interval. Moreover, theoretical results for these samplers often require boundedness conditions of the transition rate or they focus on a specific type of source distributions. To address those limitations, we establish non-asymptotic discretization error bounds for those samplers without any restriction on transition rates and source distributions, under the framework of discrete flow models. Furthermore, by analyzing a one-step lower bound of the Euler sampler, we propose two corrected samplers: \textit{time-corrected sampler} and \textit{location-corrected sampler}, which can reduce the discretization error of tau-leaping and Euler solver with almost no additional computational cost. We rigorously show that the location-corrected sampler has a lower complexity than existing parallel samplers. We validate the effectiveness of the proposed method by achieving better generation quality with reduced inference time on simulations and text-to-image generation tasks. Code can be found in https://github.com/WanZhengyan/Corrected-Samplers-for-Discrete-Flow-Models. --- ### SCOPE-PD: Explainable AI on Subjective and Clinical Objective Measurements of Parkinson's Disease for Precision Decision-Making Authors: Md Mezbahul Islam, John Michael Templeton, Masrur Sobhan, Christian Poellabauer, Ananda Mohan Mondal Published: 2026-01-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.22516v1 Parkinson's disease (PD) is a chronic and complex neurodegenerative disorder influenced by genetic, clinical, and lifestyle factors. Predicting this disease early is challenging because it depends on traditional diagnostic methods that face issues of subjectivity, which commonly delay diagnosis. Several objective analyses are currently in practice to help overcome the challenges of subjectivity; however, a proper explanation of these analyses is still lacking. While machine learning (ML) has demonstrated potential in supporting PD diagnosis, existing approaches often rely on subjective reports only and lack interpretability for individualized risk estimation. This study proposes SCOPE-PD, an explainable AI-based prediction framework, by integrating subjective and objective assessments to provide personalized health decisions. Subjective and objective clinical assessment data are collected from the Parkinson's Progression Markers Initiative (PPMI) study to construct a multimodal prediction framework. Several ML techniques are applied to these data, and the best ML model is selected to interpret the results. Model interpretability is examined using SHAP-based analysis. The Random Forest algorithm achieves the highest accuracy of 98.66 percent using combined features from both subjective and objective test data. Tremor, bradykinesia, and facial expression are identified as the top three contributing features from the MDS-UPDRS test in the prediction of PD. --- ### DNA: Uncovering Universal Latent Forgery Knowledge Authors: Jingtong Dou, Chuancheng Shi, Yemin Wang, Shiming Guo, Anqi Yi, Wenhua Wu, Li Zhang, Fei Shen, Tat-Seng Chua Published: 2026-01-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.22515v1 As generative AI achieves hyper-realism, superficial artifact detection has become obsolete. While prevailing methods rely on resource-intensive fine-tuning of black-box backbones, we propose that forgery detection capability is already encoded within pre-trained models rather than requiring end-to-end retraining. To elicit this intrinsic capability, we propose the discriminative neural anchors (DNA) framework, which employs a coarse-to-fine excavation mechanism. First, by analyzing feature decoupling and attention distribution shifts, we pinpoint critical intermediate layers where the focus of the model logically transitions from global semantics to local anomalies. Subsequently, we introduce a triadic fusion scoring metric paired with a curvature-truncation strategy to strip away semantic redundancy, precisely isolating the forgery-discriminative units (FDUs) inherently imprinted with sensitivity to forgery traces. Moreover, we introduce HIFI-Gen, a high-fidelity synthetic benchmark built upon the very latest models, to address the lag in existing datasets. Experiments demonstrate that by solely relying on these anchors, DNA achieves superior detection performance even under few-shot conditions. Furthermore, it exhibits remarkable robustness across diverse architectures and against unseen generative models, validating that waking up latent neurons is more effective than extensive fine-tuning. --- ### Why Self-Rewarding Works: Theoretical Guarantees for Iterative Alignment of Language Models Authors: Shi Fu, Yingjie Wang, Shengchao Hu, Peng Wang, Dacheng Tao Published: 2026-01-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.22513v2 Self-Rewarding Language Models (SRLMs) achieve notable success in iteratively improving alignment without external feedback. Yet, despite their striking empirical progress, the core mechanisms driving their capabilities remain unelucidated, leaving a critical gap in theoretical understanding. This paper provides the first rigorous theoretical guarantees for SRLMs. We first establish a lower bound