Showing 1–50 of 104 results for author: Ke, L

UI-Mate: Advancing Open-Weight Foundation GUI Agents with In-Context Demonstrations

Authors: Zihan Ding, Longxu Dou, Qi Gao, Xiangwu Guo, Shengchao Hu, Zilong Huang, Zihang Jiang, Lei Ke, Mengcheng Lan, Weixian Lei, Hanxuan Li, Honglin Li, Xiyun Li, Zaitang Li, Leowei Liang, Xin Luo, Haozhe Ma, Jiayi Mao, Zhoujie Pan, Can Qin, Tianyuan Qu, Weiqi Wang, Wenkai Wang, Yonglin Wang, Yuxin Wang , et al. (4 additional authors not shown)

Abstract: Foundation GUI agents can automate complex digital tasks, but deployment is hindered by scarce and biased training data, ambiguous prompts, and unreliable execution. Routine workflows rely on user-specific tools and tacit conventions, so unstated instructions can produce arbitrary variations across runs. We present UI-Mate, a foundation GUI agent that integrates an environment-grounded training st… ▽ More Foundation GUI agents can automate complex digital tasks, but deployment is hindered by scarce and biased training data, ambiguous prompts, and unreliable execution. Routine workflows rely on user-specific tools and tacit conventions, so unstated instructions can produce arbitrary variations across runs. We present UI-Mate, a foundation GUI agent that integrates an environment-grounded training stack with in-context demonstration learning. UI-Mate makes three contributions: A Scalable Environment-Grounded Training Stack: A closed-loop data engine automates task generation, environment construction, rollout, filtering, capability balancing, SFT, and online RL across massively parallel environments via unified task-verifier bundles. In-Context Demonstration Learning: A mechanism that transforms multimodal demonstrations into flexible subtask-level workflows, follows relevant demonstrated steps, and re-plans from the live interface. OSWorkerBench Benchmark and Insights: A benchmark of 100 long-horizon office tasks across 41 applications that supports instruction-only and demonstration-guided evaluation. Its demonstration resources separate a 33-task self-demo setting, built from successful strong-agent rollouts of the same targets, from a 45-task variant-demo setting, built from human recordings of related but non-identical tasks. Experiments show that UI-Mate-27B sets a new open-weight state of the art on general computer-use benchmarks, scoring 77.0% on OSWorld-Verified and 66.2% on WindowsAgentArena. On OSWorkerBench, it reaches 41.0% strict success and 76.9% progress, outperforming its Qwen3.6-27B base by 17.7 and 24.5 points. On the 33-task self-demo subset, one demonstration raises strict success from 17.2% to 35.4% and progress from 67.9% to 81.1%, substantially improving long-horizon reliability. Project page: https://ui-mate.github.io. △ Less

Submitted 16 August, 2026; originally announced August 2026.

Comments: UI-Mate Technical Report. Project page: https://ui-mate.github.io

Recursive Synthesis for Long-Horizon Terminal Tasks

Authors: Zhongzhi Li, Yucheng Shi, Zongxia Li, Ruhan Wang, Anhao Li, Zixun Huang, Junyao Yang, Lei Ke, Ninghao Liu, Haitao Mi, Leowei Liang

Abstract: High-quality long-horizon training data for terminal agents is expensive to produce, often costing hundreds to thousands of dollars per task, because each task must keep the instruction, environment, reference solution, and verifier mutually consistent. Human authoring does not scale, and direct generation with large language models (LLMs) often breaks these dependencies. We present Recursive Synt… ▽ More High-quality long-horizon training data for terminal agents is expensive to produce, often costing hundreds to thousands of dollars per task, because each task must keep the instruction, environment, reference solution, and verifier mutually consistent. Human authoring does not scale, and direct generation with large language models (LLMs) often breaks these dependencies. We present Recursive Synthetic Terminal Tasks (RST), a recursive verified synthesis framework for constructing long-horizon terminal-agent tasks at scale. Starting from verified seed tasks, RST extends the reference solution, realigns the verifier and instruction to the new workflow, validates the result in a fresh sandbox, and reuses accepted tasks as seeds for subsequent rounds. Across fifteen recursive rounds, RST produces 37,484 synthesized terminal-agent tasks at roughly $0.05 per task. Task difficulty increases substantially over rounds: the median reference solution grows from 67 to 374 lines, the median number of executed commands grows from 40 to 244, and DeepSeek-V4-Pro pass@4 drops from 90% at R1 to 2.5% at R15. To demonstrate training utility, we collect rejection-sampled Qwen3.5 trajectories on the synthesized tasks and use them for supervised fine-tuning. Fine-tuning on these trajectories improves Qwen3.5-27B and Qwen3.5-122B-A10B by up to 10 points on Terminal-Bench 2, Terminal-Bench Hard, and Long-Horizon Terminal Bench, while agentic PPO lifts Qwen3.5-27B to 49.44%, 32.00%, and 22.07% on the three benchmarks, corresponding to relative gains of 20.0%, 41.2%, and 21.9% over the base model. Moreover, after 15 rounds, the recursion shows no ceiling: synthesis yield and validation rates remain stable as difficulty keeps climbing, indicating that the process can continue well beyond the scale reported here. △ Less

Submitted 12 August, 2026; v1 submitted 5 August, 2026; originally announced August 2026.

DVPSFormer: Efficient Online Depth-aware Video Panoptic Segmentation for Autonomous Driving

Authors: Yung-Hsu Yang, Luigi Piccinelli, Siyuan Li, Mattia Segu, Lei Ke, Martin Danelljan, Yuqian Fu, Zuria Bauer, Fisher Yu, Hermann Blum, Marc Pollefeys

Abstract: Safe autonomous navigation requires a holistic understanding of dynamic environments, necessitating the simultaneous estimation of metric depth, semantic segmentation, and instance trajectories. While depth-aware video panoptic segmentation (DVPS) unifies these tasks, existing approaches often rely on computationally expensive, multi-stage pipelines or offline tracking, rendering them unsuitable f… ▽ More Safe autonomous navigation requires a holistic understanding of dynamic environments, necessitating the simultaneous estimation of metric depth, semantic segmentation, and instance trajectories. While depth-aware video panoptic segmentation (DVPS) unifies these tasks, existing approaches often rely on computationally expensive, multi-stage pipelines or offline tracking, rendering them unsuitable for real-time decision-making. To address this, we propose DVPSFormer, a unified online architecture designed for efficient 4D scene understanding. Central to our approach is explicit scene discretization (ESD), a novel mechanism that leverages segmentation queries to represent foreground and background regions, enabling a discrete-to-continuous (D2C) depth head to decode metric depth in a single pass. This tightly couples semantic and geometric learning while significantly reducing latency. Furthermore, we propose an online majority voting (OMV) mechanism that exploits temporal consistency to refine classification during instance tracking. DVPSFormer establishes a new state-of-the-art on the Cityscapes-DVPS and SemKITTI-DVPS benchmarks, offering a streamlined solution for online robotic perception. Code and models are available at https://royyang0714.github.io/DVPSFormer. △ Less

Submitted 28 July, 2026; originally announced July 2026.

Large Language Models Do Not Always Need Readable Language

Authors: Jiayi Zhu, Haoxuan Peng, Junxi Wang, Liang Ke, Chen Zhang, Linfeng Zhang

Abstract: Large language models (LLMs) are commonly prompted and interfaced with human-readable natural language, even when the intended reader is another model. This paper investigates whether semantic information can be encoded in compact, non-standard textual forms that sacrifice human readability while remaining recoverable by LLMs. We refer to this class of model-centric textual representations as Babe… ▽ More Large language models (LLMs) are commonly prompted and interfaced with human-readable natural language, even when the intended reader is another model. This paper investigates whether semantic information can be encoded in compact, non-standard textual forms that sacrifice human readability while remaining recoverable by LLMs. We refer to this class of model-centric textual representations as BabelTele, approached here not as a fixed protocol but as an empirical probe into LLMs' capacity to generate and interpret such representations. Through readability diagnostics, model likelihood measures, human questionnaires, and downstream task evaluations, we find that BabelTele can substantially depart from ordinary natural language while preserving core semantics for instruction-tuned LLMs. As a task-agnostic representational paradigm, BabelTele demonstrates high information density, maintaining 99.5% semantic fidelity even when the text volume is condensed to 27.9% of its original length. We further evaluate its semantic robustness in cross-model transfer, agent memory, and multi-agent communication. Results suggest that BabelTele can reduce context overhead while generally maintaining reliable downstream performance, although its effectiveness depends on the compressor-reader pair and task setting. These findings indicate that human readability, natural-language typicality, and model-side semantic recoverability can be partially decoupled, opening a path toward model-native representations in future exploration of LLM systems. △ Less

Submitted 18 June, 2026; originally announced June 2026.

Comments: 23 pages, 10 figures. Preprint

AudioX-Turbo: A Unified Framework for Efficient Anything-to-Audio Generation

Authors: Zeyue Tian, Lei Ke, Zhaoyang Liu, Ruibin Yuan, Liumeng Xue, Yujiu Yang, Weijia Chen, Xu Tan, Qifeng Chen, Wei Xue, Yike Guo

Abstract: Audio and music generation based on flexible multimodal control signals is a widely applicable topic, with the following key challenges: 1) a unified multimodal modeling framework, 2) large-scale, high-quality training data, and 3) the prohibitive inference cost of multi-step diffusion sampling. As such, we propose AudioX-Turbo, a unified and efficient framework for anything-to-audio generation th… ▽ More Audio and music generation based on flexible multimodal control signals is a widely applicable topic, with the following key challenges: 1) a unified multimodal modeling framework, 2) large-scale, high-quality training data, and 3) the prohibitive inference cost of multi-step diffusion sampling. As such, we propose AudioX-Turbo, a unified and efficient framework for anything-to-audio generation that integrates varied multimodal conditions (i.e., text, video, and audio signals) in this work. AudioX-Turbo follows a teacher-student paradigm. The teacher AudioX-Base is built on a Multimodal Diffusion Transformer with a Multimodal Adaptive Fusion module that aligns diverse multimodal inputs for high-fidelity synthesis, and is then distilled into the few-step student AudioX-Turbo via Distribution Matching Distillation adapted to flow matching, complemented by a diffusion-based discriminator for high-quality few-step generation. To support the training of AudioX-Turbo, we construct a large-scale, high-quality dataset, IF-caps-Pro, comprising approximately 9.2M samples curated through a two-stage data collection and annotation pipeline. We benchmark AudioX-Turbo across a wide range of tasks, finding that our model achieves superior performance, especially on text-to-audio and text-to-music generation, while operating at only 4 sampling steps and requiring approximately 25x fewer function evaluations (NFE) than multi-step baselines. These results demonstrate that our method is capable of audio generation under flexible multimodal control, showing efficient and powerful instruction-following capabilities. The code and datasets will be available at https://zeyuet.github.io/AudioX-Turbo/. △ Less

Submitted 2 July, 2026; v1 submitted 10 June, 2026; originally announced June 2026.

AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution Customization

Authors: Yu Li, Menghan Xia, Gongye Liu, Xintao Wang, Conglang Zhang, Lei Ke, Yuxuan Lin, Ruihang Chu, Pengfei Wan, Kun Gai, Yujiu Yang

Abstract: Despite being a pivotal frontier, interactive world modeling remains underexplored in terms of the versatile controllability required by practical scenarios. To bridge this gap, we present AnchorWorld, a framework that advances egocentric simulation through enhanced interaction integrity and a flexible mechanism for world customization. First, we utilize 3D human motion as the primary interaction… ▽ More Despite being a pivotal frontier, interactive world modeling remains underexplored in terms of the versatile controllability required by practical scenarios. To bridge this gap, we present AnchorWorld, a framework that advances egocentric simulation through enhanced interaction integrity and a flexible mechanism for world customization. First, we utilize 3D human motion as the primary interaction modality. To complement the out-of-view or truncated body parts in egocentric views, we introduce an auxiliary training supervision that incorporates exogenous viewpoints decoupled from the agent's first-person sensorium. It allows the model to observe the agent's full-body positioning relative to the environment, facilitating a more robust spatial grounding of human-world interactions. Furthermore, we propose a simple yet effective mechanism for customizing self-evolving worlds. This is achieved by defining anchor views within a unified world coordinate system, coupled with textual descriptions dictating the dynamic evolution of local scenes. Experimental results show that AnchorWorld significantly outperforms state-of-the-art baselines, while ablation studies validate the effectiveness of our key designs. Notably, our customization scheme exhibits promising spatio-temporal geometric consistency and adheres strictly to the prescribed evolutionary dynamics. △ Less

Submitted 5 June, 2026; originally announced June 2026.

Stream3D-VLM: Online 3D Spatial Understanding with Incremental Geometry Priors

Authors: Hanxun Yu, Xuan Qu, Lei Ke, Boqiang Zhang, Yuxin Wang, Jianke Zhu, Dong Yu

Abstract: Despite advances in 3D scene understanding, existing 3D Large Multimodal Models operate in offline settings, requiring complete scene observations or predefined video clips. In this paper, we present an online 3D vision-language model that enables real-time spatial understanding from streaming video. Our approach adopts an autoregressive streaming control modeling based on the LLM's next-token pre… ▽ More Despite advances in 3D scene understanding, existing 3D Large Multimodal Models operate in offline settings, requiring complete scene observations or predefined video clips. In this paper, we present an online 3D vision-language model that enables real-time spatial understanding from streaming video. Our approach adopts an autoregressive streaming control modeling based on the LLM's next-token prediction objective to learn when to respond, and employs a lightweight Visual-Spatial Feature Integration (VSFI) module to incrementally inject temporally aligned geometry priors into the visual stream. To alleviate long-context decoding overhead, we propose a plug-and-play Geometry-Adaptive Voxel Compression (GAVC) module for efficient visual token compression. To address the scarcity of streaming 3D-language data, we further develop a scalable data generation pipeline that curates over 1M online spatio-temporal 3D QA pairs and establishes a comprehensive benchmark spanning 29 tasks. Extensive experiments show that our approach significantly outperforms both proprietary and open-source models across online and offline 3D spatial understanding, reasoning, and grounding tasks. The project page is available at https://stream3d-vlm.github.io/ △ Less

Submitted 5 June, 2026; originally announced June 2026.

Comments: Project Page: https://stream3d-vlm.github.io/

Unlocking Dense Metric Depth Estimation in VLMs

Authors: Hanxun Yu, Xuan Qu, Yuxin Wang, Jianke Zhu, Lei Ke

Abstract: Vision-Language Models (VLMs) excel at 2D tasks such as grounding and captioning, yet remain limited in 3D understanding. A key limitation is their text-only supervision paradigm, which under-constrains fine-grained visual perception and prevents the recovery of dense geometry. Prior methods either distill geometry from external vision models, introducing error accumulation, or enable direct predi… ▽ More Vision-Language Models (VLMs) excel at 2D tasks such as grounding and captioning, yet remain limited in 3D understanding. A key limitation is their text-only supervision paradigm, which under-constrains fine-grained visual perception and prevents the recovery of dense geometry. Prior methods either distill geometry from external vision models, introducing error accumulation, or enable direct prediction with inefficient per-pixel query or coarse token-level outputs. In this paper, we propose DepthVLM, a simple yet effective framework that transforms a single VLM into a native dense geometry predictor while preserving its multimodal capability. By attaching a lightweight depth head to the LLM backbone and training under a unified vision-text supervision paradigm with a two-stage schedule, DepthVLM generates full-resolution depth maps alongside language outputs in a single forward pass. We further introduce a unified indoor-outdoor metric depth benchmark in a VLM-compatible format. Experiments show that DepthVLM significantly outperforms existing VLMs with higher inference efficiency, surpasses leading pure vision models, and improves complex 3D spatial reasoning, moving toward a truly unified multimodal foundation model. The project page is available at https://depthvlm.github.io/ △ Less

Submitted 20 May, 2026; v1 submitted 15 May, 2026; originally announced May 2026.

Comments: Project Page: https://depthvlm.github.io/

RL Token: Bootstrapping Online RL with Vision-Language-Action Models

Authors: Charles Xu, Jost Tobias Springenberg, Michael Equi, Ali Amin, Adnan Esmail, Sergey Levine, Liyiming Ke

Abstract: Vision-language-action (VLA) models can learn to perform diverse manipulation skills "out of the box," but achieving the precision and speed that real-world tasks demand requires further fine-tuning -- for example, via reinforcement learning (RL). We introduce a lightweight method that enables sample-efficient online RL fine-tuning of pretrained VLAs using just a few hours of real-world practice.… ▽ More Vision-language-action (VLA) models can learn to perform diverse manipulation skills "out of the box," but achieving the precision and speed that real-world tasks demand requires further fine-tuning -- for example, via reinforcement learning (RL). We introduce a lightweight method that enables sample-efficient online RL fine-tuning of pretrained VLAs using just a few hours of real-world practice. We (1) adapt the VLA to expose an "RL token," a compact readout representation that preserves task-relevant pretrained knowledge while serving as an efficient interface for online RL, and (2) train a small actor-critic head on this RL token to refine the actions, while anchoring the learned policy to the VLA. Online RL with the RL token (RLT) makes it possible to fine-tune even large VLAs with RL quickly and efficiently. Across four real-robot tasks (screw installation, zip tie fastening, charger insertion, and Ethernet insertion), RLT improves the speed on the hardest part of the task by up to 3x and raises success rates significantly within minutes to a few hours of practice. It can even surpass the speed of human teleoperation on some of the tasks. △ Less

Submitted 30 April, 2026; v1 submitted 24 April, 2026; originally announced April 2026.

$π_{0.7}$: a Steerable Generalist Robotic Foundation Model with Emergent Capabilities

Authors: Physical Intelligence, Bo Ai, Ali Amin, Raichelle Aniceto, Ashwin Balakrishna, Greg Balke, Kevin Black, George Bokinsky, Shihao Cao, Thomas Charbonnier, Vedant Choudhary, Foster Collins, Ken Conley, Grace Connors, James Darpinian, Karan Dhabalia, Maitrayee Dhaka, Jared DiCarlo, Danny Driess, Michael Equi, Adnan Esmail, Yunhao Fang, Chelsea Finn, Catherine Glossop, Thomas Godden , et al. (63 additional authors not shown)

Abstract: We present a new robotic foundation model, called $π_{0.7}$, that can enable strong out-of-the-box performance in a wide range of scenarios. $π_{0.7}$ can follow diverse language instructions in unseen environments, including multi-stage tasks with various kitchen appliances, provide zero-shot cross-embodiment generalization, for example enabling a robot to fold laundry without seeing the task bef… ▽ More We present a new robotic foundation model, called $π_{0.7}$, that can enable strong out-of-the-box performance in a wide range of scenarios. $π_{0.7}$ can follow diverse language instructions in unseen environments, including multi-stage tasks with various kitchen appliances, provide zero-shot cross-embodiment generalization, for example enabling a robot to fold laundry without seeing the task before, and perform challenging tasks such as operating an espresso machine out of the box at a level of performance that matches much more specialized RL-finetuned models. The main idea behind $π_{0.7}$ is to use diverse context conditioning during training. This conditioning information, contained in the prompt, makes it possible to steer the model precisely to perform many tasks with different strategies. It is conditioned not just on a language command that describes what it should do, but on additional multimodal information that also describes the manner or strategy in which it should do it, including metadata about task performance and subgoal images. This enables $π_{0.7}$ to use very diverse data, including demonstrations, potentially suboptimal (autonomous) data including failures, and data from non-robot sources. Our experiments evaluate $π_{0.7}$ across numerous tasks with multiple robot platforms, on tasks that require speed and dexterity, language following, and compositional task generalization. △ Less

Submitted 24 April, 2026; v1 submitted 16 April, 2026; originally announced April 2026.

Comments: Website: https://www.pi.website/blog/pi07

Communication Gain and Delay Cost Under Cross-Timestep Delays in Cooperative Multi-Agent Reinforcement Learning

Authors: Zihong Gao, Hongjian Liang, Lei Hao, Liangjun Ke

Abstract: Communication is essential for coordination in \emph{cooperative} multi-agent reinforcement learning under partial observability, yet \emph{cross-timestep} delays cause messages to arrive multiple timesteps after generation, inducing temporal misalignment and making information stale when consumed. We formalize this setting as a delayed-communication partially observable Markov game (DeComm-POMG… ▽ More Communication is essential for coordination in \emph{cooperative} multi-agent reinforcement learning under partial observability, yet \emph{cross-timestep} delays cause messages to arrive multiple timesteps after generation, inducing temporal misalignment and making information stale when consumed. We formalize this setting as a delayed-communication partially observable Markov game (DeComm-POMG) and decompose a message's effect into \emph{communication gain} and \emph{delay cost}, yielding the Communication Gain and Delay Cost (CGDC) metric. We further establish a value-loss bound showing that the degradation induced by delayed messages is upper-bounded by a discounted accumulation of an information gap between the action distributions induced by timely versus delayed messages. Guided by CGDC, we propose \textbf{CDCMA}, an actor--critic framework that requests messages only when predicted CGDC is positive, predicts future observations to reduce misalignment at consumption, and fuses delayed messages via CGDC-guided attention. Experiments on no-teammate-vision variants of Cooperative Navigation and Predator Prey, and on SMAC maps across multiple delay levels show consistent improvements in performance, robustness, and generalization, with ablations validating each component. △ Less

Submitted 25 May, 2026; v1 submitted 4 April, 2026; originally announced April 2026.

Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders

Authors: Boqiang Zhang, Lei Ke, Ruihan Yang, Qi Gao, Tianyuan Qu, Rossell Chen, Dong Yu, Leoweiliang

Abstract: Vision Language Model (VLM) development has largely relied on scaling model size, which hinders deployment on compute-constrained mobile and edge devices such as smartphones and robots. In this work, we explore the performance limits of compact (e.g., 2B and 8B) VLMs. We challenge the prevailing practice that state-of-the-art VLMs must rely on vision encoders initialized via massive contrastive pr… ▽ More Vision Language Model (VLM) development has largely relied on scaling model size, which hinders deployment on compute-constrained mobile and edge devices such as smartphones and robots. In this work, we explore the performance limits of compact (e.g., 2B and 8B) VLMs. We challenge the prevailing practice that state-of-the-art VLMs must rely on vision encoders initialized via massive contrastive pretraining (e.g., CLIP/SigLIP). We identify an objective mismatch: contrastive learning, optimized for discrimination, enforces coarse and category-level invariances that suppress fine-grained visual cues needed for dense captioning and complex VLM reasoning. To address this issue, we present Penguin-VL, whose vision encoder is initialized from a text-only LLM. Our experiments reveal that Penguin-Encoder serves as a superior alternative to traditional contrastive pretraining, unlocking a higher degree of visual fidelity and data efficiency for multimodal understanding. Across various image and video benchmarks, Penguin-VL achieves performance comparable to leading VLMs (e.g., Qwen3-VL) in mathematical reasoning and surpasses them in tasks such as document understanding, visual knowledge, and multi-perspective video understanding. Notably, these gains are achieved with a lightweight architecture, demonstrating that improved visual representation rather than model scaling is the primary driver of performance. Our ablations show that Penguin-Encoder consistently outperforms contrastive-pretrained encoders, preserving fine-grained spatial and temporal cues that are critical for dense perception and complex reasoning. This makes it a strong drop-in alternative for compute-efficient VLMs and enables high performance in resource-constrained settings. Code: https://github.com/tencent-ailab/Penguin-VL △ Less

Submitted 14 March, 2026; v1 submitted 6 March, 2026; originally announced March 2026.

