Showing 1–50 of 357 results for author: Yue, X

Efficient Learned Data Compression via Dual-Stream Feature Decoupling

Authors: Huidong Ma, Xinyan Shi, Hui Sun, Xiaofei Yue, Xiaoguang Liu, Gang Wang, Wentong Cai

Abstract: While Learned Data Compression (LDC) has achieved superior compression ratios, balancing precise probability modeling with system efficiency remains challenging. Crucially, uniform single-stream architectures struggle to simultaneously capture micro-syntactic and macro-semantic features, necessitating deep serial stacking that exacerbates latency. Compounding this, heterogeneous systems are constr… ▽ More While Learned Data Compression (LDC) has achieved superior compression ratios, balancing precise probability modeling with system efficiency remains challenging. Crucially, uniform single-stream architectures struggle to simultaneously capture micro-syntactic and macro-semantic features, necessitating deep serial stacking that exacerbates latency. Compounding this, heterogeneous systems are constrained by device speed mismatches, where throughput is capped by Amdahl's Law due to serial processing. To this end, we propose a Dual-Stream Multi-Scale Decoupler that disentangles local and global contexts to replace deep serial processing with shallow parallel streams, and incorporate a Hierarchical Gated Refiner for adaptive feature refinement and precise probability modeling. Furthermore, we design a Concurrent Stream-Parallel Pipeline, which overcomes systemic bottlenecks to achieve full-pipeline parallelism. Extensive experiments demonstrate that our method achieves state-of-the-art performance in both compression ratio and throughput, while maintaining the lowest latency and memory usage. The code is available at https://github.com/huidong-ma/FADE. △ Less

Submitted 8 April, 2026; originally announced April 2026.

Comments: Accepted to ACL 2026

The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook

Authors: Xinlei Yu, Zhangquan Chen, Yongbo He, Tianyu Fu, Cheng Yang, Chengming Xu, Yue Ma, Xiaobin Hu, Zhe Cao, Jie Xu, Guibin Zhang, Jiale Tao, Jiayi Zhang, Siyuan Ma, Kaituo Feng, Haojie Huang, Youxing Li, Ronghao Chen, Huacan Wang, Chenglin Wu, Zikun Su, Xiaogang Xu, Kelu Yao, Kun Wang, Chen Gao , et al. (12 additional authors not shown)

Abstract: Latent space is rapidly emerging as a native substrate for language-based models. While modern systems are still commonly understood through explicit token-level generation, an increasing body of work shows that many critical internal processes are more naturally carried out in continuous latent space than in human-readable verbal traces. This shift is driven by the structural limitations of expli… ▽ More Latent space is rapidly emerging as a native substrate for language-based models. While modern systems are still commonly understood through explicit token-level generation, an increasing body of work shows that many critical internal processes are more naturally carried out in continuous latent space than in human-readable verbal traces. This shift is driven by the structural limitations of explicit-space computation, including linguistic redundancy, discretization bottlenecks, sequential inefficiency, and semantic loss. This survey aims to provide a unified and up-to-date landscape of latent space in language-based models. We organize the survey into five sequential perspectives: Foundation, Evolution, Mechanism, Ability, and Outlook. We begin by delineating the scope of latent space, distinguishing it from explicit or verbal space and from the latent spaces commonly studied in generative visual models. We then trace the field's evolution from early exploratory efforts to the current large-scale expansion. To organize the technical landscape, we examine existing work through the complementary lenses of mechanism and ability. From the perspective of Mechanism, we identify four major lines of development: Architecture, Representation, Computation, and Optimization. From the perspective of Ability, we show how latent space supports a broad capability spectrum spanning Reasoning, Planning, Modeling, Perception, Memory, Collaboration, and Embodiment. Beyond consolidation, we discuss the key open challenges, and outline promising directions for future research. We hope this survey serves not only as a reference for existing work, but also as a foundation for understanding latent space as a general computational and systems paradigm for next-generation intelligence. △ Less

Submitted 2 April, 2026; originally announced April 2026.

Gen-Searcher: Reinforcing Agentic Search for Image Generation

Authors: Kaituo Feng, Manyuan Zhang, Shuang Chen, Yunlong Lin, Kaixuan Fan, Yilei Jiang, Hongyu Li, Dian Zheng, Chenyang Wang, Xiangyu Yue

Abstract: Recent image generation models have shown strong capabilities in generating high-fidelity and photorealistic images. However, they are fundamentally constrained by frozen internal knowledge, thus often failing on real-world scenarios that are knowledge-intensive or require up-to-date information. In this paper, we present Gen-Searcher, as the first attempt to train a search-augmented image generat… ▽ More Recent image generation models have shown strong capabilities in generating high-fidelity and photorealistic images. However, they are fundamentally constrained by frozen internal knowledge, thus often failing on real-world scenarios that are knowledge-intensive or require up-to-date information. In this paper, we present Gen-Searcher, as the first attempt to train a search-augmented image generation agent, which performs multi-hop reasoning and search to collect the textual knowledge and reference images needed for grounded generation. To achieve this, we construct a tailored data pipeline and curate two high-quality datasets, Gen-Searcher-SFT-10k and Gen-Searcher-RL-6k, containing diverse search-intensive prompts and corresponding ground-truth synthesis images. We further introduce KnowGen, a comprehensive benchmark that explicitly requires search-grounded external knowledge for image generation and evaluates models from multiple dimensions. Based on these resources, we train Gen-Searcher with SFT followed by agentic reinforcement learning with dual reward feedback, which combines text-based and image-based rewards to provide more stable and informative learning signals for GRPO training. Experiments show that Gen-Searcher brings substantial gains, improving Qwen-Image by around 16 points on KnowGen and 15 points on WISE. We hope this work can serve as an open foundation for search agents in image generation, and we fully open-source our data, models, and code. △ Less

Submitted 30 March, 2026; originally announced March 2026.

Comments: Project page: https://gen-searcher.vercel.app Code: https://github.com/tulerfeng/Gen-Searcher

Option pricing model under the G-expectation framework

Authors: Ziting Pei, Xingye Yue, Xiaotao Zheng

Abstract: G-expectation, as a sublinear expectation, provides a powerful framework for modeling uncertainty in financial markets. Motivated by the need for robust valuation under model uncertainty, this work develops a unified risk-neutral valuation approach within the G-expectation environment, yielding a nonlinear generalization of the Black-Scholes model, termed the G-Black-Scholes equation. To enhance c… ▽ More G-expectation, as a sublinear expectation, provides a powerful framework for modeling uncertainty in financial markets. Motivated by the need for robust valuation under model uncertainty, this work develops a unified risk-neutral valuation approach within the G-expectation environment, yielding a nonlinear generalization of the Black-Scholes model, termed the G-Black-Scholes equation. To enhance computational efficiency and reduce numerical cost, we introduce a logarithmic transformation of the asset price, which yields an alternative nonlinear PDE. Based on this transformed formulation, we design both explicit and implicit finite difference schemes that are rigorously demonstrated to be consistent, stable, monotone, and convergent to the viscosity solution. Numerical examples confirm that the proposed schemes achieve high accuracy, while the logarithmic transformation relaxes the stability constraints of explicit schemes and improves computational efficiency. △ Less

Submitted 24 March, 2026; originally announced March 2026.

GIDE: Unlocking Diffusion LLMs for Precise Training-Free Image Editing

Authors: Zifeng Zhu, Jiaming Han, Jiaxiang Zhao, Minnan Luo, Xiangyu Yue

Abstract: While Diffusion Large Language Models (DLLMs) have demonstrated remarkable capabilities in multi-modal generation, performing precise, training-free image editing remains an open challenge. Unlike continuous diffusion models, the discrete tokenization inherent in DLLMs hinders the application of standard noise inversion techniques, often leading to structural degradation during editing. In this pa… ▽ More While Diffusion Large Language Models (DLLMs) have demonstrated remarkable capabilities in multi-modal generation, performing precise, training-free image editing remains an open challenge. Unlike continuous diffusion models, the discrete tokenization inherent in DLLMs hinders the application of standard noise inversion techniques, often leading to structural degradation during editing. In this paper, we introduce GIDE (Grounded Inversion for DLLM Image Editing), a unified framework designed to bridge this gap. GIDE incorporates a novel Discrete Noise Inversion mechanism that accurately captures latent noise patterns within the discrete token space, ensuring high-fidelity reconstruction. We then decompose the editing pipeline into grounding, inversion, and refinement stages. This design enables GIDE supporting various editing instructions (text, point and box) and operations while strictly preserving the unedited background. Furthermore, to overcome the limitations of existing single-step evaluation protocols, we introduce GIDE-Bench, a rigorous benchmark comprising 805 compositional editing scenarios guided by diverse multi-modal inputs. Extensive experiments on GIDE-Bench demonstrate that GIDE significantly outperforms prior training-free methods, improving Semantic Correctness by 51.83% and Perceptual Quality by 50.39%. Additional evaluations on ImgEdit-Bench confirm its broad applicability, demonstrating consistent gains over trained baselines and yielding photorealistic consistency on par with leading models. △ Less

Submitted 22 March, 2026; originally announced March 2026.

Comments: 25 pages, 7 figures

GaussianPile: A Unified Sparse Gaussian Splatting Framework for Slice-based Volumetric Reconstruction

Authors: Di Kong, Yikai Wang, Wenjie Guo, Yifan Bu, Boya Zhang, Yuexin Duan, Xiawei Yue, Wenbiao Du, Yiman Zhong, Yuwen Chen, Cheng Ma

Abstract: Slice-based volumetric imaging is widely applied and it demands representations that compress aggressively while preserving internal structure for analysis. We introduce GaussianPile, unifying 3D Gaussian splatting with an imaging system-aware focus model to address this challenge. Our proposed method introduces three key innovations: (i) a slice-aware piling strategy that positions anisotropic 3D… ▽ More Slice-based volumetric imaging is widely applied and it demands representations that compress aggressively while preserving internal structure for analysis. We introduce GaussianPile, unifying 3D Gaussian splatting with an imaging system-aware focus model to address this challenge. Our proposed method introduces three key innovations: (i) a slice-aware piling strategy that positions anisotropic 3D Gaussians to model through-slice contributions, (ii) a differentiable projection operator that encodes the finite-thickness point spread function of the imaging acquisition system, and (iii) a compact encoding and joint optimization pipeline that simultaneously reconstructs and compresses the Gaussian sets. Our CUDA-based design retains the compression and real-time rendering efficiency of Gaussian primitives while preserving high-frequency internal volumetric detail. Experiments on microscopy and ultrasound datasets demonstrate that our method reduces storage and reconstruction cost, sustains diagnostic fidelity, and enables fast 2D visualization, along with 3D voxelization. In practice, it delivers high-quality results in as few as 3 minutes, up to 11x faster than NeRF-based approaches, and achieves consistent 16x compression over voxel grids, offering a practical path to deployable compression and exploration of slice-based volumetric datasets. △ Less

Submitted 20 March, 2026; originally announced March 2026.

