# Research Papers — 2026-01 · bundle page 13 of 189 > Full-text markdown of papers #601–650 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/13 [← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/12.md) [Next bundle →](https://aipod.dev/papers/archive/2026-01/page/14.md) ### ArabicDialectHub: A Cross-Dialectal Arabic Learning Resource and Platform Authors: Salem Lahlou Published: 2026-01-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.22987v1 We present ArabicDialectHub, a cross-dialectal Arabic learning resource comprising 552 phrases across six varieties (Moroccan Darija, Lebanese, Syrian, Emirati, Saudi, and MSA) and an interactive web platform. Phrases were generated using LLMs and validated by five native speakers, stratified by difficulty, and organized thematically. The open-source platform provides translation exploration, adaptive quizzing with algorithmic distractor generation, cloud-synchronized progress tracking, and cultural context. Both the dataset and complete platform source code are released under MIT license. Platform: https://arabic-dialect-hub.netlify.app. --- ### dgMARK: Decoding-Guided Watermarking for Diffusion Language Models Authors: Pyo Min Hong, Albert No Published: 2026-01-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.22985v2 We propose dgMARK, a decoding-guided watermarking method for discrete diffusion language models (dLLMs). Unlike autoregressive models, dLLMs can generate tokens in arbitrary order. While an ideal conditional predictor would be invariant to this order, practical dLLMs exhibit strong sensitivity to the unmasking order, creating a new channel for watermarking. dgMARK steers the unmasking order toward positions whose high-reward candidate tokens satisfy a simple parity constraint induced by a binary hash, without explicitly reweighting the model's learned probabilities. The method is plug-and-play with common decoding strategies (e.g., confidence, entropy, and margin-based ordering) and can be strengthened with a one-step lookahead variant. Watermarks are detected via elevated parity-matching statistics, and a sliding-window detector ensures robustness under post-editing operations including insertion, deletion, substitution, and paraphrasing. Project website: https://dgmark-watermarking.github.io --- ### Why Your Deep Research Agent Fails? On Hallucination Evaluation in Full Research Trajectory Authors: Yuhao Zhan, Tianyu Fan, Linxuan Huang, Zirui Guo, Chao Huang Published: 2026-01-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.22984v2 Diagnosing failure patterns in Deep Research Agents (DRAs) remains a critical challenge. Existing benchmarks predominantly rely on end-to-end evaluation, obscuring intermediate hallucinations that accumulate throughout the research trajectory. To bridge this gap, we propose a shift from outcome-based to processaware evaluation by auditing hallucinations in the full plan-search-summarize trajectory. We introduce the PING Taxonomy, which categorizes DRA hallucinations into four complementary types: Propagation, Intent, Noiseinduced, and Grounding. We further instantiate this taxonomy into a fine-grained evaluation framework that decomposes trajectories into atomic actions, claims, and sub-queries for rigorous verification. Leveraging this framework to isolate 100 distinctively hallucinationprone tasks including adversarial scenarios, we curate DeepHalluBench. Experiments on six representative DRAs show that, on our hallucination-prone stress-test set, all evaluated systems still exhibit non-negligible reliability gaps. Furthermore, our diagnostic analysis traces these failures to systemic deficits, especially hallucination propagation and cognitive biases, providing actionable insights for future architectural optimization. Code and data are available in https://github.com/yuhao-zhan/DeepHalluBench. --- ### PIDSMaker: Building and Evaluating Provenance-based Intrusion Detection Systems Authors: Tristan Bilot, Baoxiang Jiang, Thomas Pasquier Published: 2026-01-30 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2601.22983v2 Recent provenance-based intrusion detection systems (PIDSs) have demonstrated strong potential for detecting advanced persistent threats (APTs) by applying machine learning to system provenance graphs. However, evaluating and comparing PIDSs remains difficult: prior work uses inconsistent preprocessing pipelines, non-standard dataset splits, and incompatible ground-truth labeling and metrics. These discrepancies undermine reproducibility, impede fair comparison, and impose substantial re-implementation overhead on researchers. We present PIDSMaker, an open-source framework for developing and evaluating PIDSs under consistent protocols. PIDSMaker consolidates eight state-of-the-art systems into a modular, extensible architecture with standardized preprocessing and ground-truth labels, enabling consistent experiments and apples-to-apples comparisons. A YAML-based configuration interface supports rapid prototyping by composing components across systems without code changes. PIDSMaker also includes utilities for ablation studies, hyperparameter tuning, multi-run instability measurement, and visualization, addressing methodological gaps identified in prior work. We demonstrate PIDSMaker through concrete use cases and release it with preprocessed datasets and labels to support shared evaluation for the PIDS community. --- ### About an Automating Annotation Method for Robot Markers Authors: Wataru Uemura, Takeru Nagashima Published: 2026-01-30 Categories: cs.CV, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2601.22982v1 Factory automation has become increasingly important due to labor shortages, leading to the introduction of autonomous mobile robots for tasks such as material transportation. Markers are commonly used for robot self-localization and object identification. In the RoboCup Logistics League (RCLL), ArUco markers are employed both for robot localization and for identifying processing modules. Conventional recognition relies on OpenCV-based image processing, which detects black-and-white marker patterns. However, these methods often fail under noise, motion blur, defocus, or varying illumination conditions. Deep-learning-based recognition offers improved robustness under such conditions, but requires large amounts of annotated data. Annotation must typically be done manually, as the type and position of objects cannot be detected automatically, making dataset preparation a major bottleneck. In contrast, ArUco markers include built-in recognition modules that provide both ID and positional information, enabling automatic annotation. This paper proposes an automated annotation method for training deep-learning models on ArUco marker images. By leveraging marker detection results obtained from the ArUco module, the proposed approach eliminates the need for manual labeling. A YOLO-based model is trained using the automatically annotated dataset, and its performance is evaluated under various conditions. Experimental results demonstrate that the proposed method improves recognition performance compared with conventional image-processing techniques, particularly for images affected by blur or defocus. Automatic annotation also reduces human effort and ensures consistent labeling quality. Future work will investigate the relationship between confidence thresholds and recognition performance. --- ### Learnable Permutation for Structured Sparsity on Transformer Models Authors: Zekai Li, Ji Liu, Guanchen Li, Yixing Xu, Ziqiong Liu, Xuanwu Yin, Dong Li, Emad Barsoum Published: 2026-01-30 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2601.22980v1 Structured sparsity has emerged as a popular model pruning technique, widely adopted in various architectures, including CNNs, Transformer models, and especially large language models (LLMs) in recent years. A promising direction to further improve post-pruning performance is weight permutation, which reorders model weights into patterns more amenable to pruning. However, the exponential growth of the permutation search space with the scale of Transformer architectures forces most methods to rely on greedy or heuristic algorithms, limiting the effectiveness of reordering. In this work, we propose a novel end-to-end learnable permutation framework. Our method introduces a learnable permutation cost matrix to quantify the cost of swapping any two input channels of a given weight matrix, a differentiable bipartite matching solver to obtain the optimal binary permutation matrix given a cost matrix, and a sparsity optimization loss function to directly optimize the permutation operator. We extensively validate our approach on vision and language Transformers, demonstrating that our method achieves state-of-the-art permutation results for structured sparsity. --- ### Quantifying Model Uniqueness in Heterogeneous AI Ecosystems Authors: Lei You Published: 2026-01-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.22977v2 As AI systems evolve from isolated predictors into complex, heterogeneous ecosystems of foundation models and specialized adapters, distinguishing genuine behavioral novelty from functional redundancy becomes a critical governance challenge. Here, we introduce a statistical framework for auditing model uniqueness based on In-Silico Quasi-Experimental Design (ISQED). By enforcing matched interventions across models, we isolate intrinsic model identity and quantify uniqueness as the Peer-Inexpressible Residual (PIER), i.e. the component of a target's behavior strictly irreducible to any stochastic convex combination of its peers, with vanishing PIER characterizing when such a routing-based substitution becomes possible. We establish the theoretical foundations of ecosystem auditing through three key contributions. First, we prove a fundamental limitation of observational logs: uniqueness is mathematically non-identifiable