that characterizes the fundamental limits of a single update step, revealing a critical dependence on the quality of the initial model. We then derive finite-sample error bounds for the full iterative paradigm, showing that performance improves at a rate of $\widetilde{\mathcal{O}}\left(1/\sqrt{n}\right)$ with sample size $n$. Crucially, our analysis reveals that the dependence on the initial model decays exponentially with the number of iterations $T$. This provides a formal explanation for why self-rewarding succeeds: it robustly overcomes poor initialization by steering the dynamics toward internal stability and consistency. Finally, we instantiate our theoretical framework for the linear softmax model class, yielding tailored guarantees that connect our high-level insights to practical model architectures. --- ### DRL-Enabled Trajectory Planing for UAV-Assisted VLC: Optimal Altitude and Reward Design Authors: Tian-Tian Lin, Yi Liu, Xiao-Wei Tang, Yunmei Shi, Yi Huang, Zhongxiang Wei, Qingqing Wu, Yuhan Dong Published: 2026-01-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.22512v1 Recently, the integration of unmanned aerial vehicle (UAV) and visible light communication (VLC) technologies has emerged as a promising solution to offer flexible communication and efficient lighting. This letter investigates the three-dimensional trajectory planning in a UAV-assisted VLC system, where a UAV is dispatched to collect data from ground users (GUs). The core objective is to develop a trajectory planning framework that minimizes UAV flight distance, which is equivalent to maximizing the data collection efficiency. This issue is formulated as a challenging mixed-integer non-convex optimization problem. To tackle it, we first derive a closed-form optimal flight altitude under specific VLC channel gain threshold. Subsequently, we optimize the UAV horizontal trajectory by integrating a novel pheromone-driven reward mechanism with the twin delayed deep deterministic policy gradient algorithm, which enables adaptive UAV motion strategy in complex environments. Simulation results validate that the derived optimal altitude effectively reduces the flight distance by up to 35% compared to baseline methods. Additionally, the proposed reward mechanism significantly shortens the convergence steps by approximately 50%, demonstrating notable efficiency gains in the context of UAV-assisted VLC data collection. --- ### Mock Worlds, Real Skills: Building Small Agentic Language Models with Synthetic Tasks, Simulated Environments, and Rubric-Based Rewards Authors: Yuanjie Lyu, Chengyu Wang, Lei Shen, Jun Huang, Tong Xu Published: 2026-01-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.22511v2 Small LLMs often struggle to match the agentic capabilities of large, costly models. While reinforcement learning can help, progress has been limited by two structural bottlenecks: existing open-source agentic training data are narrow in task variety and easily solved; real-world APIs lack diversity and are unstable for large-scale reinforcement learning rollout processes. We address these challenges with SYNTHAGENT, a framework that jointly synthesizes diverse tool-use training data and simulates complete environments. Specifically, a strong teacher model creates novel tasks and tool ecosystems, then rewrites them into intentionally underspecified instructions. This compels agents to actively query users for missing details. When handling synthetic tasks, an LLM-based user simulator provides user-private information, while a mock tool system delivers stable tool responses. For rewards, task-level rubrics are constructed based on required subgoals, user-agent interactions, and forbidden behaviors. Across 14 challenging datasets in math, search, and tool use, models trained on our synthetic data achieve substantial gains, with small models outperforming larger baselines. --- ### Shattered Compositionality: Counterintuitive Learning Dynamics of Transformers for Arithmetic Authors: Xingyu Zhao, Darsh Sharma, Rheeya Uppaal, Yiqiao Zhong Published: 2026-01-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.22510v2 Large language models (LLMs) often achieve strong benchmark accuracy yet remain brittle under small distribution shifts. While recent mechanistic studies reveal the discrepancy between LLMs and humans in skill compositions, the learning dynamics of skill acquisition and the role of data distributions remain elusive. In this study, we train transformers on synthetic arithmetic tasks with black-box model-agnostic metrics for analyzing non-human skill compositions. We discover that transformers often acquire skills for arithmetic in reverse order or in parallel instead of human-like sequential rules--a phenomenon we refer to as shattered compositionality. To explain these behaviors, we provide evidence that correlational matching to the training data, rather than causal or procedural composition, shapes learning dynamics. As a consequence, this non-human acquisition creates competition between partially learned skills, producing characteristic mixing errors and weaker robustness under controlled distribution shifts. We further show