Conditional Optimal Transport (COT) problem aims to find a transport map between conditional source and target distributions while minimizing the transport cost. Recently, these transport maps have been utilized in conditional generative modeling tasks to establish efficient mappings between the distributions. However, classical COT inherits a fundamental limitation of optimal transport, i.e., sensitivity to outliers, which arises from the hard distribution matching constraints. This limitation becomes more pronounced in a conditional setting, where each conditional distribution is estimated from a limited subset of data. To address this, we introduce the Conditional Unbalanced Optimal Transport (CUOT) framework, which relaxes conditional distribution-matching constraints through Csiszár divergence penalties while strictly preserving the conditioning marginals. We establish a rigorous formulation of the CUOT problem and derive its dual and semi-dual formulations. Based on the semi-dual form, we propose Conditional Unbalanced Optimal Transport Maps (CUOTM), an outlier-robust conditional generative model built upon a triangular $c$-transform parameterization. We theoretically justify the validity of this parameterization by proving that the optimal triangular map satisfies the $c$-transform relationships. Our experiments on 2D synthetic and image-scale datasets demonstrate that CUOTM achieves superior outlier robustness and competitive distribution-matching performance compared to existing COT-based baselines, while maintaining high sampling efficiency.

Semantic segmentation across visual modalities such as 3D point clouds and panoramic images remains a challenging task, primarily due to the scarcity of annotated data and the limited adaptability of fixed-label models. In this paper, we present JOPP-3D, an open-vocabulary semantic segmentation framework that jointly leverages panoramic and point cloud data to enable language-driven scene understanding. We convert RGB-D panoramic images into their corresponding tangential perspective images and 3D point clouds, then use these modalities to extract and align foundational vision-language features. This allows natural language querying to generate semantic masks on both input modalities. Experimental evaluation on the Stanford-2D-3D-s and ToF-360 datasets demonstrates the capability of JOPP-3D to produce coherent and semantically meaningful segmentations across panoramic and 3D domains. Our proposed method achieves a significant improvement compared to the SOTA in open and closed vocabulary 2D and 3D semantic segmentation.

Modeling spinal motion is fundamental to understanding human biomechanics, yet remains underexplored in computer vision due to the spine's complex multi-joint kinematics and the lack of large-scale 3D annotations. We present a biomechanics-aware keypoint simulation framework that augments existing human pose datasets with anatomically consistent 3D spinal keypoints derived from musculoskeletal modeling. Using this framework, we create the first open dataset, named SIMSPINE, which provides sparse vertebra-level 3D spinal annotations for natural full-body motions in indoor multi-camera capture without external restraints. With 2.14 million frames, this enables data-driven learning of vertebral kinematics from subtle posture variations and bridges the gap between musculoskeletal simulation and computer vision. In addition, we release pretrained baselines covering fine-tuned 2D detectors, monocular 3D pose lifting models, and multi-view reconstruction pipelines, establishing a unified benchmark for biomechanically valid spine motion estimation. Specifically, our 2D spine baselines improve the state-of-the-art from 0.63 to 0.80 AUC in controlled environments, and from 0.91 to 0.93 AP for in-the-wild spine tracking. Together, the simulation framework and SIMSPINE dataset advance research in vision-based biomechanics, motion analysis, and digital human modeling by enabling reproducible, anatomically grounded 3D spine estimation under natural conditions.

