Generalist robot manipulation policies have developed rapidly, yet their reliable evaluation remains challenging due to fundamental flaws in existing simulation benchmarks: prominent sim-to-real gaps, narrow task coverage, and unfair evaluation caused by ambiguous training-test pipelines. Prior works only partially res...
Lian Ruan, Jade Yang, Sherphylan Gao et al.· 0 citations
This work presents X-Planner, a planning front-end that addresses both the supervision and representation of embodied reasoning, and describes planning-text quality and downstream execution.
Howard Lu, Shalfun Li, Porter Pan et al.· 0 citations
Task planning bridges high-level instructions and executable behavior in long-horizon manipulation, yet modern Vision-Language-Action (VLA) systems often leave this intermediate structure implicit. Existing chain-of-thought (CoT) planners also tend to rely on coarse task-level annotations or serialize long reasoning tr...
Howard Lu, Shalfun Li, Porter Pan et al.· 0 citations
X2-NativeCursor is proposed, a lightweight observer that tracks progress from native speech tokens before waveform decoding without changing the TTS generator, and its normalization plan links spoken labels to their original-text spans.
A frame-synchronous turn state head that operates in parallel with the ASR head on shared streaming representations, jointly predicting ASR tokens and fine-grained turn states at the frame level is introduced.
Kaiqi Fu, Rime Wen, Altman Lin et al.· 4 citations
X2Streaming-ASR is proposed, which decomposes streaming recognition into when to commit and what to commit, and achieves the best streaming CER among the evaluated systems on AISHELL-1 and AISHELL-3 with substantially lower latency.
Zhi-Wei Lin, Kaiqi Fu, Rime Wen et al.· 0 citations
X2Streaming-TTS is presented, a causal TTS framework that consumes asynchronously arriving text tokens and emits speech without accessing future input that outperforms existing pseudo-streaming models on most subjective and objective metrics.
WALL-SS is introduced, a world model that generates visual futures through Scale-wise autoregressive Scaling, enabling action-controllable and long-horizon robotic simulation, and consistently benefits from on-policy alignment in reducing action drift and long-horizon inconsistency.
Maeve Zhang, Rainy Sun, Xiang Wang et al.· 2 citations· ⚡1
HOST (Human-to-robot One-Shot Skill AcquisiTion), a framework that enables a robot to acquire skills in seconds from a single human video while retaining previously mastered skills.
Guangyan Chen, Meiling Wang, Te Cui et al.· arXiv.org· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