Comments: Penguin-VL demonstrates that text-only initialized vision encoders can achieve superior performance in multimodal understanding tasks; Code: https://github.com/tencent-ailab/Penguin-VL

JAEGER: Joint 3D Audio-Visual Grounding and Reasoning in Simulated Physical Environments

Authors: Zhan Liu, Changli Tang, Yuxin Wang, Zhiyuan Zhu, Youjun Chen, Yiwen Shao, Tianzi Wang, Lei Ke, Zengrui Jin, Chao Zhang

Abstract: Current audio-visual large language models (AV-LLMs) are predominantly restricted to 2D perception, relying on RGB video and monaural audio. This design choice introduces a fundamental dimensionality mismatch that precludes reliable source localization and spatial reasoning in complex 3D environments. We address this limitation by presenting JAEGER, a framework that extends AV-LLMs to 3D space, to… ▽ More Current audio-visual large language models (AV-LLMs) are predominantly restricted to 2D perception, relying on RGB video and monaural audio. This design choice introduces a fundamental dimensionality mismatch that precludes reliable source localization and spatial reasoning in complex 3D environments. We address this limitation by presenting JAEGER, a framework that extends AV-LLMs to 3D space, to enable joint spatial grounding and reasoning through the integration of RGB-D observations and multi-channel first-order ambisonics. A core contribution of our work is the neural intensity vector (Neural IV), a learned spatial audio representation that encodes robust directional cues to enhance direction-of-arrival estimation, even in adverse acoustic scenarios with overlapping sources. To facilitate large-scale training and systematic evaluation, we propose SpatialSceneQA, a benchmark of 61k instruction-tuning samples curated from simulated physical environments. Extensive experiments demonstrate that our approach consistently surpasses 2D-centric baselines across diverse spatial perception and reasoning tasks, underscoring the necessity of explicit 3D modelling for advancing AI in physical environments. Our source code, pre-trained model checkpoints, and datasets are available at https://github.com/liuzhan22/JAEGER. △ Less

Submitted 28 May, 2026; v1 submitted 19 February, 2026; originally announced February 2026.

Comments: Accepted to ICML 2026

DCTracks: An Open Dataset for Machine Learning-Based Drift Chamber Track Reconstruction

Authors: Qian Liyan, Zhang Yao, Yuan Ye, Zhang Zhaoke, Fang Jin, Jiang Shimiao, Zhang Jin, Li Ke, Liu Beijiang, Xu Chenglin, Zhang Yifan, Jia Xiaoqian, Qin Xiaoshuai, Huang Xingtao

Abstract: We introduce a Monte Carlo (MC) dataset of single- and two-track drift chamber events to advance Machine Learning (ML)-based track reconstruction. To enable standardized and comparable evaluation, we define track reconstruction specific metrics and report results for traditional track reconstruction algorithms and a Graph Neural Networks (GNNs) method, facilitating rigorous, reproducible validatio… ▽ More We introduce a Monte Carlo (MC) dataset of single- and two-track drift chamber events to advance Machine Learning (ML)-based track reconstruction. To enable standardized and comparable evaluation, we define track reconstruction specific metrics and report results for traditional track reconstruction algorithms and a Graph Neural Networks (GNNs) method, facilitating rigorous, reproducible validation for future research. △ Less

Submitted 16 February, 2026; originally announced February 2026.

InjectRBP: Steering Large Language Model Reasoning Behavior via Pattern Injection

Authors: Xiuping Wu, Zhao Yu, Yuxin Cheng, Ngai Wong, Liangjun Ke, Tapas Mishra, Konstantinos V. Katsikopoulos

Abstract: Reasoning can significantly enhance the performance of Large Language Models. While recent studies have exploited behavior-related prompts adjustment to enhance reasoning, these designs remain largely intuitive and lack a systematic analysis of the underlying behavioral patterns. Motivated by this, we investigate how models' reasoning behaviors shape reasoning from the perspective of behavioral pa… ▽ More Reasoning can significantly enhance the performance of Large Language Models. While recent studies have exploited behavior-related prompts adjustment to enhance reasoning, these designs remain largely intuitive and lack a systematic analysis of the underlying behavioral patterns. Motivated by this, we investigate how models' reasoning behaviors shape reasoning from the perspective of behavioral patterns. We observe that models exhibit adaptive distributions of reasoning behaviors when responding to specific types of questions, and that structurally injecting these patterns can substantially influence the quality of the models' reasoning processes and outcomes. Building on these findings, we propose two optimization methods that require no parameter updates: InjectCorrect and InjectRLOpt. InjectCorrect guides the model by imitating behavioral patterns derived from its own past correct answers. InjectRLOpt learns a value function from historical behavior-pattern data and, via our proposed Reliability-Aware Softmax Policy, generates behavioral injectant during inference to steer the reasoning process. Our experiments demonstrate that both methods can improve model performance across various reasoning tasks without requiring any modifications to model parameters, achieving gains of up to 5.34% and 8.67%, respectively. △ Less

Submitted 12 February, 2026; originally announced February 2026.

Beyond VLM-Based Rewards: Diffusion-Native Latent Reward Modeling

Authors: Gongye Liu, Bo Yang, Yida Zhi, Zhizhou Zhong, Lei Ke, Didan Deng, Han Gao, Yongxiang Huang, Kaihao Zhang, Hongbo Fu, Wenhan Luo

Abstract: Preference optimization for diffusion and flow-matching models relies on reward functions that are both discriminatively robust and computationally efficient. Vision-Language Models (VLMs) have emerged as the primary reward provider, leveraging their rich multimodal priors to guide alignment. However, their computation and memory cost can be substantial, and optimizing a latent diffusion generator… ▽ More Preference optimization for diffusion and flow-matching models relies on reward functions that are both discriminatively robust and computationally efficient. Vision-Language Models (VLMs) have emerged as the primary reward provider, leveraging their rich multimodal priors to guide alignment. However, their computation and memory cost can be substantial, and optimizing a latent diffusion generator through a pixel-space reward introduces a domain mismatch that complicates alignment. In this paper, we propose DiNa-LRM, a diffusion-native latent reward model that formulates preference learning directly on noisy diffusion states. Our method introduces a noise-calibrated Thurstone likelihood with diffusion-noise-dependent uncertainty. DiNa-LRM leverages a pretrained latent diffusion backbone with a timestep-conditioned reward head, and supports inference-time noise ensembling, providing a diffusion-native mechanism for test-time scaling and robust rewarding. Across image alignment benchmarks, DiNa-LRM substantially outperforms existing diffusion-based reward baselines and achieves performance competitive with state-of-the-art VLMs at a fraction of the computational cost. In preference optimization, we demonstrate that DiNa-LRM improves preference optimization dynamics, enabling faster and more resource-efficient model alignment. △ Less

Submitted 22 May, 2026; v1 submitted 11 February, 2026; originally announced February 2026.

Comments: Accepted by ICML 2026. Code: https://github.com/HKUST-C4G/diffusion-rm

A New Mode of Teaching Chinese as a Foreign Language from the Perspective of Smart System Studied by Using Rongzhixue

Authors: Xiaohui Zou, Lijun Ke, Shunpeng Zou

Abstract: The purpose of this study is to introduce a new model of teaching Chinese as a foreign language from the perspective of integrating wisdom. Its characteristics are as follows: focusing on the butterfly model of interpretation before translation, highlighting the new method of bilingual thinking training, on the one hand, applying the new theory of Chinese characters, the theory of the relationship… ▽ More The purpose of this study is to introduce a new model of teaching Chinese as a foreign language from the perspective of integrating wisdom. Its characteristics are as follows: focusing on the butterfly model of interpretation before translation, highlighting the new method of bilingual thinking training, on the one hand, applying the new theory of Chinese characters, the theory of the relationship between language and speech, and the forward-looking research results of language science; On the other hand, the application of the new model of teaching Chinese as a foreign language, AI empowering teaching and learning, and the forward-looking research results of educational science fully reflect a series of characteristics of the new model of teaching Chinese as a foreign language from the perspective of integrating wisdom. Its beneficial effects are: not only the old view of language and education, especially the old view of teaching Chinese as a foreign language, but also the old view of human-computer interaction. Its significance lies in that a series of great cross-border Rongzhixue such as language, knowledge, education and teaching, as well as new methods and new topics of bilingual thinking training are clearly put forward from the perspective of integrating wisdom. Especially in the face of the challenge of Chat GPT to human learning ability and even creativity, the existing concepts of language knowledge education and teaching are already very backward. The old concepts of Chinese language education, and teaching Chinese as a foreign language are all facing a series of subversive innovation challenges. How to seek changes in adaptation? This study has made a series of innovative attempts, hoping to benefit academic colleagues, teachers and students. △ Less

Submitted 28 January, 2026; originally announced February 2026.

Comments: 11 pages, in Chinese language, 22 figures

Stable and Efficient Single-Rollout RL for Multimodal Reasoning

Authors: Rui Liu, Dian Yu, Lei Ke, Haolin Liu, Yujun Zhou, Zhenwen Liang, Haitao Mi, Pratap Tokekar, Dong Yu

Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has become a key paradigm to improve the reasoning capabilities of Multimodal Large Language Models (MLLMs). However, prevalent group-based algorithms such as GRPO require multi-rollout sampling for each prompt. While more efficient single-rollout variants have recently been explored in text-only settings, we find that they suffer from severe i… ▽ More Reinforcement Learning with Verifiable Rewards (RLVR) has become a key paradigm to improve the reasoning capabilities of Multimodal Large Language Models (MLLMs). However, prevalent group-based algorithms such as GRPO require multi-rollout sampling for each prompt. While more efficient single-rollout variants have recently been explored in text-only settings, we find that they suffer from severe instability in multimodal contexts, often leading to training collapse. To address this training efficiency-stability trade-off, we introduce $\textbf{MSSR}$ (Multimodal Stabilized Single-Rollout), a group-free RLVR framework that achieves both stable optimization and effective multimodal reasoning performance. MSSR achieves this via an entropy-based advantage-shaping mechanism that adaptively regularizes advantage magnitudes, preventing collapse and maintaining training stability. While such mechanisms have been used in group-based RLVR, we show that in the multimodal single-rollout setting they are not merely beneficial but essential for stability. In in-distribution evaluations, MSSR demonstrates superior training compute efficiency, achieving similar validation accuracy to the group-based baseline with half the training steps. When trained for the same number of steps, MSSR's performance surpasses the group-based baseline and shows consistent generalization improvements across five diverse reasoning-intensive benchmarks. Together, these results demonstrate that MSSR enables stable, compute-efficient, and effective RLVR for complex multimodal reasoning tasks. △ Less

Submitted 20 December, 2025; originally announced December 2025.

