5 papers
PACE: Phase-Aware Chunk Execution for Robot Policies with Action Chunking
Junnan Nie, Jiayi Li, Jiachen Zhang +5
Recent vision-language-action and diffusion-based robot policies often use action chunking, where each policy query predicts a sequence of future actions and the robot executes an…
BAT-Nav: Belief-Based Arbitration and Termination via Remaining Discoverability in Multi-Goal Semantic Navigation
Xi Lin, Kangyi Wu, Jiayi Li +3
Multi-goal semantic navigation couples searches through a shrinking horizon: effort spent on one request can make another effectively undiscoverable. Discoverability therefore depe…
Accelerating Diffusion Models for Inverse Problems through Shortcut Sampling
Gongye Liu, Haoze Sun, Jiayi Li +2
Diffusion models have recently demonstrated an impressive ability to address inverse problems in an unsupervised manner. While existing methods primarily focus on modifying the pos…
Weight-Inherited Distillation for Task-Agnostic BERT Compression
Taiqiang Wu, Cheng Hou, Shanshan Lao +4
Knowledge Distillation (KD) is a predominant approach for BERT compression. Previous KD-based methods focus on designing extra alignment losses for the student model to mimic the b…
ACDER: Augmented Curiosity-Driven Experience Replay
Boyao Li, Tao Lu, Jiayi Li +3
Exploration in environments with sparse feedback remains a challenging research problem in reinforcement learning (RL). When the RL agent explores the environment randomly, it resu…