without intervention control. Second, we derive a scaling law for active auditing, showing that our adaptive query protocol achieves minimax-optimal sample efficiency ($dσ^2γ^{-2}\log(Nd/δ)$). Third, we demonstrate that cooperative game-theoretic methods, such as Shapley values, fundamentally fail to detect redundancy. We implement this framework via the DISCO (Design-Integrated Synthetic Control) estimator and deploy it across diverse ecosystems, including computer vision models (ResNet/ConvNeXt/ViT), large language models (BERT/RoBERTa), and city-scale traffic forecasters. These results move trustworthy AI beyond explaining single models: they establish a principled, intervention-based science of auditing and governing heterogeneous model ecosystems. --- ### Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text Authors: Ximing Lu, David Acuna, Jaehun Jung, Jian Hu, Di Zhang, Shizhe Diao, Yunheng Zou, Shaokun Zhang, Brandon Cui, Mingjie Liu, Hyunwoo Kim, Prithviraj Ammanabrolu et al. Published: 2026-01-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.22975v2 Reinforcement Learning with Verifiable Rewards (RLVR) has become a cornerstone for unlocking complex reasoning in Large Language Models (LLMs). Yet, scaling up RL is bottlenecked by limited existing verifiable data, where improvements increasingly saturate over prolonged training. To overcome this, we propose Golden Goose, a simple trick to synthesize unlimited RLVR tasks from unverifiable internet text by constructing a multiple-choice question-answering version of the fill-in-the-middle task. Given a source text, we prompt an LLM to identify and mask key reasoning steps, then generate a set of diverse, plausible distractors. This enables us to leverage reasoning-rich unverifiable corpora typically excluded from prior RLVR data construction (e.g., science textbooks) to synthesize GooseReason-0.7M, a large-scale RLVR dataset with over 0.7 million tasks spanning mathematics, programming, and general scientific domains. Empirically, GooseReason effectively revives models saturated on existing RLVR data, yielding robust, sustained gains under continuous RL and achieving new state-of-the-art results for 1.5B and 4B-Instruct models across 15 diverse benchmarks. Finally, we deploy Golden Goose in a real-world setting, synthesizing RLVR tasks from raw FineWeb scrapes for the cybersecurity domain, where no prior RLVR data exists. Training Qwen3-4B-Instruct on the resulting data GooseReason-Cyber sets a new state-of-the-art in cybersecurity, surpassing a 7B domain-specialized model with extensive domain-specific pre-training and post-training. This highlights the potential of automatically scaling up RLVR data by exploiting abundant, reasoning-rich, unverifiable internet text. --- ### MiTa: A Hierarchical Multi-Agent Collaboration Framework with Memory-integrated and Task Allocation Authors: XiaoJie Zhang, JianHan Wu, Xiaoyang Qu, Jianzong Wang Published: 2026-01-30 Categories: cs.ET, cs.CL arXiv: https://arxiv.org/abs/2601.22974v1 Recent advances in large language models (LLMs) have substantially accelerated the development of embodied agents. LLM-based multi-agent systems mitigate the inefficiency of single agents in complex tasks. However, they still suffer from issues such as memory inconsistency and agent behavioral conflicts. To address these challenges, we propose MiTa, a hierarchical memory-integrated task allocative framework to enhance collaborative efficiency. MiTa organizes agents into a manager-member hierarchy, where the manager incorporates additional allocation and summary modules that enable (1) global task allocation and (2) episodic memory integration. The allocation module enables the manager to allocate tasks from a global perspective, thereby avoiding potential inter-agent conflicts. The summary module, triggered by task progress updates, performs episodic memory integration by condensing recent collaboration history into a concise summary that preserves long-horizon context. By combining task allocation with episodic memory, MiTa attains a clearer understanding of the task and facilitates globally consistent task distribution. Experimental results confirm that MiTa achieves superior efficiency and adaptability in complex multi-agent cooperation over strong baseline methods. --- ### Stabilizing the Q-Gradient Field for Policy Smoothness in Actor-Critic Methods Authors: Jeong Woon Lee, Kyoleen Kwak, Daeho Kim, Hyoseok Hwang Published: 2026-01-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.22970v2 Policies learned via continuous actor-critic methods often exhibit erratic, high-frequency oscillations, making them unsuitable for physical deployment. Current approaches attempt to enforce smoothness by directly regularizing the policy's output. We argue that this approach treats the symptom rather than the cause. In this work, we theoretically establish that policy non-smoothness is fundamentally governed by the differential geometry of the critic. By applying implicit differentiation to the actor-critic objective, we prove that the sensitivity of the optimal policy is bounded by the ratio of the Q-function's mixed-partial derivative (noise sensitivity) to its action-space curvature (signal distinctness). To empirically validate this theoretical insight, we introduce PAVE (Policy-Aware Value-field Equalization), a critic-centric regularization framework that treats the critic as a scalar field and stabilizes its induced action-gradient field. PAVE rectifies the learning signal by minimizing the Q-gradient volatility while preserving local curvature. Experimental results demonstrate that PAVE achieves smoothness comparable to policy-side smoothness regularization methods, while maintaining competitive task performance, without modifying the actor. --- ### Improved Algorithms for Nash Welfare in Linear Bandits Authors: Dhruv Sarkar, Nishant Pandey, Sayak Ray Chowdhury Published: 2026-01-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.22969v2 Nash regret has recently emerged as a principled fairness-aware performance metric for stochastic multi-armed bandits, motivated by the Nash Social Welfare objective. Although this notion has been extended to linear bandits, existing results suffer from suboptimality in ambient dimension $d$, stemming from proof techniques that rely on restrictive concentration inequalities. In this work, we resolve this open problem by introducing new analytical tools that yield an order-optimal Nash regret bound in linear bandits. Beyond Nash regret, we initiate the study of $p$-means regret in linear bandits, a unifying framework that interpolates between fairness and utility objectives and strictly generalizes Nash regret. We propose a generic algorithmic framework, FairLinBandit, that works as a meta-algorithm on top of any linear bandit strategy. We instantiate this framework using two bandit algorithms: Phased Elimination and Upper Confidence Bound, and prove that both achieve sublinear $p$-means regret for the entire range of $p$. Extensive experiments on linear bandit instances generated from real-world datasets demonstrate that our methods consistently outperform the existing state-of-the-art baseline. --- ### A Unified View of Attention and Residual Sinks: Outlier-Driven Rescaling is Essential for Transformer Training Authors: Zihan Qiu, Zeyu Huang, Kaiyue Wen, Peng Jin, Bo Zheng, Yuxin Zhou, Haofeng Huang, Zekun Wang, Xiao Li, Huaqing Zhang, Yang Xu, Haoran Lian et al. Published: 2026-01-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.22966v1 We investigate the functional role of emergent outliers in large language models, specifically attention sinks (a few tokens that consistently receive large attention logits) and residual sinks (a few fixed dimensions with persistently large activations across most tokens). We hypothesize that these outliers, in conjunction with the corresponding normalizations (\textit{e.g.}, softmax attention and RMSNorm), effectively rescale other non-outlier components. We term this phenomenon \textit{outlier-driven rescaling} and validate this hypothesis across different model architectures and training token counts. This view unifies the origin and mitigation of both sink types. Our main conclusions and observations include: (1) Outliers function jointly with normalization: removing normalization eliminates the corresponding outliers but degrades training stability and performance; directly clipping outliers while retaining normalization leads to degradation, indicating that outlier-driven rescaling contributes to training stability. (2) Outliers serve more as rescale factors rather than contributors, as the final contributions of attention and residual sinks are significantly smaller than those of non-outliers. (3) Outliers can be absorbed into learnable parameters or mitigated via explicit gated rescaling, leading to improved training performance (average gain of 2 points) and enhanced quantization robustness (1.2 points degradation under W4A4 quantization). --- ### EvoClinician: A Self-Evolving Agent for Multi-Turn Medical Diagnosis via Test-Time Evolutionary Learning Authors: Yufei He, Juncheng Liu, Zhiyuan Hu, Yulin Chen, Yue Liu, Yuan Sui, Yibo Li, Nuo Chen, Jun Hu, Bryan Hooi, Xinxing Xu, Jiang Bian Published: 2026-01-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.22964v1 Prevailing medical AI operates on an unrealistic ''one-shot'' model, diagnosing from a complete patient file. However, real-world diagnosis is an iterative inquiry where Clinicians sequentially ask questions and order tests to strategically gather information while managing cost and time. To address this, we first propose Med-Inquire, a new benchmark designed to evaluate an agent's ability to perform multi-turn diagnosis. Built upon a dataset of real-world clinical cases, Med-Inquire simulates the diagnostic process by hiding a complete patient file behind specialized Patient and