6 papers
Track4Action: Distilling World-Centric 3D Tracker into Vision-Language-Action Policies
Chenyi Wang, Xinkai Wang, Bokai Lin +4
Action labels tell a vision-language-action (VLA) policy which robot commands to imitate, but not how those commands change the 3D world. The aligned demonstration clip contains th…
ChronoFlow-Policy: Unifying Past-Current-Future Interaction Flow in Visuomotor Policy Learning
Bokai Lin, Yifu Xu, Xinyu Zhan +6
Visual signals play a crucial role in policy learning by enabling models to capture object motion and interaction dynamics. Just as humans reason about actions using both past expe…
LIDEA: Human-to-Robot Imitation Learning via Implicit Feature Distillation and Explicit Geometry Alignment
Yifu Xu, Bokai Lin, Xinyu Zhan +4
Scaling up robot learning is hindered by the scarcity of robotic demonstrations, whereas human videos offer a vast, untapped source of interaction data. However, bridging the embod…
MatryoshkaKV: Adaptive KV Compression via Trainable Orthogonal Projection
Bokai Lin, Zihao Zeng, Zipeng Xiao +5
KV cache has become a de facto technique for the inference of large language models (LLMs), where tensors of shape (layer number, head number, sequence length, feature dimension) a…
In-context KV-Cache Eviction for LLMs via Attention-Gate
Zihao Zeng, Bokai Lin, Tianqi Hou +2
The KV-Cache technique has become the standard for the inference of large language models (LLMs). Yet, it is widely criticized that KV-Cache can become a bottleneck of the LLM infe…
Improved Operator Learning by Orthogonal Attention
Zipeng Xiao, Zhongkai Hao, Bokai Lin +2
Neural operators, as an efficient surrogate model for learning the solutions of PDEs, have received extensive attention in the field of scientific machine learning. Among them, att…