11 papers
EgoJEPA: Beyond Retargeting for Dexterous Manipulation from Egocentric Videos
Meng Cao, Can Zhao, Jinjie Wei +12
Egocentric human videos offer a scalable alternative to costly robot demonstra- tions, yet transferring their manipulation priors to robot control remains chal- lenging. The common…
X-Planner: Event-Structured Task Planning for Embodied Intelligence
Howard Lu, Shalfun Li, Porter Pan +30
Task planning bridges high-level instructions and executable behavior in long-horizon manipulation, yet modern Vision-Language-Action (VLA) systems often leave this intermediate st…
X2-NativeCursor: Native-Token Text Progress Tracking for Incremental-Text Streaming Codec TTS
Zehan Liu, Carl Chen, Rime Wen +7
Incremental-text streaming text-to-speech (TTS) needs online text progress tracking for synchronized highlighting, interruption handling, and dialogue-history updates. Input text a…
X2Streaming-ASR: wait when uncertain, emit when ready for streaming ASR
Zhiwei Lin, Kaiqi Fu, Rime Wen +5
Streaming automatic speech recognition (ASR) for real-time voice agents and full-duplex dialogue must provide accurate partial transcripts with low commit latency. Existing systems…
X2-Turn: Frame-Synchronous Dual-Head Modeling for Joint Streaming ASR and Turn State Prediction
Kaiqi Fu, Rime Wen, Altman Lin +4
Accurate and responsive turn-taking is essential for spoken dialogue systems, which must distinguish in real time between user interruptions, backchannels that should be ignored, a…
X2Streaming-TTS: Causal Token-Level Text-to-Speech from Streaming Text with Speech-State Inheritance
Rime Wen, Zehan Liu, Shawn Qin +4
Streaming text-to-speech is essential for low-latency spoken dialogue systems, yet many systems wait for sentence-level text and are therefore only pseudo-streaming. True token-lev…
DMuon: Efficient Distributed Muon Training with Near-Adam Overhead
Vincent Chen, Starrick Liu, Regis Cheng +8
Matrix-orthogonalization-based optimizers, exemplified by Muon, have demonstrated strong convergence behavior across a wide range of modern deep learning workloads. The matrix-awar…
XRZero-G0: Pushing the Frontier of Dexterous Robotic Manipulation with Interfaces, Quality and Ratios
James Wang, Primo Pu, Zephyr Fung +19
The acquisition of high-quality, action-aligned demonstration data remains a fundamental bottleneck in scaling foundation models for dexterous robot manipulation. Although robot-fr…
LongCat-Next: Lexicalizing Modalities as Discrete Tokens
Meituan LongCat Team, Bin Xiao, Chao Wang +86
The prevailing Next-Token Prediction (NTP) paradigm has driven the success of large language models through discrete autoregressive modeling. However, contemporary multimodal syste…
ManipArena: Comprehensive Real-world Evaluation of Reasoning-Oriented Generalist Robot Manipulation
Yu Sun, Meng Cao, Yang Ping +24
Vision-Language-Action (VLA) models and world-action models have emerged as central paradigms for general-purpose robotic intelligence, yet their empirical progress remains constra…
Igniting VLMs toward the Embodied Space
Andy Zhai, Brae Liu, Bruno Fang +17
While foundation models show remarkable progress in language and vision, existing vision-language models (VLMs) still have limited spatial and embodiment understanding. Transferrin…