Leveraging Multimodal Large Language Models (MLLMs) has become pivotal for advancing Universal Multimodal Embeddings (UME) in addressing diverse cross-modal tasks. Recent studies demonstrate that incorporating generative Chain-of-Thought (CoT) reasoning can substantially enhance task-specific representations compared to discriminative methods. However, the generated reasoning CoTs of existing generative embedding methods are limited to the textual analysis of queries and are irrelevant to the retrieval of the targets. To address these limitations, we propose a reasoning-driven UME framework that integrates Embedder-Guided Reinforcement Learning (EG-RL) to optimize the Reasoner to produce evidential Traceability CoT (T-CoT). Our key contributions are threefold: (1) We design an EG-RL framework where the Embedder provides explicit supervision to the Reasoner, ensuring the generated CoT traces are aligned with embedding tasks. (2) We introduce T-CoT, which extracts critical multimodal cues to focus on retrieval-relevant elements and provides multimodal inputs for the Embedder. (3) With limited computational resources, our framework outperforms the pioneering embedding model on both MMEB-V2 and UVRB benchmarks. The integration of multimodal evidence in structured reasoning, paired with retrieval-oriented alignment, effectively strengthens cross-modal semantic consistency and boosts the fine-grained matching capability of the model as well as the generalization across complex scenarios. Our work demonstrates that targeted reasoning optimization can significantly improve multimodal embedding quality, providing a practical and efficient solution for reasoning-driven UME development.

Recent advancements in Large Language Models (LLMs) have largely focused on depth scaling, where a single agent solves long-horizon problems with multi-turn reasoning and tool use. However, as tasks grow broader, the key bottleneck shifts from individual competence to organizational capability. In this work, we explore a complementary dimension of width scaling with multi-agent systems to address broad information seeking. Existing multi-agent systems often rely on hand-crafted workflows and turn-taking interactions that fail to parallelize work effectively. To bridge this gap, we propose WideSeek-R1, a lead-agent-subagent framework trained via multi-agent reinforcement learning (MARL) to synergize scalable orchestration and parallel execution. By utilizing a shared LLM with isolated contexts and specialized tools, WideSeek-R1 jointly optimizes the lead agent and parallel subagents on a curated dataset of 20k broad information-seeking tasks. Extensive experiments show that WideSeek-R1-4B achieves an item F1 score of 40.0% on the WideSearch benchmark, which is comparable to the performance of single-agent DeepSeek-R1-671B. Furthermore, WideSeek-R1-4B exhibits consistent performance gains as the number of parallel subagents increases, highlighting the effectiveness of width scaling.

Robotic Manipulation Surfaces (RMS) manipulate objects by deforming the surface on which they rest, offering safe, parallel handling of diverse and fragile items. However, existing designs face a fundamental tradeoff: achieving fine control typically demands dense actuator arrays that limit scalability. Modular architectures can extend the workspace, but transferring objects reliably across module boundaries on soft, continuously deformable surfaces remains an open challenge. We present a multi-modular soft manipulation platform that achieves coordinated inter-module object transfer and precise positioning across interconnected fabric-based modules. A hierarchical control framework, combining conflict-free Manhattan-based path planning with directional object passing and a geometric PID controller, achieves sub-centimeter positioning and consistent transfer of heterogeneous objects including fragile items. The platform employs shared-boundary actuation, where adjacent modules share edge actuators, reducing the required count from $4n^2$ to $(n + 1)^2$ for an $n \times n$ grid; a $2\times 2$ prototype covers $1\times 1$ m with only 9 actuators. This scaling comes at a cost: shared actuators mechanically couple neighbouring modules, creating interference during simultaneous manipulation. We systematically characterise this coupling across spatial configurations and propose compensation strategies that reduce passive-object displacement by 59--78\%. Together, these contributions establish a scalable foundation for soft manipulation surfaces in applications such as food processing and logistics.

Multi-Object Tracking (MOT) is evolving from geometric localization to Semantic MOT (SMOT) to answer complex relational queries, yet progress is hindered by semantic data scarcity and a structural disconnect between tracking architectures and Multi-modal Large Language Models (MLLMs). To address this, we introduce Grand-SMOT, a large-scale, open-world benchmark providing high-density, dual-stream narratives that comprehensively decouple individual behaviors from environmental contexts. Furthermore, we propose LLMTrack, the first framework to seamlessly integrate MLLMs into the SMOT task. LLMTrack establishes a Macro-Understanding-First paradigm, utilizing a novel Spatio-Temporal Fusion Module to align discrete geometric trajectories with continuous semantic features, effectively suppressing temporal hallucinations during online processing. Extensive experiments demonstrate that LLMTrack achieves state-of-the-art geometric tracking performance while delivering a qualitative leap in dynamic semantic reasoning. Notably, our analysis reveals that high-quality semantic narratives empower the language model to deduce complex social interactions naturally, demonstrating that direct cognitive reasoning is more effective than cumbersome explicit visual modeling. Ultimately, our contributions bridge the gap between perceptual tracking and cognitive reasoning, establishing a robust new foundation for comprehensive video understanding and intelligent narrative generation.

