Robotics
LoopWAM: Closed-Loop Generalist Policy Improvement from Deployment Rollouts
Wenxuan Guo, Yingping Liang, Zhaoguo Wang et al. (+11 more)
Scaling expert demonstrations alone does not enable generalist
robot policies to improve from deployment. Real-world rollouts contain successes, suboptimal behavior, and failures: imitating every recorded action can reinforce poor behavior, while filtering out failures discards evidence of physical interactions and their consequences. We introduce LoopWAM, a closed-loop world-action model that learns directly from this full quality spectrum, using rollouts from both itself and other deployed policies. Source-dependent noise sampling unifies behavior learning and action-conditioned world modeling, while quality steering and quality-weighted supervision retain full
video supervision across qualities and regulate action imitation.
Video and action
tokens interact throughout parallel denoising, allowing learned consequences to inform action generation directly. On RoboChallenge Table30-V2, three deployment-and-training rounds raise success from 23.67% to 43.33%, a 19.7-percentage-point gain, with a final score of 56.80. LoopWAM also achieves 94.5% average success on RoboTwin 2.0 and 49.5% overall success on RoboCasa365 without additional embodied pretraining, obtaining the best overall results among the compared methods across all three
benchmarks. On challenging shirt folding task, two rounds of deployment-driven improvement after single-task post-training raise success from 13.20% to 55.56%. These results demonstrate closed-loop improvement from mixed-quality experience under both multi-task learning and single-task post-training. Project page: https://loop-wam.github.io/
Read the full abstract ▾
All authors Wenxuan Guo, Yingping Liang, Zhaoguo Wang, Ziyuan Li, Angyuan Ma, Zhenyu Wu, Chengkun Wang, Bingyao Yu, Ze Chen, Borui Zhang, Xiuwei Xu, Meng Zhang, Erjin Zhou, Jiwen Lu
Robotics
EgoExplorer: A Vision-Motion-Touch Observatory for Human Loco-Manipulation In Situ
Yunsong Zhou, Xuekun Jiang, Haiqi Shen et al. (+11 more)
Learning humanoid loco-manipulation from human demonstrations rests on observing how locomotion, posture, and object interaction evolve together as tasks unfold. Scaling collection across diverse environments, in turn, favors lightweight, portable capture systems. Yet, existing
datasets provide only partial views of this coordination. Thus, we introduce EgoExplorer, a 100-hour
vision-motion-touch observatory of human loco-manipulation built with a wearable system. With an emphasis on professional activities, its continuous recordings align egocentric
video with reconstructed whole-body motion, fine-grained finger articulation, and tactile observations, accompanied by step-level descriptions. To achieve this coverage with sparse body sensing, we develop the Calibrate-Complete-Constrain pipeline. Concretely, reusable calibration fixes participant geometry and sensor attachments before motion inference to disentangle mounting offsets from articulation. A temporal prior then completes unobserved joint motion, while layered constraints promote measurement agreement, temporal continuity, and
geometric consistency, properties that motion plausibility alone does not guarantee. Against tracker-fitted references, the method reduces body-point error by 71.9% relative to the strongest baseline; matched evaluations also show gains in hand stability and contact estimation. Preliminary studies explore
multimodal generation and conditioning alongside humanoid retargeting with whole-body control in simulation.
Read the full abstract ▾
All authors Yunsong Zhou, Xuekun Jiang, Haiqi Shen, Hangxu Liu, Chaojian Shi, Yujie Liu, Jingyuan Li, Haoran Yang, Jiafei Cao, Dongzhan Zhou, Dong Wang, Yao Mu, Chunhua Shen, Weinan Zhang
Computer Vision
Cepheid: Decoupling Scale from Structure for Cross-Family Motion Completion
Chih-Hai Su, Tsung-Wei Ke and Yu-Lun Liu
Sparse-to-dense motion completion recovers dense mesh motion from sparse vertex displacements. Residual priors trained on one geometry family frequently fail to beat parameter-free harmonic extension off-family. Moreover, cross-family training meets a scaling barrier: residual amplitude varies by more than an order of magnitude across geometry families and collapses as observations become denser. Since this scale depends on unknown target motion, it cannot be measured directly at test time. We decouple residual structure from physical scale by learning a dimensionless prior, estimating amplitude from observables and a lightweight correction fitted only on training sources. Our unified model surpasses harmonic extension across all evaluated families, including unseen cloth and legged bodies, without skeletons, registration, or cross-mesh correspondence. The same prior applies without retraining to point-tracked animal
video and a
robot grasping a soft body. Project page: https://su-terry.github.io/cepheid-website/
Read the full abstract ▾
Computer Vision
MiniDog: Dog-Breed Text-to-image Flow Matching from Pretraining to Fine-Tuning on 4 Consumer GPUs
Reyhaneh Esmailizadeh, Xingjian Leng, Zhanhao Liang et al. (+1 more)
We generally perceive that training text-to-image
diffusion models requires heavy compute: it is true if we aim at a comprehensive frontier model. This understanding prevents people from training their own models when getting started in the field. We develop MiniDog, a framework that enables pretraining
diffusion transformers in 55 minutes and fine-tuning in another 15 minutes on four 3090 GPUs. For data, we use 26k dog images from ImageNet and caption them for pretraining and use 2k images generated by FLUX.1-schnell for fine-tuning. We precompute the image and text features and cache them for efficiency. For architecture, we use E2E-INVAE for its semantic latent space, a small
transformer with 22M parameters, a small Qwen model for text encoding, and in-context conditioning. For training, we use iREPA and an EUPE perception encoder for acceleration. For evaluation, our repository supports FID, HPSv2 score, PickScore, and various VAE reconstruction metrics. The project is open-sourced at https://github.com/Reyhaneesmailizadeh/MiniDog. We do not claim technical novelty.
