论文检索

Theory · Optimization

Keitaro Sakamoto, Issei Sato

The training dynamics of deep neural networks often defy expectations, even as these models form the foundation of modern machine learning. Two prominent examples are grokking, where test performance improves abruptly long after the training loss has plateaued, and the information bottleneck principle, where models progressively discard input information irrelevant to the prediction task as training proceeds. However, the mechanisms underlying these phenomena and their relations remain poorly understood. In this work, we present a unified explanation of such late-phase phenomena through the lens of neural collapse, which characterizes the geometry of learned representations. We show that the contraction of population within-class variance is a key factor underlying both grokking and information bottleneck, and relate this measure to the neural collapse measure defined on the training set. By analyzing the dynamics of neural collapse, we show that distinct time scales between fitting the training set and the progression of neural collapse account for the behavior of the late-phase phenomena. Finally, we validate our theoretical findings on multiple datasets and architectures.

Applications · Language, Speech and Dialog

Zixin Song, Bowen Zhang, QIANWEN ZHANG, di yin, Xing Sun, Chunping Li

Conditional Semantic Textual Similarity (C-STS) measures the semantic proximity between text segments under a specific condition, thereby overcoming the ambiguity inherent in traditional STS. However, existing methods are largely confined to discriminative models, failing to fully leverage recent breakthroughs in the NLP community involving Large Language Models (LLMs) and Reinforcement Learning (RL). RL is a particularly well-suited paradigm for this task, as it can directly optimize the non-differentiable Spearman ranking metric and guide the reasoning process required by C-STS. Nevertheless, we find that naively applying listwise RL fails to produce meaningful improvements, as the model struggles with complex, coarse-grained reward signals, leading to optimization difficulties. To address this challenge, we introduce PoLi-RL, a novel Point-to-List Reinforcement Learning framework. PoLi-RL employs a two-stage curriculum: it first trains the model with a simple pointwise reward to establish fundamental scoring capabilities, then transitions to a hybrid reward that combines pointwise, pairwise, and listwise objectives to refine the model's ability to discern subtle semantic distinctions. Crucially, we propose an innovative Parallel Slice Ranking Reward (PSRR) mechanism that computes ranking rewards in parallel slices, where each slice consists of completions with the same index from different samples. This provides a precise, differentiated learning signal for each individual completion, enabling granular credit assignment and effective optimization. On the official C-STS benchmark, PoLi-RL achieves a Spearman correlation coefficient of 48.18, establishing a new SOTA for the cross-encoder architecture. Furthermore, PoLi-RL also maintains SOTA status on the re-annotated C-STS dataset, confirming its robust generalization capabilities. As the first work to successfully apply RL to C-STS, our study introduces a powerful paradigm for aligning LLMs for complex, ranking-based conditional judgment tasks. Our code and checkpoints are available at https://github.com/ZBWpro/PoLi-RL.

Applications · Language, Speech and Dialog

Alexandros Haliassos, Rodrigo Mira, Stavros Petridis

Unified Speech Recognition (USR) has emerged as a semi-supervised framework for training a single model for audio, visual, and audiovisual speech recognition, achieving state-of-the-art results on in-distribution benchmarks. However, its reliance on autoregressive pseudo-labelling makes training expensive, while its decoupled supervision of CTC and attention branches increases susceptibility to self-reinforcing errors, particularly under distribution shifts involving longer sequences, noise, or unseen domains. We propose CTC-driven teacher forcing, where greedily decoded CTC pseudo-labels are fed into the decoder to generate attention targets in a single forward pass. Although these can be globally incoherent, in the pseudo-labelling setting they enable efficient and effective knowledge transfer. Because CTC and CTC-driven attention pseudo-labels have the same length, the decoder can predict both simultaneously, benefiting from the robustness of CTC and the expressiveness of attention without costly beam search. We further propose mixed sampling to mitigate the exposure bias of the decoder relying solely on CTC inputs. The resulting method, USR 2.0, halves training time, improves robustness to out-of-distribution inputs, and achieves state-of-the-art results on LRS3, LRS2, and WildVSR, surpassing USR and modality-specific self-supervised baselines.