Examination agents. They force the agent to proactively ask questions and order tests to gather information piece by piece. To tackle the challenges posed by Med-Inquire, we then introduce EvoClinician, a self-evolving agent that learns efficient diagnostic strategies at test time. Its core is a ''Diagnose-Grade-Evolve'' loop: an Actor agent attempts a diagnosis; a Process Grader agent performs credit assignment by evaluating each action for both clinical yield and resource efficiency; finally, an Evolver agent uses this feedback to update the Actor's strategy by evolving its prompt and memory. Our experiments show EvoClinician outperforms continual learning baselines and other self-evolving agents like memory agents. The code is available at https://github.com/yf-he/EvoClinician --- ### Improving Supervised Machine Learning Performance in Optical Quality Control via Generative AI for Dataset Expansion Authors: Dennis Sprute, Hanna Senke, Holger Flatt Published: 2026-01-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.22961v1 Supervised machine learning algorithms play a crucial role in optical quality control within industrial production. These approaches require representative datasets for effective model training. However, while non-defective components are frequent, defective parts are rare in production, resulting in highly imbalanced datasets that adversely impact model performance. Existing strategies to address this challenge, such as specialized loss functions or traditional data augmentation techniques, have limitations, including the need for careful hyperparameter tuning or the alteration of only simple image features. Therefore, this work explores the potential of generative artificial intelligence (GenAI) as an alternative method for expanding limited datasets and enhancing supervised machine learning performance. Specifically, we investigate Stable Diffusion and CycleGAN as image generation models, focusing on the segmentation of combine harvester components in thermal images for subsequent defect detection. Our results demonstrate that dataset expansion using Stable Diffusion yields the most significant improvement, enhancing segmentation performance by 4.6 %, resulting in a Mean Intersection over Union (Mean IoU) of 84.6 %. --- ### Triage: Hierarchical Visual Budgeting for Efficient Video Reasoning in Vision-Language Models Authors: Anmin Wang, Nan Zhang, Wei Tao, Xiaoyang Qu, Guokuan Li, Jiguang Wan, Jianzong Wang Published: 2026-01-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.22959v1 Vision-Language Models (VLMs) face significant computational challenges in video processing due to massive data redundancy, which creates prohibitively long token sequences. To address this, we introduce Triage, a training-free, plug-and-play framework that reframes video reasoning as a resource allocation problem via hierarchical visual budgeting. Its first stage, Frame-Level Budgeting, identifies keyframes by evaluating their visual dynamics and relevance, generating a strategic prior based on their importance scores. Guided by this prior, the second stage, Token-Level Budgeting, allocates tokens in two phases: it first secures high-relevance Core Tokens, followed by diverse Context Tokens selected with an efficient batched Maximal Marginal Relevance (MMR) algorithm. Extensive experiments demonstrate that Triage improves inference speed and reduces memory footprint, while maintaining or surpassing the performance of baselines and other methods on various video reasoning benchmarks. --- ### Residual Context Diffusion Language Models Authors: Yuezhou Hu, Harman Singh, Monishwaran Maheswaran, Haocheng Xi, Coleman Hooper, Jintao Zhang, Aditya Tomar, Michael W. Mahoney, Sewon Min, Mehrdad Farajtabar, Kurt Keutzer, Amir Gholami et al. Published: 2026-01-30 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.22954v2 Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to purely autoregressive language models because they can decode multiple tokens in parallel. However, state-of-the-art block-wise dLLMs rely on a "remasking" mechanism that decodes only the most confident tokens and discards the rest, effectively wasting computation. We demonstrate that recycling computation from the discarded tokens is beneficial, as these tokens retain contextual information useful for subsequent decoding iterations. In light of this, we propose Residual Context Diffusion (RCD), a module that converts these discarded token representations into contextual residuals and injects them back for the next denoising step. RCD uses a decoupled two-stage training pipeline to bypass the memory bottlenecks associated with backpropagation. We validate our method on both long CoT reasoning (SDAR) and short CoT instruction following (LLaDA) models. We demonstrate that a standard dLLM can be efficiently converted to the RCD paradigm with merely ~300 million tokens. RCD consistently improves frontier dLLMs by 4-11 percentage points in accuracy with minimal extra computation overhead across a wide range of benchmarks. Notably, on the most challenging AIME tasks, RCD nearly doubles baseline accuracy and attains up to 4-5x fewer denoising steps at baseline's peak accuracy. --- ### OneFlowSBI: One Model, Many Queries for Simulation-Based Inference Authors: Mayank Nautiyal, Li Ju, Melker Ernfors, Klara Hagland, Ville Holma, Maximilian Werkö Söderholm, Andreas Hellander, Prashant Singh Published: 2026-01-30 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2601.22951v1 We introduce \textit{OneFlowSBI}, a unified framework for simulation-based inference that learns a single flow-matching generative model over the joint distribution of parameters and observations. Leveraging a query-aware masking distribution during training, the same model supports multiple inference tasks, including posterior sampling, likelihood estimation, and arbitrary conditional distributions, without task-specific retraining. We evaluate \textit{OneFlowSBI} on ten benchmark inference problems and two high-dimensional real-world inverse problems across multiple simulation budgets. \textit{OneFlowSBI} is shown to deliver competitive performance against state-of-the-art generalized inference solvers and specialized posterior estimators, while enabling efficient sampling with few ODE integration steps and remaining robust under noisy and partially observed data. --- ### Perplexity Cannot Always Tell Right from Wrong Authors: Petar Veličković, Federico Barbero, Christos Perivolaropoulos, Simon Osindero, Razvan Pascanu Published: 2026-01-30 Categories: cs.LG, cs.AI, cs.CL, stat.ML arXiv: https://arxiv.org/abs/2601.22950v1 Perplexity -- a function measuring a model's overall level of "surprise" when encountering a particular output -- has gained significant traction in recent years, both as a loss function and as a simple-to-compute metric of model quality. Prior studies have pointed out several limitations of perplexity, often from an empirical manner. Here we leverage recent results on Transformer continuity to show in a rigorous manner how perplexity may be an unsuitable metric for model selection. Specifically, we prove that, if there is any sequence that a compact decoder-only Transformer model predicts accurately and confidently -- a necessary pre-requisite for strong generalisation -- it must imply existence of another sequence with very low perplexity, but not predicted correctly by that same model. Further, by analytically studying iso-perplexity plots, we find that perplexity will not always select for the more accurate model -- rather, any increase in model confidence must be accompanied by a commensurate rise in accuracy for the new model to be selected. --- ### Autonomous Chain-of-Thought Distillation for Graph-Based Fraud Detection Authors: Yuan Li, Jun Hu, Bryan Hooi, Bingsheng He, Cheng Chen Published: 2026-01-30 Categories: cs.CL, cs.CR arXiv: https://arxiv.org/abs/2601.22949v1 Graph-based fraud detection on text-attributed graphs (TAGs) requires jointly modeling rich textual semantics and relational dependencies. However, existing LLM-enhanced GNN approaches are constrained by predefined prompting and decoupled training pipelines, limiting reasoning autonomy and weakening semantic-structural alignment. We propose FraudCoT, a unified framework that advances TAG-based fraud detection through autonomous, graph-aware chain-of-thought (CoT) reasoning and scalable LLM-GNN co-training. To address the limitations of predefined prompts, we introduce a fraud-aware selective CoT distillation mechanism that generates diverse reasoning paths and enhances semantic-structural understanding. These distilled CoTs are integrated into node texts, providing GNNs with enriched, multi-hop semantic and structural cues for fraud detection. Furthermore, we develop an efficient asymmetric co-training strategy that enables end-to-end optimization while significantly reducing the computational cost of naive joint training. Extensive experiments on public and industrial benchmarks demonstrate that FraudCoT achieves up to 8.8% AUPRC improvement over state-of-the-art methods and delivers up to 1,066x speedup in training throughput, substantially advancing both detection performance and efficiency. --- ### Alignment among Language, Vision and Action Representations Authors: Nicola Milano, Stefano Nolfi Published: 2026-01-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.22948v1 A fundamental question in cognitive science and AI concerns whether different learning modalities: language, vision, and action, give rise to distinct or shared internal representations. Traditional views assume that models trained on different data types develop specialized, non-transferable representations. However, recent evidence suggests unexpected convergence: models optimized for distinct tasks may develop similar representational geometries. We investigate whether this convergence extends to