that the same qualitative behavior persists in modern LLMs and is not mitigated by pure model scaling or scratchpad supervision. Our results highlight a mismatch between training-time skill acquisition and the human-like hierarchical compositions, with implications for reasoning reliability and out-of-distribution robustness. --- ### Keep Rehearsing and Refining: Lifelong Learning Vehicle Routing under Continually Drifting Tasks Authors: Jiyuan Pei, Yi Mei, Jialin Liu, Mengjie Zhang, Xin Yao Published: 2026-01-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.22509v2 Existing neural solvers for vehicle routing problems (VRPs) are typically trained either in a one-off manner on a fixed set of pre-defined tasks or in a lifelong manner with tasks arriving sequentially, assuming sufficient training on each task. Both settings overlook a common real-world property: problem patterns may drift continually over time, yielding massive tasks sequentially arising, each with only limited training resources. In this paper, we propose a novel lifelong learning paradigm for neural VRP solvers under continual task drift over time, where each task is locally stationary at one learning time step but receives only insufficient training resources. We empirically demonstrate that such continual drift arises in practice using a real-world logistics dataset. We then propose Dual Replay with Experience Enhancement (DREE), a general framework to improve learning efficiency and mitigate catastrophic forgetting under such drift. Extensive experiments based on both the real-world logistics dataset and commonly used synthetic dataset show that, under such continual drift, DREE effectively learns new tasks, preserves prior knowledge, improves generalization to unseen tasks, and can be applied to various existing neural solvers. --- ### CoVA: Text-Guided Composed Video Retrieval for Audio-Visual Content Authors: Gyuwon Han, Young Kyun Jang, Chanho Eom Published: 2026-01-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.22508v1 Composed Video Retrieval (CoVR) aims to retrieve a target video from a large gallery using a reference video and a textual query specifying visual modifications. However, existing benchmarks consider only visual changes, ignoring videos that differ in audio despite visual similarity. To address this limitation, we introduce Composed retrieval for Video with its Audio CoVA, a new retrieval task that accounts for both visual and auditory variations. To support this, we construct AV-Comp, a benchmark consisting of video pairs with cross-modal changes and corresponding textual queries that describe the differences. We also propose AVT Compositional Fusion (AVT), which integrates video, audio, and text features by selectively aligning the query to the most relevant modality. AVT outperforms traditional unimodal fusion and serves as a strong baseline for CoVA. Examples from the proposed dataset, including both visual and auditory information, are available at https://perceptualai-lab.github.io/CoVA/. --- ### DreamVAR: Taming Reinforced Visual Autoregressive Model for High-Fidelity Subject-Driven Image Generation Authors: Xin Jiang, Jingwen Chen, Yehao Li, Yingwei Pan, Kezhou Chen, Zechao Li, Ting Yao, Tao Mei Published: 2026-01-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.22507v1 Recent advances in subject-driven image generation using diffusion models have attracted considerable attention for their remarkable capabilities in producing high-quality images. Nevertheless, the potential of Visual Autoregressive (VAR) models, despite their unified architecture and efficient inference, remains underexplored. In this work, we present DreamVAR, a novel framework for subject-driven image synthesis built upon a VAR model that employs next-scale prediction. Technically, multi-scale features of the reference subject are first extracted by a visual tokenizer. Instead of interleaving these conditional features with target image tokens across scales, our DreamVAR pre-fills the full subject feature sequence prior to predicting target image tokens. This design simplifies autoregressive dependencies and mitigates the train-test discrepancy in multi-scale conditioning scenario within the VAR paradigm. DreamVAR further incorporates reinforcement learning to jointly enhance semantic alignment and subject consistency. Extensive experiments demonstrate that DreamVAR achieves superior appearance preservation compared to leading diffusion-based methods. --- ### MIRRORTALK: Forging Personalized Avatars Via Disentangled Style and Hierarchical Motion Control Authors: Renjie Lu, Xulong Zhang, Xiaoyang Qu, Jianzong Wang, Shangfei Wang Published: 2026-01-30 Categories: cs.CV, cs.SD arXiv: https://arxiv.org/abs/2601.22501v1 Synthesizing personalized talking faces that uphold and highlight a speaker's unique style while maintaining lip-sync accuracy remains a significant challenge. A primary limitation of existing approaches is the intrinsic confounding of speaker-specific talking style and semantic content within facial motions, which prevents the faithful transfer of a speaker's unique persona to arbitrary speech. In this paper, we