Applications · Everything Else

Yu Wang, Yi Wang, Rui Dai, Yujie Wang, Kaikui Liu, Xiangxiang Chu, Yansheng Li

As hubs of human activity, urban surfaces consist of a wealth of semantic entities. Segmenting these various entities from satellite imagery is crucial for a range of downstream applications. Current advanced segmentation models can reliably segment entities defined by physical attributes (e.g., buildings, water bodies) but still struggle with socially defined categories (e.g., schools, parks). In this work, we achieve socio-semantic segmentation by vision-language model reasoning. To facilitate this, we introduce the Urban Socio-Semantic Segmentation dataset named SocioSeg, a new resource comprising satellite imagery, digital maps, and pixel-level labels of social semantic entities organized in a hierarchical structure. Additionally, we propose a novel vision-language reasoning framework called SocioReasoner that simulates the human process of identifying and annotating social semantic entities via cross-modal recognition and multi-stage reasoning. We employ reinforcement learning to optimize this non-differentiable process and elicit the reasoning capabilities of the vision-language model. Experiments demonstrate our approach's gains over state-of-the-art models and strong zero-shot generalization. The dataset and code are open-sourced under the Apache License 2.0 at https://github.com/AMAP-ML/SocioReasoner.

Applications · Language, Speech and Dialog

Renzhi Wang, Chongqiang Wei, Zhisheng Wang, Piji Li

Role-playing dialogue presents unique challenges for large language models (LLMs): beyond producing coherent text, models must sustain character persona, integrate contextual knowledge, and convey emotional nuance. Despite strong reasoning abilities, current LLMs often generate dialogue that is literal, stylistically bland, and misaligned with character-specific traits. Existing approaches such as retrieval-augmented generation (RAG) or reinforcement learning (RL) with scalar rewards are insufficient, as they cannot capture nuanced preferences or adapt reliably to diverse character contexts. In this work, we introduce R4, a unified framework that equips both the reward model and the role-playing agent with reasoning and retrieval capabilities. Our reward model reformulates evaluation as structured reasoning: it integrates multi-step deliberation and retrieved knowledge to assess responses along multiple dimensions. This reward supervision is then used within reinforcement learning to train a dialogue agent with the same dual capabilities, enabling contextually grounded and persona-consistent generation. Experiments demonstrate that R4 substantially improves dialogue quality, particularly in persona fidelity, narrative coherence, and emotional expressiveness. Analysis of training dynamics and case studies further shows that R4 agents employ retrieval more effectively, engage in retrieval-informed self-reflection, and achieve emergent role-playing behaviors unattainable by prior methods.

Social Aspects · Trustworthy Machine Learning

Zikai Zhang, Rui Hu, Jiahao Xu

Large Language Models (LLMs) have demonstrated remarkable effectiveness in adapting to downstream tasks through fine-tuning. Federated Learning (FL) extends this capability by enabling collaborative fine-tuning across distributed clients using Low-Rank Adaptation (LoRA), while preserving data privacy by avoiding raw data sharing. However, practical deployments face challenges when clients have heterogeneous resources and thus adopt different LoRA ranks, leading to substantial initialization and aggregation noise that undermines performance. To address these challenges, we propose Fed-PLoRA, a novel lightweight heterogeneous federated fine-tuning (FFT) framework. Fed-PLoRA introduces Parallel One-Rank Adaptation (PLoRA), a new LoRA variant that replaces the classic multi-rank LoRA module with multiple parallel one-rank modules, and a novel Select-N-Fold strategy that folds untrained PLoRA modules into the pre-trained weights before local training, thereby accommodating heterogeneous client resources. We provide a unified analysis of initialization and aggregation noise of Fed-PLoRA and demonstrate how it addresses the limitations of state-of-the-art methods. Extensive experiments on diverse LLM fine-tuning tasks demonstrate that Fed-PLoRA consistently outperforms existing methods in both accuracy and efficiency. The code is available at \url{https://github.com/TNI-playground/Fed-PLoRA}.

Cheng Jiayang, Dongyu Ru, Lin Qiu, Yiyang Li, Xuezhi Cao, Yangqiu Song, Xunliang Cai

Long-horizon interactions between users and LLM-based assistants necessitate effective memory management, yet current approaches face challenges in training and evaluation of memory. Existing memory benchmarks rely on static, off-policy data as context, limiting evaluation reliability and scalability. To address these gaps, we introduce AMemGym, an interactive environment enabling on-policy evaluation and optimization for memory-driven personalization. AMemGym employs structured data sampling to predefine user profiles, state-dependent questions, and state evolution trajectories, enabling cost-effective generation of high-quality, evaluation-aligned interactions. LLM-simulated users expose latent states through role-play while maintaining structured state consistency. Comprehensive metrics based on structured data guide both assessment and optimization of assistants. Extensive experiments reveal performance gaps in existing memory systems (e.g., RAG, long-context LLMs, and agentic memory) and corresponding reasons. AMemGym not only enables effective selection among competing approaches but also can potentially drive the self-evolution of memory management strategies. By bridging structured state evolution with free-form interactions, our framework provides a scalable, diagnostically rich environment for advancing memory capabilities in conversational agents.