Comments: Accepted by IEEE/CVF Conference on Computer Vision and Pattern Recognition 2026 (CVPR 2026)

FailureMem: A Failure-Aware Multimodal Framework for Autonomous Software Repair

Authors: Ruize Ma, Yilei Jiang, Shilin Zhang, Zheng Ma, Yi Feng, Vincent Ng, Zhi Wang, Xiangyu Yue, Chuanyi Li, Lewei Lu

Abstract: Multimodal Automated Program Repair (MAPR) extends traditional program repair by requiring models to jointly reason over source code, textual issue descriptions, and visual artifacts such as GUI screenshots. While recent LLM-based repair systems have shown promising results, existing approaches face several limitations: rigid workflow pipelines restrict exploration during debugging, visual reasoni… ▽ More Multimodal Automated Program Repair (MAPR) extends traditional program repair by requiring models to jointly reason over source code, textual issue descriptions, and visual artifacts such as GUI screenshots. While recent LLM-based repair systems have shown promising results, existing approaches face several limitations: rigid workflow pipelines restrict exploration during debugging, visual reasoning is often performed over full-page screenshots without localized grounding, and failed repair attempts are rarely transformed into reusable knowledge. To address these challenges, we propose FailureMem, a multimodal repair framework that integrates three key mechanisms: a hybrid workflow-agent architecture that balances structured localization with flexible reasoning, active perception tools that enable region-level visual grounding, and a Failure Memory Bank that converts past repair attempts into reusable guidance. Experiments on SWE-bench Multimodal demonstrate FailureMem improves the resolved rate over GUIRepair by 3.7%. △ Less

Submitted 18 March, 2026; originally announced March 2026.

PreciseCache: Precise Feature Caching for Efficient and High-fidelity Video Generation

Authors: Jiangshan Wang, Kang Zhao, Jiayi Guo, Jiayu Wang, Hang Guo, Chenyang Zhu, Xiu Li, Xiangyu Yue

Abstract: High computational costs and slow inference hinder the practical application of video generation models. While prior works accelerate the generation process through feature caching, they often suffer from notable quality degradation. In this work, we reveal that this issue arises from their inability to distinguish truly redundant features, which leads to the unintended skipping of computations on… ▽ More High computational costs and slow inference hinder the practical application of video generation models. While prior works accelerate the generation process through feature caching, they often suffer from notable quality degradation. In this work, we reveal that this issue arises from their inability to distinguish truly redundant features, which leads to the unintended skipping of computations on important features. To address this, we propose \textbf{PreciseCache}, a plug-and-play framework that precisely detects and skips truly redundant computations, thereby accelerating inference without sacrificing quality. Specifically, PreciseCache contains two components: LFCache for step-wise caching and BlockCache for block-wise caching. For LFCache, we compute the Low-Frequency Difference (LFD) between the prediction features of the current step and those from the previous cached step. Empirically, we observe that LFD serves as an effective measure of step-wise redundancy, accurately detecting highly redundant steps whose computation can be skipped through reusing cached features. To further accelerate generation within each non-skipped step, we propose BlockCache, which precisely detects and skips redundant computations at the block level within the network. Extensive experiments on various backbones demonstrate the effectiveness of our PreciseCache, such as achieving an average of $2.6\times$ speedup on Wan2.1-14B without noticeable quality loss. △ Less

Submitted 2 March, 2026; v1 submitted 1 March, 2026; originally announced March 2026.

Comments: ICLR 2026

Whisper-MLA: Reducing GPU Memory Consumption of ASR Models based on MHA2MLA Conversion

Authors: Sen Zhang, Jianguo Wei, Wenhuan Lu, Xianghu Yue, Wei Li, Qiang Li, Pengcheng Zhao, Ming Cai, Luo Si

Abstract: The Transformer-based Whisper model has achieved state-of-the-art performance in Automatic Speech Recognition (ASR). However, its Multi-Head Attention (MHA) mechanism results in significant GPU memory consumption due to the linearly growing Key-Value (KV) cache usage, which is problematic for many applications especially with long-form audio. To address this, we introduce Whisper-MLA, a novel arch… ▽ More The Transformer-based Whisper model has achieved state-of-the-art performance in Automatic Speech Recognition (ASR). However, its Multi-Head Attention (MHA) mechanism results in significant GPU memory consumption due to the linearly growing Key-Value (KV) cache usage, which is problematic for many applications especially with long-form audio. To address this, we introduce Whisper-MLA, a novel architecture that incorporates Multi-Head Latent Attention (MLA) into the Whisper model. Specifically, we adapt MLA for Whisper's absolute positional embeddings and systematically investigate its application across encoder self-attention, decoder self-attention, and cross-attention modules. Empirical results indicate that applying MLA exclusively to decoder self-attention yields the desired balance between performance and memory efficiency. Our proposed approach allows conversion of a pretrained Whisper model to Whisper-MLA with minimal fine-tuning. Extensive experiments on the LibriSpeech benchmark validate the effectiveness of this conversion, demonstrating that Whisper-MLA reduces the KV cache size by up to 87.5% while maintaining competitive accuracy. △ Less

Submitted 28 February, 2026; originally announced March 2026.

Comments: 5 pages, 3 figures, accepted at ICASSP 2026

UniWeTok: An Unified Binary Tokenizer with Codebook Size $\mathit{2^{128}}$ for Unified Multimodal Large Language Model

Authors: Shaobin Zhuang, Yuang Ai, Jiaming Han, Weijia Mao, Xiaohui Li, Fangyikang Wang, Xiao Wang, Yan Li, Shanchuan Lin, Kun Xu, Zhenheng Yang, Huaibo Huang, Xiangyu Yue, Hao Chen, Yali Wang

Abstract: Unified Multimodal Large Language Models (MLLMs) require a visual representation that simultaneously supports high-fidelity reconstruction, complex semantic extraction, and generative suitability. However, existing visual tokenizers typically struggle to satisfy these conflicting objectives within a single framework. In this paper, we introduce UniWeTok, a unified discrete tokenizer designed to br… ▽ More Unified Multimodal Large Language Models (MLLMs) require a visual representation that simultaneously supports high-fidelity reconstruction, complex semantic extraction, and generative suitability. However, existing visual tokenizers typically struggle to satisfy these conflicting objectives within a single framework. In this paper, we introduce UniWeTok, a unified discrete tokenizer designed to bridge this gap using a massive binary codebook ($\mathit{2^{128}}$). For training framework, we introduce Pre-Post Distillation and a Generative-Aware Prior to enhance the semantic extraction and generative prior of the discrete tokens. In terms of model architecture, we propose a convolution-attention hybrid architecture with the SigLu activation function. SigLu activation not only bounds the encoder output and stabilizes the semantic distillation process but also effectively addresses the optimization conflict between token entropy loss and commitment loss. We further propose a three-stage training framework designed to enhance UniWeTok's adaptability cross various image resolutions and perception-sensitive scenarios, such as those involving human faces and textual content. On ImageNet, UniWeTok achieves state-of-the-art image generation performance (FID: UniWeTok 1.38 vs. REPA 1.42) while requiring a remarkably low training compute (Training Tokens: UniWeTok 33B vs. REPA 262B). On general-domain, UniWeTok demonstrates highly competitive capabilities across a broad range of tasks, including multimodal understanding, image generation (DPG Score: UniWeTok 86.63 vs. FLUX.1 [Dev] 83.84), and editing (GEdit Overall Score: UniWeTok 5.09 vs. OmniGen 5.06). We release code and models to facilitate community exploration of unified tokenizer and MLLM. △ Less

Submitted 11 March, 2026; v1 submitted 15 February, 2026; originally announced February 2026.

Comments: 29 pages, 9 figures, 33 tables

BitDance: Scaling Autoregressive Generative Models with Binary Tokens

Authors: Yuang Ai, Jiaming Han, Shaobin Zhuang, Weijia Mao, Xuefeng Hu, Ziyan Yang, Zhenheng Yang, Yali Wang, Huaibo Huang, Xiangyu Yue, Hao Chen

Abstract: We present BitDance, a scalable autoregressive (AR) image generator that predicts binary visual tokens instead of codebook indices. With high-entropy binary latents, BitDance lets each token represent up to $2^{256}$ states, yielding a compact yet highly expressive discrete representation. Sampling from such a huge token space is difficult with standard classification. To resolve this, BitDance us… ▽ More We present BitDance, a scalable autoregressive (AR) image generator that predicts binary visual tokens instead of codebook indices. With high-entropy binary latents, BitDance lets each token represent up to $2^{256}$ states, yielding a compact yet highly expressive discrete representation. Sampling from such a huge token space is difficult with standard classification. To resolve this, BitDance uses a binary diffusion head: instead of predicting an index with softmax, it employs continuous-space diffusion to generate the binary tokens. Furthermore, we propose next-patch diffusion, a new decoding method that predicts multiple tokens in parallel with high accuracy, greatly speeding up inference. On ImageNet 256x256, BitDance achieves an FID of 1.24, the best among AR models. With next-patch diffusion, BitDance beats state-of-the-art parallel AR models that use 1.4B parameters, while using 5.4x fewer parameters (260M) and achieving 8.7x speedup. For text-to-image generation, BitDance trains on large-scale multimodal tokens and generates high-resolution, photorealistic images efficiently, showing strong performance and favorable scaling. When generating 1024x1024 images, BitDance achieves a speedup of over 30x compared to prior AR models. We release code and models to facilitate further research on AR foundation models. Code and models are available at: https://github.com/shallowdream204/BitDance. △ Less

Submitted 13 March, 2026; v1 submitted 15 February, 2026; originally announced February 2026.

Comments: Code and models: https://github.com/shallowdream204/BitDance

Elastic Diffusion Transformer

Authors: Jiangshan Wang, Zeqiang Lai, Jiarui Chen, Jiayi Guo, Hang Guo, Xiu Li, Xiangyu Yue, Chunchao Guo

Abstract: Diffusion Transformers (DiT) have demonstrated remarkable generative capabilities but remain highly computationally expensive. Previous acceleration methods, such as pruning and distillation, typically rely on a fixed computational capacity, leading to insufficient acceleration and degraded generation quality. To address this limitation, we propose \textbf{Elastic Diffusion Transformer (E-DiT)}, a… ▽ More Diffusion Transformers (DiT) have demonstrated remarkable generative capabilities but remain highly computationally expensive. Previous acceleration methods, such as pruning and distillation, typically rely on a fixed computational capacity, leading to insufficient acceleration and degraded generation quality. To address this limitation, we propose \textbf{Elastic Diffusion Transformer (E-DiT)}, an adaptive acceleration framework for DiT that effectively improves efficiency while maintaining generation quality. Specifically, we observe that the generative process of DiT exhibits substantial sparsity (i.e., some computations can be skipped with minimal impact on quality), and this sparsity varies significantly across samples. Motivated by this observation, E-DiT equips each DiT block with a lightweight router that dynamically identifies sample-dependent sparsity from the input latent. Each router adaptively determines whether the corresponding block can be skipped. If the block is not skipped, the router then predicts the optimal MLP width reduction ratio within the block. During inference, we further introduce a block-level feature caching mechanism that leverages router predictions to eliminate redundant computations in a training-free manner. Extensive experiments across 2D image (Qwen-Image and FLUX) and 3D asset (Hunyuan3D-3.0) demonstrate the effectiveness of E-DiT, achieving up to $\sim$2$\times$ speedup with negligible loss in generation quality. Code will be available at https://github.com/wangjiangshan0725/Elastic-DiT. △ Less

Submitted 15 February, 2026; originally announced February 2026.

RISE: Self-Improving Robot Policy with Compositional World Model

Authors: Jiazhi Yang, Kunyang Lin, Jinwei Li, Wencong Zhang, Tianwei Lin, Longyan Wu, Zhizhong Su, Hao Zhao, Ya-Qin Zhang, Li Chen, Ping Luo, Xiangyu Yue, Hongyang Li

Abstract: Despite the sustained scaling on model capacity and data acquisition, Vision-Language-Action (VLA) models remain brittle in contact-rich and dynamic manipulation tasks, where minor execution deviations can compound into failures. While reinforcement learning (RL) offers a principled path to robustness, on-policy RL in the physical world is constrained by safety risk, hardware cost, and environment… ▽ More Despite the sustained scaling on model capacity and data acquisition, Vision-Language-Action (VLA) models remain brittle in contact-rich and dynamic manipulation tasks, where minor execution deviations can compound into failures. While reinforcement learning (RL) offers a principled path to robustness, on-policy RL in the physical world is constrained by safety risk, hardware cost, and environment reset. To bridge this gap, we present RISE, a scalable framework of robotic reinforcement learning via imagination. At its core is a Compositional World Model that (i) predicts multi-view future via a controllable dynamics model, and (ii) evaluates imagined outcomes with a progress value model, producing informative advantages for the policy improvement. Such compositional design allows state and value to be tailored by best-suited yet distinct architectures and objectives. These components are integrated into a closed-loop self-improving pipeline that continuously generates imaginary rollouts, estimates advantages, and updates the policy in imaginary space without costly physical interaction. Across three challenging real-world tasks, RISE yields significant improvement over prior art, with more than +35% absolute performance increase in dynamic brick sorting, +45% for backpack packing, and +35% for box closing, respectively. △ Less

Submitted 11 February, 2026; originally announced February 2026.

