Recent Large Reasoning Models (LRMs) with thinking traces have shown strong performance on English reasoning tasks. However, their ability to think in other languages is less studied. This capability is as important as answer accuracy for real world applications because users may find the reasoning trace useful for oversight only when it is expressed in their own language. We comprehensively evaluate two leading families of LRMs on our XReasoning benchmark and find that even the most advanced models often revert to English or produce fragmented reasoning in other languages, revealing a substantial gap in multilingual reasoning. Prompt based interventions that force models to reason in the users language improve readability and oversight but reduce answer accuracy, exposing an important trade off. We further show that targeted post training on just 100 examples mitigates this mismatch, though some accuracy loss remains. Our results highlight the limited multilingual reasoning capabilities of current LRMs and outline directions for future work. Code and data are available at https://github.com/Betswish/mCoT-XReasoning.

Abstract-- Perceptual voice quality assessment plays a vital role in diagnosing and monitoring voice disorders. Traditional methods, such as the Consensus Auditory-Perceptual Evaluation of Voice (CAPE-V) and the Grade, Roughness, Breathiness, Asthenia, and Strain (GRBAS) scales, rely on expert raters and are prone to inter-rater variability, emphasizing the need for objective solutions. This study introduces the Voice Quality Assessment Network (VOQANet), a deep learning framework that employs an attention mechanism and Speech Foundation Model (SFM) embeddings to extract high-level features. To further enhance performance, we propose VO-QANet+, which integrates self-supervised SFM embeddings with low-level acoustic descriptors--namely jitter, shimmer, and harmonics-to-noise ratio (HNR). Unlike previous approaches that focus solely on vowel-based phonation (PVQD-A), our models are evaluated on both vowel-level and sentence-level speech (PVQD-S) to assess general-izability. Experimental results demonstrate that sentence-based inputs yield higher accuracy, particularly at the patient level. Overall, VOQANet consistently outperforms baseline models in terms of root mean squared error (RMSE) and Pearson correlation coefficient across CAPE-V and GRBAS dimensions, with VOQANet+ achieving even greater performance gains. Additionally, VOQANet+ maintains consistent performance under noisy conditions, suggesting enhanced robustness for real-world and telehealth applications. This work highlights the value of combining SFM embeddings with low-level features for accurate and robust pathological voice assessment. This work was supported in part by the National Science and T ech-nology Council and Academia Sinica. Whenty Ariyanti is with the Department of Computer Science and Information Engineering, National T aiwan University of Science and T echnology, T aipei 106, T aiwan, and also with the Research Center for Information T echnology Innovation, Academia Sinica, T aipei 11529, T aiwan (e-mail: d11115805@mail.ntust.edu.tw). Kuan-Y u Chen is with the Department of Computer Science and Information Engineering, National T aiwan University of Science and T echnology, T aipei 106, T aiwan (e-mail: kychen@mail.ntust.edu.tw). Sabato Marco Siniscalchi is the University of Palermo, Palermo, Italy (e-mail: sabatomarco.siniscalchi@unipa.it).

Traffic signal control (TSC) is a core challenge in urban mobility, where real-time decisions must balance efficiency and safety. Existing methods - ranging from rule-based heuristics to reinforcement learning (RL) - often struggle to generalize to complex, dynamic, and safety-critical scenarios. We introduce VLMLight, a novel TSC framework that integrates vision-language meta-control with dual-branch reasoning. At the core of VLMLight is the first image-based traffic simulator that enables multi-view visual perception at intersections, allowing policies to reason over rich cues such as vehicle type, motion, and spatial density. A large language model (LLM) serves as a safety-prioritized meta-controller, selecting between a fast RL policy for routine traffic and a structured reasoning branch for critical cases. In the latter, multiple LLM agents collaborate to assess traffic phases, prioritize emergency vehicles, and verify rule compliance. Experiments show that VLMLight reduces waiting times for emergency vehicles by up to 65% over RL-only systems, while preserving real-time performance in standard conditions with less than 1% degradation. VLMLight offers a scalable, interpretable, and safety-aware solution for next-generation traffic signal control.