Read the full abstract ▾
All authors Reyhaneh Esmailizadeh, Xingjian Leng, Zhanhao Liang, Liang Zheng
Robotics
What Matters in Quality-Aware VLA Pretraining: A Benchmark and Empirical Study
Mingxuan Yan, Litian Gong, Dihong Huang et al. (+19 more)
How should demonstration quality be used during
vision-
language-action (VLA) pretraining to improve performance after target-task fine-tuning? We compare weighting, filtering, and conditioning across reward definitions and label granularities using 5,000 naturally suboptimal human demonstrations and 24 target tasks. Within each VLA, we match demonstrations and training budgets. Additional comparisons examine pretraining data size and the roles of quality tags during fine-tuning and inference. Across three VLAs, we find that approach-aware episode conditioning improves mean success over plain behavioral cloning; conditioning and filtering favor episode and chunk labels, respectively, on average, with model-dependent reversals; and constant-tag fine-tuning improves mean success after conditioned pretraining with either tagged or untagged inference. We introduce AXIS-Bench to support these controlled comparisons. Built on crowdsourced simulation demonstrations, it provides recorded object and contact states for recomputing quality labels on shared trajectories. Replayable trajectories support workspace-aligned rendering and user-defined real-world target tasks. In our real-world experiment, simulation pretraining raises success from 9.6% to 31.7%. Project page: https://axis-bench.github.io/.
Read the full abstract ▾
All authors Mingxuan Yan, Litian Gong, Dihong Huang, Zhixu Li, Tianyu Zhang, Wenqian Zhang, Hefeifei Jiang, Peihao Li, Jian Zhang, Mengfei Zhao, Yikai Tang, Hai Zhai, Zehao Wang, Ruijian Liang, Yanjia Huang, Lin Shao, Changliu Liu, Kaiyu Hang, Zhiwen Fan, Masayoshi Tomizuka, Jianfei Yang, Jiachen Li
Computation and Language
Tev: Scaling Long-Horizon Agentic Environments with Dense Progress Rewards
Wenbo Hu, Shraman Pramanick, Krishna Kumar Singh et al. (+3 more)
Long-horizon
agents have drawn growing
attention for their ability to work autonomously – from hours to days – on economically valuable tasks, a capability essential to automated discovery and recursive self-improvement (RSI). Yet open-source models still struggle on long-horizon tasks, largely for lack of both training data and a working recipe, and scaling both is hard: long, complex tasks are difficult to curate and verify, and their rewards are sparse. We address both. First, we introduce Tev-Gym, the first long-horizon
agent training
dataset with verifiable, dense, progressive rewards – 1,170 verified task environments across 7 domains. It is built on a latent-world-first approach that first constructs a latent world: a complete and correct hidden specification of the task domain, workflow, and expected state after each step. Each task is then progressively rendered from this specification into an
agent-facing environment, enabling controllable complexity and a natural progress metric. Second, we turn this metric into a training recipe: via progress-potential reward shaping (PPRS), we convert progress into a dense per-step reward that improves training efficiency and makes otherwise-intractable tasks trainable. Training with this recipe yields Tev-27B, which achieves substantial gains on the
Agents' Last Exam computing and math sciences domains (ALE-CM), matching GPT-6 Astra and Claude Opus 5 at Pass@5. Despite training only on ALE-related data, it generalizes to the Terminal-Bench (TB) 3.0 and 4.0 subsets, surpassing GLM 5.2 and Gemini 3.7 Flash, and reaches Claude Opus 4.8-level performance on middle-horizon tasks such as TB 2.1.
Read the full abstract ▾
All authors Wenbo Hu, Shraman Pramanick, Krishna Kumar Singh, Nanyun Peng, Kai-Wei Chang, Yong Jae Lee
Robotics
EmbodiedEvo: Self-Evolving Coding Agent For Physical Intelligence
Wenyi Li, Yizhe Chi, Youjie Zheng et al. (+8 more)
Coding
agents can construct executable programs and revise them through feedback, offering a foundation for embodied control without target-task fine-tuning. Through a programmatic
robot interface, the
agent observes the scene, executes control programs, and adapts them to the resulting physical state, serving as the closed-loop policy. However, this within-episode adaptation does not automatically preserve experience across scenes. Our trajectory analysis shows that
agents spend interaction and inference budgets establishing effective operations and identifying their preconditions, while fresh
agents cannot reuse these discoveries. This motivates EmbodiedEvo, a self-evolving coding
agent that distills physical feedback into reusable code Skills and diagnostic Lessons. Experience is acquired on one Playground scene per task, then frozen for independent
agents in unseen scenes, without updating model weights. On RoboDojo-Sim, EmbodiedEvo achieves an average score of 44.48 and a success rate of 37.82%, surpassing all officially verified results. Paired tests show the largest gains on
memory-dependent tasks and successful reuse of coordinated procedures, while fine contact control remains difficult. Experience from stronger models also improves weaker executors: Astra's experience raises Sol and Luna's success rates by 8.86 and 5.50 percentage points over no experience. Compared with raw interaction history, Skills and Lessons achieve comparable task performance at 53.0% lower execution cost.
Read the full abstract ▾
All authors Wenyi Li, Yizhe Chi, Youjie Zheng, Chunyu Liu, Xiaoqiu Wang, Mingju Gao, Zheng Jiang, Deyao Hong, Calvin Xiao, Kaisen Yang, Qinhuai Na
Robotics
AutoAgent0: An Agentic Runtime for Safe Closed-Loop Driving
Jiageng Liu, Seth Z. Zhao, Zewei Zhou et al. (+9 more)
Safe autonomous driving requires more than accurate planning at a single frame: it demands reliable closed-loop execution in dynamic environments. Although end-to-end driving policies have advanced rapidly, the accumulated closed-loop errors, especially in unseen scenarios, can push vehicles into states from which the same policy struggles to recover. We address the challenge by treating closed-loop driving safety as a test-time execution problem. We introduce AutoAgent0, an agentic runtime and harness framework that augments existing driving experts with complementary detection skills, rule-based action verification, and feedback-driven recovery. To address inaccurate scene perception, an independent detection module constructs scene context using complementary perception skills, and a rule-based verifier checks proposed trajectories against this context before execution. When the nominal trajectories are unreliable, the orchestrator of the runtime activates Recovery Planning, where an agentic loop constructs alternative action proposals from action primitives and iteratively refines them using verification feedback. This design combines independent scene assessment with feasibility checks and online recovery, addressing both perception errors and the limited recovery capabilities of individual experts. Evaluations on Fail2Drive and NavSafe-$\infty$ demonstrate improved closed-loop robustness over single-expert execution in long-tail and safety-critical scenarios. These results demonstrate that runtime supervision can improve closed-loop robustness across multiple driving experts without retraining the underlying policies.
