Gao Huang

A novel PEFT method termed position anchor tuning (PAT) is proposed, which performs comparably to state-of-the-art methods while incurring significantly lower computational overhead and fewer trainable parameters.

This framework surveys manipulation, navigation, locomotion, autonomous driving, and general embodied learning, tracing technical progressions, clarifying capability requirements, and examining datasets, benchmarks, and evaluation protocols.

OPDVR transforms the landscape of model distillation by ensuring that only correct trajectories enhance learning, leading to significant performance gains on reasoning tasks.

Bypassing final-layer perturbations can significantly enhance reasoning capabilities in aligned LLMs, achieving better performance with zero memory overhead.

MemoryVLA++ achieves up to 28% performance gains in robotic manipulation tasks by integrating memory and imagination, transforming how robots handle temporal dependencies.

Achieving comparable text-to-image quality with a linearized model that accelerates inference by up to 1.47 times, all while leveraging pretrained weights.

Decoupling visual perception from motor control in robot learning yields a 27% performance boost and better generalization.

Decomposing complex reasoning problems into verifiable subproblems unlocks significant performance gains in LLM reasoning, especially on hard problems previously stuck in gradient dead zones.