Prompt-based evaluations suggest that large language models (LLMs) perform poorly on time series classification, raising doubts about whether they encode meaningful temporal structure. We show that this conclusion reflects limitations of prompt-based generation rather than the model's representational capacity by directly comparing prompt outputs with linear probes over the same internal representations. While zero-shot prompting performs near chance, linear probes improve average F1 from 0.15-0.26 to 0.61-0.67, often matching or exceeding specialized time series models. Layer-wise analyses further show that class-discriminative time series information emerges in early transformer layers and is amplified by visual and multimodal inputs. Together, these results demonstrate a systematic mismatch between what LLMs internally represent and what prompt-based evaluation reveals, leading current evaluations to underestimate their time series understanding.

The rapid emergence of Large Language Models (LLMs) has precipitated a profound paradigm shift in Artificial Intelligence, delivering monumental engineering successes that increasingly impact modern society. However, a critical paradox persists within the current field: despite the empirical efficacy, our theoretical understanding of LLMs remains disproportionately nascent, forcing these systems to be treated largely as ``black boxes''. To address this theoretical fragmentation, this survey proposes a unified lifecycle-based taxonomy that organizes the research landscape into six distinct stages: Data Preparation, Model Preparation, Training, Alignment, Inference, and Evaluation. Within this framework, we provide a systematic review of the foundational theories and internal mechanisms driving LLM performance. Specifically, we analyze core theoretical issues such as the mathematical justification for data mixtures, the representational limits of various architectures, and the optimization dynamics of alignment algorithms. Moving beyond current best practices, we identify critical frontier challenges, including the theoretical limits of synthetic data self-improvement, the mathematical bounds of safety guarantees, and the mechanistic origins of emergent intelligence. By connecting empirical observations with rigorous scientific inquiry, this work provides a structured roadmap for transitioning LLM development from engineering heuristics toward a principled scientific discipline.

We generalize the AIXI reinforcement learning agent to admit a wider class of utility functions. Assigning a utility to each possible interaction history forces us to confront the ambiguity that some hypotheses in the agent's belief distribution only predict a finite prefix of the history, which is sometimes interpreted as implying a chance of death equal to a quantity called the semimeasure loss. This death interpretation suggests one way to assign utilities to such history prefixes. We argue that it is as natural to view the belief distributions as imprecise probability distributions, with the semimeasure loss as total ignorance. This motivates us to consider the consequences of computing expected utilities with Choquet integrals from imprecise probability theory, including an investigation of their computability level. We recover the standard recursive value function as a special case. However, our most general expected utilities under the death interpretation cannot be characterized as such Choquet integrals.

Modern neural networks exhibit a striking property: basins of attraction in the loss landscape are often connected by low-loss paths, yet optimization dynamics generally remain confined to a single convex basin and rarely explore intermediate points. We resolve this paradox by identifying entropic barriers arising from the interplay between curvature variations along these paths and noise in optimization dynamics. Empirically, we find that curvature systematically rises away from minima, producing effective forces that bias noisy dynamics back toward the endpoints - even when the loss remains nearly flat. These barriers persist longer than energetic barriers, shaping the late-time localization of solutions in parameter space. Our results highlight the role of curvature-induced entropic forces in governing both connectivity and confinement in deep learning landscapes.