Read the full abstract ▾
All authors Jiageng Liu, Seth Z. Zhao, Zewei Zhou, Alejandro Huerta, Aidan Bayer-Calvert, Yuxin Bao, Haotian Lin, Robert Spataru, Zijun Cui, Yining Hong, Bolei Zhou, Jiaqi Ma
Computer Vision
PLAYGROUND: Progressive Layout Generation with Render-Grounded Planning
Jaeho Lee, Junhwan Heo, Junghyun Park et al. (+5 more)
Generating editable graphic designs requires arranging visual and textual elements into a coherent composition while preserving their content and editability. Although recent MLLM-based approaches employ iterative generation and visual refinement to reflect the real-world design workflows, their high-level plans are predetermined prior to execution, limiting their adaptability as the design evolves. To address this limitation, we propose PlayGround, a progressive layout generation framework that dynamically adapts to the current rendered canvas. PlayGround establishes a progressive design loop comprising a Progressive Planner, a Layout Generator, and a Visual Verifier, guided by a Structure-Aware Retriever. Given an initial set of unordered elements, the Structure-Aware Retriever initially infers a coarse layout structure to retrieve structurally similar reference designs. Subsequently, at each turn, the Progressive Planner examines the current rendered canvas alongside the remaining elements, forms the next functional group, and plans its composition. The Layout Generator then predicts editable layout attributes, while the Visual Verifier evaluates rendered candidates and provides feedback when refinement is necessary. To train the Progressive Planner with step-wise supervision, we construct a two-stage data generation pipeline that extracts functional groups and turn-level planning trajectories from completed designs. Experiments on Crello and LICA demonstrate the effectiveness of PlayGround over existing methods. Our code and weights will be publicly released.
Read the full abstract ▾
All authors Jaeho Lee, Junhwan Heo, Junghyun Park, WonJun Moon, Eunju Yang, Seungho Jang, Seongchan Kim, Seungryong Kim
Machine Learning · Cross-listed from hep-lat
Data Free Training of Diffusion Models for Lattice Field Theories
Dennis Grinwald, Ankur Singha, Khaled Kahouli et al. (+2 more)
Sampling
equilibrium field configurations remains a major computational bottleneck in
lattice field theory, motivating the development of generative samplers that can produce independent configurations.
Diffusion models are promising for this purpose, but their standard denoising score matching objective requires samples from the target distribution, seemingly reintroducing the original sampling problem. Here, we show that
diffusion models can instead be trained from their own generated samples using the target score identity, provided access to the unnormalized probability density. Importance-weighted formulations of this identity yield a consistent target throughout training, while unweighted variants define a self-consistent fixed-point training scheme. We
benchmark the different approaches in two-dimensional \(\phi^4\) theory and identify effective choices that enable efficient training and sampling across the symmetric, critical, and broken phases. Ultimately, our data-free training approach achieves comparable performance to training on HMC reference data.
Read the full abstract ▾
All authors Dennis Grinwald, Ankur Singha, Khaled Kahouli, Karl Jansen, Shinichi Nakajima
Computation and Language
DoubtLess: Training-Free Contrastive Decoding for Efficient Reasoning
Minghao Luo and Liang Chen
Reasoning models achieve strong performance through long chains of thought (CoT), but often spend more
tokens than needed to solve a problem. Existing ways to shorten the CoT require additional training for each model, add a fixed steering vector to the model's hidden states, or use decoding heuristics such as stopping early or banning words like "wait", which can reduce accuracy. We propose DoubtLess, a training-free decoding method in which a much smaller
reasoning model steers the large one towards brevity. The small model reads the large model's CoT so far twice, once prompted to be brief (the brief thinker) and once prompted to be verbose (the verbose thinker), and the difference between its two logit vectors, scaled by a strength, is added to the large model's logits at every step of the CoT. On seven
benchmarks of competition mathematics, graduate-level science and competitive programming, DoubtLess shortens the CoT of Qwen3-32B by 31% with unchanged accuracy, outperforming five inference-time baselines. We also show that DoubtLess reduces thinking
tokens per turn by 20% in a self-debugging coding
agent with unchanged task performance. It also generalizes to two other model families with unchanged accuracy. When combined with training-based compression, it further shortens the CoT of a model already trained for brevity. Ablations and behavioral analysis show that DoubtLess reduces repeated checking, with most
token savings coming after the correct answer first appears in the CoT. Our code is available at https://github.com/leoluolol/DoubtLess.
