Autoregressive video generation models generate videos sequentially, with each new block conditioned on previously generated blocks. By training on the model's own rollouts, Self Forcing and its follow-up methods substantially mitigate exposure bias caused by the mismatch between training- and inference-time history di...
Chen-Xi Xia, Yi-Xuan Xu, Shan Liu et al.· 0 citations
The Agentic Reward System (ARS) is introduced, an inference framework for progress reward modeling with general-purpose vision-language models (VLMs), without additional reward-model training, and its results suggest that structured inference and verification can improve the usefulness of general-purpose VLMs for robot...
Sheng-Miao Hu, Wei-Yi Lu, Ling-Bing Zeng et al.· 0 citations
Experiments on a real robot platform demonstrate that MaskHarness-WAM substantially outperforms limited-horizon policies on sequential multi-object manipulation, showing its effectiveness in extending local manipulation skills to reliable long-horizon execution.
Zi-Tai Huang, Taiyi Su, Jian Zhu et al.· 0 citations
The Causal Semantic World Action Model (CSWAM) is presented, which augments FastWAM with a causal semantic expert built on V-JEPA 2.1, which provides temporally grounded representations of semantic state changes and motion with less dependence on appearance-specific details.
Tian-Bin Liu, Jian Zhu, Taiyi Su et al.· 1 citation
Shiva-DiT, based on Residual-Based Differentiable Top-k Selection, provides four fidelity-latency operating points and reaches a 1.54x wall-clock speedup with competitive fidelity.