RePlan: Reasoning-guided Region Planning for Complex Instruction-based Image Editing

Authors: Tianyuan Qu, Lei Ke, Xiaohang Zhan, Longxiang Tang, Yuqi Liu, Bohao Peng, Bei Yu, Dong Yu, Jiaya Jia

Abstract: Instruction-based image editing enables natural-language control over visual modifications, yet existing models falter under Instruction-Visual Complexity (IV-Complexity), where intricate instructions meet cluttered or ambiguous scenes. We introduce RePlan (Region-aligned Planning), a plan-then-execute framework that couples a vision-language planner with a diffusion editor. The planner decomposes… ▽ More Instruction-based image editing enables natural-language control over visual modifications, yet existing models falter under Instruction-Visual Complexity (IV-Complexity), where intricate instructions meet cluttered or ambiguous scenes. We introduce RePlan (Region-aligned Planning), a plan-then-execute framework that couples a vision-language planner with a diffusion editor. The planner decomposes instructions via step-by-step reasoning and explicitly grounds them to target regions; the editor then applies changes using a training-free attention-region injection mechanism, enabling precise, parallel multi-region edits without iterative inpainting. To strengthen planning, we apply GRPO-based reinforcement learning using 1K instruction-only examples, yielding substantial gains in reasoning fidelity and format reliability. We further present IV-Edit, a benchmark focused on fine-grained grounding and knowledge-intensive edits. Across IV-Complex settings, RePlan consistently outperforms strong baselines trained on far larger datasets, improving regional precision and overall consistency. Our project page: https://replan-iv-edit.github.io △ Less

Submitted 16 July, 2026; v1 submitted 18 December, 2025; originally announced December 2025.

Comments: [ECCV2026] Precise multi-region control and planning for instruction-based image editing. Our project page: https://replan-iv-edit.github.io

N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Models

Authors: Yuxin Wang, Lei Ke, Boqiang Zhang, Tianyuan Qu, Hanxun Yu, Zhenpeng Huang, Meng Yu, Dan Xu, Dong Yu

Abstract: While current multimodal models can answer questions based on 2D images, they lack intrinsic 3D object perception, limiting their ability to comprehend spatial relationships and depth cues in 3D scenes. In this work, we propose N3D-VLM, a novel unified framework that seamlessly integrates native 3D object perception with 3D-aware visual reasoning, enabling both precise 3D grounding and interpretab… ▽ More While current multimodal models can answer questions based on 2D images, they lack intrinsic 3D object perception, limiting their ability to comprehend spatial relationships and depth cues in 3D scenes. In this work, we propose N3D-VLM, a novel unified framework that seamlessly integrates native 3D object perception with 3D-aware visual reasoning, enabling both precise 3D grounding and interpretable spatial understanding. Unlike conventional end-to-end models that directly predict answers from RGB/RGB-D inputs, our approach equips the model with native 3D object perception capabilities, enabling it to directly localize objects in 3D space based on textual descriptions. Building upon accurate 3D object localization, the model further performs explicit reasoning in 3D, achieving more interpretable and structured spatial understanding. To support robust training for these capabilities, we develop a scalable data construction pipeline that leverages depth estimation to lift large-scale 2D annotations into 3D space, significantly increasing the diversity and coverage for 3D object grounding data, yielding over six times larger than the largest existing single-image 3D detection dataset. Moreover, the pipeline generates spatial question-answering datasets that target chain-of-thought (CoT) reasoning in 3D, facilitating joint training for both 3D object localization and 3D spatial reasoning. Experimental results demonstrate that our unified framework not only achieves state-of-the-art performance on 3D grounding tasks, but also consistently surpasses existing methods in 3D spatial reasoning in vision-language model. △ Less

Submitted 18 December, 2025; originally announced December 2025.

Comments: Project Page: https://n3d-vlm.github.io

MotionEdit: Benchmarking and Learning Motion-Centric Image Editing

Authors: Yixin Wan, Lei Ke, Wenhao Yu, Kai-Wei Chang, Dong Yu

Abstract: We introduce MotionEdit, a novel dataset for motion-centric image editing-the task of modifying subject actions and interactions while preserving identity, structure, and physical plausibility. Unlike existing image editing datasets that focus on static appearance changes or contain only sparse, low-quality motion edits, MotionEdit provides high-fidelity image pairs depicting realistic motion tran… ▽ More We introduce MotionEdit, a novel dataset for motion-centric image editing-the task of modifying subject actions and interactions while preserving identity, structure, and physical plausibility. Unlike existing image editing datasets that focus on static appearance changes or contain only sparse, low-quality motion edits, MotionEdit provides high-fidelity image pairs depicting realistic motion transformations extracted and verified from continuous videos. This new task is not only scientifically challenging but also practically significant, powering downstream applications such as frame-controlled video synthesis and animation. To evaluate model performance on the novel task, we introduce MotionEdit-Bench, a benchmark that challenges models on motion-centric edits and measures model performance with generative, discriminative, and preference-based metrics. Benchmark results reveal that motion editing remains highly challenging for existing state-of-the-art diffusion-based editing models. To address this gap, we propose MotionNFT (Motion-guided Negative-aware Fine Tuning), a post-training framework that computes motion alignment rewards based on how well the motion flow between input and model-edited images matches the ground-truth motion, guiding models toward accurate motion transformations. Extensive experiments on FLUX.1 Kontext and Qwen-Image-Edit show that MotionNFT consistently improves editing quality and motion fidelity of both base models on the motion editing task without sacrificing general editing ability, demonstrating its effectiveness. Our code is at https://github.com/elainew728/motion-edit/. △ Less

Submitted 13 December, 2025; v1 submitted 10 December, 2025; originally announced December 2025.

Comments: Technical Report. We propose MotionEdit, a dataset and benchmark for motion-centric image editing. We also introduce MotionNFT, a reward training framework to improve existing models with motion-aware guidance. Github: https://github.com/elainew728/motion-edit/

FlowSteer: Guiding Few-Step Image Synthesis with Authentic Trajectories

Authors: Lei Ke, Hubery Yin, Gongye Liu, Zhengyao Lv, Jingcai Guo, Chen Li, Wenhan Luo, Yujiu Yang, Jing Lyu

Abstract: With the success of flow matching in visual generation, sampling efficiency remains a critical bottleneck for its practical application. Among flow models' accelerating methods, ReFlow has been somehow overlooked although it has theoretical consistency with flow matching. This is primarily due to its suboptimal performance in practical scenarios compared to consistency distillation and score disti… ▽ More With the success of flow matching in visual generation, sampling efficiency remains a critical bottleneck for its practical application. Among flow models' accelerating methods, ReFlow has been somehow overlooked although it has theoretical consistency with flow matching. This is primarily due to its suboptimal performance in practical scenarios compared to consistency distillation and score distillation. In this work, we investigate this issue within the ReFlow framework and propose FlowSteer, a method unlocks the potential of ReFlow-based distillation by guiding the student along teacher's authentic generation trajectories. We first identify that Piecewised ReFlow's performance is hampered by a critical distribution mismatch during the training and propose Online Trajectory Alignment(OTA) to resolve it. Then, we introduce a adversarial distillation objective applied directly on the ODE trajectory, improving the student's adherence to the teacher's generation trajectory. Furthermore, we find and fix a previously undiscovered flaw in the widely-used FlowMatchEulerDiscreteScheduler that largely degrades few-step inference quality. Our experiment result on SD3 demonstrates our method's efficacy. △ Less

Submitted 24 November, 2025; originally announced November 2025.

Comments: Few-Step Image Synthesis

$π^{*}_{0.6}$: a VLA That Learns From Experience

Authors: Physical Intelligence, Ali Amin, Raichelle Aniceto, Ashwin Balakrishna, Kevin Black, Ken Conley, Grace Connors, James Darpinian, Karan Dhabalia, Jared DiCarlo, Danny Driess, Michael Equi, Adnan Esmail, Yunhao Fang, Chelsea Finn, Catherine Glossop, Thomas Godden, Ivan Goryachev, Lachy Groom, Hunter Hancock, Karol Hausman, Gashon Hussein, Brian Ichter, Szymon Jakubczak, Rowan Jen , et al. (31 additional authors not shown)

Abstract: We study how vision-language-action (VLA) models can improve through real-world deployments via reinforcement learning (RL). We present a general-purpose method, RL with Experience and Corrections via Advantage-conditioned Policies (RECAP), that provides for RL training of VLAs via advantage conditioning. Our method incorporates heterogeneous data into the self-improvement process, including demon… ▽ More We study how vision-language-action (VLA) models can improve through real-world deployments via reinforcement learning (RL). We present a general-purpose method, RL with Experience and Corrections via Advantage-conditioned Policies (RECAP), that provides for RL training of VLAs via advantage conditioning. Our method incorporates heterogeneous data into the self-improvement process, including demonstrations, data from on-policy collection, and expert teleoperated interventions provided during autonomous execution. RECAP starts by pre-training a generalist VLA with offline RL, which we call $π^{*}_{0.6}$, that can then be specialized to attain high performance on downstream tasks through on-robot data collection. We show that the $π^{*}_{0.6}$ model trained with the full RECAP method can fold laundry in real homes, reliably assemble boxes, and make espresso drinks using a professional espresso machine. On some of the hardest tasks, RECAP more than doubles task throughput and roughly halves the task failure rate. △ Less

Submitted 18 November, 2025; v1 submitted 18 November, 2025; originally announced November 2025.

Test-driven Reinforcement Learning in Continuous Control

Authors: Zhao Yu, Xiuping Wu, Liangjun Ke

Abstract: Reinforcement learning (RL) has been recognized as a powerful tool for robot control tasks. RL typically employs reward functions to define task objectives and guide agent learning. However, since the reward function serves the dual purpose of defining the optimal goal and guiding learning, it is challenging to design the reward function manually, which often results in a suboptimal task represent… ▽ More Reinforcement learning (RL) has been recognized as a powerful tool for robot control tasks. RL typically employs reward functions to define task objectives and guide agent learning. However, since the reward function serves the dual purpose of defining the optimal goal and guiding learning, it is challenging to design the reward function manually, which often results in a suboptimal task representation. To tackle the reward design challenge in RL, inspired by the satisficing theory, we propose a Test-driven Reinforcement Learning (TdRL) framework. In the TdRL framework, multiple test functions are used to represent the task objective rather than a single reward function. Test functions can be categorized as pass-fail tests and indicative tests, each dedicated to defining the optimal objective and guiding the learning process, respectively, thereby making defining tasks easier. Building upon such a task definition, we first prove that if a trajectory return function assigns higher returns to trajectories closer to the optimal trajectory set, maximum entropy policy optimization based on this return function will yield a policy that is closer to the optimal policy set. Then, we introduce a lexicographic heuristic approach to compare the relative distance relationship between trajectories and the optimal trajectory set for learning the trajectory return function. Furthermore, we develop an algorithm implementation of TdRL. Experimental results on the DeepMind Control Suite benchmark demonstrate that TdRL matches or outperforms handcrafted reward methods in policy training, with greater design simplicity and inherent support for multi-objective optimization. We argue that TdRL offers a novel perspective for representing task objectives, which could be helpful in addressing the reward design challenges in RL applications. △ Less

Submitted 9 December, 2025; v1 submitted 11 November, 2025; originally announced November 2025.