Read the full abstract ▾
Computation and Language
Jiaru Zou, Yunzhe Qi, Sirui Chen et al. (+5 more)
How can we build an
agent that thinks beyond human
language, yet still acts through it in the external environment? Modern LLM
agents still reason and interact through text, while latent
reasoning offers an efficient internal medium but lacks native tool access and
reasoning transparency. We bridge these two directions with Hybrid
Reasoning Agents (HybridAgents), which dynamically navigate between latent
reasoning and text-based interaction throughout a unified generation process. Architecturally, a lightweight HybridLink enables seamless transitions between text and latent modes, while the
agent's continuous working
memory preserves lossless hybrid context across multiple turns. These designs preserve tool-integrated agentic capabilities while making latent thoughts directly inspectable. Building on this architecture, we further develop dedicated post-training
algorithms for hybrid
reasoning: HybridSFT stabilizes tool-integrated hybrid generation by teaching the backbone to coordinate with HybridLink, then HybridRL scales
reasoning by learning when to think in latent space and when to act through text. We evaluate HybridAgent at 3 model scales across 11
benchmarks covering mathematics, science, medicine, search, and agentic
reasoning. Compared with frontier LLM
Agents and agentic frameworks spanning both text-based and latent methods, HybridAgent consistently improves performance by 10.4%, while delivering 35.5%-54.7%
token reduction, 1.8x-2.6x faster inference, and 2.7x-3.7x cost savings. Code and data are available at https://github.com/togethercomputer/HybridAgent.
Read the full abstract ▾
All authors Jiaru Zou, Yunzhe Qi, Sirui Chen, Federico Bianchi, Shang Zhu, Pan Lu, Jingrui He, James Zou
Artificial Intelligence
AesCode: Aesthetic Code Generation with Decoupled Cross-Modal Rewards
Xin Gao, Yifan Yang, Xin Li et al. (+13 more)
Generating information-rich visual artifacts such as slides, posters, and dashboards as code is appealing because the outputs are structured, editable, and verifiable. Yet code models cannot see how their choices of layout and color come together on the canvas, often limiting spatial planning and aesthetic quality. Image generators excel at visual design but can misrender requested content, making their outputs unreliable targets for direct reproduction. We therefore introduce AesCode, which generates code grounded in the content
prompt while using an image generated from the same
prompt as an aesthetic guidance. To do so, AesCode represents the target as a design graph that describes the whole canvas and makes each property attributable. From this graph, we derive complementary cross-modal rewards: deterministic verifiers score properties parsable from code and rendering, while a VLM judge assesses the non-parsable ones with a sample-specific Visual Graph Rubric (VGR) tied to graph elements and relations. We optimize these decoupled rewards through reinforcement learning with per-channel normalization to jointly improve spatial planning, aesthetic quality, and verifiable correctness. To evaluate this setting, we build a
benchmark that scores verifiable correctness and visual quality separately, with visual scores highly consistent with human judgments. We find that reference images substantially improve the visual quality of code generated by existing models, and ablations show that AesCode benefits from references both as model input and as a source of visual rewards. Relative to same-scale Qwen3-VL baselines given the same references, AesCode-8B and AesCode-32B improve visual quality by 31.1 and 22.4 percentage points, reaching scores comparable to those of closed-source frontier models such as GPT-5.5 and Claude Opus 4.8.
Read the full abstract ▾
All authors Xin Gao, Yifan Yang, Xin Li, Pan Wang, Yan Li, Muzhao Tian, Mingxi Cheng, Bei Liu, Kai Qiu, Qi Dai, Dong Chen, Yue Dong, Leandros Tassiulas, Rex Ying, Ji Li, Chong Luo
Computer Vision
Visual Tokens on Demand: Visual Budgeting for Scalable and Efficient Multi-Image Reasoning in Multimodal LLMs
Aimon Rahman, Joymallya Chakraborty, Vidit Bansal et al. (+1 more)
Multimodal large
language models have advanced rapidly, but most remain optimized for single-image inputs. Multi-image
reasoning is costly because each image adds many visual
tokens, increasing encoding and
attention demands. Existing techniques that address the above issue, including visual
token pruning,
token merging, visual
token compression, learned resampling, hierarchical compression,
retrieval-augmented visual
reasoning, and
memory-based architectures, have largely been designed for single-image scenarios, where redundancy is primarily spatial and local. Multi-image
reasoning introduces additional challenges: redundancy may occur across images, task-relevant evidence may be sparse or distributed, and aggressive per-image compression can remove details needed for comparison, counting, temporal
reasoning,
retrieval, or evidence grounding. Moreover, existing
token-reduction methods are often either (i) training-free but inference-inefficient, typically relying on accessing
attention matrices to get
token-importance that may be impractical to access with
memory-efficient
attention implementations such as FlashAttention, or (ii) training-dependent, requiring the base MLLM to be retrained or adapted to a new compressed-
token paradigm. In this work, we study scalable multi-image
reasoning and understanding without retraining the base model and without accessing
attention matrices at inference time. To this end, we propose mmVB, a lightweight plug-and-play module that assigns query-conditioned per-image
token budgets via cross-image context, adding only 1.6M trainable parameters while reducing visual input
tokens by 9x. This reduction yields 5x faster time-to-first-
token and 7x fewer prefill FLOPs, while maintaining 94.4% of full-resolution accuracy across eight multi-image
reasoning benchmarks.
Read the full abstract ▾
All authors Aimon Rahman, Joymallya Chakraborty, Vidit Bansal, Abhishek Dan
Computer Vision
PixelMoE: Scaling Pixel-Space Diffusion with LLM-Style Mixture-of-Experts
Ruixiao Dong, Jianmin Bao, Bozhi Luan et al. (+6 more)
Pixel-space
diffusion models provide an appealing alternative to latent-space
diffusion models by directly modeling raw images without relying on a learned tokenizer. However, scaling pixel-space models has predominantly followed dense strategies, tightly coupling model capacity with active computation. In this work, we show that standard LLM-style Mixture-of-Experts (MoE) architectures can be effectively transferred to pixel-space
diffusion. Building on this finding, we introduce PixelMoE, a pixel-space generative framework that sparsely scales model capacity with standard LLM-style MoE, without
diffusion-specific routing mechanisms or auxiliary routing objectives. Specifically, PixelMoE combines standard
Token-Choice (TC) routing with fine-grained routed experts for input-adaptive sparse computation, a shared expert for capturing common representations, and a bias-based load-balancing strategy. To complement sparse capacity scaling, PixelMoE further introduces Pixel-Space Hierarchical Flow Matching, which varies spatial resolution along the denoising trajectory from global structure formation to fine-grained detail refinement. At comparable active parameter counts, PixelMoE consistently outperforms its dense counterparts across model scales, demonstrating effective sparse capacity scaling in pixel space. On class-conditional ImageNet-1K, PixelMoE achieves FID scores of 1.47 at 256x256 and 1.53 at 512x512 without representation
alignment or perceptual losses, comparing favorably with leading pixel-space and latent-space generative models. Code and models will be released soon.