Social Aspects · Trustworthy Machine Learning

Guang Yang, Ziye Geng, Yihang Chen, Changqing Luo

Adversarial-example-based fingerprinting approaches, which leverage the decision boundary characteristics of deep neural networks (DNNs) to craft fingerprints, has proven effective for protecting model ownership. However, a fundamental challenge remains unresolved: how far a fingerprint should be placed from the decision boundary to simultaneously satisfy two essential properties—robustness and uniqueness—required for effective and reliable ownership protection. Despite the importance of the fingerprint-to-boundary distance, existing works offer no theoretical solution and instead rely on empirical heuristics to determine it, which may lead to violations of either robustness or uniqueness properties. We propose AnaFP, an analytical fingerprinting scheme that constructs fingerprints under theoretical guidance. Specifically, we formulate the fingerprint generation task as the problem of controlling the fingerprint-to-boundary distance through a tunable stretch factor. To ensure both robustness and uniqueness, we mathematically formalize these properties that determine the lower and upper bounds of the stretch factor. These bounds jointly define an admissible interval within which the stretch factor must lie, thereby establishing a theoretical connection between the two constraints and the fingerprint-to-boundary distance. To enable practical fingerprint generation, we approximate the original (infinite) sets of pirated and independently trained models using two finite surrogate model pools and employ a quantile-based relaxation strategy to relax the derived bounds. Particularly, due to the circular dependency between the lower bound and the stretch factor, we apply a grid search strategy over the admissible interval to determine the most feasible stretch factor. Extensive experimental results demonstrate that AnaFP consistently outperforms prior methods, achieving effective and reliable ownership verification across diverse model architectures and model modification attacks.

Reinforcement Learning · Planning

Xinyu Tang, Zhenduo Zhang, Yurou Liu, Xin Zhao, zujie wen, Zhiqiang Zhang, JUN ZHOU

Recent advances in large language models (LLMs) have utilized reinforcement learning with verifiable rewards (RLVR) to improve reasoning capabilities. However, scaling these methods typically requires massive data and extensive rollout computations, leading to high training costs and low data efficiency. To mitigate this issue, we propose DEPO, a Data-Efficient Policy Optimization approach that combines optimized strategies for both offline and online data selection. In the offline phase, we curate a high-quality subset of training data based on multiple objectives, including diversity, influence, and difficulty. During online RLVR training, we propose a sample-level explorability metric to dynamically filter out samples with low exploration potential, thereby reducing substantial rollout computational costs. Additionally, we employ a replay mechanism for under-explored samples to ensure sufficient training, which enhances the final convergence performance. Experiments on five reasoning benchmarks show that DEPO consistently outperforms existing methods in both offline and online data selection scenarios. Notably, using only 20% of the training data, our approach achieves a 1.85 $\times$ speed-up on AIME24 and a 1.66 $\times$ speed-up on AIME25 compared to GRPO trained on the full dataset.

Gabrijel Boduljak, Laurynas Karazija, Iro Laina, Christian Rupprecht, Andrea Vedaldi

We consider the problem of forecasting motion from a single image, i.e., predicting how objects in the world are likely to move, without the ability to observe other parameters such as the object velocities or the forces applied to them. We formulate this task as conditional generation of dense trajectory grids with a model that closely follows the architecture of modern video generators but outputs motion trajectories instead of pixels. This approach captures scene-wide dynamics and uncertainty, yielding more accurate and diverse predictions than prior regressors and generators. Although recent state-of-the-art video generators are often regarded as world models, we show that they struggle with forecasting motion from a single image, even in simple physical scenarios such as falling blocks or mechanical object interactions, despite fine-tuning on such data. We show that this limitation arises from the overhead of generating pixels rather than directly modeling motion.