Personalized alignment is essential for enabling large language models (LLMs) to engage effectively in user-centric dialogue. While recent prompt-based and offline optimization methods offer preliminary solutions, they fall short in cold-start scenarios and long-term personalization due to their inherently static and shallow designs. In this work, we introduce the Reinforcement Learning for Personalized Alignment (RLPA) framework, in which an LLM interacts with a simulated user model to iteratively infer and refine user profiles through dialogue. The training process is guided by a dual-level reward structure: the Profile Reward encourages accurate construction of user representations, while the Response Reward incentivizes generation of responses consistent with the inferred profile. We instantiate RLPA by fine-tuning Qwen-2.5-3B-Instruct, resulting in Qwen-RLPA, which achieves state-of-the-art performance in personalized dialogue. Empirical evaluations demonstrate that Qwen-RLPA consistently outperforms prompting and offline fine-tuning baselines, and even surpasses advanced commercial models such as Claude-3.5 and GPT-4o. Further analysis highlights Qwen-RLPA's robustness in reconciling conflicting user preferences, sustaining long-term personalization and delivering more efficient inference compared to recent reasoning-focused LLMs. These results emphasize the potential of dynamic profile inference as a more effective paradigm for building personalized dialogue systems.

Multilingual reasoning remains a significant challenge for large language models (LLMs), with performance disproportionately favoring high-resource languages. Drawing inspiration from cognitive neuroscience, which suggests that human reasoning functions largely independently of language processing, we hypothesize that LLMs similarly encode reasoning and language as separable components that can be disentangled to enhance multilingual reasoning. To evaluate this, we perform a causal intervention by ablating language-specific representations at inference time. Experiments on 10 open-weight LLMs spanning 11 typologically diverse languages show that this language-specific ablation consistently boosts multilingual reasoning performance. Layer-wise analyses further confirm that language and reasoning representations can be effectively disentangled throughout the model, yielding improved multilingual reasoning capabilities, while preserving top-layer language features remains essential for maintaining linguistic fidelity. Compared to post-training methods such as supervised fine-tuning or reinforcement learning, our training-free language-reasoning disentanglement achieves comparable or superior results with minimal computational overhead. These findings shed light on the internal mechanisms underlying multilingual reasoning in LLMs and suggest a lightweight and interpretable strategy for improving cross-lingual generalization.

With the increasing adoption of Large Language Models (LLMs) and Vision-Language Models (VLMs), rich document analysis technologies for applications like Retrieval-Augmented Generation (RAG) and visual RAG are gaining significant attention. Recent research indicates that using VLMs yields better RAG performance, but processing rich documents remains a challenge since a single page contains large amounts of information. In this paper, we present SCAN (SemantiC Document Layout ANalysis), a novel approach that enhances both textual and visual Retrieval-Augmented Generation (RAG) systems that work with visually rich documents. It is a VLM-friendly approach that identifies document components with appropriate semantic granularity, balancing context preservation with processing efficiency. SCAN uses a coarse-grained semantic approach that divides documents into coherent regions covering contiguous components. We trained the SCAN model by fine-tuning object detection models on an annotated dataset. Our experimental results across English and Japanese datasets demonstrate that applying SCAN improves end-to-end textual RAG performance by up to 9.4 points and visual RAG performance by up to 10.4 points, outperforming conventional approaches and even commercial document processing solutions.

Vision-language reinforcement learning (RL) has primarily focused on narrow domains (e.g. geometry or chart reasoning). This leaves broader training scenarios and resources underexplored, limiting the exploration and learning of Vision Language Models (VLMs) through RL. We find video games inherently provide rich visual elements and mechanics that are easy to verify. To fully use the multimodal and verifiable reward in video games, we propose Game-RL, constructing diverse game tasks for RL training to boost VLMs general reasoning ability. To obtain training data, we propose Code2Logic, a novel approach that adapts game code to synthesize game reasoning task data, thus obtaining the GameQA dataset of 30 games and 158 tasks with controllable difficulty gradation. Unexpectedly, RL training solely on GameQA enables multiple VLMs to achieve performance improvements across 7 diverse vision-language benchmarks, demonstrating the value of Game-RL for enhancing VLMs' general reasoning. Furthermore, this suggests that video games may serve as valuable scenarios and resources to boost general reasoning abilities. Our code, dataset and models are available at the GitHub repository.