Whole Slide Image (WSI) MLLMs are difficult to build and deploy because gigapixel slides induce thousands of visual tokens, while only a small fraction of regions is diagnostically relevant. Existing slide-level pathology MLLMs typically combine heavy slide-level encoders with long visual prefixes, making end-to-end slide-level development and deployment expensive under limited computational resources. We revisit this regime and show that WSI tile features are highly redundant at both global and local scales, while task-relevant evidence is sparse and query-dependent. We therefore introduce LoC-Path, a resource-efficient slide-level MLLM that compresses before fusion. LoC-Path uses a Sparse Token Merger (STM) and an MAE-pretrained resampler to replace expensive slide-level encoding with a compact latent interface, then uses a Token Importance Scorer (TIS) to select the most relevant latents and a Cross-Attention Routing Adapter (CARA) to fuse them into a few LLM decoder layers. This design lowers both multimodal tuning cost and inference-time latency/memory by avoiding heavy slide-level encoding and long visual prefixes. Extensive experiments show that LoC-Path remains competitive with prior slide-level MLLMs while making end-to-end development and deployment more practical under limited computational resources.

Capturing accurate 3D human pose in the wild would provide valuable data for training pose estimation and motion generation methods. While video-based estimation approaches have become increasingly accurate, they often fail in common scenarios involving self-contact, such as a hand touching the face. In contrast, wearable bioimpedance sensing can cheaply and unobtrusively measure ground-truth skin-to-skin contact. Consequently, we propose a novel framework that combines visual pose estimators with bioimpedance sensing to capture the 3D pose of people by taking self-contact into account. Our method, BioTUCH, initializes the pose using an off-the-shelf estimator and introduces contact-aware pose optimization during measured self-contact: reprojection error and deviations from the input estimate are minimized while enforcing vertex proximity constraints. We validate our approach using a new dataset of synchronized RGB video, bioimpedance measurements, and 3D motion capture. Testing with three input pose estimators, we demonstrate an average of 11.7% improvement in reconstruction accuracy. We also present a miniature wearable bioimpedance sensor that enables efficient large-scale collection of contact-aware training data for improving pose estimation and generation using BioTUCH. Code and data are available at biotuch.is.tue.mpg.de

Tubular tree structures such as blood vessels and lung airways are central to many clinical tasks, including diagnosis, treatment planning, and surgical navigation. Accurate centerline extraction with correct topology is essential, as missing small branches can lead to incomplete assessments or overlooked abnormalities. We propose RefTr, a 3D image-to-graph framework that generates vascular centerlines via recurrent refinement of confluent trajectories. RefTr adopts a Transformer-based Producer-Refiner architecture in which the Producer predicts candidate trajectories and a shared Refiner iteratively refines them toward the target branches. The confluent trajectory representation enables whole-branch refinement while explicitly enforcing valid topology. This recurrent scheme improves precision and reduces decoder parameters by 2.4x compared to the state-of-the-art. We further introduce an efficient non-maximum suppression algorithm for spatial tree graphs to merge duplicate branches and extend evaluation metrics to be radius-aware for robust comparison. Experiments on multiple public datasets demonstrate stronger overall performance, faster inference, and substantially fewer parameters, highlighting the effectiveness of RefTr for 3D vascular tree analysis.

While existing feed-forward Gaussian splatting models offer computational efficiency and can generalize to sparse view settings, their performance is fundamentally constrained by relying on a single forward pass for inference. We propose ReSplat, a feed-forward recurrent Gaussian splatting model that iteratively refines 3D Gaussians without explicitly computing gradients. Our key insight is that the Gaussian splatting rendering error serves as a rich feedback signal, guiding the recurrent network to learn effective Gaussian updates. This feedback signal naturally adapts to unseen data distributions at test time, enabling robust generalization across datasets, view counts, and image resolutions. To initialize the recurrent process, we introduce a compact reconstruction model that operates in a $16 \times$ subsampled space, producing $16 \times$ fewer Gaussians than previous per-pixel Gaussian models. This substantially reduces computational overhead and allows for efficient Gaussian updates. Extensive experiments across varying number of input views (2, 8, 16, 32), resolutions ($256 \times 256$ to $540 \times 960$), and datasets (DL3DV, RealEstate10K, and ACID) demonstrate that our method achieves state-of-the-art performance while significantly reducing the number of Gaussians and improving the rendering speed. Our project page is at https://haofeixu.github.io/resplat/.