Comments: AAAI 2026 oral

RobotArena $\infty$: Scalable Robot Benchmarking via Real-to-Sim Translation

Authors: Yash Jangir, Yidi Zhang, Pang-Chi Lo, Kashu Yamazaki, Chenyu Zhang, Kuan-Hsun Tu, Tsung-Wei Ke, Lei Ke, Yonatan Bisk, Katerina Fragkiadaki

Abstract: The pursuit of robot generalists, agents capable of performing diverse tasks across diverse environments, demands rigorous and scalable evaluation. Yet real-world testing of robot policies remains fundamentally constrained: it is labor-intensive, slow, unsafe at scale, and difficult to reproduce. As policies expand in scope and complexity, these barriers only intensify, since defining "success" in… ▽ More The pursuit of robot generalists, agents capable of performing diverse tasks across diverse environments, demands rigorous and scalable evaluation. Yet real-world testing of robot policies remains fundamentally constrained: it is labor-intensive, slow, unsafe at scale, and difficult to reproduce. As policies expand in scope and complexity, these barriers only intensify, since defining "success" in robotics often hinges on nuanced human judgments of execution quality. We introduce RobotArena Infinity, a new benchmarking framework that overcomes these challenges by shifting vision-language-action (VLA) evaluation into large-scale simulated environments augmented with online human feedback. Leveraging advances in vision-language models, 2D-to-3D generative modeling, and differentiable rendering, our approach automatically converts video demonstrations from widely used robot datasets into simulated counterparts. Within these digital twins, we assess VLA policies using both automated vision-language-model-guided scoring and scalable human preference judgments collected from crowdworkers, transforming human involvement from tedious scene setup, resetting, and safety supervision into lightweight preference comparisons. To measure robustness, we systematically perturb simulated environments along multiple axes, including textures and object placements, stress-testing policy generalization under controlled variation. The result is a continuously evolving, reproducible, and scalable benchmark for real-world-trained robot manipulation policies, addressing a critical missing capability in today's robotics landscape. △ Less

Submitted 19 March, 2026; v1 submitted 27 October, 2025; originally announced October 2025.

Comments: Website: https://robotarenainf.github.io

Pilot selection in the era of Virtual reality: algorithms for accurate and interpretable machine learning models

Authors: Luoma Ke, Guangpeng Zhang, Jibo He, Yajing Li, Yan Li, Xufeng Liu, Peng Fang

Abstract: With the rapid growth of the aviation industry, there is a need for a large number of flight crew. How to select the right pilots in a cost-efficient manner has become an important research question. In the current study, twenty-three pilots were recruited from China Eastern Airlines, and 23 novices were from the community of Tsinghua University. A novel approach incorporating machine learning and… ▽ More With the rapid growth of the aviation industry, there is a need for a large number of flight crew. How to select the right pilots in a cost-efficient manner has become an important research question. In the current study, twenty-three pilots were recruited from China Eastern Airlines, and 23 novices were from the community of Tsinghua University. A novel approach incorporating machine learning and virtual reality technology was applied to distinguish features between these participants with different flight skills. Results indicate that SVM with the MIC feature selection method consistently achieved the highest prediction performance on all metrics with an Accuracy of 0.93, an AUC of 0.96, and an F1 of 0.93, which outperforms four other classifier algorithms and two other feature selection methods. From the perspective of feature selection methods, the MIC method can select features with a nonlinear relationship to sampling labels, instead of a simple filter-out. Our new implementation of the SVM + MIC algorithm outperforms all existing pilot selection algorithms and perhaps provides the first implementation based on eye tracking and flight dynamics data. This study's VR simulation platforms and algorithms can be used for pilot selection and training. △ Less

Submitted 2 October, 2025; originally announced October 2025.

Multi-View 3D Point Tracking

Authors: Frano Rajič, Haofei Xu, Marko Mihajlovic, Siyuan Li, Irem Demir, Emircan Gündoğdu, Lei Ke, Sergey Prokudin, Marc Pollefeys, Siyu Tang

Abstract: We introduce the first data-driven multi-view 3D point tracker, designed to track arbitrary points in dynamic scenes using multiple camera views. Unlike existing monocular trackers, which struggle with depth ambiguities and occlusion, or prior multi-camera methods that require over 20 cameras and tedious per-sequence optimization, our feed-forward model directly predicts 3D correspondences using a… ▽ More We introduce the first data-driven multi-view 3D point tracker, designed to track arbitrary points in dynamic scenes using multiple camera views. Unlike existing monocular trackers, which struggle with depth ambiguities and occlusion, or prior multi-camera methods that require over 20 cameras and tedious per-sequence optimization, our feed-forward model directly predicts 3D correspondences using a practical number of cameras (e.g., four), enabling robust and accurate online tracking. Given known camera poses and either sensor-based or estimated multi-view depth, our tracker fuses multi-view features into a unified point cloud and applies k-nearest-neighbors correlation alongside a transformer-based update to reliably estimate long-range 3D correspondences, even under occlusion. We train on 5K synthetic multi-view Kubric sequences and evaluate on two real-world benchmarks: Panoptic Studio and DexYCB, achieving median trajectory errors of 3.1 cm and 2.0 cm, respectively. Our method generalizes well to diverse camera setups of 1-8 views with varying vantage points and video lengths of 24-150 frames. By releasing our tracker alongside training and evaluation datasets, we aim to set a new standard for multi-view 3D tracking research and provide a practical tool for real-world applications. Project page available at https://ethz-vlg.github.io/mvtracker. △ Less

Submitted 28 August, 2025; originally announced August 2025.

Comments: ICCV 2025, Oral. Project page: https://ethz-vlg.github.io/mvtracker

Generative Video Matting

Authors: Yongtao Ge, Kangyang Xie, Guangkai Xu, Mingyu Liu, Li Ke, Longtao Huang, Hui Xue, Hao Chen, Chunhua Shen

Abstract: Video matting has traditionally been limited by the lack of high-quality ground-truth data. Most existing video matting datasets provide only human-annotated imperfect alpha and foreground annotations, which must be composited to background images or videos during the training stage. Thus, the generalization capability of previous methods in real-world scenarios is typically poor. In this work, we… ▽ More Video matting has traditionally been limited by the lack of high-quality ground-truth data. Most existing video matting datasets provide only human-annotated imperfect alpha and foreground annotations, which must be composited to background images or videos during the training stage. Thus, the generalization capability of previous methods in real-world scenarios is typically poor. In this work, we propose to solve the problem from two perspectives. First, we emphasize the importance of large-scale pre-training by pursuing diverse synthetic and pseudo-labeled segmentation datasets. We also develop a scalable synthetic data generation pipeline that can render diverse human bodies and fine-grained hairs, yielding around 200 video clips with a 3-second duration for fine-tuning. Second, we introduce a novel video matting approach that can effectively leverage the rich priors from pre-trained video diffusion models. This architecture offers two key advantages. First, strong priors play a critical role in bridging the domain gap between synthetic and real-world scenes. Second, unlike most existing methods that process video matting frame-by-frame and use an independent decoder to aggregate temporal information, our model is inherently designed for video, ensuring strong temporal consistency. We provide a comprehensive quantitative evaluation across three benchmark datasets, demonstrating our approach's superior performance, and present comprehensive qualitative results in diverse real-world scenes, illustrating the strong generalization capability of our method. The code is available at https://github.com/aim-uofa/GVM. △ Less

Submitted 11 August, 2025; originally announced August 2025.

Journal ref: SIGGRAPH Conference Papers 2025

BiVM: Accurate Binarized Neural Network for Efficient Video Matting

Authors: Haotong Qin, Xianglong Liu, Xudong Ma, Lei Ke, Yulun Zhang, Jie Luo, Michele Magno

Abstract: Deep neural networks for real-time video matting suffer significant computational limitations on edge devices, hindering their adoption in widespread applications such as online conferences and short-form video production. Binarization emerges as one of the most common compression approaches with compact 1-bit parameters and efficient bitwise operations. However, accuracy and efficiency limitation… ▽ More Deep neural networks for real-time video matting suffer significant computational limitations on edge devices, hindering their adoption in widespread applications such as online conferences and short-form video production. Binarization emerges as one of the most common compression approaches with compact 1-bit parameters and efficient bitwise operations. However, accuracy and efficiency limitations exist in the binarized video matting network due to its degenerated encoder and redundant decoder. Following a theoretical analysis based on the information bottleneck principle, the limitations are mainly caused by the degradation of prediction-relevant information in the intermediate features and the redundant computation in prediction-irrelevant areas. We present BiVM, an accurate and resource-efficient Binarized neural network for Video Matting. First, we present a series of binarized computation structures with elastic shortcuts and evolvable topologies, enabling the constructed encoder backbone to extract high-quality representation from input videos for accurate prediction. Second, we sparse the intermediate feature of the binarized decoder by masking homogeneous parts, allowing the decoder to focus on representation with diverse details while alleviating the computation burden for efficient inference. Furthermore, we construct a localized binarization-aware mimicking framework with the information-guided strategy, prompting matting-related representation in full-precision counterparts to be accurately and fully utilized. Comprehensive experiments show that the proposed BiVM surpasses alternative binarized video matting networks, including state-of-the-art (SOTA) binarization methods, by a substantial margin. Moreover, our BiVM achieves significant savings of 14.3x and 21.6x in computation and storage costs, respectively. We also evaluate BiVM on ARM CPU hardware. △ Less

Submitted 6 July, 2025; originally announced July 2025.

ATK: Automatic Task-driven Keypoint Selection for Robust Policy Learning

Authors: Yunchu Zhang, Shubham Mittal, Zhengyu Zhang, Liyiming Ke, Siddhartha Srinivasa, Abhishek Gupta

Abstract: Visuomotor policies often suffer from perceptual challenges, where visual differences between training and evaluation environments degrade policy performance. Policies relying on state estimations, like 6D pose, require task-specific tracking and are difficult to scale, while raw sensor-based policies may lack robustness to small visual disturbances. In this work, we leverage 2D keypoints--spatial… ▽ More Visuomotor policies often suffer from perceptual challenges, where visual differences between training and evaluation environments degrade policy performance. Policies relying on state estimations, like 6D pose, require task-specific tracking and are difficult to scale, while raw sensor-based policies may lack robustness to small visual disturbances. In this work, we leverage 2D keypoints--spatially consistent features in the image frame--as a flexible state representation for robust policy learning and apply it to both sim-to-real transfer and real-world imitation learning. However, the choice of which keypoints to use can vary across objects and tasks. We propose a novel method, ATK, to automatically select keypoints in a task-driven manner so that the chosen keypoints are predictive of optimal behavior for the given task. Our proposal optimizes for a minimal set of keypoints that focus on task-relevant parts while preserving policy performance and robustness. We distill expert data (either from an expert policy in simulation or a human expert) into a policy that operates on RGB images while tracking the selected keypoints. By leveraging pre-trained visual modules, our system effectively encodes states and transfers policies to the real-world evaluation scenario despite wide scene variations and perceptual challenges such as transparent objects, fine-grained tasks, and deformable objects manipulation. We validate ATK on various robotic tasks, demonstrating that these minimal keypoint representations significantly improve robustness to visual disturbances and environmental variations. See all experiments and more details at https://yunchuzhang.github.io/ATK/. △ Less

Submitted 4 October, 2025; v1 submitted 16 June, 2025; originally announced June 2025.