propose MirrorTalk, a generative framework based on a conditional diffusion model, combined with a Semantically-Disentangled Style Encoder (SDSE) that can distill pure style representations from a brief reference video. To effectively utilize this representation, we further introduce a hierarchical modulation strategy within the diffusion process. This mechanism guides the synthesis by dynamically balancing the contributions of audio and style features across distinct facial regions, ensuring both precise lip-sync accuracy and expressive full-face dynamics. Extensive experiments demonstrate that MirrorTalk achieves significant improvements over state-of-the-art methods in terms of lip-sync accuracy and personalization preservation. --- ### Fairness-Aware Performance Evaluation for Multi-Party Multi-Objective Optimization Authors: Zifan Zhao, Peilan Xu, Wenjian Luo Published: 2026-01-30 Categories: cs.NE arXiv: https://arxiv.org/abs/2601.22497v1 In multiparty multiobjective optimization problems, solution sets are usually evaluated using classical performance metrics, aggregated across DMs. However, such mean-based evaluations may be unfair by favoring certain parties, as they assume identical geometric approximation quality to each party's PF carries comparable evaluative significance. Moreover, prevailing notions of MPMOP optimal solutions are restricted to strictly common Pareto optimal solutions, representing a narrow form of cooperation in multiparty decision making scenarios. These limitations obscure whether a solution set reflects balanced relative gains or meaningful consensus among heterogeneous DMs. To address these issues, this paper develops a fairness-aware performance evaluation framework grounded in a generalized notion of consensus solutions. From a cooperative game-theoretic perspective, we formalize four axioms that a fairness-aware evaluation function for MPMOPs should satisfy. By introducing a concession rate vector to quantify acceptable compromises by individual DMs, we generalize the classical definition of MPMOP optimal solutions and embed classical performance metrics into a Nash-product-based evaluation framework, which is theoretically shown to satisfy all axioms. To support empirical validation, we further construct benchmark problems that extend existing MPMOP suites by incorporating consensus-deficient negotiation structures. Experimental results demonstrate that the proposed evaluation framework is able to distinguish algorithmic performance in a manner consistent with consensus-aware fairness considerations. Specifically, algorithms converging toward strictly common solutions are assigned higher evaluation scores when such solutions exist, whereas in the absence of strictly common solutions, algorithms that effectively cover the commonly acceptable region are more favorably evaluated. --- ### Action-Sufficient Goal Representations Authors: Jinu Hyeon, Woobin Park, Hongjoon Ahn, Taesup Moon Published: 2026-01-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.22496v2 In offline goal-conditioned reinforcement learning (GCRL), hierarchical approaches decompose long-horizon tasks into high-level subgoal prediction and low-level action execution. A critical design choice in such architectures is the goal representation-the compressed encoding of goals that serves as the interface between these levels. Existing methods derive this representation from value learning, implicitly assuming that information sufficient for value estimation is adequate for optimal action prediction. We show that this assumption can fail even under exact value estimation, as such representations may collapse goals requiring distinct optimal actions. To address this, we introduce action sufficiency, an information-theoretic condition on goal representations necessary for optimal action prediction. We prove that value sufficiency, the preservation of sufficient information for value estimation, does not imply action sufficiency and empirically verify that the latter is more strongly associated with control success in a discrete environment. We further demonstrate that an actor-based representation, naturally induced by standard log-likelihood training of the low-level policy, is approximately action-sufficient. Empirically, our actor-based representations consistently outperform representations learned via value function estimation. --- ### Gradual Fine-Tuning for Flow Matching Models Authors: Gudrun Thorkelsdottir, Arindam Banerjee Published: 2026-01-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.22495v2 Fine-tuning flow matching models is a central challenge in settings with limited data, evolving distributions, or computational constraints. While recent work has produced significant advances, particularly in the area of reward-based fine-tuning, current methods fail to demonstrate both theoretical correctness as well as strong empirical results in terms of stability, efficiency, and diversity preservation. In this work, we propose Gradual Fine-Tuning (GFT), a simple yet principled annealing-based framework for fine-tuning flow generative models when only samples from the target distribution are