Read the full abstract ▾
All authors Ruixiao Dong, Jianmin Bao, Bozhi Luan, Zijie Meng, Xin Tao, Pengfei Wan, Kun Gai, Li Li, Houqiang Li
Machine Learning
Exact Topological Compliance: Generating Persistence-Equivalent Graphs
Mattie Ji, Indradyumna Roy and Vikas Garg
Persistent homology summarizes the topological
evolution of a graph as persistence diagrams (PDs). Generating graphs whose
topology matches a target descriptor is increasingly important, yet existing
topology-aware generative models rely on soft regularization, producing graphs whose PDs may only be approximately similar. We initiate a principled investigation of the generation problem: produce graphs that realize a target PD exactly. We propose two approaches guided by the implicit local and global constraints a target PD imposes. The local approach builds degree-based PD-equivalent graphs iteratively, and we prove that every output realizes the target PD and that every degree-based PD-equivalent graph is reachable. However, as shown thereafter, local generation necessarily trades off between sample diversity and reaching infeasible states. We therefore recast generation as a global constraint satisfaction problem with a complete encoding solvable by modern constraint programming solvers. This is applicable to any vertex-based permutation equivariant filtration scheme and is minimal under the degree filtration. Experiments on four standard graph generation
benchmarks confirm that both methods realize the target PD exactly. Together, our methods provide a principled treatment of strict
topology-compliant graph generation. Code is available at https://github.com/Aalto-QuML/ExactCompliance.
Read the full abstract ▾
Robotics
Interaction Latents as Actions for Contact-Rich Manipulation
Yuhang Zheng, Yujie Zang, Yuchen Liu et al. (+9 more)
Contact-rich manipulation requires
robots to coordinate not only where to move, but also how contact and force should evolve throughout an interaction. Yet most
robot policies represent actions primarily as motion trajectories, using tactile signals as inputs or auxiliary prediction targets without explicitly encoding contact dynamics in the action representation. We propose ILA (Interaction Latents as Actions), which uses decodable interaction latents that jointly capture the
evolution of motion, contact, and force application as policy action units, providing a shared representation for action generation, evaluation, and offline improvement. We learn these latents through visually conditioned joint action-tactile reconstruction with a time-conditioned implicit decoder. Using them as flow-matching generation targets supports post-training of pretrained
vision-
language-action models (VLAs) and world action models (WAMs), as well as training flow-matching policies from scratch. A shared decoder maps generated latents to executable actions. For offline improvement, we learn a tactile-conditioned expert reference model from interaction latents encoded from expert demonstrations. The resulting expert-consistency rewards guide weighted learning from successful rollouts, while observation-compatible expert references guide correction of low-reward predictions from failed rollouts. Across three policy families, ILA improves success rates averaged over four real-world tasks by 21.0-36.5 percentage points relative to tactile-conditioned direct-action baselines. Ablations highlight the benefit of encoding contact
evolution in action targets beyond tactile conditioning, while the same latent space supports expert-guided offline improvement. Project website: https://mrsecant.github.io/ILA/.
Read the full abstract ▾
All authors Yuhang Zheng, Yujie Zang, Yuchen Liu, Yupeng Zheng, Zhennan Jiang, Zebin Xing, Shuai Tian, Songen Gu, Jingxiang Guo, Chen Gao, Zhongpu Xia, Shuicheng Yan
Machine Learning
Two Clocks: Why Larger Rollout Batches Learn Slower but Fail on Schedule in Reinforcement Learning with Verifiable Rewards
Yuante Li, Junwei Quan, Kai Qiu et al. (+2 more)
Reinforcement learning with verifiable rewards (RLVR) relies on costly model-generated responses, motivating larger rollout batches and square-root learning-rate scaling. Reported to approximately preserve progress per sample with one optimizer step per rollout, this rule is less understood in practical multi-step training. We develop a two-clock framework that separates the samples needed to make progress from those consumed before collapse. Under a local quadratic model, the square-root rule preserves first-order drift per sample but not progress: larger batches take fewer, longer updates and lose more to
curvature, yielding a learning-rate-dependent critical batch beyond which sample efficiency degrades. A drift-threshold hypothesis predicts a complementary failure clock whose sample count remains approximately invariant along the square-root rule. Controlled GRPO experiments on Qwen2.5-Math-1.5B across a $16\times$ batch range support both predictions. Ratio clipping delays failure, especially for larger batches, but the progress gap persists without it. Widening the clip trades stability for a transient speed gain. The progress gap reappears on another
dataset, a general-purpose checkpoint, and a 7B model. Finally, we use the two-clock framework to derive a simple multi-step RLVR schedule: start below the critical batch and switch to a larger batch before failure. Our code is available at: https://github.com/WinstonLiyt/two-clocks-rlvr.