Generative 4D Scene Gaussian Splatting with Object View-Synthesis Priors

Authors: Wen-Hsuan Chu, Lei Ke, Jianmeng Liu, Mingxiao Huo, Pavel Tokmakov, Katerina Fragkiadaki

Abstract: We tackle the challenge of generating dynamic 4D scenes from monocular, multi-object videos with heavy occlusions, and introduce GenMOJO, a novel approach that integrates rendering-based deformable 3D Gaussian optimization with generative priors for view synthesis. While existing models perform well on novel view synthesis for isolated objects, they struggle to generalize to complex, cluttered sce… ▽ More We tackle the challenge of generating dynamic 4D scenes from monocular, multi-object videos with heavy occlusions, and introduce GenMOJO, a novel approach that integrates rendering-based deformable 3D Gaussian optimization with generative priors for view synthesis. While existing models perform well on novel view synthesis for isolated objects, they struggle to generalize to complex, cluttered scenes. To address this, GenMOJO decomposes the scene into individual objects, optimizing a differentiable set of deformable Gaussians per object. This object-wise decomposition allows leveraging object-centric diffusion models to infer unobserved regions in novel viewpoints. It performs joint Gaussian splatting to render the full scene, capturing cross-object occlusions, and enabling occlusion-aware supervision. To bridge the gap between object-centric priors and the global frame-centric coordinate system of videos, GenMOJO uses differentiable transformations that align generative and rendering constraints within a unified framework. The resulting model generates 4D object reconstructions over space and time, and produces accurate 2D and 3D point tracks from monocular input. Quantitative evaluations and perceptual human studies confirm that GenMOJO generates more realistic novel views of scenes and produces more accurate point tracks compared to existing approaches. △ Less

Submitted 15 June, 2025; originally announced June 2025.

Comments: This is an updated and extended version of our CVPR paper "Robust Multi-Object 4D Generation in Complex Video Scenarios"

Score-based Generative Modeling for Conditional Independence Testing

Authors: Yixin Ren, Chenghou Jin, Yewei Xia, Li Ke, Longtao Huang, Hui Xue, Hao Zhang, Jihong Guan, Shuigeng Zhou

Abstract: Determining conditional independence (CI) relationships between random variables is a fundamental yet challenging task in machine learning and statistics, especially in high-dimensional settings. Existing generative model-based CI testing methods, such as those utilizing generative adversarial networks (GANs), often struggle with undesirable modeling of conditional distributions and training insta… ▽ More Determining conditional independence (CI) relationships between random variables is a fundamental yet challenging task in machine learning and statistics, especially in high-dimensional settings. Existing generative model-based CI testing methods, such as those utilizing generative adversarial networks (GANs), often struggle with undesirable modeling of conditional distributions and training instability, resulting in subpar performance. To address these issues, we propose a novel CI testing method via score-based generative modeling, which achieves precise Type I error control and strong testing power. Concretely, we first employ a sliced conditional score matching scheme to accurately estimate conditional score and use Langevin dynamics conditional sampling to generate null hypothesis samples, ensuring precise Type I error control. Then, we incorporate a goodness-of-fit stage into the method to verify generated samples and enhance interpretability in practice. We theoretically establish the error bound of conditional distributions modeled by score-based generative models and prove the validity of our CI tests. Extensive experiments on both synthetic and real-world datasets show that our method significantly outperforms existing state-of-the-art methods, providing a promising way to revitalize generative model-based CI testing. △ Less

Submitted 29 May, 2025; originally announced May 2025.

Comments: Accepted by KDD2025

Zero-P-to-3: Zero-Shot Partial-View Images to 3D Object

Authors: Yuxuan Lin, Ruihang Chu, Zhenyu Chen, Xiao Tang, Lei Ke, Haoling Li, Yingji Zhong, Zhihao Li, Shiyong Liu, Xiaofei Wu, Jianzhuang Liu, Yujiu Yang

Abstract: Generative 3D reconstruction shows strong potential in incomplete observations. While sparse-view and single-image reconstruction are well-researched, partial observation remains underexplored. In this context, dense views are accessible only from a specific angular range, with other perspectives remaining inaccessible. This task presents two main challenges: (i) limited View Range: observations c… ▽ More Generative 3D reconstruction shows strong potential in incomplete observations. While sparse-view and single-image reconstruction are well-researched, partial observation remains underexplored. In this context, dense views are accessible only from a specific angular range, with other perspectives remaining inaccessible. This task presents two main challenges: (i) limited View Range: observations confined to a narrow angular scope prevent effective traditional interpolation techniques that require evenly distributed perspectives. (ii) inconsistent Generation: views created for invisible regions often lack coherence with both visible regions and each other, compromising reconstruction consistency. To address these challenges, we propose \method, a novel training-free approach that integrates the local dense observations and multi-source priors for reconstruction. Our method introduces a fusion-based strategy to effectively align these priors in DDIM sampling, thereby generating multi-view consistent images to supervise invisible views. We further design an iterative refinement strategy, which uses the geometric structures of the object to enhance reconstruction quality. Extensive experiments on multiple datasets show the superiority of our method over SOTAs, especially in invisible regions. △ Less

Submitted 28 May, 2025; originally announced May 2025.

$π_{0.5}$: a Vision-Language-Action Model with Open-World Generalization

Authors: Physical Intelligence, Kevin Black, Noah Brown, James Darpinian, Karan Dhabalia, Danny Driess, Adnan Esmail, Michael Equi, Chelsea Finn, Niccolo Fusai, Manuel Y. Galliker, Dibya Ghosh, Lachy Groom, Karol Hausman, Brian Ichter, Szymon Jakubczak, Tim Jones, Liyiming Ke, Devin LeBlanc, Sergey Levine, Adrian Li-Bell, Mohith Mothukuri, Suraj Nair, Karl Pertsch, Allen Z. Ren , et al. (11 additional authors not shown)

Abstract: In order for robots to be useful, they must perform practically relevant tasks in the real world, outside of the lab. While vision-language-action (VLA) models have demonstrated impressive results for end-to-end robot control, it remains an open question how far such models can generalize in the wild. We describe $π_{0.5}$, a new model based on $π_{0}$ that uses co-training on heterogeneous tasks… ▽ More In order for robots to be useful, they must perform practically relevant tasks in the real world, outside of the lab. While vision-language-action (VLA) models have demonstrated impressive results for end-to-end robot control, it remains an open question how far such models can generalize in the wild. We describe $π_{0.5}$, a new model based on $π_{0}$ that uses co-training on heterogeneous tasks to enable broad generalization. $π_{0.5}$\ uses data from multiple robots, high-level semantic prediction, web data, and other sources to enable broadly generalizable real-world robotic manipulation. Our system uses a combination of co-training and hybrid multi-modal examples that combine image observations, language commands, object detections, semantic subtask prediction, and low-level actions. Our experiments show that this kind of knowledge transfer is essential for effective generalization, and we demonstrate for the first time that an end-to-end learning-enabled robotic system can perform long-horizon and dexterous manipulation skills, such as cleaning a kitchen or bedroom, in entirely new homes. △ Less

Submitted 22 April, 2025; originally announced April 2025.

TAPIP3D: Tracking Any Point in Persistent 3D Geometry

Authors: Bowei Zhang, Lei Ke, Adam W. Harley, Katerina Fragkiadaki

Abstract: We introduce TAPIP3D, a novel approach for long-term 3D point tracking in monocular RGB and RGB-D videos. TAPIP3D represents videos as camera-stabilized spatio-temporal feature clouds, leveraging depth and camera motion information to lift 2D video features into a 3D world space where camera movement is effectively canceled out. Within this stabilized 3D representation, TAPIP3D iteratively refines… ▽ More We introduce TAPIP3D, a novel approach for long-term 3D point tracking in monocular RGB and RGB-D videos. TAPIP3D represents videos as camera-stabilized spatio-temporal feature clouds, leveraging depth and camera motion information to lift 2D video features into a 3D world space where camera movement is effectively canceled out. Within this stabilized 3D representation, TAPIP3D iteratively refines multi-frame motion estimates, enabling robust point tracking over long time horizons. To handle the irregular structure of 3D point distributions, we propose a 3D Neighborhood-to-Neighborhood (N2N) attention mechanism - a 3D-aware contextualization strategy that builds informative, spatially coherent feature neighborhoods to support precise trajectory estimation. Our 3D-centric formulation significantly improves performance over existing 3D point tracking methods and even surpasses state-of-the-art 2D pixel trackers in accuracy when reliable depth is available. The model supports inference in both camera-centric (unstabilized) and world-centric (stabilized) coordinates, with experiments showing that compensating for camera motion leads to substantial gains in tracking robustness. By replacing the conventional 2D square correlation windows used in prior 2D and 3D trackers with a spatially grounded 3D attention mechanism, TAPIP3D achieves strong and consistent results across multiple 3D point tracking benchmarks. Project Page: https://tapip3d.github.io △ Less

Submitted 14 November, 2025; v1 submitted 20 April, 2025; originally announced April 2025.

Comments: NeurIPS 2025. Long-term feed-forward 3D point tracking in persistent 3D point maps. Code:https://github.com/zbw001/TAPIP3D

ProReflow: Progressive Reflow with Decomposed Velocity

Authors: Lei Ke, Haohang Xu, Xuefei Ning, Yu Li, Jiajun Li, Haoling Li, Yuxuan Lin, Dongsheng Jiang, Yujiu Yang, Linfeng Zhang

Abstract: Diffusion models have achieved significant progress in both image and video generation while still suffering from huge computation costs. As an effective solution, flow matching aims to reflow the diffusion process of diffusion models into a straight line for a few-step and even one-step generation. However, in this paper, we suggest that the original training pipeline of flow matching is not opti… ▽ More Diffusion models have achieved significant progress in both image and video generation while still suffering from huge computation costs. As an effective solution, flow matching aims to reflow the diffusion process of diffusion models into a straight line for a few-step and even one-step generation. However, in this paper, we suggest that the original training pipeline of flow matching is not optimal and introduce two techniques to improve it. Firstly, we introduce progressive reflow, which progressively reflows the diffusion models in local timesteps until the whole diffusion progresses, reducing the difficulty of flow matching. Second, we introduce aligned v-prediction, which highlights the importance of direction matching in flow matching over magnitude matching. Experimental results on SDv1.5 and SDXL demonstrate the effectiveness of our method, for example, conducting on SDv1.5 achieves an FID of 10.70 on MSCOCO2014 validation set with only 4 sampling steps, close to our teacher model (32 DDIM steps, FID = 10.05). △ Less

Submitted 4 March, 2025; originally announced March 2025.