available. For stochastic flows, GFT defines a temperature-controlled sequence of intermediate objectives that smoothly interpolate between the pretrained and target drifts, provably approaching the true target as the temperature approaches zero. We analytically demonstrate that sample generation after GFT can be made substantially more efficient with the use of arbitrary (e.g., optimal transport) couplings, as well as by utilizing few-step inference methods. Empirically, GFT significantly improves convergence stability, while maintaining or improving generation quality, training speed, and generation diversity compared to other fine-tuning methods. Our results position GFT as a simple yet theoretically grounded and practically effective alternative for scalable adaptation of flow matching models under distribution shift. --- ### PromptMAD: Cross-Modal Prompting for Multi-Class Visual Anomaly Localization Authors: Duncan McCain, Hossein Kashiani, Fatemeh Afghah Published: 2026-01-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.22492v1 Visual anomaly detection in multi-class settings poses significant challenges due to the diversity of object categories, the scarcity of anomalous examples, and the presence of camouflaged defects. In this paper, we propose PromptMAD, a cross-modal prompting framework for unsupervised visual anomaly detection and localization that integrates semantic guidance through vision-language alignment. By leveraging CLIP-encoded text prompts describing both normal and anomalous class-specific characteristics, our method enriches visual reconstruction with semantic context, improving the detection of subtle and textural anomalies. To further address the challenge of class imbalance at the pixel level, we incorporate Focal loss function, which emphasizes hard-to-detect anomalous regions during training. Our architecture also includes a supervised segmentor that fuses multi-scale convolutional features with Transformer-based spatial attention and diffusion iterative refinement, yielding precise and high-resolution anomaly maps. Extensive experiments on the MVTec-AD dataset demonstrate that our method achieves state-of-the-art pixel-level performance, improving mean AUC to 98.35% and AP to 66.54%, while maintaining efficiency across diverse categories. --- ### SSL: Sweet Spot Learning for Differentiated Guidance in Agentic Optimization Authors: Jinyang Wu, Changpeng Yang, Yuhao Shen, Fangzhi Xu, Bolin Ni, Chonghua Liao, Yuchen Liu, Hongzhen Wang, Shuai Nie, Shuai Zhang, Haoran Luo, Jiaming Xu Published: 2026-01-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.22491v1 Reinforcement learning with verifiable rewards has emerged as a powerful paradigm for training intelligent agents. However, existing methods typically employ binary rewards that fail to capture quality differences among trajectories achieving identical outcomes, thereby overlooking potential diversity within the solution space. Inspired by the ``sweet spot'' concept in tennis-the racket's core region that produces optimal hitting effects, we introduce \textbf{S}weet \textbf{S}pot \textbf{L}earning (\textbf{SSL}), a novel framework that provides differentiated guidance for agent optimization. SSL follows a simple yet effective principle: progressively amplified, tiered rewards guide policies toward the sweet-spot region of the solution space. This principle naturally adapts across diverse tasks: visual perception tasks leverage distance-tiered modeling to reward proximity, while complex reasoning tasks reward incremental progress toward promising solutions. We theoretically demonstrate that SSL preserves optimal solution ordering and enhances the gradient signal-to-noise ratio, thereby fostering more directed optimization. Extensive experiments across GUI perception, short/long-term planning, and complex reasoning tasks show consistent improvements over strong baselines on 12 benchmarks, achieving up to 2.5X sample efficiency gains and effective cross-task transferability. Our work establishes SSL as a general principle for training capable and robust agents. --- ### Elastic Spectral State Space Models for Train-Once Budgeted Inference Authors: Dachuan Song, Junyu Yin, Zechen Hu, Xuan Wang Published: 2026-01-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.22488v3 Modern sequence models are typically trained at a fixed computational capacity, while real-world applications require deployment across platforms with different resource constraints. Existing approaches either train or distill separate compact models for selected budgets, or use elastic architectures that shrink dimensions such as width, depth, Feed-Forward Network (FFN) size, or SSM state dimension. In this paper, we propose Elastic Spectral State Space Models (ES-SSM), a train-once, export-many sequence modeling framework that gains elasticity through spectral approximation of the SSM sequence operator. ES-SSM builds on Hankel spectral filtering for state space models, where long-range token mixing is represented through fixed Hankel spectral channels that define an operator-level approximation resolution. To make this spectral elasticity reliably deployable, ES-SSM