Read the full abstract ▾
All authors Yuante Li, Junwei Quan, Kai Qiu, Kate Zhang, Yicheng Tao
Robotics
ForceWAM: Decoupling Future and Response Learning from Demo and Play Data for Contact-Rich Manipulation
Zijun Xu, Wendi Chen, Xinkai Wang et al. (+16 more)
Expert demonstrations show how to complete contact-rich tasks, but provide limited coverage of how interaction forces respond to different actions. Task-agnostic play provides broader experience of contact dynamics without specifying task goals. To fully leverage these two types of data, we introduce ForceWAM, a force world action model that decouples knowledge of task-compatible interaction outcomes from knowledge of how local actions change contact. A world model learns from successful demonstrations to jointly predict future
video and six-axis force/torque trajectories. Together, these futures describe the expected
evolution of motion and contact during the task. A separate inverse dynamics model (IDM) learns from both task and play, mapping current observations and recorded visual-wrench futures to their associated
robot actions. Play data thus provide knowledge of force responses for goal-directed execution. At deployment, the IDM reactively translates generated futures into actions, reusing them with fresh wrench feedback between world-model updates. Across real-
robot force-regulated sliding, box flipping with and without disturbances, and ring placement, ForceWAM achieves $85$-$95\%$ mean success, surpassing world-modeling and reactive baselines. Our experiments further show that adding task-agnostic play data improves success by $15$-$45$ percentage points, demonstrating its value for learning contact-rich execution. Project page and code are available at https://force-wam.github.io/.
Read the full abstract ▾
All authors Zijun Xu, Wendi Chen, Xinkai Wang, Jiachen Zou, Hongjin Chen, Hairuo Liu, Bokai Lin, Shihao Ma, Ke Ma, Zhiwei Zhang, Zhuohao Yan, Ke Wu, Haoming Song, Xueqi Li, Chuan Wen, Jieru Zhao, Wenchao Ding, Cewu Lu, Lixin Yang
Artificial Intelligence
MFG: Multi-turn Feedback Guided Molecular Optimization
Trieu Nguyen, Frazier N. Baker, Ruoxi Gao et al. (+2 more)
Multi-objective molecular optimization is a critical process in drug discovery that aims to modify a given molecule to simultaneously improve multiple properties while maintaining a similar overall structure. This process often requires iterative modifications guided by computational or experimental feedback. Recent large
language model (LLM)-based methods have begun to explore this iterative approach; however, these methods are not explicitly trained to leverage such feedback, while existing approaches primarily focus on single-turn molecular optimization. To address this gap, we introduce Multi-turn Feedback Guided (MFG) molecular optimization, a reinforcement learning framework that trains an LLM to progressively optimize molecules using feedback from previous turns. MFG introduces a feedback vector capturing both property improvements and source molecule similarity, alongside a feedback-aligned reward function that promotes progressive improvement across turns. We apply MFG over $\text{GeLLM}^{3}\text{O}$, a state-of-the-art LLM model for multi-objective molecular optimization, evaluate $\text{GeLLM}^{3}\text{O-MFG}$ on ten multi-objective molecular optimization tasks. The results demonstrate that $\text{GeLLM}^{3}\text{O-MFG}$ achieves the highest average similarity-constrained success rate ($81.50%$), outperforming the base model $\text{GeLLM}^{3}\text{O}$ ($70.81%$).
Read the full abstract ▾
All authors Trieu Nguyen, Frazier N. Baker, Ruoxi Gao, Daniel Adu-Ampratwum, Xia Ning
Robotics
Collaborative Planning for UAV-UGV Teams under Operational Constraints via Masked Error-bounded Neuro-Symbolic Diffusion
Zihao Deng, Qianhuang Li, Maggie Wigness et al. (+3 more)
Collaborative planning under operational constraints is essential for heterogeneous
robot teams in large-scale missions. Unmanned Aerial Vehicles (
UAVs) provide rapid area coverage but are limited by onboard energy, while Unmanned Ground Vehicles (UGVs) can serve as mobile recharging stations yet are constrained by road-network traversability. Effective collaboration must enforce operational constraints during execution while enabling parallel, coordinated actions. Masked
Diffusion Models (MDMs) have shown promise through
token unmasking but have two key limitations:
entropy-guided scheduling assumes distributional
alignment and reliance on differentiable constraints for
diffusion-time optimization. We propose Masked Error-bounded Neuro-Symbolic
Diffusion (MEND), which formulates collaborative planning as a conditional masked generative process to generate context-aware action sequences for
UAV-UGV teams. MEND introduces a neuro-symbolic
diffusion paradigm that constrains conditional masked
diffusion policies at execution by reweighting the learned action distribution with a logic-induced admissibility indicator, thereby enforcing compliance with operational constraints. MEND introduces an error-bounded inference scheduling at execution that constructs the unmasking schedule by selecting positions with minimal predictive
entropy over the constraint-aware action distribution, enhancing collaborative planning optimality under operational constraints. Extensive experimental results in simulation, on real-world maps, and with physical
robot teams demonstrate that MEND advances
UAV-UGV collaborative planning under operational constraints.
Read the full abstract ▾
All authors Zihao Deng, Qianhuang Li, Maggie Wigness, John Rogers, Donghyun Kim, Hao Zhang
Robotics
Contact Trajectory Prompting: In-Context Transfer of Contact-Rich Behaviors from a Single Demonstration
Xian Nie, Yujie Zang, Yuhang Zheng et al. (+8 more)
In-context
robot learning enables
robots to acquire new behaviors from demonstrations without test-time parameter updates. However, visual and kinematic specifications alone may not distinguish contact-rich behaviors that share similar motions but require different interaction intensities or patterns. We propose Contact Trajectory Prompting (CTP), a framework for one-shot transfer of contact-rich manipulation behaviors. CTP encodes motion and contact information from a single demonstration into an ordered contact trajectory
prompt that captures their temporal
evolution and specifies the desired physical interaction behavior. During execution, the policy uses online sensory feedback to retrieve interaction-relevant information from the
prompt, conditioning closed-loop action generation on the demonstrated contact behavior. Across real-world wiping, rotation, and insertion tasks on objects excluded from training, CTP achieves 78.7% overall success, outperforming the strongest evaluated baseline by 13.0 percentage points. Changing only the reference demonstration enables CTP to follow contact specifications for both intensity and direction, including an intermediate wiping force level and clockwise or counterclockwise cap rotation. These results demonstrate that contact trajectories serve as effective behavioral specifications, extending in-context
robot learning beyond motion imitation to physical interaction transfer. Project website: https://ctp-robotics.github.io/project_page.