Comments: Our codes will be released at Github

Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Models

Authors: Lucy Xiaoyang Shi, Brian Ichter, Michael Equi, Liyiming Ke, Karl Pertsch, Quan Vuong, James Tanner, Anna Walling, Haohuan Wang, Niccolo Fusai, Adrian Li-Bell, Danny Driess, Lachy Groom, Sergey Levine, Chelsea Finn

Abstract: Generalist robots that can perform a range of different tasks in open-world settings must be able to not only reason about the steps needed to accomplish their goals, but also process complex instructions, prompts, and even feedback during task execution. Intricate instructions (e.g., "Could you make me a vegetarian sandwich?" or "I don't like that one") require not just the ability to physically… ▽ More Generalist robots that can perform a range of different tasks in open-world settings must be able to not only reason about the steps needed to accomplish their goals, but also process complex instructions, prompts, and even feedback during task execution. Intricate instructions (e.g., "Could you make me a vegetarian sandwich?" or "I don't like that one") require not just the ability to physically perform the individual steps, but the ability to situate complex commands and feedback in the physical world. In this work, we describe a system that uses vision-language models in a hierarchical structure, first reasoning over complex prompts and user feedback to deduce the most appropriate next step to fulfill the task, and then performing that step with low-level actions. In contrast to direct instruction following methods that can fulfill simple commands ("pick up the cup"), our system can reason through complex prompts and incorporate situated feedback during task execution ("that's not trash"). We evaluate our system across three robotic platforms, including single-arm, dual-arm, and dual-arm mobile robots, demonstrating its ability to handle tasks such as cleaning messy tables, making sandwiches, and grocery shopping. Videos are available at https://www.pi.website/research/hirobot △ Less

Submitted 15 July, 2025; v1 submitted 26 February, 2025; originally announced February 2025.

Comments: ICML 2025

QExplorer: Large Language Model Based Query Extraction for Toxic Content Exploration

Authors: Shaola Ren, Li Ke, Longtao Huang, Dehong Gao, Hui Xue

Abstract: Automatically extracting effective queries is challenging in information retrieval, especially in toxic content exploration, as such content is likely to be disguised. With the recent achievements in generative Large Language Model (LLM), we are able to leverage the capabilities of LLMs to extract effective queries for similar content exploration directly. This study proposes QExplorer, an approac… ▽ More Automatically extracting effective queries is challenging in information retrieval, especially in toxic content exploration, as such content is likely to be disguised. With the recent achievements in generative Large Language Model (LLM), we are able to leverage the capabilities of LLMs to extract effective queries for similar content exploration directly. This study proposes QExplorer, an approach of large language model based Query Extraction for toxic content Exploration. The QExplorer approach involves a 2-stage training process: instruction Supervised FineTuning (SFT) and preference alignment using Direct Preference Optimization (DPO), as well as the datasets construction with feedback of search system. To verify the effectiveness of QExplorer, a series of offline and online experiments are conducted on our real-world system. The offline empirical results demonstrate that the performance of our automatic query extraction outperforms that of several LLMs and humans. The online deployment shows a significant increase in the detection of toxic items. △ Less

Submitted 6 February, 2025; originally announced February 2025.

M$^3$PC: Test-time Model Predictive Control for Pretrained Masked Trajectory Model

Authors: Kehan Wen, Yutong Hu, Yao Mu, Lei Ke

Abstract: Recent work in Offline Reinforcement Learning (RL) has shown that a unified Transformer trained under a masked auto-encoding objective can effectively capture the relationships between different modalities (e.g., states, actions, rewards) within given trajectory datasets. However, this information has not been fully exploited during the inference phase, where the agent needs to generate an optimal… ▽ More Recent work in Offline Reinforcement Learning (RL) has shown that a unified Transformer trained under a masked auto-encoding objective can effectively capture the relationships between different modalities (e.g., states, actions, rewards) within given trajectory datasets. However, this information has not been fully exploited during the inference phase, where the agent needs to generate an optimal policy instead of just reconstructing masked components from unmasked ones. Given that a pretrained trajectory model can act as both a Policy Model and a World Model with appropriate mask patterns, we propose using Model Predictive Control (MPC) at test time to leverage the model's own predictive capability to guide its action selection. Empirical results on D4RL and RoboMimic show that our inference-phase MPC significantly improves the decision-making performance of a pretrained trajectory model without any additional parameter training. Furthermore, our framework can be adapted to Offline to Online (O2O) RL and Goal Reaching RL, resulting in more substantial performance gains when an additional online interaction budget is provided, and better generalization capabilities when different task targets are specified. Code is available: https://github.com/wkh923/m3pc. △ Less

Submitted 6 February, 2025; v1 submitted 7 December, 2024; originally announced December 2024.

Comments: ICLR 2025

Video Depth without Video Models

Authors: Bingxin Ke, Dominik Narnhofer, Shengyu Huang, Lei Ke, Torben Peters, Katerina Fragkiadaki, Anton Obukhov, Konrad Schindler

Abstract: Video depth estimation lifts monocular video clips to 3D by inferring dense depth at every frame. Recent advances in single-image depth estimation, brought about by the rise of large foundation models and the use of synthetic training data, have fueled a renewed interest in video depth. However, naively applying a single-image depth estimator to every frame of a video disregards temporal continuit… ▽ More Video depth estimation lifts monocular video clips to 3D by inferring dense depth at every frame. Recent advances in single-image depth estimation, brought about by the rise of large foundation models and the use of synthetic training data, have fueled a renewed interest in video depth. However, naively applying a single-image depth estimator to every frame of a video disregards temporal continuity, which not only leads to flickering but may also break when camera motion causes sudden changes in depth range. An obvious and principled solution would be to build on top of video foundation models, but these come with their own limitations; including expensive training and inference, imperfect 3D consistency, and stitching routines for the fixed-length (short) outputs. We take a step back and demonstrate how to turn a single-image latent diffusion model (LDM) into a state-of-the-art video depth estimator. Our model, which we call RollingDepth, has two main ingredients: (i) a multi-frame depth estimator that is derived from a single-image LDM and maps very short video snippets (typically frame triplets) to depth snippets. (ii) a robust, optimization-based registration algorithm that optimally assembles depth snippets sampled at various different frame rates back into a consistent video. RollingDepth is able to efficiently handle long videos with hundreds of frames and delivers more accurate depth videos than both dedicated video depth estimators and high-performing single-frame models. Project page: rollingdepth.github.io. △ Less

Submitted 17 March, 2025; v1 submitted 28 November, 2024; originally announced November 2024.

Comments: Project page: rollingdepth.github.io

$π_0$: A Vision-Language-Action Flow Model for General Robot Control

Authors: Kevin Black, Noah Brown, Danny Driess, Adnan Esmail, Michael Equi, Chelsea Finn, Niccolo Fusai, Lachy Groom, Karol Hausman, Brian Ichter, Szymon Jakubczak, Tim Jones, Liyiming Ke, Sergey Levine, Adrian Li-Bell, Mohith Mothukuri, Suraj Nair, Karl Pertsch, Lucy Xiaoyang Shi, James Tanner, Quan Vuong, Anna Walling, Haohuan Wang, Ury Zhilinsky

Abstract: Robot learning holds tremendous promise to unlock the full potential of flexible, general, and dexterous robot systems, as well as to address some of the deepest questions in artificial intelligence. However, bringing robot learning to the level of generality required for effective real-world systems faces major obstacles in terms of data, generalization, and robustness. In this paper, we discuss… ▽ More Robot learning holds tremendous promise to unlock the full potential of flexible, general, and dexterous robot systems, as well as to address some of the deepest questions in artificial intelligence. However, bringing robot learning to the level of generality required for effective real-world systems faces major obstacles in terms of data, generalization, and robustness. In this paper, we discuss how generalist robot policies (i.e., robot foundation models) can address these challenges, and how we can design effective generalist robot policies for complex and highly dexterous tasks. We propose a novel flow matching architecture built on top of a pre-trained vision-language model (VLM) to inherit Internet-scale semantic knowledge. We then discuss how this model can be trained on a large and diverse dataset from multiple dexterous robot platforms, including single-arm robots, dual-arm robots, and mobile manipulators. We evaluate our model in terms of its ability to perform tasks in zero shot after pre-training, follow language instructions from people and from a high-level VLM policy, and its ability to acquire new skills via fine-tuning. Our results cover a wide variety of tasks, such as laundry folding, table cleaning, and assembling boxes. △ Less

Submitted 8 January, 2026; v1 submitted 31 October, 2024; originally announced October 2024.

Comments: See project website for videos: https://physicalintelligence.company/blog/pi0 Published in RSS 2025

Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RL

Authors: Andrew Wagenmaker, Kevin Huang, Liyiming Ke, Byron Boots, Kevin Jamieson, Abhishek Gupta

Abstract: In order to mitigate the sample complexity of real-world reinforcement learning, common practice is to first train a policy in a simulator where samples are cheap, and then deploy this policy in the real world, with the hope that it generalizes effectively. Such \emph{direct sim2real} transfer is not guaranteed to succeed, however, and in cases where it fails, it is unclear how to best utilize the… ▽ More In order to mitigate the sample complexity of real-world reinforcement learning, common practice is to first train a policy in a simulator where samples are cheap, and then deploy this policy in the real world, with the hope that it generalizes effectively. Such \emph{direct sim2real} transfer is not guaranteed to succeed, however, and in cases where it fails, it is unclear how to best utilize the simulator. In this work, we show that in many regimes, while direct sim2real transfer may fail, we can utilize the simulator to learn a set of \emph{exploratory} policies which enable efficient exploration in the real world. In particular, in the setting of low-rank MDPs, we show that coupling these exploratory policies with simple, practical approaches -- least-squares regression oracles and naive randomized exploration -- yields a polynomial sample complexity in the real world, an exponential improvement over direct sim2real transfer, or learning without access to a simulator. To the best of our knowledge, this is the first evidence that simulation transfer yields a provable gain in reinforcement learning in settings where direct sim2real transfer fails. We validate our theoretical results on several realistic robotic simulators and a real-world robotic sim2real task, demonstrating that transferring exploratory policies can yield substantial gains in practice as well. △ Less

Submitted 26 October, 2024; originally announced October 2024.

Comments: NeurIPS 2024

SLAck: Semantic, Location, and Appearance Aware Open-Vocabulary Tracking

Authors: Siyuan Li, Lei Ke, Yung-Hsu Yang, Luigi Piccinelli, Mattia Segù, Martin Danelljan, Luc Van Gool

Abstract: Open-vocabulary Multiple Object Tracking (MOT) aims to generalize trackers to novel categories not in the training set. Currently, the best-performing methods are mainly based on pure appearance matching. Due to the complexity of motion patterns in the large-vocabulary scenarios and unstable classification of the novel objects, the motion and semantics cues are either ignored or applied based on h… ▽ More Open-vocabulary Multiple Object Tracking (MOT) aims to generalize trackers to novel categories not in the training set. Currently, the best-performing methods are mainly based on pure appearance matching. Due to the complexity of motion patterns in the large-vocabulary scenarios and unstable classification of the novel objects, the motion and semantics cues are either ignored or applied based on heuristics in the final matching steps by existing methods. In this paper, we present a unified framework SLAck that jointly considers semantics, location, and appearance priors in the early steps of association and learns how to integrate all valuable information through a lightweight spatial and temporal object graph. Our method eliminates complex post-processing heuristics for fusing different cues and boosts the association performance significantly for large-scale open-vocabulary tracking. Without bells and whistles, we outperform previous state-of-the-art methods for novel classes tracking on the open-vocabulary MOT and TAO TETA benchmarks. Our code is available at \href{https://github.com/siyuanliii/SLAck}{github.com/siyuanliii/SLAck}. △ Less

Submitted 17 September, 2024; originally announced September 2024.