Deep Learning · Algorithms

Zijin Liu, Xu Geng, Wenshuai Xu, Xiang Zhao, Yan Xia, You Song

Accurate crowd simulation is crucial for public safety management, emergency evacuation planning, and intelligent transportation systems. However, existing methods, which typically model crowds as a collection of independent individual trajectories, are limited in their ability to capture macroscopic physical laws. This microscopic approach often leads to error accumulation and compromises simulation stability. Furthermore, deep learning-driven methods tend to suffer from low inference efficiency and high computational overhead, making them impractical for large-scale, efficient simulations. To address these challenges, we propose the Spatio-Temporal Decoupled Differential Equation Network (STDDN), a novel framework that guides microscopic trajectory prediction with macroscopic physics. We innovatively introduce the continuity equation from fluid dynamics as a strong physical constraint. A Neural Ordinary Differential Equation (Neural ODE) is employed to model the macroscopic density evolution driven by individual movements, thereby physically regularizing the microscopic trajectory prediction model. We design a density-velocity coupled dynamic graph learning module to formulate the derivative of the density field within the Neural ODE, effectively mitigating error accumulation. We also propose a differentiable density mapping module to eliminate discontinuous gradients caused by discretization and introduce a cross-grid detection module to accurately model the impact of individual cross-grid movements on local density changes. The proposed STDDN method has demonstrated significantly superior simulation performance compared to state-of-the-art methods on long-term tasks across four real-world datasets, as well as a major reduction in inference latency.

Deep Learning · Generative Models and Autoencoders

Dachuan Shi, Abedelkadir Asi, Keying Li, Xiangchi Yuan, Leyan Pan, Wenke Lee, Wen Xiao

Recent work shows that, beyond discrete reasoning through explicit chain-of-thought steps, which are limited by the boundaries of natural languages, large language models (LLMs) can also reason continuously in latent space, allowing richer information per step and thereby improving token efficiency. Despite this promise, latent reasoning still faces two challenges, especially in training-free settings: 1) purely latent reasoning broadens the search distribution by maintaining multiple implicit paths, which diffuses probability mass, introduces noise, and impedes convergence to a single high-confidence solution, thereby hurting accuracy; and 2) overthinking persists even without explicit text, wasting tokens and degrading efficiency. To address these issues, we introduce SwiReasoning, a training-free framework for LLM reasoning which features two key innovations: 1) SwiReasoning dynamically switches between explicit and latent reasoning, guided by block-wise confidence estimated from entropy trends in next-token distributions, to balance exploration and exploitation and promote timely convergence. 2) By limiting the maximum number of thinking-block switches, SwiReasoning curbs overthinking and improves token efficiency across varying problem difficulties. On widely used mathematics, STEM, coding, and general benchmarks, SwiReasoning consistently improves average accuracy by 1.8%–3.1% across reasoning LLMs of different model families and scales. Furthermore, under constrained budgets, SwiReasoning improves average token efficiency by 57%-79%, with larger gains as budgets tighten.

Theory · Optimization

Mohammad Moshtaghifar, Anton Rodomanov, Daniil Vankov, Sebastian Stich

We present a novel parameter-free universal gradient method for solving convex optimization problems. Our algorithm—Dual Averaging with Distance Adaptation (DADA)–is based on the classical scheme of dual averaging and dynamically adjusts its coefficients based on the observed gradients and the distance between its iterates to the starting point, without the need for knowing any problem-specific parameters. DADA is a universal algorithm that simultaneously works for a wide range of problem classes as long as one is able to bound the local growth of the objective around its minimizer. Particular examples of such problem classes are nonsmooth Lipschitz functions, Lipschitz-smooth functions, Hölder-smooth functions, functions with high-order Lipschitz derivative, quasi-self-concordant functions, and (L0, L1)-smooth functions. Furthermore, in contrast to many existing methods, DADA is suitable not only for unconstrained problems, but also constrained ones, possibly with unbounded domain, and it does not require fixing neither the number of iterations nor the accuracy in advance.