Color representation is essential in computer vision and human-computer interaction. There are multiple color models available. The choice of a suitable color model is critical for various applications. This paper presents a review of color models and spaces, analyzing their theoretical foundations, computational properties, and practical applications. We explore traditional models such as RGB, CMYK, and YUV, perceptually uniform spaces like CIELAB and CIELUV, and fuzzy-based approaches as well. Additionally, we conduct a series of experiments to evaluate color models from various perspectives, like device dependency, chromatic consistency, and computational complexity. Our experimental results reveal gaps in existing color models and show that the HS* family is the most aligned with human perception. The review also identifies key strengths and limitations of different models and outlines open challenges and future directions This study provides a reference for researchers in image processing, perceptual computing, digital media, and any other color-related field.

Feed-forward 3D Gaussian Splatting (3DGS) has emerged as a highly effective solution for novel view synthesis. Existing methods predominantly rely on a \emph{pixel-aligned} Gaussian prediction paradigm, where each 2D pixel is mapped to a 3D Gaussian. We rethink this widely adopted formulation and identify several inherent limitations: it renders the reconstructed 3D models heavily dependent on the number of input views, leads to view-biased density distributions, and introduces alignment errors, particularly when source views contain occlusions or low texture. To address these challenges, we introduce VolSplat, a new multi-view feed-forward paradigm that replaces pixel alignment with voxel-aligned Gaussians. By directly predicting Gaussians from a predicted 3D voxel grid, it overcomes pixel alignment's reliance on error-prone 2D feature matching, ensuring robust multi-view consistency. Furthermore, it enables adaptive control over density based on 3D scene complexity, yielding more faithful Gaussians, improved geometric consistency, and enhanced novel-view rendering quality. Experiments on widely used benchmarks demonstrate that VolSplat achieves state-of-the-art performance, while producing more plausible and view-consistent results. The video results, code and trained models are available on our project page: https://lhmd.top/volsplat.

Accurate knowledge of the tire-road friction coefficient (TRFC) is essential for vehicle safety, stability, and performance, especially in autonomous racing, where vehicles often operate at the friction limit. However, TRFC cannot be directly measured with standard sensors, and existing estimation methods either depend on vehicle or tire models with uncertain parameters or require large training datasets. In this paper, we present a lightweight approach for online slip detection and TRFC estimation. Our approach relies solely on IMU and LiDAR measurements and the control actions, without special dynamical or tire models, parameter identification, or training data. Slip events are detected in real time by comparing commanded and measured motions, and the TRFC is then estimated directly from observed accelerations under no-slip conditions. Experiments with a 1:10-scale autonomous racing car across different friction levels demonstrate that the proposed approach achieves accurate and consistent slip detections and friction coefficients, with results closely matching ground-truth measurements. These findings highlight the potential of our simple, deployable, and computationally efficient approach for real-time slip monitoring and friction coefficient estimation in autonomous driving.

Line segment detection in images has been studied for several decades. Existing methods can be roughly divided into two categories: generic line segment detectors and wireframe line segment detectors. Generic detectors aim to detect all meaningful line segments in images and traditional approaches usually fall into this category. Recent deep learning based approaches are mostly wireframe detectors. They detect only line segments that are geometrically meaningful and have large spatial support. Due to the difference in the aim of design, methods designed for one paradigm often perform poorly on the other, and few approaches demonstrate robust performance across both tasks. In this work, we propose a robust framework that is efficient for both tasks based on an Adaptive Dual-Constrained Line Aggregation (ADLA) algorithm. ADLA aggregates pixels into candidate line segments only if they satisfy dual geometric constraints: (1) orientation coherence and (2) bounded orthogonal distance to an adaptively estimated line model. Crucially, the parameters of the candidate line (its orientation and centroid) are dynamically updated as new pixels are incorporated. This progressive model refinement improves geometric accuracy. Moreover, by leveraging edge strength maps in orientation estimation and line segment validation, ADLA requires little parameter tuning. Extensive experiments on three publicly available datasets demonstrate that ADLA achieves competitive or superior performance than previous methods, highlighting its robustness, versatility, and practical usability.