Comments: Project page: https://opendrivelab.com/kai0-rl/

MVISTA-4D: View-Consistent 4D World Model with Test-Time Action Inference for Robotic Manipulation

Authors: Jiaxu Wang, Yicheng Jiang, Tianlun He, Jingkai Sun, Qiang Zhang, Junhao He, Jiahang Cao, Zesen Gan, Mingyuan Sun, Qiming Shao, Xiangyu Yue

Abstract: World-model-based imagine-then-act becomes a promising paradigm for robotic manipulation, yet existing approaches typically support either purely image-based forecasting or reasoning over partial 3D geometry, limiting their ability to predict complete 4D scene dynamics. This work proposes a novel embodied 4D world model that enables geometrically consistent, arbitrary-view RGBD generation: given o… ▽ More World-model-based imagine-then-act becomes a promising paradigm for robotic manipulation, yet existing approaches typically support either purely image-based forecasting or reasoning over partial 3D geometry, limiting their ability to predict complete 4D scene dynamics. This work proposes a novel embodied 4D world model that enables geometrically consistent, arbitrary-view RGBD generation: given only a single-view RGBD observation as input, the model imagines the remaining viewpoints, which can then be back-projected and fused to assemble a more complete 3D structure across time. To efficiently learn the multi-view, cross-modality generation, we explicitly design cross-view and cross-modality feature fusion that jointly encourage consistency between RGB and depth and enforce geometric alignment across views. Beyond prediction, converting generated futures into actions is often handled by inverse dynamics, which is ill-posed because multiple actions can explain the same transition. We address this with a test-time action optimization strategy that backpropagates through the generative model to infer a trajectory-level latent best matching the predicted future, and a residual inverse dynamics model that turns this trajectory prior into accurate executable actions. Experiments on three datasets demonstrate strong performance on both 4D scene generation and downstream manipulation, and ablations provide practical insights into the key design choices. △ Less

Submitted 10 February, 2026; originally announced February 2026.

CausalGDP: Causality-Guided Diffusion Policies for Reinforcement Learning

Authors: Xiaofeng Xiao, Xiao Hu, Yang Ye, Xubo Yue

Abstract: Reinforcement learning (RL) has achieved remarkable success in a wide range of sequential decision-making problems. Recent diffusion-based policies further improve RL by modeling complex, high-dimensional action distributions. However, existing diffusion policies primarily rely on statistical associations and fail to explicitly account for causal relationships among states, actions, and rewards, l… ▽ More Reinforcement learning (RL) has achieved remarkable success in a wide range of sequential decision-making problems. Recent diffusion-based policies further improve RL by modeling complex, high-dimensional action distributions. However, existing diffusion policies primarily rely on statistical associations and fail to explicitly account for causal relationships among states, actions, and rewards, limiting their ability to identify which action components truly cause high returns. In this paper, we propose Causality-guided Diffusion Policy (CausalGDP), a unified framework that integrates causal reasoning into diffusion-based RL. CausalGDP first learns a base diffusion policy and an initial causal dynamical model from offline data, capturing causal dependencies among states, actions, and rewards. During real-time interaction, the causal information is continuously updated and incorporated as a guidance signal to steer the diffusion process toward actions that causally influence future states and rewards. By explicitly considering causality beyond association, CausalGDP focuses policy optimization on action components that genuinely drive performance improvements. Experimental results demonstrate that CausalGDP consistently achieves competitive or superior performance over state-of-the-art diffusion-based and offline RL methods, especially in complex, high-dimensional control tasks. △ Less

Submitted 9 February, 2026; originally announced February 2026.

InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery

Authors: Shiyang Feng, Runmin Ma, Xiangchao Yan, Yue Fan, Yusong Hu, Songtao Huang, Shuaiyu Zhang, Zongsheng Cao, Tianshuo Peng, Jiakang Yuan, Zijie Guo, Zhijie Zhong, Shangheng Du, Weida Wang, Jinxin Shi, Yuhao Zhou, Xiaohan He, Zhiyin Yu, Fangchen Yu, Qihao Zheng, Jiamin Wu, Mianxin Liu, Chi Zhang, Shaowei Hou, Shuya Li , et al. (32 additional authors not shown)

Abstract: We introduce InternAgent-1.5, a unified system designed for end-to-end scientific discovery across computational and empirical domains. The system is built on a structured architecture composed of three coordinated subsystems for generation, verification, and evolution. These subsystems are supported by foundational capabilities for deep research, solution optimization, and long horizon memory. Th… ▽ More We introduce InternAgent-1.5, a unified system designed for end-to-end scientific discovery across computational and empirical domains. The system is built on a structured architecture composed of three coordinated subsystems for generation, verification, and evolution. These subsystems are supported by foundational capabilities for deep research, solution optimization, and long horizon memory. The architecture allows InternAgent-1.5 to operate continuously across extended discovery cycles while maintaining coherent and improving behavior. It also enables the system to coordinate computational modeling and laboratory experimentation within a single unified system. We evaluate InternAgent-1.5 on scientific reasoning benchmarks such as GAIA, HLE, GPQA, and FrontierScience, and the system achieves leading performance that demonstrates strong foundational capabilities. Beyond these benchmarks, we further assess two categories of discovery tasks. In algorithm discovery tasks, InternAgent-1.5 autonomously designs competitive methods for core machine learning problems. In empirical discovery tasks, it executes complete computational or wet lab experiments and produces scientific findings in earth, life, biological, and physical domains. Overall, these results show that InternAgent-1.5 provides a general and scalable framework for autonomous scientific discovery. △ Less

Submitted 9 February, 2026; originally announced February 2026.

Comments: Code and project page: https://github.com/InternScience/InternAgent

Physics as the Inductive Bias for Causal Discovery

Authors: Jianhong Chen, Naichen Shi, Xubo Yue

Abstract: Causal discovery is often a data-driven paradigm to analyze complex real-world systems. In parallel, physics-based models such as ordinary differential equations (ODEs) provide mechanistic structure for many dynamical processes. Integrating these paradigms potentially allows physical knowledge to act as an inductive bias, improving identifiability, stability, and robustness of causal discovery in… ▽ More Causal discovery is often a data-driven paradigm to analyze complex real-world systems. In parallel, physics-based models such as ordinary differential equations (ODEs) provide mechanistic structure for many dynamical processes. Integrating these paradigms potentially allows physical knowledge to act as an inductive bias, improving identifiability, stability, and robustness of causal discovery in dynamical systems. However, such integration remains challenging: real dynamical systems often exhibit feedback, cyclic interactions, and non-stationary data trend, while many widely used causal discovery methods are formulated under acyclicity or equilibrium-based assumptions. In this work, we propose an integrative causal discovery framework for dynamical systems that leverages partial physical knowledge as an inductive bias. Specifically, we model system evolution as a stochastic differential equation (SDE), where the drift term encodes known ODE dynamics and the diffusion term corresponds to unknown causal couplings beyond the prescribed physics. We develop a scalable sparsity-inducing MLE algorithm that exploits causal graph structure for efficient parameter estimation. Under mild conditions, we establish guarantees to recover the causal graph. Experiments on dynamical systems with diverse causal structures show that our approach improves causal graph recovery and produces more stable, physically consistent estimates than purely data-driven state-of-the-art baselines. △ Less

Submitted 3 February, 2026; originally announced February 2026.

Asymmetric Hierarchical Anchoring for Audio-Visual Joint Representation: Resolving Information Allocation Ambiguity for Robust Cross-Modal Generalization

Authors: Bixing Wu, Yuhong Zhao, Zongli Ye, Jiachen Lian, Xiangyu Yue, Gopala Anumanchipalli

Abstract: Audio-visual joint representation learning under Cross-Modal Generalization (CMG) aims to transfer knowledge from a labeled source modality to an unlabeled target modality through a unified discrete representation space. Existing symmetric frameworks often suffer from information allocation ambiguity, where the absence of structural inductive bias leads to semantic-specific leakage across modaliti… ▽ More Audio-visual joint representation learning under Cross-Modal Generalization (CMG) aims to transfer knowledge from a labeled source modality to an unlabeled target modality through a unified discrete representation space. Existing symmetric frameworks often suffer from information allocation ambiguity, where the absence of structural inductive bias leads to semantic-specific leakage across modalities. We propose Asymmetric Hierarchical Anchoring (AHA), which enforces directional information allocation by designating a structured semantic anchor within a shared hierarchy. In our instantiation, we exploit the hierarchical discrete representations induced by audio Residual Vector Quantization (RVQ) to guide video feature distillation into a shared semantic space. To ensure representational purity, we replace fragile mutual information estimators with a GRL-based adversarial decoupler that explicitly suppresses semantic leakage in modality-specific branches, and introduce Local Sliding Alignment (LSA) to encourage fine-grained temporal alignment across modalities. Extensive experiments on AVE and AVVP benchmarks demonstrate that AHA consistently outperforms symmetric baselines in cross-modal transfer. Additional analyses on talking-face disentanglement experiment further validate that the learned representations exhibit improved semantic consistency and disentanglement, indicating the broader applicability of the proposed framework. △ Less

Submitted 3 February, 2026; originally announced February 2026.

Comments: 18 pages, 11 figures

CVE-Factory: Scaling Expert-Level Agentic Tasks for Code Security Vulnerability

Authors: Xianzhen Luo, Jingyuan Zhang, Shiqi Zhou, Rain Huang, Chuan Xiao, Qingfu Zhu, Zhiyuan Ma, Xing Yue, Yang Yue, Wencong Zeng, Wanxiang Che

Abstract: Evaluating and improving the security capabilities of code agents requires high-quality, executable vulnerability tasks. However, existing works rely on costly, unscalable manual reproduction and suffer from outdated data distributions. To address these, we present CVE-Factory, the first multi-agent framework to achieve expert-level quality in automatically transforming sparse CVE metadata into fu… ▽ More Evaluating and improving the security capabilities of code agents requires high-quality, executable vulnerability tasks. However, existing works rely on costly, unscalable manual reproduction and suffer from outdated data distributions. To address these, we present CVE-Factory, the first multi-agent framework to achieve expert-level quality in automatically transforming sparse CVE metadata into fully executable agentic tasks. Cross-validation against human expert reproductions shows that CVE-Factory achieves 95\% solution correctness and 96\% environment fidelity, confirming its expert-level quality. It is also evaluated on the latest realistic vulnerabilities and achieves a 66.2\% verified success. This automation enables two downstream contributions. First, we construct LiveCVEBench, a continuously updated benchmark of 190 tasks spanning 14 languages and 153 repositories that captures emerging threats including AI-tooling vulnerabilities. Second, we synthesize over 1,000 executable training environments, the first large-scale scaling of agentic tasks in code security. Fine-tuned Qwen3-32B improves from 5.3\% to 35.8\% on LiveCVEBench, surpassing Claude 4.5 Sonnet, with gains generalizing to Terminal Bench (12.5\% to 31.3\%). We open-source CVE-Factory, LiveCVEBench, Abacus-cve (fine-tuned model), training dataset, and leaderboard. All resources are available at https://github.com/livecvebench/CVE-Factory . △ Less

Submitted 2 February, 2026; originally announced February 2026.

