arXiv subjects

Zipeng Ye

Publications and source records attributed to Zipeng Ye.

17 recordsLinked to original sources

arXiv2026

ClothDojo: Learned Data Generation and Benchmarking for Bimanual Garment Flattening and Folding

Garment flattening and folding require robots to identify garment structure during manipulation and adapt their actions as the cloth deforms. We present ClothDojo, a simulation platform that generates adaptive manipulation trajectories at scale across diverse garments and initial states and evaluates policies in closed loop. ClothDojo encodes each garment's canonical mesh coordinates as an NOCS texture, providing canonical surface-position cues through the visual interface of a pretrained vision-language-action model. We fine-tune the model on human demonstrations and corrections to obtain a data-generation policy. The policy autonomously generates simulated manipulation trajectories, and we retain rollouts that satisfy task-specific success criteria. Each retained trajectory is re-rendered under a randomly sampled appearance to provide RGB observations for downstream policies that do not receive NOCS. Across both tasks, the policy produces nearly 8,000 successful trajectories over hundreds of garments. RGB policies trained on these generated trajectories outperform those trained directly on the original human demonstrations and corrections across all evaluated garment splits and appearance settings. Evaluations across multiple policy models show that overall performance and appearance robustness vary across models and tasks, while generalization to unseen garments remains a common challenge.

cs.RO↗

arXiv2026

HandMimicX: Learning Human-Like Dexterous Manipulation via an Object-Centric Policy from Egocentric Videos

Learning dexterous manipulation from human videos remains an open challenge, particularly in the context of transferring a single demonstration into a spatially generalizable robotic skill and maintaining physically plausible human-like interactions. Unlike prior works that emphasize hand-motion imitation, we introduce an object-centric framework for acquiring dexterous skills from egocentric human RGB-D videos. Within our framework, we formulate the reinforcement learning (RL) objective in terms of object motion to decouple the underlying skill from the specific hand trajectory and impose constraints on hand-object interaction states to promote more anatomically natural hand configurations. Extensive experiments in simulation and on real robots demonstrate that our method enables efficient learning from human videos and generalizable skill transfer across novel spatial configurations.

cs.RO↗

arXiv2026

SimPT: An Automated Simulation Framework for Intervention-Based VLA Post-Training

Human-in-the-loop (HIL) post-training improves vision-language-action (VLA) policies through expert corrections, but costly human supervision and repeated real-robot evaluation limit algorithm exploration and development. We introduce SimPT (Simulation-based Post-Training), a simulation framework that automates intervention-based VLA post-training by integrating policy rollouts, corrective data collection, policy training, and standalone evaluation. To automatically determine intervention timing and recovery strategies, we develop an Agent-Compiled Progress Graph that tracks task progress using privileged simulator state and retains stable snapshots during policy execution. After a rollout fails, a CuRobo-based expert attempts recovery from these snapshots, starting at more advanced task stages and falling back to earlier ones as needed to generate corrective trajectories. We implement and compare four post-training methods, RECAP, HG-DAgger, DPO+SFT, and FlowPRO, across seven RoboTwin manipulation tasks. Relative to a fixed-interval snapshot baseline, the Progress Graph reduces recovery attempts by 75.0% and increases recovery success from 93.4% to 98.9%. Using SimPT, we develop RECAP-CF-LPF, a refinement of RECAP that combines cross-fitting and low-pass filtering of value predictions. This refinement increases the overall success rate from 76.50% to 79.36% in held-out simulation trials. In real-robot HIL post-training, it increases the success rate from 72% to 96% across 25 scenarios of an Ethernet cable-insertion task. These results demonstrate the utility of SimPT for exploring and developing VLA post-training algorithms.

cs.RO↗

arXiv2026

MARC: Mechanism-Aware Reflective Correction for Articulated Object Code Generation

Generating an articulated object from images and text requires more than plausible parts and movable joints: the assembled mechanism must execute the intended motion. This is particularly challenging for closed-chain and coupled mechanisms, where an error in one connection can block motion or separate connected parts. We introduce MARC, Mechanism-Aware Reflective Correction, which shares an executable kinematic graph across program construction, motion solving, and correction. The graph binds physical connections to local attachment frames and represents loop closures and joint-coordinate couplings. Given prescribed driver inputs, a numerical solver computes follower motion and associates errors with specific connections and configurations. The agent uses these diagnostics to probe possible causes, revise connections or geometry, and retest the mechanism along the original motion paths. On a 20-object test set, MARC with Kimi-K3 achieves 67.8% valid motion coverage and 60.0% overall success, outperforming six baselines. Starting from the same initial candidates, correction improves these scores by 13.7 and 20.0 percentage points, respectively. Ablations further show the benefits of graph-based mechanism support and graph-guided repair. Project homepage: https://demianmusk.github.io/MARC-Home/.

cs.CV↗

arXiv2026

What Limits Cross-Task Generalization in World Action Models?

