Recent coding large language models (LLMs) can synthesize dynamic 4D worlds from natural language, but the resulting content remains a visual artifact. It lacks physical semantics such as the collision geometry, mass, friction, inertia, and joint structure, required to enable it to simulate the physical world, and its...
Hao-Yu Zhang, Si-Ming Li, Ze-Yu Zhang et al.· 0 citations
Flow-based policies provide an expressive framework for continuous robot control, but their iterative ODE integration incurs substantial inference cost. Naively reducing the integration budget can severely degrade control, since policies optimized under full-step execution are not explicitly constrained to remain relia...
Ting Huang, Li-Rui Pan, Hao-Yu Wang et al.· 0 citations
Experiments demonstrate that, compared with direct gaming-world generation by coding agents and existing baseline methods, Code2Games consistently improves the visual quality and interactive fidelity of generated gaming worlds, as well as the quality of the resulting games after engine adaptation.
Wei Wu, Zi-Yang Xu, Ze-Yu Zhang et al.· 1 citation
Text-to-motion (T2M) generation maps natural language to human joint movements, aiding gaming, VR, and robotics. Retrieval-Augmented Text-to-Motion (RAG-T2M) improves generation on complex descriptions by conditioning on retrieved motion-text pairs. However, existing RAG-T2M models face two challenges: coarse-grained r...
Yi-Ran Wang, Ze-Yu Zhang, Ling Shao et al.· 0 citations
Reinforcement learning (RL) for dexterous manipulation must discover finger-object contacts and then control the object precisely; the action noise that serves the first goal can interfere with the second. In trajectory-guided settings such as ViViDex, where RL refine hand-object trajectories from human video, our base...
Hao-Yu Wang, Si-Yuan Qian, Yan-Jun Li et al.· 0 citations
Recent diffusion and autoregressive models have substantially improved text-to-video generation, yet producing coherent long-form story videos with consistent characters and aligned audio remains challenging. Existing methods often suffer from narrative drift, unstable character identity, weak cross-scene continuity, a...
Ting Huang, Biao Wu, Rong-Hao Chen et al.· 0 citations
This work proposes DeltaWAM, which jointly predicts visual deltas and actions using dense-anchor, sparse-delta, and action streams, with three architectures that differ in representation and computation sharing, and develops Streaming Delta Memory (SDM), which updates cached anchor context with compact observed deltas,...
Han Yan, Zi-Shang Xiang, Hao-Kai Jiang et al.· 0 citations
This work proposes MobileVLA-R1 2.0, an RL-enhanced VLA framework that explicitly couples structured embodied reasoning with executable mobile robot control, and introduces a reasoning-conditioned action decoder that maps multimodal reasoning representations to task-level action targets, which are subsequently translat...
Ting Huang, Yue Huang, Ze-Yu Zhang et al.· 1 citation
Averaged over five seeds, MemGuard achieves the best success metric and lowest average steps in all 16 backbone-benchmark settings, improving over ReasoningBank, the strongest prior baseline among the memory methods the authors evaluate.
Hao-Yu Wang, Guang-Yuan Dong, He Liang et al.· 4 citations
ConsiSpace is proposed, a geometry-consistency-aware framework for geometry-sensitive video spatial reasoning that turns spatial consistency into both an evidence organization principle and an explicit post-SFT learning signal, and utilizes unified consistency self-supervised reinforcement learning (UC-SSRL) after supe...