Facial expression recognition (FER) models are widely used in video-based affective computing applications, such as human-computer interaction and healthcare monitoring. However, deep FER models often struggle with subtle expressions and high inter-subject variability, limiting performance in real-world settings. Source-free domain adaptation (SFDA) has been proposed to personalize a pretrained source model using only unlabeled target data, avoiding privacy, storage, and transmission constraints. We address a particularly challenging setting where source data is unavailable and the target data contains only neutral expressions. Existing SFDA methods are not designed for adaptation from a single target class, while generating non-neutral facial images is often unstable and expensive. To address this, we propose Source-Free Domain Adaptation with Personalized Feature Translation (SFDA-PFT), a lightweight latent-space approach. A translator is first pretrained on source data to map subject-specific style features between subjects while preserving expression information through expression-consistency and style-aware objectives. It is then adapted to neutral target data without source data or image synthesis. By operating in the latent space, SFDA-PFT avoids noisy facial image generation, reduces computation, and learns discriminative embeddings for classification. Experiments on BioVid, StressID, BAH, and Aff-Wild2 show that SFDA-PFT consistently outperforms state-of-the-art SFDA methods in privacy-sensitive FER scenarios. Our code is publicly available at: \href{https://github.com/MasoumehSharafi/SFDA-PFT}{GitHub}.

The large language model (LLM) community focuses almost exclusively on decoder-only language models, since they are easier to use for text generation. However, a large subset of the community still uses encoder-only models for tasks such as classification or retrieval. Previous work has attempted to compare these architectures, but is forced to make comparisons with models that have different numbers of parameters, training techniques, and datasets. We introduce the SOTA open-data Ettin suite of models: paired encoder-only and decoder-only models ranging from 17 million parameters to 1 billion, trained on up to 2 trillion tokens. Using the same recipe for both encoder-only and decoder-only models produces SOTA recipes in both categories for their respective sizes, beating ModernBERT as an encoder and Llama 3.2 and SmolLM2 as decoders. Like previous work, we find that encoder-only models excel at classification and retrieval tasks while decoders excel at generative tasks. However, we show that adapting a decoder model to encoder tasks (and vice versa) through continued training is subpar compared to using only the reverse objective (i.e. a 400M encoder outperforms a 1B decoder on MNLI, and vice versa for generative tasks). We open-source all artifacts of this study including training data, training order segmented by checkpoint, and 200+ checkpoints to allow future work to analyze or extend all aspects of training.

We introduce NeuralOS, a neural framework that simulates graphical user interfaces (GUIs) of operating systems by directly predicting screen frames in response to user inputs such as mouse movements, clicks, and keyboard events. NeuralOS combines a recurrent neural network (RNN), which tracks computer state, with a diffusion-based neural renderer that generates screen images. The model is trained on a dataset of Ubuntu XFCE recordings, which include both randomly generated interactions and realistic interactions produced by AI agents. Experiments show that NeuralOS successfully renders realistic GUI sequences, accurately captures mouse interactions, and reliably predicts state transitions like application launches. Beyond reproducing existing systems, NeuralOS shows that synthesized training data can teach the model to simulate applications that were never installed, as illustrated by a Doom application, and suggests a path toward learning user interfaces purely from synthetic demonstrations.

Multi-lingual competence in large language models is often evaluated via static data benchmarks such as Belebele, M-MMLU and M-GSM. However, these evaluations often fail to provide an adequate understanding of the practical performance and robustness of models across multi-lingual settings. In response, we create multi-lingual functional benchmarks -- Cross-Lingual Grade School Math Symbolic (CL-GSM Symbolic) and Cross-Lingual Instruction-Following Eval (CL-IFEval)-- by translating existing functional benchmark templates from English to five additional languages that span the range of resources available for NLP: French, Spanish, Hindi, Arabic and Yoruba. Our results reveal that some static multi-lingual benchmarks capture functional performance much more closely than others (i.e. across models, there is a 24%, 17% and 18% decrease in performance between M-GSM and CL-GSM Symbolic in English, French and Spanish respectively; similarly there's a 15 - 24% performance drop across languages between Belebele and CL-IFEval, and only a 0.5% to 3% performance drop between M-MMLU and CL-IFEval). Similarly, we find that model robustness across languages varies significantly, with certain languages (eg. Arabic, English) being the most consistently well performing across evaluation iterations.