Cross-task generalization remains difficult for world action models (WAMs), even when their predicted futures depict plausible manipulation. This gap can be attributed directly: we make this gap directly testable by decoupling a WAM into a world model and an inverse-dynamics model (IDM), then holding the IDM fixed while replacing the source of future images. We introduce Align Once, Evaluate Everywhere (AoE), a camera-space inverse-dynamics model pretrained on large-scale robot data, which provides this recovery interface for different future sources across tasks and environments. Through it, we find that actions recovered from recorded futures of unseen tasks execute almost as well as replayed demonstrations, whereas futures predicted by world models collapse across benchmarks. The failures are not generic: they concentrate on the gripper and interaction geometry while generation capacity is spent on task-irrelevant background. This diagnosis suggests that supervision should target exactly these regions. We therefore introduce the vision-to-action (VITA) loss, which passes generated futures through the frozen AoE and penalizes discrepancies in the recovered actions, redirecting generation toward action-relevant detail. Across two world models and three manipulation benchmarks, this simple change raises the execution success of generated futures from near zero to 47.0%. The same loss also transfers to WAMs and yields consistent gains in native control.

cs.RO↗

arXiv2026

ProWorld: Multi-View World Model with Proprioceptive Feedback for Closed-Loop Policy Evaluation

Evaluating robot manipulation policies through repeated physical trials is costly. We study whether an action-conditioned world model can serve as a closed-loop test environment whose policy success rates track those on real robots. Beyond realistic video, the model must return the camera views and proprioceptive state needed for the policy's next action and preserve failed-action outcomes to avoid overestimating policy capability. We introduce ProWorld, a world model that jointly predicts multi-view video and robot state, then feeds both back to a frozen policy for repeated interaction. ProWorld comprises a shared transformer for joint video-state flow prediction and Shared-Time View Encoding to distinguish cameras while preserving temporal synchronization. To reduce interaction hallucinations that turn missed grasps into successful lifts, we augment training with failed interactions collected in high-fidelity simulation, reducing inflated success rates in the generated environment. ProWorld achieves the highest overall TriWorldBench score among the compared methods. Across three policies and four local manipulation tasks, it attains a Pearson correlation of 0.95 and a Spearman correlation of 0.94 between generated and real success rates. These results support joint visual-proprioceptive feedback and failure-aware training as a basis for world-model-based policy evaluation.

cs.RO↗

arXiv2026

Flow-Support-Weighted Proposals for Test-Time Verified VLA Policies

Test-time sampling promises to turn one action prediction into a set of distinct executable candidates that a verifier can choose among. Downstream fine-tuning works against that promise. A vision-language-action model trained to solve one task distribution concentrates its flow-matching decoder around the dominant demonstrated action, so repeated samples differ only marginally and the verifier receives many copies of one decision. We call this proposal contraction and identify it as a key constraint on test-time scaling: repeated samples can remain highly redundant as the candidate budget grows. Action Dynamic Sampling (ADS) alleviates the constraint on the proposal side, during training. At each training step, ADS integrates $K$ additional trajectories from the current policy under fresh base noise, scores each by the flow support along its path with a Hutchinson trace estimator, and corrects the policy's local action distribution toward this weighted set through a detached finite-set KL term. Training cost rises; deployment cost is unchanged. Across simulation and four physical-robot tasks, ADS raises proposal spread without the success penalty that Gaussian perturbation incurs, lifts oracle best-of-8 success on RoboCasa from 57.6% to 63.0%, improves fixed verifiers by 2.4 to 4.9 points in simulation, and raises TokenPB by up to 13.0 points on real-world manipulation.

cs.RO↗

arXiv2026

Beyond Placement and Articulation: Usage-Driven Code Scenes for Embodied Interaction

Indoor scene synthesis provides essential environments for embodied AI, robotic manipulation, and simulation-based policy learning. Recent code-based scene generation methods produce editable and extensible environments, yet they remain focused on visual construction and object-level articulation, leaving the functional usage of scenes largely unmodeled. To address this problem, we present RoomWright, an agentic usage-driven framework for generating 3D scenes represented entirely as code for embodied interaction. RoomWright performs usage-driven object reasoning, which treats each anchor as a task centre and admits task-required objects and their affordances. A code agent further enables multi-part interaction by compiling each interaction into a trigger, condition, effect rule that updates structured object states, capturing causal dependencies across objects. Moreover, since manipuland orientation is ambiguous and hard to recover from pixels, RoomWright alleviates this via annotation-informed usage-guided orientation. Extensive experiments demonstrate the effectiveness of our method. The resulting scenes are executable, editable, and simulation-ready, providing interactive environments for embodied AI and policy learning.