combines input-adaptive channel-wise gates with budget dropout, training the same spectral prefixes that are used by compact models at inference time. This encourages low-index channels to become predictive on their own, while higher-index channels provide refinements for larger budgets. We evaluate ES-SSM across byte-level language modeling, Long Range Arena, Speech Commands V2, and offline reinforcement learning benchmarks. Across these settings, a single trained ES-SSM can be truncated to competitive compact models compared with modern Transformer and SSM baselines at similar parameter scales. Furthermore, by testing under various runtime budgets, we observe smooth and stable quality-cost curves over a wide range of truncation levels. --- ### AI Literacy, Safety Awareness, and STEM Career Aspirations of Australian Secondary Students: Evaluating the Impact of Workshop Interventions Authors: Christian Bergh, Alexandra Vassar, Natasha Banks, Jessica Xu, Jake Renzella Published: 2026-01-30 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2601.22486v1 Deepfakes and other forms of synthetic media pose growing safety risks for adolescents, yet evidence on students' exposure and related behaviours remains limited. This study evaluates the impact of Day of AI Australia's workshop-based intervention designed to improve AI literacy and conceptual understanding among Australian secondary students (Years 7-10). Using a mixed-methods approach with pre- and post-intervention surveys (N=205 pre; N=163 post), we analyse changes in students' ability to identify AI in everyday tools, their understanding of AI ethics, training, and safety, and their interest in STEM-related careers. Baseline data revealed notable synthetic media risks: 82.4% of students reported having seen deepfakes, 18.5% reported sharing them, and 7.3% reported creating them. Results show higher self-reported AI knowledge and confidence after the intervention, alongside improved recognition of AI in widely used platforms such as Netflix, Spotify, and TikTok. This pattern suggests a shift from seeing these tools as merely "algorithm-based" to recognising them as AI-driven systems. Students also reported increased interest in STEM careers post-workshop; however, effect sizes were small, indicating that sustained approaches beyond one-off workshops may be needed to influence longer-term aspirations. Overall, the findings support scalable AI literacy programs that pair foundational AI concepts with an explicit emphasis on synthetic media safety. --- ### FraudShield: Knowledge Graph Empowered Defense for LLMs against Fraud Attacks Authors: Naen Xu, Jinghuai Zhang, Ping He, Chunyi Zhou, Jun Wang, Zhihui Fu, Tianyu Du, Zhaoxiang Wang, Shouling Ji Published: 2026-01-30 Categories: cs.CR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2601.22485v1 Large language models (LLMs) have been widely integrated into critical automated workflows, including contract review and job application processes. However, LLMs are susceptible to manipulation by fraudulent information, which can lead to harmful outcomes. Although advanced defense methods have been developed to address this issue, they often exhibit limitations in effectiveness, interpretability, and generalizability, particularly when applied to LLM-based applications. To address these challenges, we introduce FraudShield, a novel framework designed to protect LLMs from fraudulent content by leveraging a comprehensive analysis of fraud tactics. Specifically, FraudShield constructs and refines a fraud tactic-keyword knowledge graph to capture high-confidence associations between suspicious text and fraud techniques. The structured knowledge graph augments the original input by highlighting keywords and providing supporting evidence, guiding the LLM toward more secure responses. Extensive experiments show that FraudShield consistently outperforms state-of-the-art defenses across four mainstream LLMs and five representative fraud types, while also offering interpretable clues for the model's generations. --- ### Mitigating Cognitive Inertia in Large Reasoning Models via Latent Spike Steering Authors: Seojin Lee, ByeongJeong Kim, Hwanhee Lee Published: 2026-01-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.22484v1 While Large Reasoning Models (LRMs) have achieved remarkable performance by scaling test-time compute, they frequently suffer from Cognitive Inertia, a failure pattern manifesting as either overthinking (inertia of motion) or reasoning rigidity (inertia of direction). Existing detection methods, typically relying on superficial textual heuristics like self-correction tokens, often fail to capture the model's unvoiced internal conflicts. To address this, we propose STARS (Spike-Triggered Adaptive Reasoning Steering), a training-free framework designed to rectify cognitive inertia by monitoring latent dynamics. STARS identifies Cognitive Pivots-critical moments of reasoning transition-by detecting distinct L2 distance spikes in the hidden states. Upon detection, the framework employs geometric trajectory analysis to diagnose the structural nature of the transition and injects state-aware