This paper presents a new long-form release of the Swiss Parliaments Corpus, converting entire multi-hour Swiss German debate sessions (each aligned with the official session protocols) into high-quality speech-text pairs. Our pipeline starts by transcribing all session audio into Standard German using Whisper Large-v3 under high-compute settings. We then apply a two-step GPT-4o correction process: first, GPT-4o ingests the raw Whisper output alongside the official protocols to refine misrecognitions, mainly named entities. Second, a separate GPT-4o pass evaluates each refined segment for semantic completeness. We filter out any segments whose Predicted BLEU score (derived from Whisper's average token log-probability) and GPT-4o evaluation score fall below a certain threshold. The final corpus contains 801 hours of audio, of which 555 hours pass our quality control. Compared to the original sentence-level SPC release, our long-form dataset achieves a 6-point BLEU improvement, demonstrating the power of combining robust ASR, LLM-based correction, and data-driven filtering for low-resource, domain-specific speech corpora.

Large Language Models (LLMs) are rapidly advancing across diverse domains, yet their application in theoretical physics remains inadequate. While current models show competence in mathematical reasoning and code generation, we identify critical gaps in physical intuition, constraint satisfaction, and reliable reasoning that cannot be addressed through prompting alone. Physics demands approximation judgment, symmetry exploitation, and physical grounding that require AI agents specifically trained on physics reasoning patterns and equipped with physics-aware verification tools. We argue that LLM would require such domain-specialized training and tooling to be useful in real-world for physics research. We envision physics-specialized AI agents that seamlessly handle multimodal data, propose physically consistent hypotheses, and autonomously verify theoretical results. Realizing this vision requires developing physics-specific training datasets, reward signals that capture physical reasoning quality, and verification frameworks encoding fundamental principles. We call for collaborative efforts between physics and AI communities to build the specialized infrastructure necessary for AI-driven scientific discovery.

Multimodal large language models (MLLMs) have demonstrated significant progress in semantic scene understanding and text-image alignment, with reasoning variants enhancing performance on more complex tasks involving mathematics and logic. To bridge this gap, we introduce ReasonMap, a novel benchmark specifically designed to evaluate these capabilities. ReasonMap encompasses high-resolution transit maps from 30 cities and includes 1,008 question-answer pairs spanning two question types and three templates. Furthermore, we design a two-level evaluation pipeline that properly assesses answer correctness and quality. Our comprehensive evaluation of 16 popular MLLMs reveals a counterintuitive pattern: among open-source models, base variants outperform their reasoning-tuned counterparts, whereas the opposite trend is observed in closed-source models. Further analysis under the visual-masking setting confirms that strong performance necessitates direct visual grounding, rather than relying solely on language priors. We further establish a training baseline with reinforcement fine-tuning, providing a reference for future exploration. We hope this benchmark study offers new insights into visual reasoning and helps investigate the gap between open- and closed-source models.

Deep generative models hold great promise for representing complex physical systems, but their deployment is currently limited by the lack of guarantees on the physical plausibility of the generated outputs. Ensuring that known physical constraints are enforced is therefore critical when applying generative models to scientific and engineering problems. We address this limitation by developing a principled framework for sampling from a target distribution while rigorously satisfying mathematical constraints. Leveraging the variational formulation of Langevin dynamics and Lagrangian duality, we propose Constrained Alternated Split Augmented Langevin (CASAL), a novel primal-dual sampling algorithm that enforces constraints progressively through variable splitting. We analyze our algorithm in Wasserstein space and derive explicit mixing time rates. While the method is developed theoretically for Langevin dynamics, we demonstrate its applicability to diffusion models. We apply our method to diffusion-based data assimilation on a complex physical system, where enforcing physical constraints substantially improves both forecast accuracy and the preservation of critical conserved quantities. We also demonstrate the potential of CASAL for challenging non-convex feasibility problems in optimal control.