Equivariant neural networks are designed to respect symmetries through their architecture, boosting generalization and sample efficiency when those symmetries are present in the data distribution. Real-world data, however, often departs from perfect symmetry because of noise, structural variation, measurement bias, or other symmetry-breaking effects. Strictly equivariant models may struggle to fit the data, while unconstrained models lack a principled way to leverage partial symmetries. Even when the data is fully symmetric, enforcing equivariance can hurt training by limiting the model to a restricted region of the parameter space. Guided by homotopy principles, where an optimization problem is solved by gradually transforming a simpler problem into a complex one, we introduce Adaptive Constrained Equivariance (ACE), a constrained optimization approach that starts with a flexible, non-equivariant model and gradually reduces its deviation from equivariance. This gradual tightening smooths training early on and settles the model at a data-driven equilibrium, balancing between equivariance and non-equivariance. Across multiple architectures and tasks, our method consistently improves performance metrics, sample efficiency, and robustness to input perturbations compared with strictly equivariant models and heuristic equivariance relaxations.

Panoramic imaging enables capturing 360° images with an ultra-wide Field-of-View (FoV) for dense omnidirectional perception, which is critical to applications, such as autonomous driving and augmented reality, etc. However, current panoramic semantic segmentation methods fail to identify outliers, and pinhole Out-of-distribution Segmentation (OoS) models perform unsatisfactorily in the panoramic domain due to pixel distortions and background clutter. To address these issues, we introduce a new task, Panoramic Out-of-distribution Segmentation (PanOoS), with the aim of achieving comprehensive and safe scene understanding. Furthermore, we propose the first solution, POS, which adapts to the characteristics of panoramic images through text-guided prompt distribution learning. Specifically, POS integrates a disentanglement strategy designed to materialize the cross-domain generalization capability of CLIP. The proposed Prompt-based Restoration Attention (PRA) optimizes semantic decoding by prompt guidance and self-adaptive correction, while Bilevel Prompt Distribution Learning (BPDL) refines the manifold of per-pixel mask embeddings via semantic prototype supervision. Besides, to compensate for the scarcity of PanOoS datasets, we establish two benchmarks: DenseOoS, which features diverse outliers in complex environments, and QuadOoS, captured by a quadruped robot with a panoramic annular lens system. Extensive experiments demonstrate superior performance of POS, with AuPRC improving by 34.25% and FPR95 decreasing by 21.42% on DenseOoS, outperforming state-of-the-art pinhole-OoS methods. Moreover, POS achieves leading closed-set segmentation capabilities and advances the development of panoramic understanding. Code and datasets will be available at https://github.com/MengfeiD/PanOoS.

Online class-incremental learning (OCIL) focuses on gradually learning new classes (called plasticity) from a stream of data in a single-pass, while concurrently preserving knowledge of previously learned classes (called stability). The primary challenge in OCIL lies in maintaining a good balance between the knowledge of old and new classes within the continually updated model. Most existing methods rely on explicit knowledge interaction through experience replay, and often employ exclusive training separation to address bias problems. Nevertheless, it still remains a big challenge to achieve a well-balanced learner, as these methods often exhibit either reduced plasticity or limited stability due to difficulties in continually integrating knowledge in the OCIL setting. In this paper, we propose a novel replay-based method, called Balanced Inclusive Separation for Online iNcremental learning (BISON), which can achieve both high plasticity and stability, thus ensuring more balanced performance in OCIL. Our BISON method proposes an inclusive training separation strategy using dual classifiers so that knowledge from both old and new classes can effectively be integrated into the model, while introducing implicit approaches for transferring knowledge across the two classifiers. Extensive experimental evaluations over three widely-used OCIL benchmark datasets demonstrate the superiority of BISON, showing more balanced yet better performance compared to state-of-the-art replay-based OCIL methods.