Comments: Under Review

Learning While Staying Curious: Entropy-Preserving Supervised Fine-Tuning via Adaptive Self-Distillation for Large Reasoning Models

Authors: Hao Wang, Hao Gu, Hongming Piao, Kaixiong Gong, Yuxiao Ye, Xiangyu Yue, Sirui Han, Yike Guo, Dapeng Wu

Abstract: The standard post-training recipe for large reasoning models, supervised fine-tuning followed by reinforcement learning (SFT-then-RL), may limit the benefits of the RL stage: while SFT imitates expert demonstrations, it often causes overconfidence and reduces generation diversity, leaving RL with a narrowed solution space to explore. Adding entropy regularization during SFT is not a cure-all; it t… ▽ More The standard post-training recipe for large reasoning models, supervised fine-tuning followed by reinforcement learning (SFT-then-RL), may limit the benefits of the RL stage: while SFT imitates expert demonstrations, it often causes overconfidence and reduces generation diversity, leaving RL with a narrowed solution space to explore. Adding entropy regularization during SFT is not a cure-all; it tends to flatten token distributions toward uniformity, increasing entropy without improving meaningful exploration capability. In this paper, we propose CurioSFT, an entropy-preserving SFT method designed to enhance exploration capabilities through intrinsic curiosity. It consists of (a) Self-Exploratory Distillation, which distills the model toward a self-generated, temperature-scaled teacher to encourage exploration within its capability; and (b) Entropy-Guided Temperature Selection, which adaptively adjusts distillation strength to mitigate knowledge forgetting by amplifying exploration at reasoning tokens while stabilizing factual tokens. Extensive experiments on mathematical reasoning tasks demonstrate that, in SFT stage, CurioSFT outperforms the vanilla SFT by 2.5 points on in-distribution tasks and 2.9 points on out-of-distribution tasks. We also verify that exploration capabilities preserved during SFT successfully translate into concrete gains in RL stage, yielding an average improvement of 5.0 points. △ Less

Submitted 7 February, 2026; v1 submitted 2 February, 2026; originally announced February 2026.

Exploring Reasoning Reward Model for Agents

Authors: Kaixuan Fan, Kaituo Feng, Manyuan Zhang, Tianshuo Peng, Zhixun Li, Yilei Jiang, Shuang Chen, Peng Pei, Xunliang Cai, Xiangyu Yue

Abstract: Agentic Reinforcement Learning (Agentic RL) has achieved notable success in enabling agents to perform complex reasoning and tool use. However, most methods still relies on sparse outcome-based reward for training. Such feedback fails to differentiate intermediate reasoning quality, leading to suboptimal training results. In this paper, we introduce Agent Reasoning Reward Model (Agent-RRM), a mult… ▽ More Agentic Reinforcement Learning (Agentic RL) has achieved notable success in enabling agents to perform complex reasoning and tool use. However, most methods still relies on sparse outcome-based reward for training. Such feedback fails to differentiate intermediate reasoning quality, leading to suboptimal training results. In this paper, we introduce Agent Reasoning Reward Model (Agent-RRM), a multi-faceted reward model that produces structured feedback for agentic trajectories, including (1) an explicit reasoning trace , (2) a focused critique that provides refinement guidance by highlighting reasoning flaws, and (3) an overall score that evaluates process performance. Leveraging these signals, we systematically investigate three integration strategies: Reagent-C (text-augmented refinement), Reagent-R (reward-augmented guidance), and Reagent-U (unified feedback integration). Extensive evaluations across 12 diverse benchmarks demonstrate that Reagent-U yields substantial performance leaps, achieving 43.7% on GAIA and 46.2% on WebWalkerQA, validating the effectiveness of our reasoning reward model and training schemes. Code, models, and datasets are all released to facilitate future research. △ Less

Submitted 29 January, 2026; originally announced January 2026.

Comments: Project page: https://github.com/kxfan2002/Reagent

How to Build Robust, Scalable Models for GSV-Based Indicators in Neighborhood Research

Authors: Xiaoya Tang, Xiaohe Yue, Heran Mane, Dapeng Li, Quynh Nguyen, Tolga Tasdizen

Abstract: A substantial body of health research demonstrates a strong link between neighborhood environments and health outcomes. Recently, there has been increasing interest in leveraging advances in computer vision to enable large-scale, systematic characterization of neighborhood built environments. However, the generalizability of vision models across fundamentally different domains remains uncertain, f… ▽ More A substantial body of health research demonstrates a strong link between neighborhood environments and health outcomes. Recently, there has been increasing interest in leveraging advances in computer vision to enable large-scale, systematic characterization of neighborhood built environments. However, the generalizability of vision models across fundamentally different domains remains uncertain, for example, transferring knowledge from ImageNet to the distinct visual characteristics of Google Street View (GSV) imagery. In applied fields such as social health research, several critical questions arise: which models are most appropriate, whether to adopt unsupervised training strategies, what training scale is feasible under computational constraints, and how much such strategies benefit downstream performance. These decisions are often costly and require specialized expertise. In this paper, we answer these questions through empirical analysis and provide practical insights into how to select and adapt foundation models for datasets with limited size and labels, while leveraging larger, unlabeled datasets through unsupervised training. Our study includes comprehensive quantitative and visual analyses comparing model performance before and after unsupervised adaptation. △ Less

Submitted 10 January, 2026; originally announced January 2026.

The RoboSense Challenge: Sense Anything, Navigate Anywhere, Adapt Across Platforms

Authors: Lingdong Kong, Shaoyuan Xie, Zeying Gong, Ye Li, Meng Chu, Ao Liang, Yuhao Dong, Tianshuai Hu, Ronghe Qiu, Rong Li, Hanjiang Hu, Dongyue Lu, Wei Yin, Wenhao Ding, Linfeng Li, Hang Song, Wenwei Zhang, Yuexin Ma, Junwei Liang, Zhedong Zheng, Lai Xing Ng, Benoit R. Cottereau, Wei Tsang Ooi, Ziwei Liu, Zhanpeng Zhang , et al. (114 additional authors not shown)

Abstract: Autonomous systems are increasingly deployed in open and dynamic environments -- from city streets to aerial and indoor spaces -- where perception models must remain reliable under sensor noise, environmental variation, and platform shifts. However, even state-of-the-art methods often degrade under unseen conditions, highlighting the need for robust and generalizable robot sensing. The RoboSense 2… ▽ More Autonomous systems are increasingly deployed in open and dynamic environments -- from city streets to aerial and indoor spaces -- where perception models must remain reliable under sensor noise, environmental variation, and platform shifts. However, even state-of-the-art methods often degrade under unseen conditions, highlighting the need for robust and generalizable robot sensing. The RoboSense 2025 Challenge is designed to advance robustness and adaptability in robot perception across diverse sensing scenarios. It unifies five complementary research tracks spanning language-grounded decision making, socially compliant navigation, sensor configuration generalization, cross-view and cross-modal correspondence, and cross-platform 3D perception. Together, these tasks form a comprehensive benchmark for evaluating real-world sensing reliability under domain shifts, sensor failures, and platform discrepancies. RoboSense 2025 provides standardized datasets, baseline models, and unified evaluation protocols, enabling large-scale and reproducible comparison of robust perception methods. The challenge attracted 143 teams from 85 institutions across 16 countries, reflecting broad community engagement. By consolidating insights from 23 winning solutions, this report highlights emerging methodological trends, shared design principles, and open challenges across all tracks, marking a step toward building robots that can sense reliably, act robustly, and adapt across platforms in real-world environments. △ Less

Submitted 8 January, 2026; originally announced January 2026.

Comments: Official IROS 2025 RoboSense Challenge Report; 51 pages, 37 figures, 5 tables; Competition Website at https://robosense2025.github.io/

RePose: A Real-Time 3D Human Pose Estimation and Biomechanical Analysis Framework for Rehabilitation

Authors: Junxiao Xue, Pavel Smirnov, Ziao Li, Yunyun Shi, Shi Chen, Xinyi Yin, Xiaohan Yue, Lei Wang, Yiduo Wang, Feng Lin, Yijia Chen, Xiao Ma, Xiaoran Yan, Qing Zhang, Fengjian Xue, Xuecheng Wu

Abstract: We propose a real-time 3D human pose estimation and motion analysis method termed RePose for rehabilitation training. It is capable of real-time monitoring and evaluation of patients'motion during rehabilitation, providing immediate feedback and guidance to assist patients in executing rehabilitation exercises correctly. Firstly, we introduce a unified pipeline for end-to-end real-time human pose… ▽ More We propose a real-time 3D human pose estimation and motion analysis method termed RePose for rehabilitation training. It is capable of real-time monitoring and evaluation of patients'motion during rehabilitation, providing immediate feedback and guidance to assist patients in executing rehabilitation exercises correctly. Firstly, we introduce a unified pipeline for end-to-end real-time human pose estimation and motion analysis using RGB video input from multiple cameras which can be applied to the field of rehabilitation training. The pipeline can help to monitor and correct patients'actions, thus aiding them in regaining muscle strength and motor functions. Secondly, we propose a fast tracking method for medical rehabilitation scenarios with multiple-person interference, which requires less than 1ms for tracking for a single frame. Additionally, we modify SmoothNet for real-time posture estimation, effectively reducing pose estimation errors and restoring the patient's true motion state, making it visually smoother. Finally, we use Unity platform for real-time monitoring and evaluation of patients' motion during rehabilitation, and to display the muscle stress conditions to assist patients with their rehabilitation training. △ Less

Submitted 2 January, 2026; originally announced January 2026.

High Dimensional Data Decomposition for Anomaly Detection of Textured Images

Authors: Ji Song, Xing Wang, Jianguo Wu, Xiaowei Yue

Abstract: In the realm of diverse high-dimensional data, images play a significant role across various processes of manufacturing systems where efficient image anomaly detection has emerged as a core technology of utmost importance. However, when applied to textured defect images, conventional anomaly detection methods have limitations including non-negligible misidentification, low robustness, and excessiv… ▽ More In the realm of diverse high-dimensional data, images play a significant role across various processes of manufacturing systems where efficient image anomaly detection has emerged as a core technology of utmost importance. However, when applied to textured defect images, conventional anomaly detection methods have limitations including non-negligible misidentification, low robustness, and excessive reliance on large-scale and structured datasets. This paper proposes a texture basis integrated smooth decomposition (TBSD) approach, which is targeted at efficient anomaly detection in textured images with smooth backgrounds and sparse anomalies. Mathematical formulation of quasi-periodicity and its theoretical properties are investigated for image texture estimation. TBSD method consists of two principal processes: the first process learns the texture basis functions to effectively extract quasi-periodic texture patterns; the subsequent anomaly detection process utilizes that texture basis as prior knowledge to prevent texture misidentification and capture potential anomalies with high accuracy.The proposed method surpasses benchmarks with less misidentification, smaller training dataset requirement, and superior anomaly detection performance on both simulation and real-world datasets. △ Less

Submitted 23 December, 2025; originally announced December 2025.