Penghao Wu, Yushan Zhang, Haiwen Diao, Bo Li, Lewei Lu, Ziwei Liu

Reinforcement learning based post-training has recently emerged as a powerful paradigm for enhancing the alignment and reasoning capabilities of multimodal large language models (MLLMs). While *vision-centric* post-training is crucial for enhancing MLLMs’ intrinsic understanding of visual signals, current post-training paradigms are predominantly *text-centric*, where dense visual inputs are only leveraged to extract sparse cues for text-based reasoning. There exist a few approaches in this direction, however, they often still rely on text as an intermediate mediator or introduce additional visual generative designs. In this work, we introduce **Visual Jigsaw**, a generic *self-supervised* post-training framework designed to strengthen visual understanding in MLLMs. Visual Jigsaw is formulated as a general ordering task: visual inputs are partitioned, shuffled, and the model must reconstruct the visual information by producing the correct permutation in natural language. This naturally aligns with reinforcement learning from verifiable rewards (RLVR), requires no additional visual generative components, and derives its supervisory signal automatically without any annotations. We instantiate Visual Jigsaw across three visual modalities, including images, videos, and 3D data. Extensive experiments demonstrate substantial improvements in fine-grained perception, temporal reasoning, and 3D spatial understanding. Our findings highlight the potential of self-supervised vision-centric tasks in post-training MLLMs and aim to inspire further research on vision-centric pretext designs.

Yilin Wang, Heng Zhou, Dongxing Mao, Linjie Li, Jingru Tan, Haochen Han, Zhengyuan Yang, Alex Jinpeng Wang, Min Li

Large language models (LLMs) with Process Reward Models (PRMs) have shown strong reasoning ability, yet their potential in Operations Research (OR) remains unexplored. We present the first PRM tailored for OR, but find that directly training on mainstream datasets yields surprisingly weak performance. To understand this gap, we conduct a systematic analysis and identify the primary bottleneck: the datasets themselves, where over 30\% of annotations are severely flawed. To overcome these limitations, we first collect all existing synthetic datasets and apply a carefully designed filtering pipeline to construct a high-quality seed dataset. Building upon this seed, we then build OR-ProcessQA, the first large-scale dataset for OR with step-by-step supervision, where diverse solution pathways are generated via Monte Carlo Tree Search (MCTS) and each step is validated for logical consistency by GPT-4o. Building on this foundation, we train OR-PRM, the first Process Reward Model in the OR domain, designed to evaluate and guide reasoning at every step rather than only the final outcome. Together, these advances enable OR-PRM to substantially improve LLMs’ reasoning capability, achieving a maximum absolute improvement of 12.5\% over the base model in Best-of-N settings, and highlighting the power of process-oriented supervision for reliable problem solving in operations research.

Theory · Optimization

Yiding Shi, Jianan Zhou, Wen Song, Jieyi Bi, Yaoxin Wu, Zhiguang Cao, Jie Zhang

Heuristic design with large language models (LLMs) has emerged as a promising approach for tackling combinatorial optimization problems (COPs). However, existing approaches often rely on manually predefined evolutionary computation (EC) heuristic-optimizers and single-task training schemes, which may constrain the exploration of diverse heuristic algorithms and hinder the generalization of the resulting heuristics. To address these issues, we propose Meta-Optimization of Heuristics (MoH), a novel framework that operates at the optimizer level, discovering effective heuristic-optimizers through the principle of meta-learning. Specifically, MoH leverages LLMs to iteratively refine a meta-optimizer that autonomously constructs diverse heuristic-optimizers through (self-)invocation, thereby eliminating the reliance on a predefined EC heuristic-optimizer. These constructed heuristic-optimizers subsequently evolve heuristics for downstream tasks, enabling broader heuristic exploration. Moreover, MoH employs a multi-task training scheme to promote its generalization capability. Experiments on classic COPs demonstrate that MoH constructs an effective and interpretable meta-optimizer, achieving state-of-the-art performance across various downstream tasks, particularly in cross-size settings. Our code is available at: \url{https://github.com/yiding-s/MoH}.

Computer Vision · Image and Video Generation

Xinjie zhu, Zijing Zhao, Hui Jin, Qingxiao Guo, Yilong Ma, YUNHAO WANG, Xiaobing Guo, Weifeng Zhang