Comments: ECCV2024

Lightweight single-image super-resolution network based on dual paths

Authors: Li Ke, Liu Yukai

Abstract: The single image super-resolution(SISR) algorithms under deep learning currently have two main models, one based on convolutional neural networks and the other based on Transformer. The former uses the stacking of convolutional layers with different convolutional kernel sizes to design the model, which enables the model to better extract the local features of the image; the latter uses the self-at… ▽ More The single image super-resolution(SISR) algorithms under deep learning currently have two main models, one based on convolutional neural networks and the other based on Transformer. The former uses the stacking of convolutional layers with different convolutional kernel sizes to design the model, which enables the model to better extract the local features of the image; the latter uses the self-attention mechanism to design the model, which allows the model to establish long-distance dependencies between image pixel points through the self-attention mechanism and then better extract the global features of the image. However, both of the above methods face their problems. Based on this, this paper proposes a new lightweight multi-scale feature fusion network model based on two-way complementary convolutional and Transformer, which integrates the respective features of Transformer and convolutional neural networks through a two-branch network architecture, to realize the mutual fusion of global and local information. Meanwhile, considering the partial loss of information caused by the low-pixel images trained by the deep neural network, this paper designs a modular connection method of multi-stage feature supplementation to fuse the feature maps extracted from the shallow stage of the model with those extracted from the deep stage of the model, to minimize the loss of the information in the feature images that is beneficial to the image restoration as much as possible, to facilitate the obtaining of a higher-quality restored image. The practical results finally show that the model proposed in this paper is optimal in image recovery performance when compared with other lightweight models with the same amount of parameters. △ Less

Submitted 24 September, 2024; v1 submitted 10 September, 2024; originally announced September 2024.

Matching Anything by Segmenting Anything

Authors: Siyuan Li, Lei Ke, Martin Danelljan, Luigi Piccinelli, Mattia Segu, Luc Van Gool, Fisher Yu

Abstract: The robust association of the same objects across video frames in complex scenes is crucial for many applications, especially Multiple Object Tracking (MOT). Current methods predominantly rely on labeled domain-specific video datasets, which limits the cross-domain generalization of learned similarity embeddings. We propose MASA, a novel method for robust instance association learning, capable of… ▽ More The robust association of the same objects across video frames in complex scenes is crucial for many applications, especially Multiple Object Tracking (MOT). Current methods predominantly rely on labeled domain-specific video datasets, which limits the cross-domain generalization of learned similarity embeddings. We propose MASA, a novel method for robust instance association learning, capable of matching any objects within videos across diverse domains without tracking labels. Leveraging the rich object segmentation from the Segment Anything Model (SAM), MASA learns instance-level correspondence through exhaustive data transformations. We treat the SAM outputs as dense object region proposals and learn to match those regions from a vast image collection. We further design a universal MASA adapter which can work in tandem with foundational segmentation or detection models and enable them to track any detected objects. Those combinations present strong zero-shot tracking ability in complex domains. Extensive tests on multiple challenging MOT and MOTS benchmarks indicate that the proposed method, using only unlabeled static images, achieves even better performance than state-of-the-art methods trained with fully annotated in-domain video sequences, in zero-shot association. Project Page: https://matchinganything.github.io/ △ Less

Submitted 6 June, 2024; originally announced June 2024.

Comments: CVPR 2024 Highlight. code at: https://github.com/siyuanliii/masa

Data Efficient Behavior Cloning for Fine Manipulation via Continuity-based Corrective Labels

Authors: Abhay Deshpande, Liyiming Ke, Quinn Pfeifer, Abhishek Gupta, Siddhartha S. Srinivasa

Abstract: We consider imitation learning with access only to expert demonstrations, whose real-world application is often limited by covariate shift due to compounding errors during execution. We investigate the effectiveness of the Continuity-based Corrective Labels for Imitation Learning (CCIL) framework in mitigating this issue for real-world fine manipulation tasks. CCIL generates corrective labels by l… ▽ More We consider imitation learning with access only to expert demonstrations, whose real-world application is often limited by covariate shift due to compounding errors during execution. We investigate the effectiveness of the Continuity-based Corrective Labels for Imitation Learning (CCIL) framework in mitigating this issue for real-world fine manipulation tasks. CCIL generates corrective labels by learning a locally continuous dynamics model from demonstrations to guide the agent back toward expert states. Through extensive experiments on peg insertion and fine grasping, we provide the first empirical validation that CCIL can significantly improve imitation learning performance despite discontinuities present in contact-rich manipulation. We find that: (1) real-world manipulation exhibits sufficient local smoothness to apply CCIL, (2) generated corrective labels are most beneficial in low-data regimes, and (3) label filtering based on estimated dynamics model error enables performance gains. To effectively apply CCIL to robotic domains, we offer a practical instantiation of the framework and insights into design choices and hyperparameter selection. Our work demonstrates CCIL's practicality for alleviating compounding errors in imitation learning on physical robots. △ Less

Submitted 21 October, 2024; v1 submitted 29 May, 2024; originally announced May 2024.

Comments: Presented at IROS 2024

DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos

Authors: Wen-Hsuan Chu, Lei Ke, Katerina Fragkiadaki

Abstract: View-predictive generative models provide strong priors for lifting object-centric images and videos into 3D and 4D through rendering and score distillation objectives. A question then remains: what about lifting complete multi-object dynamic scenes? There are two challenges in this direction: First, rendering error gradients are often insufficient to recover fast object motion, and second, view p… ▽ More View-predictive generative models provide strong priors for lifting object-centric images and videos into 3D and 4D through rendering and score distillation objectives. A question then remains: what about lifting complete multi-object dynamic scenes? There are two challenges in this direction: First, rendering error gradients are often insufficient to recover fast object motion, and second, view predictive generative models work much better for objects than whole scenes, so, score distillation objectives cannot currently be applied at the scene level directly. We present DreamScene4D, the first approach to generate 3D dynamic scenes of multiple objects from monocular videos via 360-degree novel view synthesis. Our key insight is a "decompose-recompose" approach that factorizes the video scene into the background and object tracks, while also factorizing object motion into 3 components: object-centric deformation, object-to-world-frame transformation, and camera motion. Such decomposition permits rendering error gradients and object view-predictive models to recover object 3D completions and deformations while bounding box tracks guide the large object movements in the scene. We show extensive results on challenging DAVIS, Kubric, and self-captured videos with quantitative comparisons and a user preference study. Besides 4D scene generation, DreamScene4D obtains accurate 2D persistent point track by projecting the inferred 3D trajectories to 2D. We will release our code and hope our work will stimulate more research on fine-grained 4D understanding from videos. △ Less

Submitted 23 May, 2024; v1 submitted 3 May, 2024; originally announced May 2024.

Comments: Project page: https://dreamscene4d.github.io/

DeepFake-O-Meter v2.0: An Open Platform for DeepFake Detection

Authors: Yan Ju, Chengzhe Sun, Shan Jia, Shuwei Hou, Zhaofeng Si, Soumyya Kanti Datta, Lipeng Ke, Riky Zhou, Anita Nikolich, Siwei Lyu

Abstract: Deepfakes, as AI-generated media, have increasingly threatened media integrity and personal privacy with realistic yet fake digital content. In this work, we introduce an open-source and user-friendly online platform, DeepFake-O-Meter v2.0, that integrates state-of-the-art methods for detecting Deepfake images, videos, and audio. Built upon DeepFake-O-Meter v1.0, we have made significant upgrades… ▽ More Deepfakes, as AI-generated media, have increasingly threatened media integrity and personal privacy with realistic yet fake digital content. In this work, we introduce an open-source and user-friendly online platform, DeepFake-O-Meter v2.0, that integrates state-of-the-art methods for detecting Deepfake images, videos, and audio. Built upon DeepFake-O-Meter v1.0, we have made significant upgrades and improvements in platform architecture design, including user interaction, detector integration, job balancing, and security management. The platform aims to offer everyday users a convenient service for analyzing DeepFake media using multiple state-of-the-art detection algorithms. It ensures secure and private delivery of the analysis results. Furthermore, it serves as an evaluation and benchmarking platform for researchers in digital media forensics to compare the performance of multiple algorithms on the same input. We have also conducted detailed usage analysis based on the collected data to gain deeper insights into our platform's statistics. This involves analyzing two-month trends in user activity and evaluating the processing efficiency of each detector. △ Less

Submitted 27 June, 2024; v1 submitted 19 April, 2024; originally announced April 2024.

LLM-Seg: Bridging Image Segmentation and Large Language Model Reasoning

Authors: Junchi Wang, Lei Ke

Abstract: Understanding human instructions to identify the target objects is vital for perception systems. In recent years, the advancements of Large Language Models (LLMs) have introduced new possibilities for image segmentation. In this work, we delve into reasoning segmentation, a novel task that enables segmentation system to reason and interpret implicit user intention via large language model reasonin… ▽ More Understanding human instructions to identify the target objects is vital for perception systems. In recent years, the advancements of Large Language Models (LLMs) have introduced new possibilities for image segmentation. In this work, we delve into reasoning segmentation, a novel task that enables segmentation system to reason and interpret implicit user intention via large language model reasoning and then segment the corresponding target. Our work on reasoning segmentation contributes on both the methodological design and dataset labeling. For the model, we propose a new framework named LLM-Seg. LLM-Seg effectively connects the current foundational Segmentation Anything Model and the LLM by mask proposals selection. For the dataset, we propose an automatic data generation pipeline and construct a new reasoning segmentation dataset named LLM-Seg40K. Experiments demonstrate that our LLM-Seg exhibits competitive performance compared with existing methods. Furthermore, our proposed pipeline can efficiently produce high-quality reasoning segmentation datasets. The LLM-Seg40K dataset, developed through this pipeline, serves as a new benchmark for training and evaluating various reasoning segmentation approaches. Our code, models and dataset are at https://github.com/wangjunchi/LLMSeg. △ Less

Submitted 12 April, 2024; originally announced April 2024.

Comments: Github: https://github.com/wangjunchi/LLMSeg

Exploring the Frontiers of LLMs in Psychological Applications: A Comprehensive Review

Authors: Luoma Ke, Song Tong, Peng Cheng, Kaiping Peng

Abstract: This paper explores the frontiers of large language models (LLMs) in psychology applications. Psychology has undergone several theoretical changes, and the current use of Artificial Intelligence (AI) and Machine Learning, particularly LLMs, promises to open up new research directions. We provide a detailed exploration of how LLMs like ChatGPT are transforming psychological research. It discusses t… ▽ More This paper explores the frontiers of large language models (LLMs) in psychology applications. Psychology has undergone several theoretical changes, and the current use of Artificial Intelligence (AI) and Machine Learning, particularly LLMs, promises to open up new research directions. We provide a detailed exploration of how LLMs like ChatGPT are transforming psychological research. It discusses the impact of LLMs across various branches of psychology, including cognitive and behavioral, clinical and counseling, educational and developmental, and social and cultural psychology, highlighting their potential to simulate aspects of human cognition and behavior. The paper delves into the capabilities of these models to emulate human-like text generation, offering innovative tools for literature review, hypothesis generation, experimental design, experimental subjects, data analysis, academic writing, and peer review in psychology. While LLMs are essential in advancing research methodologies in psychology, the paper also cautions about their technical and ethical challenges. There are issues like data privacy, the ethical implications of using LLMs in psychological research, and the need for a deeper understanding of these models' limitations. Researchers should responsibly use LLMs in psychological studies, adhering to ethical standards and considering the potential consequences of deploying these technologies in sensitive areas. Overall, the article provides a comprehensive overview of the current state of LLMs in psychology, exploring potential benefits and challenges. It serves as a call to action for researchers to leverage LLMs' advantages responsibly while addressing associated risks. △ Less

Submitted 20 April, 2025; v1 submitted 2 January, 2024; originally announced January 2024.

Journal ref: Artif Intell Rev 58, 305 (2025)