In-Context Audio Control of Video Diffusion Transformers

Authors: Wenze Liu, Weicai Ye, Minghong Cai, Quande Liu, Xintao Wang, Xiangyu Yue

Abstract: Recent advancements in video generation have seen a shift towards unified, transformer-based foundation models that can handle multiple conditional inputs in-context. However, these models have primarily focused on modalities like text, images, and depth maps, while strictly time-synchronous signals like audio have been underexplored. This paper introduces In-Context Audio Control of video diffusi… ▽ More Recent advancements in video generation have seen a shift towards unified, transformer-based foundation models that can handle multiple conditional inputs in-context. However, these models have primarily focused on modalities like text, images, and depth maps, while strictly time-synchronous signals like audio have been underexplored. This paper introduces In-Context Audio Control of video diffusion transformers (ICAC), a framework that investigates the integration of audio signals for speech-driven video generation within a unified full-attention architecture, akin to FullDiT. We systematically explore three distinct mechanisms for injecting audio conditions: standard cross-attention, 2D self-attention, and unified 3D self-attention. Our findings reveal that while 3D attention offers the highest potential for capturing spatio-temporal audio-visual correlations, it presents significant training challenges. To overcome this, we propose a Masked 3D Attention mechanism that constrains the attention pattern to enforce temporal alignment, enabling stable training and superior performance. Our experiments demonstrate that this approach achieves strong lip synchronization and video quality, conditioned on an audio stream and reference images. △ Less

Submitted 21 December, 2025; originally announced December 2025.

AdaTooler-V: Adaptive Tool-Use for Images and Videos

Authors: Chaoyang Wang, Kaituo Feng, Dongyang Chen, Zhongyu Wang, Zhixun Li, Sicheng Gao, Meng Meng, Xu Zhou, Manyuan Zhang, Yuzhang Shang, Xiangyu Yue

Abstract: Recent advances have shown that multimodal large language models (MLLMs) benefit from multimodal interleaved chain-of-thought (CoT) with vision tool interactions. However, existing open-source models often exhibit blind tool-use reasoning patterns, invoking vision tools even when they are unnecessary, which significantly increases inference overhead and degrades model performance. To this end, we… ▽ More Recent advances have shown that multimodal large language models (MLLMs) benefit from multimodal interleaved chain-of-thought (CoT) with vision tool interactions. However, existing open-source models often exhibit blind tool-use reasoning patterns, invoking vision tools even when they are unnecessary, which significantly increases inference overhead and degrades model performance. To this end, we propose AdaTooler-V, an MLLM that performs adaptive tool-use by determining whether a visual problem truly requires tools. First, we introduce AT-GRPO, a reinforcement learning algorithm that adaptively adjusts reward scales based on the Tool Benefit Score of each sample, encouraging the model to invoke tools only when they provide genuine improvements. Moreover, we construct two datasets to support training: AdaTooler-V-CoT-100k for SFT cold start and AdaTooler-V-300k for RL with verifiable rewards across single-image, multi-image, and video data. Experiments across twelve benchmarks demonstrate the strong reasoning capability of AdaTooler-V, outperforming existing methods in diverse visual reasoning tasks. Notably, AdaTooler-V-7B achieves an accuracy of 89.8\% on the high-resolution benchmark V*, surpassing the commercial proprietary model GPT-4o and Gemini 1.5 Pro. All code, models, and data are released. △ Less

Submitted 19 December, 2025; v1 submitted 18 December, 2025; originally announced December 2025.

Comments: Project page: https://github.com/CYWang735/AdaTooler-V

OS-Oracle: A Comprehensive Framework for Cross-Platform GUI Critic Models

Authors: Zhenyu Wu, Jingjing Xie, Zehao Li, Bowen Yang, Qiushi Sun, Zhaoyang Liu, Zhoumianze Liu, Yu Qiao, Xiangyu Yue, Zun Wang, Zichen Ding

Abstract: With VLM-powered computer-using agents (CUAs) becoming increasingly capable at graphical user interface (GUI) navigation and manipulation, reliable step-level decision-making has emerged as a key bottleneck for real-world deployment. In long-horizon workflows, errors accumulate quickly and irreversible actions can cause unintended consequences, motivating critic models that assess each action befo… ▽ More With VLM-powered computer-using agents (CUAs) becoming increasingly capable at graphical user interface (GUI) navigation and manipulation, reliable step-level decision-making has emerged as a key bottleneck for real-world deployment. In long-horizon workflows, errors accumulate quickly and irreversible actions can cause unintended consequences, motivating critic models that assess each action before execution. While critic models offer a promising solution, their effectiveness is hindered by the lack of diverse, high-quality GUI feedback data and public critic benchmarks for step-level evaluation in computer use. To bridge these gaps, we introduce OS-Oracle that makes three core contributions: (1) a scalable data pipeline for synthesizing cross-platform GUI critic data; (2) a two-stage training paradigm combining supervised fine-tuning (SFT) and consistency-preserving group relative policy optimization (CP-GRPO); (3) OS-Critic Bench, a holistic benchmark for evaluating critic model performance across Mobile, Web, and Desktop platforms. Leveraging this framework, we curate a high-quality dataset containing 310k critic samples. The resulting critic model, OS-Oracle-7B, achieves state-of-the-art performance among open-source VLMs on OS-Critic Bench, and surpasses proprietary models on the mobile domain. Furthermore, when serving as a pre-critic, OS-Oracle-7B improves the performance of native GUI agents such as UI-TARS-1.5-7B in OSWorld and AndroidWorld environments. The code is open-sourced at https://github.com/numbmelon/OS-Oracle. △ Less

Submitted 18 December, 2025; originally announced December 2025.

QuadSentinel: Sequent Safety for Machine-Checkable Control in Multi-agent Systems

Authors: Yiliu Yang, Yilei Jiang, Qunzhong Wang, Yingshui Tan, Xiaoyong Zhu, Sherman S. M. Chow, Bo Zheng, Xiangyu Yue

Abstract: Safety risks arise as large language model-based agents solve complex tasks with tools, multi-step plans, and inter-agent messages. However, deployer-written policies in natural language are ambiguous and context dependent, so they map poorly to machine-checkable rules, and runtime enforcement is unreliable. Expressing safety policies as sequents, we propose \textsc{QuadSentinel}, a four-agent gua… ▽ More Safety risks arise as large language model-based agents solve complex tasks with tools, multi-step plans, and inter-agent messages. However, deployer-written policies in natural language are ambiguous and context dependent, so they map poorly to machine-checkable rules, and runtime enforcement is unreliable. Expressing safety policies as sequents, we propose \textsc{QuadSentinel}, a four-agent guard (state tracker, policy verifier, threat watcher, and referee) that compiles these policies into machine-checkable rules built from predicates over observable state and enforces them online. Referee logic plus an efficient top-$k$ predicate updater keeps costs low by prioritizing checks and resolving conflicts hierarchically. Measured on ST-WebAgentBench (ICML CUA~'25) and AgentHarm (ICLR~'25), \textsc{QuadSentinel} improves guardrail accuracy and rule recall while reducing false positives. Against single-agent baselines such as ShieldAgent (ICML~'25), it yields better overall safety control. Near-term deployments can adopt this pattern without modifying core agents by keeping policies separate and machine-checkable. Our code will be made publicly available at https://github.com/yyiliu/QuadSentinel. △ Less

Submitted 18 December, 2025; originally announced December 2025.

Comments: Preprint

R^2-HGP: A Double-Regularized Gaussian Process for Heterogeneous Transfer Learning

Authors: Duo Wang, Xinming Wang, Chao Wang, Xiaowei Yue, Jianguo Wu

Abstract: Multi-output Gaussian process (MGP) models have attracted significant attention for their flexibility and uncertainty-quantification capabilities, and have been widely adopted in multi-source transfer learning scenarios due to their ability to capture inter-task correlations. However, they still face several challenges in transfer learning. First, the input spaces of the source and target domains… ▽ More Multi-output Gaussian process (MGP) models have attracted significant attention for their flexibility and uncertainty-quantification capabilities, and have been widely adopted in multi-source transfer learning scenarios due to their ability to capture inter-task correlations. However, they still face several challenges in transfer learning. First, the input spaces of the source and target domains are often heterogeneous, which makes direct knowledge transfer difficult. Second, potential prior knowledge and physical information are typically ignored during heterogeneous transfer, hampering the utilization of domain-specific insights and leading to unstable mappings. Third, inappropriate information sharing among target and sources can easily lead to negative transfer. Traditional models fail to address these issues in a unified way. To overcome these limitations, this paper proposes a Double-Regularized Heterogeneous Gaussian Process framework (R^2-HGP). Specifically, a trainable prior probability mapping model is first proposed to align the heterogeneous input domains. The resulting aligned inputs are treated as latent variables, upon which a multi-source transfer GP model is constructed and the entire structure is integrated into a novel conditional variational autoencoder (CVAE) based framework. Physical insights is further incorporated as a regularization term to ensure that the alignment results adhere to known physical knowledge. Next, within the multi-source transfer GP model, a sparsity penalty is imposed on the transfer coefficients, enabling the model to adaptively select the most informative source outputs and suppress negative transfer. Extensive simulations and real-world engineering case studies validate the effectiveness of our R^2-HGP, demonstrating consistent superiority over state-of-the-art benchmarks across diverse evaluation metrics. △ Less

Submitted 10 December, 2025; originally announced December 2025.

Comments: 17 pages, 9 figures. Under review for IEEE TPAMI

On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models

Authors: Charlie Zhang, Graham Neubig, Xiang Yue

Abstract: Recent reinforcement learning (RL) techniques have yielded impressive reasoning improvements in language models, yet it remains unclear whether post-training truly extends a model's reasoning ability beyond what it acquires during pre-training. A central challenge is the lack of control in modern training pipelines: large-scale pre-training corpora are opaque, mid-training is often underexamined,… ▽ More Recent reinforcement learning (RL) techniques have yielded impressive reasoning improvements in language models, yet it remains unclear whether post-training truly extends a model's reasoning ability beyond what it acquires during pre-training. A central challenge is the lack of control in modern training pipelines: large-scale pre-training corpora are opaque, mid-training is often underexamined, and RL objectives interact with unknown prior knowledge in complex ways. To resolve this ambiguity, we develop a fully controlled experimental framework that isolates the causal contributions of pre-training, mid-training, and RL-based post-training. Our approach employs synthetic reasoning tasks with explicit atomic operations, parseable step-by-step reasoning traces, and systematic manipulation of training distributions. We evaluate models along two axes: extrapolative generalization to more complex compositions and contextual generalization across surface contexts. Using this framework, we reconcile competing views on RL's effectiveness. We show that: 1) RL produces true capability gains (pass@128) only when pre-training leaves sufficient headroom and when RL data target the model's edge of competence, tasks at the boundary that are difficult but not yet out of reach. 2) Contextual generalization requires minimal yet sufficient pre-training exposure, after which RL can reliably transfer. 3) Mid-training significantly enhances performance under fixed compute compared with RL only, demonstrating its central but underexplored role in training pipelines. 4) Process-level rewards reduce reward hacking and improve reasoning fidelity. Together, these results clarify the interplay between pre-training, mid-training, and RL, offering a foundation for understanding and improving reasoning LM training strategies. △ Less

Submitted 8 December, 2025; originally announced December 2025.

MIND: Multi-rationale INtegrated Discriminative Reasoning Framework for Multi-modal Large Models

Authors: Chuang Yu, Jinmiao Zhao, Mingxuan Zhao, Yunpeng Liu, Xiujun Shu, Yuanhao Feng, Bo Wang, Xiangyu Yue

Abstract: Recently, multimodal large language models (MLLMs) have been widely applied to reasoning tasks. However, they suffer from limited multi-rationale semantic modeling, insufficient logical robustness, and are susceptible to misleading interpretations in complex scenarios. Therefore, we propose a Multi-rationale INtegrated Discriminative (MIND) reasoning framework, which is designed to endow MLLMs wit… ▽ More Recently, multimodal large language models (MLLMs) have been widely applied to reasoning tasks. However, they suffer from limited multi-rationale semantic modeling, insufficient logical robustness, and are susceptible to misleading interpretations in complex scenarios. Therefore, we propose a Multi-rationale INtegrated Discriminative (MIND) reasoning framework, which is designed to endow MLLMs with human-like cognitive abilities of "Understand -> Rethink -> Correct", and achieves a paradigm evolution from passive imitation-based reasoning to active discriminative reasoning. Specifically, we introduce a Rationale Augmentation and Discrimination (RAD) paradigm, which automatically and efficiently expands existing datasets by generating diverse rationales, providing a unified and extensible data foundation. Meanwhile, we design a Progressive Two-stage Correction Learning (P2CL) strategy. The first phase enhances multi-rationale positive learning, while the second phase enables active logic discrimination and correction. In addition, to mitigate representation entanglement in the multi-rationale semantic space, we propose a Multi-rationale Contrastive Alignment (MCA) optimization strategy, which achieves semantic aggregation of correct reasoning and boundary separation of incorrect reasoning. Extensive experiments demonstrate that the proposed MIND reasoning framework achieves state-of-the-art (SOTA) performance on multiple public datasets covering scientific, commonsense, and mathematical scenarios. It provides a new perspective for advancing MLLMs towards higher levels of cognitive intelligence. Our code is available at https://github.com/YuChuang1205/MIND △ Less

Submitted 5 December, 2025; originally announced December 2025.