cs.RO↗

arXiv2026

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models

Large language models (LLMs) have demonstrated remarkable capabilities across diverse applications, yet ensuring their simultaneous safety, helpfulness, and trustworthiness remains a persistent challenge. Conventional refusal-oriented alignment strategies mitigate harmful content generation but systematically fail to serve legitimate user needs, often withholding information that could safely and constructively address the underlying intent of sensitive queries. Building upon the constructive safety paradigm pioneered by Oyster-I, which moves beyond blanket refusal toward thoughtful, response-oriented safety alignment, we identify two critical limitations of its Supervised Fine-Tuning (SFT)-based scheme: insufficient safety generalization to out-of-distribution scenarios and a phenomenon we term safety chain-of-thought (CoT) over-generalization, wherein safety-oriented reasoning patterns are excessively applied to benign queries, degrading helpfulness and user experience. To address these limitations, we propose Oyster-II, a reinforcement learning (RL)-based constructive safety alignment framework that adopts a Zero-RL paradigm combined with a multi-stage reinforcement learning strategy.Evaluated across extensive benchmarks, Oyster-II comprehensively surpasses both Qwen3-14B and its predecessor Oyster-I on safety dimensions, achieving cross-scale performance comparable to Qwen3-Max and Qwen3.5-397B.

cs.AI↗

arXiv2025

MIR: Efficient Exploration in Episodic Multi-Agent Reinforcement Learning via Mutual Intrinsic Reward

Episodic rewards present a significant challenge in reinforcement learning. While intrinsic reward methods have demonstrated effectiveness in single-agent rein-forcement learning scenarios, their application to multi-agent reinforcement learn-ing (MARL) remains problematic. The primary difficulties stem from two fac-tors: (1) the exponential sparsity of joint action trajectories that lead to rewards as the exploration space expands, and (2) existing methods often fail to account for joint actions that can influence team states. To address these challenges, this paper introduces Mutual Intrinsic Reward (MIR), a simple yet effective enhancement strategy for MARL with extremely sparse rewards like episodic rewards. MIR incentivizes individual agents to explore actions that affect their teammates, and when combined with original strategies, effectively stimulates team exploration and improves algorithm performance. For comprehensive experimental valida-tion, we extend the representative single-agent MiniGrid environment to create MiniGrid-MA, a series of MARL environments with sparse rewards. Our evalu-ation compares the proposed method against state-of-the-art approaches in the MiniGrid-MA setting, with experimental results demonstrating superior perfor-mance.

cs.AI↗

arXiv2024

Evolutionary Trigger Detection and Lightweight Model Repair Based Backdoor Defense

Deep Neural Networks (DNNs) have been widely used in many areas such as autonomous driving and face recognition. However, DNN model is fragile to backdoor attack. A backdoor in the DNN model can be activated by a poisoned input with trigger and leads to wrong prediction, which causes serious security issues in applications. It is challenging for current defenses to eliminate the backdoor effectively with limited computing resources, especially when the sizes and numbers of the triggers are variable as in the physical world. We propose an efficient backdoor defense based on evolutionary trigger detection and lightweight model repair. In the first phase of our method, CAM-focus Evolutionary Trigger Filter (CETF) is proposed for trigger detection. CETF is an effective sample-preprocessing based method with the evolutionary algorithm, and our experimental results show that CETF not only distinguishes the images with triggers accurately from the clean images, but also can be widely used in practice for its simplicity and stability in different backdoor attack situations. In the second phase of our method, we leverage several lightweight unlearning methods with the trigger detected by CETF for model repair, which also constructively demonstrate the underlying correlation of the backdoor with Batch Normalization layers. Source code will be published after accepted.

cs.CR↗

arXiv2022

Dynamic Neural Textures: Generating Talking-Face Videos with Continuously Controllable Expressions

Recently, talking-face video generation has received considerable attention. So far most methods generate results with neutral expressions or expressions that are implicitly determined by neural networks in an uncontrollable way. In this paper, we propose a method to generate talking-face videos with continuously controllable expressions in real-time. Our method is based on an important observation: In contrast to facial geometry of moderate resolution, most expression information lies in textures. Then we make use of neural textures to generate high-quality talking face videos and design a novel neural network that can generate neural textures for image frames (which we called dynamic neural textures) based on the input expression and continuous intensity expression coding (CIEC). Our method uses 3DMM as a 3D model to sample the dynamic neural texture. The 3DMM does not cover the teeth area, so we propose a teeth submodule to complete the details in teeth. Results and an ablation study show the effectiveness of our method in generating high-quality talking-face videos with continuously controllable expressions. We also set up four baseline methods by combining existing representative methods and compare them with our method. Experimental results including a user study show that our method has the best performance.

