Chenglin Li

8

Papers

2

Total Citations

Papers (8)

METEOR: Multi-Encoder Collaborative Token Pruning for Efficient Vision Language Models

Tilted Quantile Gradient Updates for Quantile-Constrained Reinforcement Learning

LBI-FL: Low-Bit Integerized Federated Learning with Temporally Dynamic Bit-Width Allocation

Improving Diffusion Models for Inverse Problems Using Optimal Posterior Covariance

Bootstrap AutoEncoders With Contrastive Paradigm for Self-supervised Gaze Estimation

Stabilizing and Accelerating Autofocus with Expert Trajectory Regularized Deep Reinforcement Learning

AMPA: Adaptive Mixed Precision Allocation for Low-Bit Integer Training

HiPART: Hierarchical Pose AutoRegressive Transformer for Occluded 3D Human Pose Estimation