embodied action learning by training a transformer-based agent to execute goal-directed behaviors in response to natural language instructions. Using behavioral cloning on the BabyAI platform, we generated action-grounded language embeddings shaped exclusively by sensorimotor control requirements. We then compared these representations with those extracted from state-of-the-art large language models (LLaMA, Qwen, DeepSeek, BERT) and vision-language models (CLIP, BLIP). Despite substantial differences in training data, modality, and objectives, we observed robust cross-modal alignment. Action representations aligned strongly with decoder-only language models and BLIP (precision@15: 0.70-0.73), approaching the alignment observed among language models themselves. Alignment with CLIP and BERT was significantly weaker. These findings indicate that linguistic, visual, and action representations converge toward partially shared semantic structures, supporting modality-independent semantic organization and highlighting potential for cross-domain transfer in embodied AI systems. --- ### Reconsidering Positional Supervision in Masked Diffusion Language Model Training Authors: Mengyu Ye, Keito Kudo, Ryosuke Takahashi, Jun Suzuki Published: 2026-01-30 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2601.22947v2 Masked diffusion language models (MDLMs) generate text by unmasking tokens in parallel and have recently emerged as alternatives to autoregressive language models. They can be viewed as parallel decoders trained with a position-wise cross-entropy (CE) loss, the same setup as non-autoregressive translation (NAT). In NAT, CE-trained parallel decoders have been argued to be sensitive to small positional shifts, since CE penalizes them harshly. We ask whether CE-trained MDLMs are similarly sensitive to such shifts under iterative decoding. To probe this, we apply a controlled intervention that introduces them during decoding. On LLaDA-8B-Instruct with Arena-Hard, displacing as little as 1% of generated tokens by one position substantially reduces win rates against the unintervened model, showing that MDLMs are sensitive to such small shifts under iterative parallel decoding. Motivated by this, we adapt connectionist temporal classification (CTC), an alignment-flexible objective known to mitigate it there, to MDLM supervised fine-tuning. By relaxing the strict position-wise match that CE imposes, CTC gives the loss room to absorb small positional shifts; concretely, we modified CTC objective to use a special <slack> token that absorbs positional uncertainty between target tokens and output positions, and a updated collapse map that preserves target surface forms. Across four open-ended generation benchmarks, the resulting model consistently improves over both the original model and a matched cross-entropy-trained baseline, with statistically significant gains on all four. These results identify training-side alignment flexibility as a useful design dimension for MDLM SFT, complementary to the inference-time approaches explored in prior work. --- ### From Data Leak to Secret Misses: The Impact of Data Leakage on Secret Detection Models Authors: Farnaz Soltaniani, Mohammad Ghafari Published: 2026-01-30 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.22946v1 Machine learning models are increasingly used for software security tasks. These models are commonly trained and evaluated on large Internet-derived datasets, which often contain duplicated or highly similar samples. When such samples are split across training and test sets, data leakage may occur, allowing models to memorize patterns instead of learning to generalize. We investigate duplication in a widely used benchmark dataset of hard coded secrets and show how data leakage can substantially inflate the reported performance of AI-based secret detectors, resulting in a misleading picture of their real-world effectiveness. --- ### Environment-Conditioned Tail Reweighting for Invariant Learning under Mixed Shifts Authors: Yuanchao Wang, Tianqi Zhong, Fengnan Li, Zhao-Rong Lai Published: 2026-01-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.22944v3 Out-of-distribution generalization becomes challenging when spurious correlations vary across environments while difficult or underrepresented samples remain insufficiently emphasized within them. Invariant learning and reweighting address complementary aspects of this mixed-shift problem, yet applying reweighting only to prediction leaves the invariance constraint evaluated on a different training risk. We introduce Environment-Conditioned Tail Reweighting (ECTR), which couples cross-environment TV invariance with within-environment adversarial tail weighting through a shared weighted risk. Sample weights are normalized within each environment, and the resulting risk is used consistently for both predictive learning and the total-variation (TV) stationarity penalty, while an environment-wise KL term controls adversarial concentration. Our analysis characterizes the stationarity-dependent weighting signal and its KL-regularized distributional interpretation, alongside conditional-risk and optimization properties under the stated assumptions. Controlled mixed-shift ablations consistently support the shared-risk coupling across three difficulty settings. Across synthetic and real-world benchmarks, ECTR achieves favorable results under both observed- and inferred-environment settings, including improvements over TV-based parent methods and strong performance against additional invariant-learning baselines. Training-corruption experiments further show that ECTR assigns less excess weight to corrupted samples than the tested fixed-tail rules. Together, these results provide a unified theoretical and empirical account of environment-conditioned tail reweighting for invariant learning under mixed shifts. --- ### Scalable Topology-Preserving Graph Coarsening: Concepts and Algorithms Authors: Xiang Wu, Rong-Hua Li, Xunkai Li, Kangfei Zhao, Hongchao Qin, Guoren Wang Published: 2026-01-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.22943v2 Graph coarsening reduces the size of a graph while preserving certain properties. Most existing methods preserve either spectral or spatial characteristics. Recent research shows that topology-preserving coarsening methods maintain GNN performance on coarsened graphs but suffer from exponential time complexity. To address these problems, we propose Scalable Topology-Preserving Graph Coarsening (STPGC) by introducing the concepts of graph strong collapse and graph edge collapse extended from algebraic topology. STPGC comprises three new algorithms, GStrongCollapse, GEdgeCollapse, and NeighborhoodConing based on these two concepts, which eliminate dominated nodes and edges while rigorously preserving topological features. We further prove that STPGC preserves the GNN receptive field and develop approximate algorithms to accelerate GNN training. Experiments on node classification with GNNs demonstrate the efficiency and effectiveness of STPGC. --- ### A Real-Time Privacy-Preserving Behavior Recognition System via Edge-Cloud Collaboration Authors: Huan Song, Shuyu Tian, Junyi Hao, Cheng Yuan, Zhenyu Jia, Jiawei Shao, Xuelong Li Published: 2026-01-30 Categories: cs.CR, cs.AI, eess.IV, eess.SP arXiv: https://arxiv.org/abs/2601.22938v1 As intelligent sensing expands into high-privacy environments such as restrooms and changing rooms, the field faces a critical privacy-security paradox. Traditional RGB surveillance raises significant concerns regarding visual recording and storage, while existing privacy-preserving methods-ranging from physical desensitization to traditional cryptographic or obfuscation techniques-often compromise semantic understanding capabilities or fail to guarantee mathematical irreversibility against reconstruction attacks. To address these challenges, this study presents a novel privacy-preserving perception technology based on the AI Flow theoretical framework and an edge-cloud collaborative architecture. The proposed methodology integrates source desensitization with irreversible feature mapping. Leveraging Information Bottleneck theory, the edge device performs millisecond-level processing to transform raw imagery into abstract feature vectors via non-linear mapping and stochastic noise injection. This process constructs a unidirectional information flow that strips identity-sensitive attributes, rendering the reconstruction of original images impossible. Subsequently, the cloud platform utilizes multimodal family models to perform joint inference solely on these abstract vectors to detect abnormal behaviors. This approach fundamentally severs the path to privacy leakage at the architectural level, achieving a breakthrough from video surveillance to de-identified behavior perception and offering a robust solution for risk management in high-sensitivity public spaces. --- ### Protecting Private Code in IDE Autocomplete using Differential Privacy Authors: Evgeny Grigorenko, David Stanojević, David Ilić, Egor Bogomolov, Kostadin Cvejoski Published: 2026-01-30 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2601.22935v1 Modern Integrated Development Environments (IDEs) increasingly leverage Large Language Models (LLMs) to provide advanced features like code autocomplete. While powerful, training these models on user-written code introduces significant privacy risks, making the models themselves a new type of data vulnerability. Malicious actors can exploit this by launching attacks to reconstruct sensitive training data or infer whether a specific code snippet was used for training. This paper investigates the use of Differential Privacy (DP) as a robust defense mechanism for training an LLM for Kotlin code completion. We fine-tune a \texttt{Mellum} model using DP and conduct a comprehensive evaluation of its privacy and utility. Our results demonstrate that