Read the full abstract ▾
All authors Xian Nie, Yujie Zang, Yuhang Zheng, Yupeng Zheng, Songen Gu, Wendi Chen, Chuan Wen, Cewu Lu, Wenchao Ding, Junchi Yan, Shuicheng Yan
Computer Vision
WorldRecon: Generative Multi-View Mesh Reconstruction for Large-Scale 3D World
Mengchen Zhang, Yang Li, Chunshi Wang et al. (+2 more)
Reconstructing complete, high-quality meshes of large-scale scenes from unposed multi-view images requires faithful
geometric grounding while plausibly completing surfaces that are unobserved or only sparsely captured. We present WorldRecon, a generative multi-view reconstruction framework for recovering complete, large-scale 3D scene meshes from unposed RGB images. WorldRecon uses a coarse, noisy global point cloud and camera poses estimated from the input images by a reconstruction model as a global scaffold for whole-scene generation and partitions it into overlapping spatial blocks. To robustly leverage these imperfect
geometric priors, we equip the native 3D generative model TRELLIS.2 with a dedicated reconstruction-based conditioning architecture that generates each block from its local point-cloud crop and block-relevant image observations, producing sparse structure, detailed geometry, and PBR materials. To maintain scene-level coherence, we introduce neighbour-aware latent inpainting and a causal world-generation procedure that propagates structural,
geometric, and material context across overlapping blocks. Together, these designs scale multi-view generative reconstruction to large-scale scenes, yielding coherent, unified meshes. Extensive experiments demonstrate that WorldRecon achieves state-of-the-art reconstruction performance, reducing Chamfer distance by 14.9% and 43.1% while improving F-score by 17.3% and 12.0% over the strongest baselines on synthetic and real-world indoor scenes, respectively, thereby demonstrating faithful and complete generative reconstruction as well as strong sim-to-real generalization. Project page: https://kszpxxzmc.github.io/WorldRecon-website/.
Read the full abstract ▾
All authors Mengchen Zhang, Yang Li, Chunshi Wang, Tong Wu, Chunchao Guo
Computer Vision
The Last Remote Sensing Model Built by Humans? Casting Any Earth Observation Task as Recursive Self-Improvement
Sijie Zhao, Zeqi Zhou, Heli Qi et al. (+6 more)
Earth observation (EO) models are still built by hand. For each new task, experts design a training recipe and tune it against a
benchmark. We show that this loop can be handed to an
agent. Any verifiable task can be cast as a harness and a verifier, where the harness defines what the
agent may use and the verifier defines what counts as success. Every EO task can be made verifiable, through labeled
benchmarks, independent sensors, physical models or the repeated observation of the same place. Given only these two components, a general-purpose coding
agent builds the EO model and improves it recursively on its own outputs. Settings long treated as separate research problems, from learning with a handful of labels to adapting across domains, become choices of harness and verifier. On six EO
benchmarks spanning optical, SAR and multispectral time-series imagery, with outputs that range from land-cover maps and ship instances to canopy heights and answers about large images,
agent-built models surpass the state of the art on every one, and on land-cover mapping, they do so from 11% of the training labels. This establishes a new paradigm for EO, in which people design harnesses and verifiers and
agents build the models, so EO models improve as
agents do.
Read the full abstract ▾
All authors Sijie Zhao, Zeqi Zhou, Heli Qi, Xuanchao Fu, Zhuo Zheng, Junshi Xia, Junjue Wang, Weihao Xuan, Naoto Yokoya
Computer Vision
RepProbe: Can Video Language Models Count Repeated Actions? A Diagnostic Benchmark
Mahsa Khoshnoodi and Sarah Adel Bargal
Repetition counting requires identifying and enumerating action cycles over time. While state-of-the-art
video language models describe actions fluently, they fail to reliably count how many times an action repeats. To investigate this limitation, we introduce RepProbe, a
benchmark of 42K real and synthetic
video clips containing exactly k in [1, 20] complete repetitions, with controls for clip position, temporal coverage, and duration. These controls allow us to study the counting failure directly and locate where in the model it arises. Counting accuracy collapses at high counts across the
video language models we evaluate, and controlled experiments show this collapse is not explained by frame sampling alone. We compare model outputs with linear probes trained on the final-layer representations used to generate those outputs. We find a consistent representation-to-output dissociation: substantial count information remains linearly decodable even when models fail to report the correct count. Further analysis shows this failure arises primarily at the output stage, where answers concentrate on a small set of preferred numbers rather than the available count information. The dissociation holds on both real and synthetic
videos and is not explained by clip duration, position, or scene content. These results indicate that models encode repetition structure but do not reliably report it in their outputs. Project page: https://arenaa.github.io/RepProbe-webpage/
Read the full abstract ▾
Robotics
LIBERO-RIG: A Hardware-Setup Robustness Benchmark for Vision-Language-Action Models
Andrea Yaoyun Cui, Hanyu Wang, Xinyi Wang et al. (+6 more)
Robot policies are expected to generalize across deployment environments, including variations in the
robot itself: cameras are bumped and remounted, calibrations drift, controllers run at different rates, and end-effector pads wear down. We present LIBERO-RIG, a
benchmark that perturbs only the
robot's hardware and setup while holding every LIBERO task fixed. The
benchmark spans eleven perturbation axes, including camera mounting and optics, camera-to-arm calibration, actuation gain, control rate, proprioceptive noise, base pose, table height, and gripper pads. Each axis has five severity levels, yielding 210 conditions across the four LIBERO suites. We evaluate nine recent
vision-
language-action models using 500 episodes per condition and substantiate each finding with rigorous statistical tests. Pooled success falls from 0.932 to 0.767 at the middle severity and 0.509 at the highest severity. Performance degradation varies substantially across perturbation axes and action interfaces, and training on visual perturbations does not mitigate faults that leave camera images unchanged. We release the
benchmark together with manifests specifying the fixed perturbation parameters for each episode.