Wheel-legged robots combine the advantages of both wheeled robots and legged robots, offering versatile locomotion capabilities with excellent stability on challenging terrains and high efficiency on flat surfaces. However, existing wheel-legged robots typically have limited hip joint mobility compared to humans, while hip joint plays a crucial role in locomotion. In this paper, we introduce Whleaper, a novel 10-degree-of-freedom (DOF) bipedal wheeled robot, with 3 DOFs at the hip of each leg. Its humanoid joint design enables adaptable motion in complex scenarios, ensuring stability and flexibility. This paper introduces the details of Whleaper, with a focus on innovative mechanical design, control algorithms and system implementation. Firstly, stability stems from the increased DOFs at the hip, which expand the range of possible postures and improve the robot's foot-ground contact. Secondly, the extra DOFs also augment its mobility. During walking or sliding, more complex movements can be adopted to execute obstacle avoidance tasks. Thirdly, we utilize two control algorithms to implement multimodal motion for walking and sliding. By controlling specific DOFs of the robot, we conducted a series of simulations and practical experiments, demonstrating that a high-DOF hip joint design can effectively enhance the stability and flexibility of wheel-legged robots. Whleaper shows its capability to perform actions such as squatting, obstacle avoidance sliding, and rapid turning in real-world scenarios.

Federated learning (FL) enables privacy-preserving collaborative model training without direct data sharing. Model-heterogeneous FL (MHFL) extends this paradigm by allowing clients to train personalized models with heterogeneous architectures tailored to their computational resources and application-specific needs. However, existing MHFL methods predominantly rely on centralized aggregation, which introduces scalability and efficiency bottlenecks, or impose restrictions requiring partially identical model architectures across clients. While peer-to-peer (P2P) FL removes server dependence, it suffers from model drift and knowledge dilution, limiting its effectiveness in heterogeneous settings. To address these challenges, we propose FedSKD, a novel MHFL framework that facilitates direct knowledge exchange through round-robin model circulation, eliminating the need for centralized aggregation while allowing fully heterogeneous model architectures across clients. FedSKD's key innovation lies in multi-dimensional similarity knowledge distillation, which enables bidirectional cross-client knowledge transfer at batch, pixel/voxel, and region levels for heterogeneous models in FL. This approach mitigates catastrophic forgetting and model drift through progressive reinforcement and distribution alignment while preserving model heterogeneity. Extensive evaluations on fMRI-based autism spectrum disorder diagnosis and skin lesion classification demonstrate that FedSKD outperforms state-of-the-art heterogeneous and homogeneous FL baselines, achieving superior personalization (client-specific accuracy) and generalization (cross-institutional adaptability). These findings underscore FedSKD's potential as a scalable and robust solution for real-world medical federated learning applications.

Graph generation is a critical yet challenging task, as empirical analyses require a deep understanding of complex, non-Euclidean structures. Diffusion models have recently made significant advances in graph generation, but these models are typically adapted from image generation frameworks and overlook inherent higher-order topology, limiting their ability to capture graph topology. In this work, we propose Higher-order Guided Diffusion (HOG-Diff), a principled framework that progressively generates plausible graphs with inherent topological structures. HOG-Diff follows a coarse-to-fine generation curriculum, guided by higher-order topology and implemented via diffusion bridges. We further prove that our model admits stronger theoretical guarantees than classical diffusion frameworks. Extensive experiments across eight graph generation benchmarks, spanning diverse domains and including large-scale settings, demonstrate the scalability of our method and its superior performance on both pairwise and higher-order topological metrics. Our project page is available \href{https://circle-group.github.io/research/hog-diff/}{here}.