Rethinking Infrared Small Target Detection: A Foundation-Driven Efficient Paradigm

Authors: Chuang Yu, Jinmiao Zhao, Yunpeng Liu, Yaokun Li, Xiujun Shu, Yuanhao Feng, Bo Wang, Yimian Dai, Xiangyu Yue

Abstract: While large-scale visual foundation models (VFMs) exhibit strong generalization across diverse visual domains, their potential for single-frame infrared small target (SIRST) detection remains largely unexplored. To fill this gap, we systematically introduce the frozen representations from VFMs into the SIRST task for the first time and propose a Foundation-Driven Efficient Paradigm (FDEP), which c… ▽ More While large-scale visual foundation models (VFMs) exhibit strong generalization across diverse visual domains, their potential for single-frame infrared small target (SIRST) detection remains largely unexplored. To fill this gap, we systematically introduce the frozen representations from VFMs into the SIRST task for the first time and propose a Foundation-Driven Efficient Paradigm (FDEP), which can seamlessly adapt to existing encoder-decoder-based methods and significantly improve accuracy without additional inference overhead. Specifically, a Semantic Alignment Modulation Fusion (SAMF) module is designed to achieve dynamic alignment and deep fusion of the global semantic priors from VFMs with task-specific features. Meanwhile, to avoid the inference time burden introduced by VFMs, we propose a Collaborative Optimization-based Implicit Self-Distillation (CO-ISD) strategy, which enables implicit semantic transfer between the main and lightweight branches through parameter sharing and synchronized backpropagation. In addition, to unify the fragmented evaluation system, we construct a Holistic SIRST Evaluation (HSE) metric that performs multi-threshold integral evaluation at both pixel-level confidence and target-level robustness, providing a stable and comprehensive basis for fair model comparison. Extensive experiments demonstrate that the SIRST detection networks equipped with our FDEP framework achieve state-of-the-art (SOTA) performance on multiple public datasets. Our code is available at https://github.com/YuChuang1205/FDEP-Framework △ Less

Submitted 5 December, 2025; originally announced December 2025.

Edged Weisfeiler-Lehman Algorithm

Authors: Xiao Yue, Bo Liu, Feng Zhang, Guangzhi Qu

Abstract: As a classical approach on graph learning, the propagation-aggregation methodology is widely exploited by many of Graph Neural Networks (GNNs), wherein the representation of a node is updated by aggregating representations from itself and neighbor nodes recursively. Similar to the propagation-aggregation methodology, the Weisfeiler-Lehman (1-WL) algorithm tests isomorphism through color refinement… ▽ More As a classical approach on graph learning, the propagation-aggregation methodology is widely exploited by many of Graph Neural Networks (GNNs), wherein the representation of a node is updated by aggregating representations from itself and neighbor nodes recursively. Similar to the propagation-aggregation methodology, the Weisfeiler-Lehman (1-WL) algorithm tests isomorphism through color refinement according to color representations of a node and its neighbor nodes. However, 1-WL does not leverage any edge features (labels), presenting a potential improvement on exploiting edge features in some fields. To address this limitation, we proposed a novel Edged-WL algorithm (E-WL) which extends the original 1-WL algorithm to incorporate edge features. Building upon the E-WL algorithm, we also introduce an Edged Graph Isomorphism Network (EGIN) model for further exploiting edge features, which addresses one key drawback in many GNNs that do not utilize any edge features of graph data. We evaluated the performance of proposed models using 12 edge-featured benchmark graph datasets and compared them with some state-of-the-art baseline models. Experimental results indicate that our proposed EGIN models, in general, demonstrate superior performance in graph learning on graph classification tasks. △ Less

Submitted 4 December, 2025; originally announced December 2025.

Comments: Author's Accepted Manuscript (AAM) of ICANN 2024 paper published in LNCS (Springer). Final version available at: https://link.springer.com/chapter/10.1007/978-3-031-72344-5_7

Journal ref: ICANN 2024, LNCS 15020, pp. 93-109, Springer, 2024

LATTICE: Democratize High-Fidelity 3D Generation at Scale

Authors: Zeqiang Lai, Yunfei Zhao, Zibo Zhao, Haolin Liu, Qingxiang Lin, Jingwei Huang, Chunchao Guo, Xiangyu Yue

Abstract: We present LATTICE, a new framework for high-fidelity 3D asset generation that bridges the quality and scalability gap between 3D and 2D generative models. While 2D image synthesis benefits from fixed spatial grids and well-established transformer architectures, 3D generation remains fundamentally more challenging due to the need to predict both spatial structure and detailed geometric surfaces fr… ▽ More We present LATTICE, a new framework for high-fidelity 3D asset generation that bridges the quality and scalability gap between 3D and 2D generative models. While 2D image synthesis benefits from fixed spatial grids and well-established transformer architectures, 3D generation remains fundamentally more challenging due to the need to predict both spatial structure and detailed geometric surfaces from scratch. These challenges are exacerbated by the computational complexity of existing 3D representations and the lack of structured and scalable 3D asset encoding schemes. To address this, we propose VoxSet, a semi-structured representation that compresses 3D assets into a compact set of latent vectors anchored to a coarse voxel grid, enabling efficient and position-aware generation. VoxSet retains the simplicity and compression advantages of prior VecSet methods while introducing explicit structure into the latent space, allowing positional embeddings to guide generation and enabling strong token-level test-time scaling. Built upon this representation, LATTICE adopts a two-stage pipeline: first generating a sparse voxelized geometry anchor, then producing detailed geometry using a rectified flow transformer. Our method is simple at its core, but supports arbitrary resolution decoding, low-cost training, and flexible inference schemes, achieving state-of-the-art performance on various aspects, and offering a significant step toward scalable, high-quality 3D asset creation. △ Less

Submitted 23 November, 2025; originally announced December 2025.

Comments: Technical Report

OneThinker: All-in-one Reasoning Model for Image and Video

Authors: Kaituo Feng, Manyuan Zhang, Hongyu Li, Kaixuan Fan, Shuang Chen, Yilei Jiang, Dian Zheng, Peiwen Sun, Yiyuan Zhang, Haoze Sun, Yan Feng, Peng Pei, Xunliang Cai, Xiangyu Yue

Abstract: Reinforcement learning (RL) has recently achieved remarkable success in eliciting visual reasoning within Multimodal Large Language Models (MLLMs). However, existing approaches typically train separate models for different tasks and treat image and video reasoning as disjoint domains. This results in limited scalability toward a multimodal reasoning generalist, which restricts practical versatilit… ▽ More Reinforcement learning (RL) has recently achieved remarkable success in eliciting visual reasoning within Multimodal Large Language Models (MLLMs). However, existing approaches typically train separate models for different tasks and treat image and video reasoning as disjoint domains. This results in limited scalability toward a multimodal reasoning generalist, which restricts practical versatility and hinders potential knowledge sharing across tasks and modalities. To this end, we propose OneThinker, an all-in-one reasoning model that unifies image and video understanding across diverse fundamental visual tasks, including question answering, captioning, spatial and temporal grounding, tracking, and segmentation. To achieve this, we construct the OneThinker-600k training corpus covering all these tasks and employ commercial models for CoT annotation, resulting in OneThinker-SFT-340k for SFT cold start. Furthermore, we propose EMA-GRPO to handle reward heterogeneity in multi-task RL by tracking task-wise moving averages of reward standard deviations for balanced optimization. Extensive experiments on diverse visual benchmarks show that OneThinker delivers strong performance on 31 benchmarks, across 10 fundamental visual understanding tasks. Moreover, it exhibits effective knowledge transfer between certain tasks and preliminary zero-shot generalization ability, marking a step toward a unified multimodal reasoning generalist. All code, model, and data are released. △ Less

Submitted 3 December, 2025; v1 submitted 2 December, 2025; originally announced December 2025.

Comments: Project page: https://github.com/tulerfeng/OneThinker

Thinking by Doing: Building Efficient World Model Reasoning in LLMs via Multi-turn Interaction

Authors: Bao Shu, Yan Cai, Jianjian Sun, Chunrui Han, En Yu, Liang Zhao, Jingcheng Hu, Yinmin Zhang, Haoran Lv, Yuang Peng, Zheng Ge, Xiangyu Zhang, Daxin Jiang, Xiangyu Yue

Abstract: Developing robust world model reasoning is crucial for large language model (LLM) agents to plan and interact in complex environments. While multi-turn interaction offers a superior understanding of environmental dynamics via authentic feedback, current approaches often impose a rigid reasoning process, which constrains the model's active learning, ultimately hindering efficient world model reason… ▽ More Developing robust world model reasoning is crucial for large language model (LLM) agents to plan and interact in complex environments. While multi-turn interaction offers a superior understanding of environmental dynamics via authentic feedback, current approaches often impose a rigid reasoning process, which constrains the model's active learning, ultimately hindering efficient world model reasoning. To address these issues, we explore world-model internalization through efficient interaction and active reasoning (WMAct), which liberates the model from structured reasoning, allowing the model to shape thinking directly through its doing, and achieves effective and efficient world model reasoning with two key mechanisms: (1) a reward rescaling mechanism adjusting outcome reward based on action efficacy to incentivize redundancy reduction and purposeful interaction; (2) an interaction frequency annealing strategy to progressively reduce the maximum allowed interaction turns, which compels the model to condense its learning and internalize environmental dynamics rather than over-relying on environmental cues. Our experiments on Sokoban, Maze, and Taxi show that WMAct yields effective world model reasoning capable of resolving tasks in a single turn that previously required multiple interactions and fosters strong transferability to complex environments, improving performance on a suite of reasoning benchmarks. △ Less

Submitted 28 November, 2025; originally announced November 2025.

Comments: 17 pages, 9 figures

EWE: An Agentic Framework for Extreme Weather Analysis

Authors: Zhe Jiang, Jiong Wang, Xiaoyu Yue, Zijie Guo, Wenlong Zhang, Fenghua Ling, Wanli Ouyang, Lei Bai

Abstract: Extreme weather events pose escalating risks to global society, underscoring the urgent need to unravel their underlying physical mechanisms. Yet the prevailing expert-driven, labor-intensive diagnostic paradigm has created a critical analytical bottleneck, stalling scientific progress. While AI for Earth Science has achieved notable advances in prediction, the equally essential challenge of autom… ▽ More Extreme weather events pose escalating risks to global society, underscoring the urgent need to unravel their underlying physical mechanisms. Yet the prevailing expert-driven, labor-intensive diagnostic paradigm has created a critical analytical bottleneck, stalling scientific progress. While AI for Earth Science has achieved notable advances in prediction, the equally essential challenge of automated diagnostic reasoning remains largely unexplored. We present the Extreme Weather Expert (EWE), the first intelligent agent framework dedicated to this task. EWE emulates expert workflows through knowledge-guided planning, closed-loop reasoning, and a domain-tailored meteorological toolkit. It autonomously produces and interprets multimodal visualizations from raw meteorological data, enabling comprehensive diagnostic analyses. To catalyze progress, we introduce the first benchmark for this emerging field, comprising a curated dataset of 103 high-impact events and a novel step-wise evaluation metric. EWE marks a step toward automated scientific discovery and offers the potential to democratize expertise and intellectual resources, particularly for developing nations vulnerable to extreme weather. △ Less

Submitted 26 November, 2025; originally announced November 2025.

