Vision-Language-Action · Zhejiang University
LabVLA: A VLA Model for Scientific Lab Robots
LabVLA trains a Qwen3-VL-4B backbone plus DiT action expert on laboratory workflows and reports 71.1% ID and 70.0% OOD success on LabUtopia.
Institution
Zhejiang University
Leading Chinese research university in Hangzhou with strong AI, NLP, and machine learning groups.
MiniMax Sparse Attention: 1M Context Without Dense Attention
MiniMax Sparse Attention keeps only 2,048 selected KV tokens per query group and reports 28.4x lower attention FLOPs plus 14.2x prefill speedup at 1M context.
SkillAdaptor: How LLM Agents Rewrite Their Own Skills
SkillAdaptor edits an agent's skill library from failed trajectories without touching model weights, lifting WebShop score +2.3 and PinchBench +1.5 over the frozen backbone.
StreamMA: Streaming Beats Waiting in Multi-Agent Reasoning
StreamMA pipes each reasoning step to the next agent the moment it is written, not after the full chain. Across 8 benchmarks it gains +7.3 pp on average (max +22.4 pp on HMMT 2026) and runs up to 26.9x faster.
Speech Synthesis · Zhejiang University
SwanSphere: Streaming Spatial Audio Generation From Video and Text
SwanSphere streams first-order ambisonic audio synced to video or text, emitting its first chunk in 0.21s while cutting Frechet Distance to 120.28 vs OmniAudio's 157.67. Quality without waiting for the whole clip.
AI Agents · Zhejiang University
Self-Distilled Agentic RL: A Privileged Teacher Steering GRPO Per Token
SDAR adds a gated, token-level self-distillation signal from a skill-augmented teacher on top of GRPO, lifting multi-turn agents by up to +10.2 points on WebShop and +9.4 on ALFWorld for small Qwen models.