language cues to steer the model in real-time. Our experiments across diverse benchmarks confirm that STARS efficiently curtails redundant loops while improving accuracy through the adaptive correction of erroneous trajectories. STARS offers a robust, unsupervised mechanism to optimize the reasoning process of LRMs without requiring additional fine-tuning. --- ### Head-Aware Visual Cropping: Enhancing Fine-Grained VQA with Attention-Guided Subimage Authors: Junfei Xie, Peng Pan, Xulong Zhang Published: 2026-01-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.22483v1 Multimodal Large Language Models (MLLMs) show strong performance in Visual Question Answering (VQA) but remain limited in fine-grained reasoning due to low-resolution inputs and noisy attention aggregation. We propose \textbf{Head Aware Visual Cropping (HAVC)}, a training-free method that improves visual grounding by leveraging a selectively refined subset of attention heads. HAVC first filters heads through an OCR-based diagnostic task, ensuring that only those with genuine grounding ability are retained. At inference, these heads are further refined using spatial entropy for stronger spatial concentration and gradient sensitivity for predictive contribution. The fused signals produce a reliable Visual Cropping Guidance Map, which highlights the most task-relevant region and guides the cropping of a subimage subsequently provided to the MLLM together with the image-question pair. Extensive experiments on multiple fine-grained VQA benchmarks demonstrate that HAVC consistently outperforms state-of-the-art cropping strategies, achieving more precise localization, stronger visual grounding, providing a simple yet effective strategy for enhancing precision in MLLMs. --- ### Changepoint Detection As Model Selection: A General Framework Authors: Michael Grantham, Xueheng Shi, Bertrand Clarke Published: 2026-01-30 Categories: stat.ME, stat.AP, stat.ML arXiv: https://arxiv.org/abs/2601.22481v2 This dissertation presents a general framework for changepoint detection based on L0 model selection. The core method, Iteratively Reweighted Fused Lasso (IRFL), improves upon the generalized lasso by adaptively reweighting penalties to enhance support recovery and minimize criteria such as the Bayesian Information Criterion (BIC). The approach allows for flexible modeling of seasonal patterns, linear and quadratic trends, and autoregressive dependence in the presence of changepoints. Simulation studies demonstrate that IRFL achieves accurate changepoint detection across a wide range of challenging scenarios, including those involving nuisance factors such as trends, seasonal patterns, and serially correlated errors. The framework is further extended to image data, where it enables edge-preserving denoising and segmentation, with applications spanning medical imaging and high-throughput plant phenotyping. Applications to real-world data demonstrate IRFL's utility. In particular, analysis of the Mauna Loa CO2 time series reveals changepoints that align with volcanic eruptions and ENSO events, yielding a more accurate trend decomposition than ordinary least squares. Overall, IRFL provides a robust, extensible tool for detecting structural change in complex data. --- ### Transformation-Augmented GRPO for Enhancing Exploration in Reasoning of Large Language Models Authors: Khiem Le, Phuc Nguyen, Youssef Mroueh, Chi-Heng Lin, Shangqian Gao, Ting Hua, Nitesh V. Chawla Published: 2026-01-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.22478v5 Group Relative Policy Optimization (GRPO) has become the dominant method for reinforcement learning with verifiable rewards in large language models, but it suffers from two critical limitations: gradient vanishing and diversity collapse. When training questions are too easy or too hard, all sampled responses receive identical rewards, yielding zero gradients. Meanwhile, the model tends to collapse its responses toward a single reasoning pattern rather than exploring diverse strategies. We propose Transformation-Augmented GRPO (TA-GRPO), a simple but effective method that addresses both issues via question rephrasing. For each training question, we automatically generate multiple problem-equivalent rephrasings that alter wording, format, and information order while preserving the underlying meaning. Because these rephrasings shift the model's perceived difficulty, pooling responses across the original and its rephrasings yields mixed rewards and more diverse reasoning paths. TA-GRPO jointly computes advantages over this expanded response set and aligns all importance ratios to the original question, enabling the model to learn from a richer set of solution attempts. Experiments on four LLMs (Qwen3-1.7B, Qwen3-4B, Llama-3.2-1B, Llama-3.2-3B) show that TA-GRPO consistently improves pass@$k$ on competition-level benchmarks (AMC, OlympiadBench, AIME24, AIME25) and out-of-distribution benchmarks (Minerva, GPQA-Diamond). Notably, it improves the average pass@32 of Qwen3-1.7B and Qwen3-4B by \textbf{4.97} and \textbf{4.34} points, respectively, and matches the exploration quality of baselines trained on up to 2.5$\times$ more data. ---