cs.CV↗

arXiv2022

Audio-Driven Talking Face Video Generation with Dynamic Convolution Kernels

In this paper, we present a dynamic convolution kernel (DCK) strategy for convolutional neural networks. Using a fully convolutional network with the proposed DCKs, high-quality talking-face video can be generated from multi-modal sources (i.e., unmatched audio and video) in real time, and our trained model is robust to different identities, head postures, and input audios. Our proposed DCKs are specially designed for audio-driven talking face video generation, leading to a simple yet effective end-to-end system. We also provide a theoretical analysis to interpret why DCKs work. Experimental results show that our method can generate high-quality talking-face video with background at 60 fps. Comparison and evaluation between our method and the state-of-the-art methods demonstrate the superiority of our method.

cs.CV↗

arXiv2021

3D-CariGAN: An End-to-End Solution to 3D Caricature Generation from Face Photos

Caricature is a type of artistic style of human faces that attracts considerable attention in the entertainment industry. So far a few 3D caricature generation methods exist and all of them require some caricature information (e.g., a caricature sketch or 2D caricature) as input. This kind of input, however, is difficult to provide by non-professional users. In this paper, we propose an end-to-end deep neural network model that generates high-quality 3D caricatures directly from a normal 2D face photo. The most challenging issue for our system is that the source domain of face photos (characterized by normal 2D faces) is significantly different from the target domain of 3D caricatures (characterized by 3D exaggerated face shapes and textures). To address this challenge, we: (1) build a large dataset of 5,343 3D caricature meshes and use it to establish a PCA model in the 3D caricature shape space; (2) reconstruct a normal full 3D head from the input face photo and use its PCA representation in the 3D caricature shape space to establish correspondences between the input photo and 3D caricature shape; and (3) propose a novel character loss and a novel caricature loss based on previous psychological studies on caricatures. Experiments including a novel two-level user study show that our system can generate high-quality 3D caricatures directly from normal face photos.

cs.CV↗

arXiv2020

Audio-driven Talking Face Video Generation with Learning-based Personalized Head Pose

Real-world talking faces often accompany with natural head movement. However, most existing talking face video generation methods only consider facial animation with fixed head pose. In this paper, we address this problem by proposing a deep neural network model that takes an audio signal A of a source person and a very short video V of a target person as input, and outputs a synthesized high-quality talking face video with personalized head pose (making use of the visual information in V), expression and lip synchronization (by considering both A and V). The most challenging issue in our work is that natural poses often cause in-plane and out-of-plane head rotations, which makes synthesized talking face video far from realistic. To address this challenge, we reconstruct 3D face animation and re-render it into synthesized frames. To fine tune these frames into realistic ones with smooth background transition, we propose a novel memory-augmented GAN module. By first training a general mapping based on a publicly available dataset and fine-tuning the mapping using the input short video of target person, we develop an effective strategy that only requires a small number of frames (about 300 frames) to learn personalized talking behavior including head pose. Extensive experiments and two user studies show that our method can generate high-quality (i.e., personalized head movements, expressions and good lip synchronization) talking face videos, which are naturally looking with more distinguishing head movement effects than the state-of-the-art methods.

cs.CV↗

arXiv2019

A Configuration-Space Decomposition Scheme for Learning-based Collision Checking

Motion planning for robots of high degrees-of-freedom (DOFs) is an important problem in robotics with sampling-based methods in configuration space C as one popular solution. Recently, machine learning methods have been introduced into sampling-based motion planning methods, which train a classifier to distinguish collision free subspace from in-collision subspace in C. In this paper, we propose a novel configuration space decomposition method and show two nice properties resulted from this decomposition. Using these two properties, we build a composite classifier that works compatibly with previous machine learning methods by using them as the elementary classifiers. Experimental results are presented, showing that our composite classifier outperforms state-of-the-art single classifier methods by a large margin. A real application of motion planning in a multi-robot system in plant phenotyping using three UR5 robotic arms is also presented.

cs.RO↗

arXiv2019

Geodesic Centroidal Voronoi Tessellations: Theories, Algorithms and Applications

Nowadays, big data of digital media (including images, videos and 3D graphical models) are frequently modeled as low-dimensional manifold meshes embedded in a high-dimensional feature space. In this paper, we summarized our recent work on geodesic centroidal Voronoi tessellations(GCVTs), which are intrinsic geometric structures on manifold meshes. We show that GCVT can find a widely range of interesting applications in computer vision and graphics, due to the efficiency of search, location and indexing inherent in these intrinsic geometric structures. Then we present the challenging issues of how to build the combinatorial structures of GCVTs and establish their time and space complexities, including both theoretical and algorithmic results.

cs.GR↗