DP provides a strong defense against Membership Inference Attacks (MIAs), reducing the attack's success rate close to a random guess (AUC from 0.901 to 0.606). Furthermore, we show that this privacy guarantee comes at a minimal cost to model performance, with the DP-trained model achieving utility scores comparable to its non-private counterpart, even when trained on 100x less data. Our findings suggest that DP is a practical and effective solution for building private and trustworthy AI-powered IDE features. --- ### DC-LA: Difference-of-Convex Langevin Algorithm Authors: Hoang Phuc Hau Luu, Zhongjian Wang Published: 2026-01-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.22932v2 We study a sampling problem whose target distribution is $π\propto \exp(-f-r)$ where the data fidelity term $f$ is Lipschitz smooth while the regularizer term $r=r_1-r_2$ is a non-smooth difference-of-convex (DC) function, i.e., $r_1,r_2$ are convex. By leveraging the DC structure of $r$, we can smooth out $r$ by applying Moreau envelopes to $r_1$ and $r_2$ separately. In line with DC programming, we then redistribute the concave part of the regularizer to the data fidelity and study its corresponding proximal Langevin algorithm (termed DC-LA). We establish convergence of DC-LA to the target distribution $π$, up to discretization and smoothing errors, in the $q$-Wasserstein distance for all $q \in \mathbb{N}^*$, under the assumption that $V$ is distant dissipative. Our results improve previous work on non-log-concave sampling in terms of a more general framework and assumptions. Numerical experiments show that DC-LA produces accurate distributions in synthetic settings and provides qualitatively reasonable uncertainty quantification in a real-world Computed Tomography application. --- ### Benchmarking Machine Translation on Chinese Social Media Texts Authors: Kaiyan Zhao, Zheyong Xie, Zhongtao Miao, Xinze Lyu, Yao Hu, Shaosheng Cao Published: 2026-01-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.22931v2 The prevalence of rapidly evolving slang, neologisms, and highly stylized expressions in informal user-generated text, particularly on Chinese social media, poses significant challenges for Machine Translation (MT) benchmarking. Specifically, we identify two primary obstacles: (1) data scarcity, as high-quality parallel data requires bilingual annotators familiar with platform-specific slang, and stylistic cues in both languages; and (2) metric limitations, where traditional evaluators like COMET often fail to capture stylistic fidelity and nonstandard expressions. To bridge these gaps, we introduce CSM-MTBench, a benchmark covering five Chinese-foreign language directions and consisting of two expert-curated subsets: Fun Posts, featuring context-rich, slang- and neologism-heavy content, and Social Snippets, emphasizing concise, emotion- and style- driven expressions. Furthermore, we propose tailored evaluation approaches for each subset: measuring the translation success rate of slang and neologisms in Fun Posts, while assessing tone and style preservation in Social Snippets via a hybrid of embedding-based metrics and LLM-as-a-judge. Experiments on over 20 models reveal substantial variation in how current MT systems handle semantic fidelity and informal, social-media-specific stylistic cues. CSM-MTBench thus serves as a rigorous testbed for advancing MT systems capable of mastering real-world Chinese social media texts. --- ### MTDrive: Multi-turn Interactive Reinforcement Learning for Autonomous Driving Authors: Xidong Li, Mingyu Guo, Chenchao Xu, Bailin Li, Wenjing Zhu, Yangang Zou, Rui Chen, Zehuan Wang Published: 2026-01-30 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.22930v1 Trajectory planning is a core task in autonomous driving, requiring the prediction of safe and comfortable paths across diverse scenarios. Integrating Multi-modal Large Language Models (MLLMs) with Reinforcement Learning (RL) has shown promise in addressing "long-tail" scenarios. However, existing methods are constrained to single-turn reasoning, limiting their ability to handle complex tasks requiring iterative refinement. To overcome this limitation, we present MTDrive, a multi-turn framework that enables MLLMs to iteratively refine trajectories based on environmental feedback. MTDrive introduces Multi-Turn Group Relative Policy Optimization (mtGRPO), which mitigates reward sparsity by computing relative advantages across turns. We further construct an interactive trajectory understanding dataset from closed-loop simulation to support multi-turn training. Experiments on the NAVSIM benchmark demonstrate superior performance compared to existing methods, validating the effectiveness of our multi-turn reasoning paradigm. Additionally, we implement system-level optimizations to reduce data transfer overhead caused by high-resolution images and multi-turn sequences, achieving 2.5x training throughput. Our data, models, and code will be made available soon. --- ### Semantic Leakage from Image Embeddings Authors: Yiyi Chen, Qiongkai Xu, Desmond Elliott, Qiongxiu Li, Johannes Bjerva Published: 2026-01-30 Categories: cs.CV, cs.CL, cs.CR arXiv: https://arxiv.org/abs/2601.22929v2 Image embeddings are generally assumed to pose limited privacy risk. We challenge this assumption by formalizing semantic leakage as the ability to recover semantic structures from compressed image embeddings. Surprisingly, we show that semantic leakage does not require exact reconstruction of the original image. Preserving local semantic neighborhoods under embedding alignment is sufficient to expose the intrinsic vulnerability of image embeddings. Crucially, this preserved neighborhood structure allows semantic information to propagate through a sequence of lossy mappings. Based on this conjecture, we propose Semantic Leakage from Image Embeddings (SLImE), a lightweight inference framework that reveals semantic information from standalone compressed image embeddings, incorporating a locally trained semantic retriever with off-the-shelf models, without training task-specific decoders. We thoroughly validate each step of the framework empirically, from aligned embeddings to retrieved tags, symbolic representations, and grammatical and coherent descriptions. We evaluate SLImE across a range of open and closed embedding models, including GEMINI, COHERE, NOMIC, and CLIP, and demonstrate consistent recovery of semantic information across diverse inference tasks. Our results reveal a fundamental vulnerability in image embeddings, whereby the preservation of semantic neighborhoods under alignment enables semantic leakage, highlighting challenges for privacy preservation.1 --- ### LLMs Explain't: A Post-Mortem on Semantic Interpretability in Transformer Models Authors: Alhassan Abdelhalim, Janick Edinger, Sören Laue, Michaela Regneri Published: 2026-01-30 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2601.22928v1 Large Language Models (LLMs) are becoming increasingly popular in pervasive computing due to their versatility and strong performance. However, despite their ubiquitous use, the exact mechanisms underlying their outstanding performance remain unclear. Different methods for LLM explainability exist, and many are, as a method, not fully understood themselves. We started with the question of how linguistic abstraction emerges in LLMs, aiming to detect it across different LLM modules (attention heads and input embeddings). For this, we used methods well-established in the literature: (1) probing for token-level relational structures, and (2) feature-mapping using embeddings as carriers of human-interpretable properties. Both attempts failed for different methodological reasons: Attention-based explanations collapsed once we tested the core assumption that later-layer representations still correspond to tokens. Property-inference methods applied to embeddings also failed because their high predictive scores were driven by methodological artifacts and dataset structure rather than meaningful semantic knowledge. These failures matter because both techniques are widely treated as evidence for what LLMs supposedly understand, yet our results show such conclusions are unwarranted. These limitations are particularly relevant in pervasive and distributed computing settings where LLMs are deployed as system components and interpretability methods are relied upon for debugging, compression, and explaining models. --- ### BEAR: Towards Beam-Search-Aware Optimization for Recommendation with Large Language Models Authors: Weiqin Yang, Bohao Wang, Zhenxiang Xu, Jiawei Chen, Shengjia Zhang, Jingbang Chen, Canghong Jin, Can Wang Published: 2026-01-30 Categories: cs.IR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.22925v3 Recent years have seen a rapid surge in research leveraging Large Language Models (LLMs) for recommendation. These methods typically employ supervised fine-tuning (SFT) to adapt LLMs to recommendation scenarios, and utilize beam search during inference to efficiently retrieve $B$ top-ranked recommended items. However, we identify a critical training-inference inconsistency: while SFT optimizes the overall probability of positive items, it does not guarantee that such items will be retrieved by beam search even if they possess high overall probabilities. Due to the greedy pruning mechanism, beam search can prematurely discard a positive item once its prefix probability is insufficient. To address this inconsistency, we propose BEAR (Beam-SEarch-Aware Regularization), a novel fine-tuning objective that explicitly accounts for beam search behavior during training. Rather than directly simulating beam search for each instance during training, which is computationally prohibitive, BEAR enforces a relaxed necessary condition: each token in a positive item must rank within the top-$B$ candidate tokens at each decoding step. This objective effectively mitigates