Related papers: RoboCurate: Harnessing Diversity with Action-Verif…
We propose a method for generating video-realistic animations of real humans under user control. In contrast to conventional human character rendering, we do not require the availability of a production-quality photo-realistic 3D model of…
The strong performance of large vision-language models (VLMs) trained with reinforcement learning (RL) has motivated similar approaches for fine-tuning vision-language-action (VLA) models in robotics. Many recent works fine-tune VLAs…
Advancements in large language models (LLMs) have demonstrated their potential in facilitating high-level reasoning, logical reasoning and robotics planning. Recently, LLMs have also been able to generate reward functions for low-level…
We present TempoMaster, a novel framework that formulates long video generation as next-frame-rate prediction. Specifically, we first generate a low-frame-rate clip that serves as a coarse blueprint of the entire video sequence, and then…
Autonomous learning of dexterous, long-horizon robotic skills has been a longstanding pursuit of embodied AI. Recent advances in robotic reinforcement learning (RL) have demonstrated remarkable performance and robustness in real-world…
Training tool-use agents typically relies on outcome-based filtering: Supervised Fine-Tuning (SFT) on successful trajectories and Reinforcement Learning (RL) on pass-rate-selected tasks. However, this paradigm ignores interaction dynamics:…
Virtual character animation control is a problem for which Reinforcement Learning (RL) is a viable approach. While current work have applied RL effectively to portray physics-based skills, social behaviours are challenging to design reward…
Visual Robot Manipulation (VRM) aims to enable a robot to follow natural language instructions based on robot states and visual observations, and therefore requires costly multi-modal data. To compensate for the deficiency of robot data,…
Achieving generalizability in solving out-of-distribution tasks is one of the ultimate goals of learning robotic manipulation. Recent progress of Vision-Language Models (VLMs) has shown that VLM-based task planners can alleviate the…
Reconstructing human vision from brain activities has been an appealing task that helps to understand our cognitive process. Even though recent research has seen great success in reconstructing static images from non-invasive brain…
Humans learn locomotion through visual observation, interpreting visual content first before imitating actions. However, state-of-the-art humanoid locomotion systems rely on either curated motion capture trajectories or sparse text…
Humans are able to seamlessly visually imitate others, by inferring their intentions and using past experience to achieve the same end goal. In other words, we can parse complex semantic knowledge from raw video and efficiently translate…
Deploying learned robot manipulation policies in industrial settings requires rigorous pre-deployment validation, yet exhaustive testing across high-dimensional parameter spaces is intractable. We present ROBOGATE, a deployment risk…
Video super-resolution (VSR) techniques, especially deep-learning-based algorithms, have drastically improved over the last few years and shown impressive performance on synthetic data. However, their performance on real-world video data…
Enhancing the generalization capability of robotic learning to enable robots to operate effectively in diverse, unseen scenes is a fundamental and challenging problem. Existing approaches often depend on pretraining with large-scale data…
Vision-Language-Action (VLA) models have recently advanced robotic manipulation by translating natural-language instructions and visual observations into control actions. However, existing VLAs are primarily trained on successful expert…
Most existing approaches formulate action quality assessment and skill proficiency estimation as discriminative prediction tasks, typically producing discrete labels or scores without explicitly modeling the reasoning process underlying the…
Generative manipulation policies can fail catastrophically under deployment-time distribution shift, yet many failures are near-misses: the robot reaches almost-correct poses and would succeed with a small corrective motion. We propose…
Current motion-controlled image-to-video generation models rigidly follow user-provided trajectories that are often sparse, imprecise, and causally incomplete. Such reliance often yields unnatural or implausible outcomes, especially by…
Research on diffusion model-based video generation has advanced rapidly. However, limitations in object fidelity and generation length hinder its practical applications. Additionally, specific domains like animated wallpapers require…