3D-Aware Multi-Task Learning with Cross-View Correlations for Dense Scene Understanding

Authors: Xiaoye Wang, Chen Tang, Xiangyu Yue, Wei-Hong Li

Abstract: This paper addresses the challenge of training a single network to jointly perform multiple dense prediction tasks, such as segmentation and depth estimation, i.e., multi-task learning (MTL). Current approaches mainly capture cross-task relations in the 2D image space, often leading to unstructured features lacking 3D-awareness. We argue that 3D-awareness is vital for modeling cross-task correlati… ▽ More This paper addresses the challenge of training a single network to jointly perform multiple dense prediction tasks, such as segmentation and depth estimation, i.e., multi-task learning (MTL). Current approaches mainly capture cross-task relations in the 2D image space, often leading to unstructured features lacking 3D-awareness. We argue that 3D-awareness is vital for modeling cross-task correlations essential for comprehensive scene understanding. We propose to address this problem by integrating correlations across views, i.e., cost volume, as geometric consistency in the MTL network. Specifically, we introduce a lightweight Cross-view Module (CvM), shared across tasks, to exchange information across views and capture cross-view correlations, integrated with a feature from MTL encoder for multi-task predictions. This module is architecture-agnostic and can be applied to both single and multi-view data. Extensive results on NYUv2 and PASCAL-Context demonstrate that our method effectively injects geometric consistency into existing MTL methods to improve performance. △ Less

Submitted 25 November, 2025; originally announced November 2025.

Comments: 3D-aware Multi-task Learning, Cross-view Correlations, Code will be available at https://github.com/WeiHongLee/CrossView3DMTL

ConceptGuard: Proactive Safety in Text-and-Image-to-Video Generation through Multimodal Risk Detection

Authors: Ruize Ma, Minghong Cai, Yilei Jiang, Jiaming Han, Yi Feng, Yingshui Tan, Xiaoyong Zhu, Bo Zhang, Bo Zheng, Xiangyu Yue

Abstract: Recent progress in video generative models has enabled the creation of high-quality videos from multimodal prompts that combine text and images. While these systems offer enhanced controllability, they also introduce new safety risks, as harmful content can emerge from individual modalities or their interaction. Existing safety methods are often text-only, require prior knowledge of the risk categ… ▽ More Recent progress in video generative models has enabled the creation of high-quality videos from multimodal prompts that combine text and images. While these systems offer enhanced controllability, they also introduce new safety risks, as harmful content can emerge from individual modalities or their interaction. Existing safety methods are often text-only, require prior knowledge of the risk category, or operate as post-generation auditors, struggling to proactively mitigate such compositional, multimodal risks. To address this challenge, we present ConceptGuard, a unified safeguard framework for proactively detecting and mitigating unsafe semantics in multimodal video generation. ConceptGuard operates in two stages: First, a contrastive detection module identifies latent safety risks by projecting fused image-text inputs into a structured concept space; Second, a semantic suppression mechanism steers the generative process away from unsafe concepts by intervening in the prompt's multimodal conditioning. To support the development and rigorous evaluation of this framework, we introduce two novel benchmarks: ConceptRisk, a large-scale dataset for training on multimodal risks, and T2VSafetyBench-TI2V, the first benchmark adapted from T2VSafetyBench for the Text-and-Image-to-Video (TI2V) safety setting. Comprehensive experiments on both benchmarks show that ConceptGuard consistently outperforms existing baselines, achieving state-of-the-art results in both risk detection and safe video generation. Our code is available at https://github.com/Ruize-Ma/ConceptGuard. △ Less

Submitted 26 November, 2025; v1 submitted 24 November, 2025; originally announced November 2025.

VisReason: A Large-Scale Dataset for Visual Chain-of-Thought Reasoning

Authors: Lingxiao Li, Yifan Wang, Xinyan Gao, Chen Tang, Xiangyu Yue, Chenyu You

Abstract: Chain-of-Thought (CoT) prompting has proven remarkably effective for eliciting complex reasoning in large language models (LLMs). Yet, its potential in multimodal large language models (MLLMs) remains largely untapped, hindered by the absence of large-scale datasets that capture the rich, spatially grounded reasoning intrinsic to visual understanding. Existing visual-CoT resources are typically sm… ▽ More Chain-of-Thought (CoT) prompting has proven remarkably effective for eliciting complex reasoning in large language models (LLMs). Yet, its potential in multimodal large language models (MLLMs) remains largely untapped, hindered by the absence of large-scale datasets that capture the rich, spatially grounded reasoning intrinsic to visual understanding. Existing visual-CoT resources are typically small, domain-specific, or lack the human-like stepwise structure necessary for compositional visual reasoning. In this paper, we introduce VisReason, a large-scale dataset designed to advance visual Chain-of-Thought reasoning. VisReason comprises 489K annotated examples spanning four diverse domains, each featuring multi-round, human-like rationales that guide MLLMs through interpretable visual reasoning steps. Building upon this, we curate VisReason-Pro, a 165K subset produced with a stronger expert-level GPT annotator, enriched with detailed reasoning traces and 3D spatial grounding via depth-informed annotations. Fine-tuning the state-of-the-art Qwen2.5-VL model on VisReason and VisReason-Pro yields substantial improvements in step-by-step visual reasoning accuracy, interpretability, and cross-benchmark generalization. These results demonstrate that VisReason equips MLLMs with more systematic and generalizable reasoning capabilities. We envision VisReason as a cornerstone for cultivating human-like visual reasoning, paving the way toward the next generation of multimodal intelligence. △ Less

Submitted 21 November, 2025; originally announced November 2025.

NaTex: Seamless Texture Generation as Latent Color Diffusion

Authors: Zeqiang Lai, Yunfei Zhao, Zibo Zhao, Xin Yang, Xin Huang, Jingwei Huang, Xiangyu Yue, Chunchao Guo

Abstract: We present NaTex, a native texture generation framework that predicts texture color directly in 3D space. In contrast to previous approaches that rely on baking 2D multi-view images synthesized by geometry-conditioned Multi-View Diffusion models (MVDs), NaTex avoids several inherent limitations of the MVD pipeline. These include difficulties in handling occluded regions that require inpainting, ac… ▽ More We present NaTex, a native texture generation framework that predicts texture color directly in 3D space. In contrast to previous approaches that rely on baking 2D multi-view images synthesized by geometry-conditioned Multi-View Diffusion models (MVDs), NaTex avoids several inherent limitations of the MVD pipeline. These include difficulties in handling occluded regions that require inpainting, achieving precise mesh-texture alignment along boundaries, and maintaining cross-view consistency and coherence in both content and color intensity. NaTex features a novel paradigm that addresses the aforementioned issues by viewing texture as a dense color point cloud. Driven by this idea, we propose latent color diffusion, which comprises a geometry-awared color point cloud VAE and a multi-control diffusion transformer (DiT), entirely trained from scratch using 3D data, for texture reconstruction and generation. To enable precise alignment, we introduce native geometry control that conditions the DiT on direct 3D spatial information via positional embeddings and geometry latents. We co-design the VAE-DiT architecture, where the geometry latents are extracted via a dedicated geometry branch tightly coupled with the color VAE, providing fine-grained surface guidance that maintains strong correspondence with the texture. With these designs, NaTex demonstrates strong performance, significantly outperforming previous methods in texture coherence and alignment. Moreover, NaTex also exhibits strong generalization capabilities, either training-free or with simple tuning, for various downstream applications, e.g., material generation, texture refinement, and part segmentation and texturing. △ Less

Submitted 20 November, 2025; originally announced November 2025.

Comments: Technical Report

Simulating Environments with Reasoning Models for Agent Training

Authors: Yuetai Li, Huseyin A Inan, Xiang Yue, Wei-Ning Chen, Lukas Wutschitz, Janardhan Kulkarni, Radha Poovendran, Robert Sim, Saravan Rajmohan

Abstract: LLM agents excel in compact environments requiring deep reasoning but remain brittle when operating in broader, more complex contexts that demand robustness across diverse tools and schemas. Building bespoke environments for training is heavy, brittle, and limits progress. In this paper, we demonstrate that LLMs can simulate realistic environment feedback without access to actual testbed data or A… ▽ More LLM agents excel in compact environments requiring deep reasoning but remain brittle when operating in broader, more complex contexts that demand robustness across diverse tools and schemas. Building bespoke environments for training is heavy, brittle, and limits progress. In this paper, we demonstrate that LLMs can simulate realistic environment feedback without access to actual testbed data or APIs. Inspired by this capability, we propose two frameworks: Simia-SFT, a pipeline that synthesizes SFT data by amplifying small seed sets into diverse trajectories in an environment-agnostic manner, and Simia-RL, a framework that enables RL training without real environment implementations through LLM-simulated feedback. Fine-tuning open models yields consistent improvements across multiple benchmarks, surpassing GPT-4o and approaching o4-mini on $τ^2$-Bench. Together, Simia-SFT and Simia-RL enable scalable agent training without environment engineering, replacing heavy and brittle implementations with flexible LLM-based simulation. △ Less

Submitted 3 November, 2025; originally announced November 2025.

The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution

Authors: Junlong Li, Wenshuo Zhao, Jian Zhao, Weihao Zeng, Haoze Wu, Xiaochen Wang, Rui Ge, Yuxuan Cao, Yuzhen Huang, Wei Liu, Junteng Liu, Zhaochen Su, Yiyang Guo, Fan Zhou, Lueyang Zhang, Juan Michelini, Xingyao Wang, Xiang Yue, Shuyan Zhou, Graham Neubig, Junxian He

Abstract: Real-world language agents must handle complex, multi-step workflows across diverse Apps. For instance, an agent may manage emails by coordinating with calendars and file systems, or monitor a production database to detect anomalies and generate reports following an operating manual. However, existing language agent benchmarks often focus on narrow domains or simplified tasks that lack the diversi… ▽ More Real-world language agents must handle complex, multi-step workflows across diverse Apps. For instance, an agent may manage emails by coordinating with calendars and file systems, or monitor a production database to detect anomalies and generate reports following an operating manual. However, existing language agent benchmarks often focus on narrow domains or simplified tasks that lack the diversity, realism, and long-horizon complexity required to evaluate agents' real-world performance. To address this gap, we introduce the Tool Decathlon (dubbed as Toolathlon), a benchmark for language agents offering diverse Apps and tools, realistic environment setup, and reliable execution-based evaluation. Toolathlon spans 32 software applications and 604 tools, ranging from everyday platforms such as Google Calendar and Notion to professional ones like WooCommerce, Kubernetes, and BigQuery. Most of the tools are based on a high-quality set of Model Context Protocol (MCP) servers that we may have revised or implemented ourselves. Unlike prior works, which primarily ensure functional realism but offer limited environment state diversity, we provide realistic initial environment states from real software, such as Canvas courses with dozens of students or real financial spreadsheets. This benchmark includes 108 manually sourced or crafted tasks in total, requiring interacting with multiple Apps over around 20 turns on average to complete. Each task is strictly verifiable through dedicated evaluation scripts. Comprehensive evaluation of SOTA models highlights their significant shortcomings: the best-performing model, Claude-4.5-Sonnet, achieves only a 38.6% success rate with 20.2 tool calling turns on average, while the top open-weights model DeepSeek-V3.2-Exp reaches 20.1%. We expect Toolathlon to drive the development of more capable language agents for real-world, long-horizon task execution. △ Less

Submitted 26 February, 2026; v1 submitted 29 October, 2025; originally announced October 2025.