the risk of incorrect pruning while incurring negligible computational overhead compared to standard SFT. Extensive experiments across four real-world datasets demonstrate that BEAR significantly outperforms strong baselines. Code is available at https://github.com/Tiny-Snow/BEAR-SIGIR-2026 . --- ### Evaluating Large Language Models for Security Bug Report Prediction Authors: Farnaz Soltaniani, Shoaib Razzaq, Mohammad Ghafari Published: 2026-01-30 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.22921v1 Early detection of security bug reports (SBRs) is critical for timely vulnerability mitigation. We present an evaluation of prompt-based engineering and fine-tuning approaches for predicting SBRs using Large Language Models (LLMs). Our findings reveal a distinct trade-off between the two approaches. Prompted proprietary models demonstrate the highest sensitivity to SBRs, achieving a G-measure of 77% and a recall of 74% on average across all the datasets, albeit at the cost of a higher false-positive rate, resulting in an average precision of only 22%. Fine-tuned models, by contrast, exhibit the opposite behavior, attaining a lower overall G-measure of 51% but substantially higher precision of 75% at the cost of reduced recall of 36%. Though a one-time investment in building fine-tuned models is necessary, the inference on the largest dataset is up to 50 times faster than that of proprietary models. These findings suggest that further investigations to harness the power of LLMs for SBR prediction are necessary. --- ### Q-Hawkeye: Reliable Visual Policy Optimization for Image Quality Assessment Authors: Wulin Xie, Rui Dai, Ruidong Ding, Kaikui Liu, Xiangxiang Chu, Xinwen Hou, Jie Wen Published: 2026-01-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.22920v3 Image Quality Assessment (IQA) predicts perceptual quality scores consistent with human judgments. Recent RL-based IQA methods built on MLLMs focus on generating visual quality descriptions and scores, ignoring two key reliability limitations: (i) although the model's prediction stability varies significantly across training samples, existing GRPO-based methods apply uniform advantage weighting, thereby amplifying noisy signals from unstable samples in gradient updates; (ii) most works emphasize text-grounded reasoning over images while overlooking the model's visual perception ability of image content. In this paper, we propose Q-Hawkeye, an RL-based reliable visual policy optimization framework that redesigns the learning signal through unified Uncertainty-Aware Dynamic Optimization and Perception-Aware Optimization. Q-Hawkeye estimates predictive uncertainty using the variance of predicted scores across multiple rollouts and leverages this uncertainty to reweight each sample's update strength, stabilizing policy optimization. To strengthen perceptual reliability, we construct paired inputs of degraded images and their original images and introduce an Implicit Perception Loss that constrains the model to ground its quality judgments in genuine visual evidence. Extensive experiments demonstrate that Q-Hawkeye outperforms state-of-the-art methods and generalizes better across multiple datasets. Our dataset and code are available at https://github.com/AMAP-ML/Q-Hawkeye. --- ### Deep in the Jungle: Towards Automating Chimpanzee Population Estimation Authors: Tom Raynes, Otto Brookes, Timm Haucke, Lukas Bösch, Anne-Sophie Crunchant, Hjalmar Kühl, Sara Beery, Majid Mirmehdi, Tilo Burghardt Published: 2026-01-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.22917v1 The estimation of abundance and density in unmarked populations of great apes relies on statistical frameworks that require animal-to-camera distance measurements. In practice, acquiring these distances depends on labour-intensive manual interpretation of animal observations across large camera trap video corpora. This study introduces and evaluates an only sparsely explored alternative: the integration of computer vision-based monocular depth estimation (MDE) pipelines directly into ecological camera trap workflows for great ape conservation. Using a real-world dataset of 220 camera trap videos documenting a wild chimpanzee population, we combine two MDE models, Dense Prediction Transformers and Depth Anything, with multiple distance sampling strategies. These components are used to generate detection distance estimates, from which population density and abundance are inferred. Comparative analysis against manually derived ground-truth distances shows that calibrated DPT consistently outperforms Depth Anything. This advantage is observed in both distance estimation accuracy and downstream density and abundance inference. Nevertheless, both models exhibit systematic biases. We show that, given complex forest environments, they tend to overestimate detection distances and consequently underestimate density and abundance relative to conventional manual approaches. We further find that failures in animal detection across distance ranges are a primary factor limiting estimation accuracy. Overall, this work provides a case study that shows MDE-driven camera trap distance sampling is a viable and practical alternative to manual distance estimation. The proposed approach yields population estimates within 22% of those obtained using traditional methods. --- ### Multi-Cue Anomaly Detection and Localization under Data Contamination Authors: Anindya Sundar Das, Monowar Bhuyan Published: 2026-01-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.22913v2 Visual anomaly detection in real-world industrial settings faces two major limitations. First, most existing methods are trained on purely normal data or on unlabeled datasets assumed to be predominantly normal, presuming the absence of contamination, an assumption that is rarely satisfied in practice. Second, they assume no access to labeled anomaly samples, limiting the model from learning discriminative characteristics of true anomalies. Therefore, these approaches often struggle to distinguish anomalies from normal instances, resulting in reduced detection and weak localization performance. In real-world applications, where training data are frequently contaminated with anomalies, such methods fail to deliver reliable performance. In this work, we propose a robust anomaly detection framework that integrates limited anomaly supervision into the adaptive deviation learning paradigm. We introduce a composite anomaly score that combines three complementary components: a deviation score capturing statistical irregularity, an entropy-based uncertainty score reflecting predictive inconsistency, and a segmentation-based score highlighting spatial abnormality. This unified scoring mechanism enables accurate detection and supports gradient-based localization, providing intuitive and explainable visual evidence of anomalous regions. Following the few-anomaly paradigm, we incorporate a small set of labeled anomalies during training while simultaneously mitigating the influence of contaminated samples through adaptive instance weighting. Extensive experiments on the MVTec and VisA benchmarks demonstrate that our framework outperforms state-of-the-art baselines and achieves strong detection and localization performance, interpretability, and robustness under various levels of data contamination. --- ### FlexLoRA: Entropy-Guided Flexible Low-Rank Adaptation Authors: Muqing Liu, Chongjie Si, Yuheng Jia Published: 2026-01-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.22905v1 Large pre-trained models achieve remarkable success across diverse domains, yet fully fine-tuning incurs prohibitive computational and memory costs. Parameter-efficient fine-tuning (PEFT) has thus become a mainstream paradigm. Among them, Low-Rank Adaptation (LoRA) introduces trainable low-rank matrices and shows strong performance, nevertheless, its fixed-rank design limits flexibility. Dynamic rank allocation methods mitigate this issue by pruning redundant directions; however, they often rely on heuristic, element-level metrics that globally sort rank directions without matrix-wise distinction, and they lack mechanisms to expand capacity in layers requiring additional adaptation. To overcome these limitations, we propose FlexLoRA, an entropy-guided flexible low-rank adaptation framework that (i) evaluates matrix importance via spectral energy entropy, (ii) supports rank pruning and expansion under a global budget, and (iii) employs zero-impact initialization for newly added singular directions to ensure stability. By addressing granularity, flexibility, and stability limitations, FlexLoRA provides a more principled solution for PEFT. Extensive experiments show that FlexLoRA consistently outperforms state-of-the-art baselines across benchmarks. Codes are available at https://github.com/Chongjie-Si/Subspace-Tuning. --- ### Hyperspherical Autoencoder for High-Fidelity Image Reconstruction and Generation Authors: Hun Chang, Byunghee Cha, Jong Chul Ye Published: 2026-01-30 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.22904v2 Recent studies have explored using pretrained Vision Foundation Models (VFMs) such as DINO for generative autoencoders, showing strong generative performance. Unfortunately, existing approaches often suffer from limited reconstruction fidelity due to the loss of high-frequency details. In this work, we present the \textbf{\em Hyperspherical Autoencoder (HAE)}, a framework that bridges semantic representation and pixel-level reconstruction. Our key insight is that while semantic information in contrastive representations is primarily directional, enforcing strict magnitude matching hinders the preservation of fine-grained details. To address this, we introduce a {\em Directional Feature Alignment} objective that enforces semantic consistency while allowing flexible feature magnitudes for detail retention, alongside a {\em Hierarchical Convolutional