Artificial Intelligence Generated Content (AIGC), particularly video generation with diffusion models, has been advanced rapidly. Invisible watermarking is a key technology for protecting AI-generated videos and tracing harmful content, and thus plays a crucial role in AI safety. Beyond post-processing watermarks which inevitably degrade video quality, recent studies have proposed distortion-free in-generation watermarking for video diffusion models. However, existing in-generation approaches are non-blind: they require maintaining all the message-key pairs and performing template-based matching during extraction, which incurs prohibitive computational costs at scale. Moreover, when applied to modern video diffusion models with causal 3D Variational Autoencoders (VAEs), their robustness against temporal disturbance becomes extremely weak. To overcome these challenges, we propose SIGMark, a Scalable In-Generation watermarking framework with blind extraction for video diffusion. To achieve blind-extraction, we propose to generate watermarked initial noise using a Global set of Frame-wise PseudoRandom Coding keys (GF-PRC), reducing the cost of storing large-scale information while preserving noise distribution and diversity for distortion-free watermarking. To enhance robustness, we further design a Segment Group-Ordering module (SGO) tailored to causal 3D VAEs, ensuring robust watermark inversion during extraction under temporal disturbance. Comprehensive experiments on modern diffusion models show that SIGMark achieves very high bit-accuracy during extraction under both temporal and spatial disturbances with minimal overhead, demonstrating its scalability and robustness. Our code is available at https://github.com/JeremyZhao1998/SIGMark-release.

Chaofan Gan, Zicheng Zhao, Yuanpeng Tu, Xi Chen, Ziran Qin, Tieyuan Chen, Mehrtash Harandi, Weiyao Lin

Massive Activations (MAs) are a well-documented phenomenon across Transformer architectures, and prior studies in both LLMs and ViTs have shown that they play a substantial role in shaping model behavior. However, the nature and function of MAs within Diffusion Transformers (DiTs) remain largely unexplored. In this work, we systematically investigate these activations to elucidate their role in visual generation. We found that these massive activations occur across all spatial tokens, and their distribution is modulated by the input timestep embeddings. Importantly, our investigations further demonstrate that these massive activations play a key role in local detail synthesis, while having minimal impact on the overall semantic content of output. Building on these insights, we propose Detail Guidance (DG), a MAs-driven, training-free self-guidance strategy to explicitly enhance local detail fidelity for DiTs. Specifically, DG constructs a degraded ``detail-deficient'' model by disrupting MAs and leverages it to guide the original network toward higher-quality detail synthesis. Our DG can seamlessly integrate with Classifier-Free Guidance (CFG), enabling joint enhancement of detail fidelity and prompt alignment. Extensive experiments demonstrate that our DG consistently improves local detail quality across various pre-trained DiTs (\eg, SD3, SD3.5, and Flux).

Applications · Robotics

Soroush Nasiriany, Sep Nasiriany, Abhiram Maddukuri, Yuke Zhu

Recent advances in robot learning have accelerated progress toward generalist robots that can perform everyday tasks in human environments. Yet it remains difficult to gauge how close we are to this vision. The field lacks a reproducible, large-scale benchmark for systematic evaluation. To fill this gap, we present RoboCasa365, a comprehensive simulation benchmark for household mobile manipulation. Built on the RoboCasa platform, RoboCasa365 introduces 365 everyday tasks across 2,500 diverse kitchen environments, with over 600 hours of human demonstration data and over 1600 hours of synthetically generated demonstration data---making it one of the most diverse and large-scale resources for studying generalist policies. RoboCasa365 is designed to support systematic evaluations for different problem settings, including multi-task learning, robot foundation model training, and lifelong learning. We conduct extensive experiments on this benchmark with state-of-the-art methods and analyze the impacts of task diversity, dataset scale, and environment variation on generalization. Our results provide new insights into what factors most strongly affect the performance of generalist robots and inform strategies for future progress in the field.

Applications · Robotics

Fanqi Lin, Ruiqian Nai, Yingdong Hu, Jiacheng You, Junming Zhao, Yang Gao

General-purpose robots capable of performing diverse tasks require synergistic reasoning and acting capabilities. However, recent dual-system approaches, which separate high-level reasoning from low-level acting, often suffer from challenges such as limited mutual understanding of capabilities between systems and latency issues. This paper introduces OneTwoVLA, a single unified vision-language-action model that can perform both acting (System One) and reasoning (System Two). Crucially, OneTwoVLA adaptively switches between two modes: explicitly reasoning at critical moments during task execution, and generating actions based on the most recent reasoning at other times. To further unlock OneTwoVLA's reasoning and generalization capabilities, we design a scalable pipeline for synthesizing embodied reasoning-centric vision-language data, used for co-training with robot data. We validate OneTwoVLA's effectiveness through extensive experiments, highlighting its superior performance across four key capabilities: long-horizon task planning, error detection and recovery, natural human-robot interaction, and generalizable visual grounding, enabling the model to perform long-horizon, highly dexterous manipulation tasks such as making hotpot or mixing cocktails.