Comments: ICLR 2026, Website: https://toolathlon.xyz/

Agent Data Protocol: Unifying Datasets for Diverse, Effective Fine-tuning of LLM Agents

Authors: Yueqi Song, Ketan Ramaneti, Zaid Sheikh, Ziru Chen, Boyu Gou, Tianbao Xie, Yiheng Xu, Danyang Zhang, Apurva Gandhi, Fan Yang, Joseph Liu, Tianyue Ou, Zhihao Yuan, Frank Xu, Shuyan Zhou, Xingyao Wang, Xiang Yue, Tao Yu, Huan Sun, Yu Su, Graham Neubig

Abstract: Public research results on large-scale supervised finetuning of AI agents remain relatively rare, since the collection of agent training data presents unique challenges. In this work, we argue that the bottleneck is not a lack of underlying data sources, but that a large variety of data is fragmented across heterogeneous formats, tools, and interfaces. To this end, we introduce the agent data prot… ▽ More Public research results on large-scale supervised finetuning of AI agents remain relatively rare, since the collection of agent training data presents unique challenges. In this work, we argue that the bottleneck is not a lack of underlying data sources, but that a large variety of data is fragmented across heterogeneous formats, tools, and interfaces. To this end, we introduce the agent data protocol (ADP), a light-weight representation language that serves as an "interlingua" between agent datasets in diverse formats and unified agent training pipelines downstream. The design of ADP is expressive enough to capture a large variety of tasks, including API/tool use, browsing, coding, software engineering, and general agentic workflows, while remaining simple to parse and train on without engineering at a per-dataset level. In experiments, we unified a broad collection of 13 existing agent training datasets into ADP format, and converted the standardized ADP data into training-ready formats for multiple agent frameworks. We performed SFT on these data, and demonstrated an average performance gain of ~20% over corresponding base models, and delivers state-of-the-art or near-SOTA performance on standard coding, browsing, tool use, and research benchmarks, without domain-specific tuning. All code and data are released publicly, in the hope that ADP could help lower the barrier to standardized, scalable, and reproducible agent training. △ Less

Submitted 3 March, 2026; v1 submitted 28 October, 2025; originally announced October 2025.

VisCoder2: Building Multi-Language Visualization Coding Agents

Authors: Yuansheng Ni, Songcheng Cai, Xiangchao Chen, Jiarong Liang, Zhiheng Lyu, Jiaqi Deng, Kai Zou, Ping Nie, Fei Yuan, Xiang Yue, Wenhu Chen

Abstract: Large language models (LLMs) have recently enabled coding agents capable of generating, executing, and revising visualization code. However, existing models often fail in practical workflows due to limited language coverage, unreliable execution, and lack of iterative correction mechanisms. Progress has been constrained by narrow datasets and benchmarks that emphasize single-round generation and s… ▽ More Large language models (LLMs) have recently enabled coding agents capable of generating, executing, and revising visualization code. However, existing models often fail in practical workflows due to limited language coverage, unreliable execution, and lack of iterative correction mechanisms. Progress has been constrained by narrow datasets and benchmarks that emphasize single-round generation and single-language tasks. To address these challenges, we introduce three complementary resources for advancing visualization coding agents. VisCode-Multi-679K is a large-scale, supervised dataset containing 679K validated and executable visualization samples with multi-turn correction dialogues across 12 programming languages. VisPlotBench is a benchmark for systematic evaluation, featuring executable tasks, rendered outputs, and protocols for both initial generation and multi-round self-debug. Finally, we present VisCoder2, a family of multi-language visualization models trained on VisCode-Multi-679K. Experiments show that VisCoder2 significantly outperforms strong open-source baselines and approaches the performance of proprietary models like GPT-4.1, with further gains from iterative self-debug, reaching 82.4% overall execution pass rate at the 32B scale, particularly in symbolic or compiler-dependent languages. △ Less

Submitted 7 April, 2026; v1 submitted 24 October, 2025; originally announced October 2025.

iDETEX: Empowering MLLMs for Intelligent DETailed EXplainable IQA

Authors: Zhaoran Zhao, Xinli Yue, Jianhui Sun, Yuhao Xie, Tao Shao, Liangchao Yao, Fan Xia, Yuetang Deng

Abstract: Image Quality Assessment (IQA) has progressed from scalar quality prediction to more interpretable, human-aligned evaluation paradigms. In this work, we address the emerging challenge of detailed and explainable IQA by proposing iDETEX-a unified multimodal large language model (MLLM) capable of simultaneously performing three key tasks: quality grounding, perception, and description. To facilitate… ▽ More Image Quality Assessment (IQA) has progressed from scalar quality prediction to more interpretable, human-aligned evaluation paradigms. In this work, we address the emerging challenge of detailed and explainable IQA by proposing iDETEX-a unified multimodal large language model (MLLM) capable of simultaneously performing three key tasks: quality grounding, perception, and description. To facilitate efficient and generalizable training across these heterogeneous subtasks, we design a suite of task-specific offline augmentation modules and a data mixing strategy. These are further complemented by online enhancement strategies to fully exploit multi-sourced supervision. We validate our approach on the large-scale ViDA-UGC benchmark, where iDETEX achieves state-of-the-art performance across all subtasks. Our model ranks first in the ICCV MIPI 2025 Detailed Image Quality Assessment Challenge, demonstrating its effectiveness and robustness in delivering accurate and interpretable quality assessments. △ Less

Submitted 20 October, 2025; originally announced October 2025.

Comments: Accepted to ICCV 2025 Workshop

BREATH: A Bio-Radar Embodied Agent for Tonal and Human-Aware Diffusion Music Generation

Authors: Yunzhe Wang, Xinyu Tang, Zhixun Huang, Xiaolong Yue, Yuxin Zeng

Abstract: We present a multimodal system for personalized music generation that integrates physiological sensing, LLM-based reasoning, and controllable audio synthesis. A millimeter-wave radar sensor non-invasively captures heart rate and respiration rate. These physiological signals, combined with environmental state, are interpreted by a reasoning agent to infer symbolic musical descriptors, such as tempo… ▽ More We present a multimodal system for personalized music generation that integrates physiological sensing, LLM-based reasoning, and controllable audio synthesis. A millimeter-wave radar sensor non-invasively captures heart rate and respiration rate. These physiological signals, combined with environmental state, are interpreted by a reasoning agent to infer symbolic musical descriptors, such as tempo, mood intensity, and traditional Chinese pentatonic modes, which are then expressed as structured prompts to guide a diffusion-based audio model in synthesizing expressive melodies. The system emphasizes cultural grounding through tonal embeddings and enables adaptive, embodied music interaction. To evaluate the system, we adopt a research-creation methodology combining case studies, expert feedback, and targeted control experiments. Results show that physiological variations can modulate musical features in meaningful ways, and tonal conditioning enhances alignment with intended modal characteristics. Expert users reported that the system affords intuitive, culturally resonant musical responses and highlighted its potential for therapeutic and interactive applications. This work demonstrates a novel bio-musical feedback loop linking radar-based sensing, prompt reasoning, and generative audio modeling. △ Less

Submitted 9 September, 2025; originally announced October 2025.

Comments: Accepted by LLM4Music @ ISMIR 2025

VR-Thinker: Boosting Video Reward Models through Thinking-with-Image Reasoning

Authors: Qunzhong Wang, Jie Liu, Jiajun Liang, Yilei Jiang, Yuanxing Zhang, Yaozhi Zheng, Xintao Wang, Pengfei Wan, Xiangyu Yue, Jiaheng Liu

Abstract: Recent advancements in multimodal reward models (RMs) have substantially improved post-training for visual generative models. However, current RMs face inherent limitations: (1) visual inputs consume large context budgets, forcing fewer frames and causing loss of fine-grained details; and (2) all visual information is packed into the initial prompt, exacerbating hallucination and forgetting during… ▽ More Recent advancements in multimodal reward models (RMs) have substantially improved post-training for visual generative models. However, current RMs face inherent limitations: (1) visual inputs consume large context budgets, forcing fewer frames and causing loss of fine-grained details; and (2) all visual information is packed into the initial prompt, exacerbating hallucination and forgetting during chain-of-thought reasoning. To overcome these issues, we introduce VideoReward Thinker (VR-Thinker), a thinking-with-image framework that equips the RM with visual reasoning operations (e.g., select frame) and a configurable visual memory window. This allows the RM to actively acquire and update visual evidence within context limits, improving reasoning fidelity and reliability. We activate visual reasoning via a reinforcement fine-tuning pipeline: (i) Cold Start with curated visual chain-of-thought data to distill basic reasoning skills and operation formatting; (ii) select samples whose per-dimension and overall judgments are all correct, then conduct Rejection sampling Fine-Tuning on these high-quality traces to further enhance reasoning; and (iii) apply Group Relative Policy Optimization (GRPO) to strengthen reasoning. Our approach delivers state-of-the-art accuracy among open-source models on video preference benchmarks, especially for longer videos: a 7B VR-Thinker achieves 80.5% on VideoGen Reward, 82.3% on GenAI-Bench, and 75.6% on MJ-Bench-Video. These results validate the effectiveness and promise of thinking-with-image multimodal reward modeling. △ Less

Submitted 19 March, 2026; v1 submitted 12 October, 2025; originally announced October 2025.

SpaceVista: All-Scale Visual Spatial Reasoning from mm to km

Authors: Peiwen Sun, Shiqiang Lang, Dongming Wu, Yi Ding, Kaituo Feng, Huadai Liu, Zhen Ye, Rui Liu, Yun-Hui Liu, Jianan Wang, Xiangyu Yue

Abstract: With the current surge in spatial reasoning explorations, researchers have made significant progress in understanding indoor scenes, but still struggle with diverse applications such as robotics and autonomous driving. This paper aims to advance all-scale spatial reasoning across diverse scenarios by tackling two key challenges: 1) the heavy reliance on indoor 3D scans and labor-intensive manual a… ▽ More With the current surge in spatial reasoning explorations, researchers have made significant progress in understanding indoor scenes, but still struggle with diverse applications such as robotics and autonomous driving. This paper aims to advance all-scale spatial reasoning across diverse scenarios by tackling two key challenges: 1) the heavy reliance on indoor 3D scans and labor-intensive manual annotations for dataset curation; 2) the absence of effective all-scale scene modeling, which often leads to overfitting to individual scenes. In this paper, we introduce a holistic solution that integrates a structured spatial reasoning knowledge system, scale-aware modeling, and a progressive training paradigm, as the first attempt to broaden the all-scale spatial intelligence of MLLMs to the best of our knowledge. Using a task-specific, specialist-driven automated pipeline, we curate over 38K video scenes across 5 spatial scales to create SpaceVista-1M, a dataset comprising approximately 1M spatial QA pairs spanning 19 diverse task types. While specialist models can inject useful domain knowledge, they are not reliable for evaluation. We then build an all-scale benchmark with precise annotations by manually recording, retrieving, and assembling video-based data. However, naive training with SpaceVista-1M often yields suboptimal results due to the potential knowledge conflict. Accordingly, we introduce SpaceVista-7B, a spatial reasoning model that accepts dense inputs beyond semantics and uses scale as an anchor for scale-aware experts and progressive rewards. Finally, extensive evaluations across 5 benchmarks, including our SpaceVista-Bench, demonstrate competitive performance, showcasing strong generalization across all scales and scenarios. Our dataset, model, and benchmark will be released on https://peiwensun2000.github.io/mm2km . △ Less

Submitted 10 October, 2025; originally announced October 2025.

Comments: Project Page: https://peiwensun2000.github.io/mm2km/