Patch Embedding} module to enhance local structure preservation. Furthermore, observing that SSL-based representations intrinsically lie on a hypersphere, we employ {\em Riemannian Flow Matching} to train a Diffusion Transformer (DiT) directly on this spherical latent manifold. Notably, our manifold-aware DiT exhibits highly efficient convergence, achieving an exceptional gFID of \textbf{1.96} alongside a reconstruction rFID of \textbf{0.78} and a PSNR of \textbf{25.2} dB, validating the advantages of our manifold-aware approach. --- ### MulFeRL: Enhancing Reinforcement Learning with Verbal Feedback in a Multi-turn Loop Authors: Xuancheng Li, Haitao Li, Yujia Zhou, YiqunLiu, Qingyao Ai Published: 2026-01-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.22900v2 Reinforcement Learning with Verifiable Rewards (RLVR) is widely used to improve reasoning across domains, but outcome-only scalar rewards are often sparse and uninformative. This limitation is especially severe for failed samples, where scalar rewards indicate only that a solution is incorrect without explaining why the reasoning breaks down. In this paper, we leverage richer verbal feedback to guide RLVR on failed samples and convert feedback-induced progress into trainable learning signals. We propose MulFeRL (Multi-turn Feedback-guided Reinforcement Learning), a multi-turn, event-triggered RLVR framework that combines progress induction for feedback-guided regeneration of failed samples, progress credit assignment for learning from verifier-confirmed progress, and structured feedback injection for integrating feedback into the model's reasoning process. Trained on sampled OpenR1-Math, MulFeRL outperforms supervised, self-distillation-based, and RLVR baselines in-domain, while also showing strong out-of-domain generalization. --- ### Uncertainty-Aware Extrapolation in Bayesian Oblique Trees Authors: Viktor Andonovikj, Sašo Džeroski, Pavle Boškoski Published: 2026-01-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.22899v1 Decision trees are widely used due to their interpretability and efficiency, but they struggle in regression tasks that require reliable extrapolation and well-calibrated uncertainty. Piecewise-constant leaf predictions are bounded by the training targets and often become overconfident under distribution shift. We propose a single-tree Bayesian model that extends VSPYCT by equipping each leaf with a GP predictor. Bayesian oblique splits provide uncertainty-aware partitioning of the input space, while GP leaves model local functional behaviour and enable principled extrapolation beyond the observed target range. We present an efficient inference and prediction scheme that combines posterior sampling of split parameters with \gls{gp} posterior predictions, and a gating mechanism that activates GP-based extrapolation when inputs fall outside the training support of a leaf. Experiments on benchmark regression tasks show improvements in the predictive performance compared to standard variational oblique trees, and substantial performance gains in extrapolation scenarios. --- ### Game-Theoretic Co-Evolution for LLM-Based Heuristic Discovery Authors: Xinyi Ke, Kai Li, Junliang Xing, Yifan Zhang, Jian Cheng Published: 2026-01-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.22896v2 Large language models (LLMs) have enabled rapid progress in automatic heuristic discovery (AHD), yet most existing methods are predominantly limited by static evaluation against fixed instance distributions, leading to potential overfitting and poor generalization under distributional shifts. We propose Algorithm Space Response Oracles (ASRO), a game-theoretic framework that reframes heuristic discovery as a program level co-evolution between solver and instance generator. ASRO models their interaction as a two-player zero-sum game, maintains growing strategy pools on both sides, and iteratively expands them via LLM-based best-response oracles against mixed opponent meta-strategies, thereby replacing static evaluation with an adaptive, self-generated curriculum. Across multiple combinatorial optimization domains, ASRO consistently outperforms static-training AHD baselines built on the same program search mechanisms, achieving substantially improved generalization and robustness on diverse and out-of-distribution instances. --- ### Calibrated Multivariate Distributional Regression with Pre-Rank Regularization Authors: Aya Laajil, Elnura Zhalieva, Naomi Desobry, Souhaib Ben Taieb Published: 2026-01-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.22895v1 The goal of probabilistic prediction is to issue predictive distributions that are as informative as possible, subject to being calibrated. Despite substantial progress in the univariate setting, achieving multivariate calibration remains challenging. Recent work has introduced pre-rank functions, scalar projections of multivariate forecasts and observations, as flexible diagnostics for assessing specific aspects of multivariate calibration, but their use has largely been limited to post-hoc evaluation. We propose a regularization-based calibration method that enforces multivariate calibration during training of multivariate distributional regression models using pre-rank functions. We further introduce a novel PCA-based pre-rank that projects predictions onto principal directions of the predictive distribution. Through simulation studies and experiments on 18 real-world multi-output regression datasets, we show that the proposed approach substantially improves multivariate pre-rank calibration without compromising predictive accuracy, and that the PCA pre-rank reveals dependence-structure misspecifications that are not detected by existing pre-ranks. --- ### PlatoLTL: Learning to Generalize Across Symbols in LTL Instructions for Multi-Task RL Authors: Jacques Cloete, Mathias Jackermeier, Ioannis Havoutis, Alessandro Abate Published: 2026-01-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.22891v2 A central challenge in multi-task reinforcement learning (RL) is to train generalist policies capable of performing tasks not seen during training. To facilitate such generalization, linear temporal logic (LTL) has emerged as a powerful formalism for specifying structured, temporally extended tasks to RL agents. While existing approaches to LTL-guided multi-task RL demonstrate generalization across LTL specifications, they are unable to generalize to unseen vocabularies of propositions (or "symbols"), which describe high-level events in LTL. We present PlatoLTL, a novel approach that enables policies to zero-shot generalize not only compositionally across LTL structures, but also parametrically across propositions. We model propositions as parameterized instances of atomic predicates, allowing policies to learn shared structure across related propositions. We propose a novel architecture that embeds and composes parameterized propositions to represent LTL formulae, and demonstrate zero-shot generalization in a range of challenging environments. --- ### DiffuSpeech: Silent Thought, Spoken Answer via Unified Speech-Text Diffusion Authors: Yuxuan Lou, Ziming Wu, Yaochen Wang, Yong Liu, Yingxuan Ren, Fuming Lai, Shaobing Lian, Jie Tang, Yang You Published: 2026-01-30 Categories: cs.CL, cs.AI, cs.LG, cs.SD arXiv: https://arxiv.org/abs/2601.22889v1 Current speech language models generate responses directly without explicit reasoning, leading to errors that cannot be corrected once audio is produced. We introduce \textbf{``Silent Thought, Spoken Answer''} -- a paradigm where speech LLMs generate internal text reasoning alongside spoken responses, with thinking traces informing speech quality. To realize this, we present \method{}, the first diffusion-based speech-text language model supporting both understanding and generation, unifying discrete text and tokenized speech under a single masked diffusion framework. Unlike autoregressive approaches, \method{} jointly generates reasoning traces and speech tokens through iterative denoising, with modality-specific masking schedules. We also construct \dataset{}, the first speech QA dataset with paired text reasoning traces, containing 26K samples totaling 319 hours. Experiments show \method{} achieves state-of-the-art speech-to-speech QA accuracy, outperforming the best baseline by up to 9 points, while attaining the best TTS quality among generative models (6.2\% WER) and preserving language understanding (66.2\% MMLU). Ablations confirm that both the diffusion architecture and thinking traces contribute to these gains. --- ### DialectLLM: A Dialect-Aware Dialog(ue) Generation Framework Beyond Standard American English Authors: Jio Oh, Paul Vicinanza, Thomas Butler, Steven Euijong Whang, Dezhi Hong, Amani Namboori Published: 2026-01-30 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.22888v4 More than 80% of the 1.6B English speakers do not use Standard American English (SAE), yet LLMs often fail to correctly identify non-SAE dialects and generate stereotyped responses for their speakers. We introduce DialectLLM, the first large-scale framework for generating high-quality multi-dialectal conversational data encompassing the three pillars of written dialect -- lexical (vocabulary), orthographic (spelling), and morphosyntactic (grammar) features. DialectLLM produces a dialect-parallel dialog dataset spanning nine English dialects. Partnering with native linguists, we design and validate SAE-to-dialect transformation rules, ensuring authenticity. Our approach challenges the prevailing practice of applying a single morphosyntactic feature set to both user utterances and model responses, showing that models should not reproduce up to 90% of the grammatical features of a dialect. Human evaluation confirms data quality, with annotators preferring DialectLLM over prior methods in 98.8% of pairwise comparisons for dialect naturalness. We then construct