Read the full abstract ▾
All authors Andrea Yaoyun Cui, Hanyu Wang, Xinyi Wang, Bangzheng Li, Lin Zhang, Zhenggang Tang, Shyamal Buch, Dejia Xu, Matthew Tancik
Artificial Intelligence
Who Improves the Robot? Toward Physical Recursive Self-Improvement
Hai Zhou, Fan Yang, Zeyi Chen et al. (+27 more)
Robots are increasingly autonomous in task execution, yet their improvement remains largely human-driven. This study investigates Physical Recursive Self-Improvement (Physical RSI), in which physical experience guides lasting updates to both a
robot's capabilities and its improvement procedure, making subsequent improvement more effective across tasks. Physical RSI faces challenges from noisy observations, continuous dynamics, costly trials, and irreversible consequences. We present an L0-L5 framework that differentiates capability-level from meta-level updates and within-task from across-task gains, reserving L5 for independently verified recursive gain. We study existing methods around harness adaptation and model training, alongside safety and control mechanisms that govern execution and successive updates. Our analysis reveals that, despite substantial progress in self-improvement, the surveyed literature does not yet demonstrate Physical RSI as defined by our framework. We identify research priorities in reliable feedback, causal attribution, safety preservation, and benchmarking, outlining a path toward
robots that autonomously improve how they learn while ensuring safety. The GitHub repository for Physical RSI is available at https://github.com/SAIL-Research-Lab/Physical-RSI.
Read the full abstract ▾
All authors Hai Zhou, Fan Yang, Zeyi Chen, Lejun Zhang, Chenyang Fu, Jianping Li, Jiayi Zhu, Xianyang Liu, Yingxuan Yang, Lili Meng, Lu Wang, Xinyang Han, Jiankai Sun, Weirui Ye, Guanchu Wang, Wanhua Li, Ming Zhou, Boyi Li, Ming Jin, Kun Shao, Muhao Chen, Guang Chen, Lei Ma, Joey Tianyi Zhou, Costas Spanos, Xia Hu, Mac Schwager, Weinan Zhang, Qian Feng, Shangding Gu
Machine Learning
Fast Rates for Offline Q-Learning with KL Regularization
Yize Hao, Guangxin Jiang and Shuang Qiu
This paper investigates offline Q-learning for finite-horizon Markov decision processes with Kullback-Leibler (KL) regularization. Recent studies have shown that KL regularization can yield fast rates in offline decision-making problems. However, it remains unclear whether Q-learning, which adopts incremental
stochastic approximation updates, can achieve such fast rates in the offline setting. We first propose KL-regularized Q-Learning (KLQ), a simple variant of classical Q-learning. By exploiting KL regularization, we prove that KLQ achieves a sample complexity of $\widetilde{O}(1/\epsilon)$ without explicit pessimism. This guarantee, however, has an exponential dependence on the KL regularization parameter and the horizon. To address this limitation, we further propose KL-regularized Pessimistic Q-Learning (KLPQ), which incorporates pessimism into KLQ. We prove that KLPQ retains the same \(\widetilde O(1/\epsilon)\) rate while removing the explicit exponential dependence, thereby further improving the sample complexity. To the best of our knowledge, these results establish the first fast-rate guarantees for offline Q-learning in tabular finite-horizon KL-regularized MDPs.
Read the full abstract ▾
Machine Learning
Scaling Online Optimal Transport Minibatches for Flow Matching
Peter Chen and Sergey Levine
A central challenge in scaling flow models is maintaining stability in training and integration. In flow matching, this stability depends critically on how source samples are paired with data. Independent random pairing introduces substantial stochasticity, motivating minibatch optimal transport (OT) to construct online source-target couplings that reduce this randomness (Tong et al., 2024). However, as applications extend to larger and higher-dimensional
datasets, small minibatches can limit these benefits, while scaling the coupling to substantially larger minibatches at every iteration is computationally prohibitive. Moreover, how OT coupling affects the full
stochastic gradient and integration remains theoretically unresolved. In this work, we develop a scalable online entropic OT approximation that enables substantially larger source-target couplings while preserving the benefits of OT. We close the theoretical gap for both unregularized and entropic OT by proving strict reductions in full
stochastic-gradient variance and integration error relative to independent pairing, and further characterize how these improvements strengthen as the online coupling minibatch grows. Experiments on single-
cell gene interpolation-flow and image-flow training validate these predictions, showing that larger online couplings consistently improve training stability and final generation performance.
Read the full abstract ▾
Numerical Analysis
Fully discrete multi-entropy-stable compact Runge–Kutta discontinuous Galerkin methods for hyperbolic conservation laws
Zheng Sun
We develop fully discrete multi-
entropy-stable high-order compact Runge–Kutta discontinuous Galerkin (cRKDG) methods for
hyperbolic conservation laws. Our main result is a weak
cell entropy inequality for multi-dimensional systems after one full high-order Runge–Kutta (RK) time step. The proof exploits the
cell-local intermediate stages of cRKDG: their perturbations are controlled by the initial in-
cell variation. The analysis does not require a strong stability preserving decomposition or stagewise
entropy correction. For a sufficiently dissipative Lax–Friedrichs flux and explicit RK methods with nonnegative output weights, the inequality holds under a suitable time-step restriction for strongly convex
entropy pairs. For a prescribed, uniformly conditioned family of such
entropies, common dissipation and time-step conditions ensure weak
cell entropy stability for all
entropy pairs. A single
cell-average-preserving scaling at the end of each step then enforces all corresponding strong
cell entropy inequalities simultaneously. We also prove a Lax–Wendroff-type
theorem: under the stated assumptions, any strongly convergent sequence of numerical solutions converges to a weak solution satisfying all prescribed
entropy inequalities. Numerical experiments in one and two dimensions demonstrate high-order accuracy, the benefit of multiple
entropy constraints for nonconvex scalar problems, and robust performance on shock problems.
Read the full abstract ▾