DialectLLM-Bench, a dialect-parallel benchmark with 50k+ dialogs, resulting in 97k+ QA pairs, and evaluate 17 LLMs on dialect identification and response generation tasks. Even frontier models achieve under 70% accuracy, fail to reach 50% for prominent dialects like Canadian English, and systematically misclassify non-SAE dialects as American or British. Beyond benchmarking, we show that DialectLLM data also serve as a scalable LLM post-training resource, suggesting a practical path toward dialect-aware conversational AI. --- ### MoVE: Mixture of Value Embeddings -- A New Axis for Scaling Parametric Memory in Autoregressive Models Authors: Yangyan Li Published: 2026-01-30 Categories: cs.LG, cs.AI, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2601.22887v1 Autoregressive sequence modeling stands as the cornerstone of modern Generative AI, powering results across diverse modalities ranging from text generation to image generation. However, a fundamental limitation of this paradigm is the rigid structural coupling of model capacity to computational cost: expanding a model's parametric memory -- its repository of factual knowledge or visual patterns -- traditionally requires deepening or widening the network, which incurs a proportional rise in active FLOPs. In this work, we introduce $\textbf{MoVE (Mixture of Value Embeddings)}$, a mechanism that breaks this coupling and establishes a new axis for scaling capacity. MoVE decouples memory from compute by introducing a global bank of learnable value embeddings shared across all attention layers. For every step in the sequence, the model employs a differentiable soft gating mechanism to dynamically mix retrieved concepts from this bank into the standard value projection. This architecture allows parametric memory to be scaled independently of network depth by simply increasing the number of embedding slots. We validate MoVE through strictly controlled experiments on two representative applications of autoregressive modeling: Text Generation and Image Generation. In both domains, MoVE yields consistent performance improvements over standard and layer-wise memory baselines, enabling the construction of "memory-dense" models that achieve lower perplexity and higher fidelity than their dense counterparts at comparable compute budgets. --- ### Leveraging LLMs For Turkish Skill Extraction Authors: Ezgi Arslan İltüzer, Özgür Anıl Özlü, Vahid Farajijobehdar, Gülşen Eryiğit Published: 2026-01-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.22885v1 Skill extraction is a critical component of modern recruitment systems, enabling efficient job matching, personalized recommendations, and labor market analysis. Despite Türkiye's significant role in the global workforce, Turkish, a morphologically complex language, lacks both a skill taxonomy and a dedicated skill extraction dataset, resulting in underexplored research in skill extraction for Turkish. This article seeks the answers to three research questions: 1) How can skill extraction be effectively performed for this language, in light of its low resource nature? 2)~What is the most promising model? 3) What is the impact of different Large Language Models (LLMs) and prompting strategies on skill extraction (i.e., dynamic vs. static few-shot samples, varying context information, and encouraging causal reasoning)? The article introduces the first Turkish skill extraction dataset and performance evaluations of automated skill extraction using LLMs. The manually annotated dataset contains 4,819 labeled skill spans from 327 job postings across different occupation areas. The use of LLM outperforms supervised sequence labeling when used in an end-to-end pipeline, aligning extracted spans with standardized skills in the ESCO taxonomy more effectively. The best-performing configuration, utilizing Claude Sonnet 3.7 with dynamic few-shot prompting for skill identification, embedding-based retrieval, and LLM-based reranking for skill linking, achieves an end-to-end performance of 0.56, positioning Turkish alongside similar studies in other languages, which are few in the literature. Our findings suggest that LLMs can improve skill extraction performance in low-resource settings, and we hope that our work will accelerate similar research on skill extraction for underrepresented languages. --- ### Reinforcement Learning-Based Co-Design and Operation of Chiller and Thermal Energy Storage for Cost-Optimal HVAC Systems Authors: Tanay Raghunandan Srinivasa, Vivek Deulkar, Aviruch Bhatia, Vishal Garg Published: 2026-01-30 Categories: eess.SY, cs.AI arXiv: https://arxiv.org/abs/2601.22880v2 We study the joint operation and sizing of cooling infrastructure for commercial HVAC systems using reinforcement learning, with the objective of minimizing life-cycle cost over a 30-year horizon. The cooling system consists of a fixed-capacity electric chiller and a thermal energy storage (TES) unit, jointly operated to meet stochastic hourly cooling demands under time-varying electricity prices. The life-cycle cost accounts for both capital expenditure and discounted operating cost, including electricity consumption and maintenance. A key challenge arises from the strong asymmetry in capital costs: increasing chiller capacity by one unit is far more expensive than an equivalent increase in TES capacity. As a result, identifying the right combination of chiller and TES sizes, while ensuring zero loss-of-cooling-load under optimal operation, is a non-trivial co-design problem. To address this, we formulate the chiller operation problem for a fixed infrastructure configuration as a finite-horizon Markov Decision Process (MDP), in which the control action is the chiller part-load ratio (PLR). The MDP is solved using a Deep Q Network (DQN) with a constrained action space. The learned DQN RL policy minimizes electricity cost over historical traces of cooling demand and electricity prices. For each candidate chiller-TES sizing configuration, the trained policy is evaluated. We then restrict attention to configurations that fully satisfy the cooling demand and perform a life-cycle cost minimization over this feasible set to identify the cost-optimal infrastructure design. Using this approach, we determine the optimal chiller and thermal energy storage capacities to be 700 and 1500, respectively. --- ### Synthetic Time Series Generation via Complex Networks Authors: Jaime Vale, Vanessa Freitas Silva, Maria Eduarda Silva, Fernando Silva Published: 2026-01-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.22879v2 Time series data are essential for a wide range of applications, yet access to high-quality datasets is often constrained by privacy concerns, acquisition costs, and labelling challenges. Synthetic time series generation has emerged as a promising approach to address these limitations. In this work, we investigate the use of complex network mappings for synthetic time series generation, focusing on the Quantile Graph (QG) representation and its inverse. While the inverse QG mapping has been previously proposed, its potential as a general-purpose data generator has not been systematically evaluated. We address this gap through a comprehensive empirical study assessing both the fidelity and utility of synthetic time series generated by the Inverse Quantile Graph (InvQG) framework. The evaluation combines statistical feature analysis, network-based topological characteristics, and performance in downstream clustering and classification tasks, using simulated and real-world datasets. The results show that InvQG effectively preserves marginal distributions and short-term temporal dependencies across a wide range of models, while exhibiting predictable limitations in capturing long-range or higher-order dynamics. --- ### Development of Domain-Invariant Visual Enhancement and Restoration (DIVER) Approach for Underwater Images Authors: Rajini Makam, Sharanya Patil, Dhatri Shankari T M, Suresh Sundaram, Narasimhan Sundararajan Published: 2026-01-30 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2601.22878v1 Underwater images suffer severe degradation due to wavelength-dependent attenuation, scattering, and illumination non-uniformity that vary across water types and depths. We propose an unsupervised Domain-Invariant Visual Enhancement and Restoration (DIVER) framework that integrates empirical correction with physics-guided modeling for robust underwater image enhancement. DIVER first applies either IlluminateNet for adaptive luminance enhancement or a Spectral Equalization Filter for spectral normalization. An Adaptive Optical Correction Module then refines hue and contrast using channel-adaptive filtering, while Hydro-OpticNet employs physics-constrained learning to compensate for backscatter and wavelength-dependent attenuation. The parameters of IlluminateNet and Hydro-OpticNet are optimized via unsupervised learning using a composite loss function. DIVER is evaluated on eight diverse datasets covering shallow, deep, and highly turbid environments, including both naturally low-light and artificially illuminated scenes, using reference and non-reference metrics. While state-of-the-art methods such as WaterNet, UDNet, and Phaseformer perform reasonably in shallow water, their performance degrades in deep, unevenly illuminated, or artificially lit conditions. In contrast, DIVER consistently achieves best or near-best performance across all datasets, demonstrating strong domain-invariant capability. DIVER yields at least a 9% improvement over SOTA methods in UCIQE. On the low-light SeaThru dataset, where color-palette references enable direct evaluation of color restoration, DIVER achieves at least a 4.9% reduction in GPMAE compared to existing methods. Beyond visual quality, DIVER also improves robotic perception by enhancing ORB-based keypoint repeatability and matching performance, confirming its robustness across diverse underwater environments. ---