Tianyi Chen

15

Papers

64

Total Citations

Papers (15)

Efficient Online Reinforcement Learning for Diffusion Policy

DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs

DREAM: Diffusion Rectification and Estimation-Adaptive Models

AFL: A Single-Round Analytic Approach for Federated Learning with Pre-trained Models

Why 1 + 1 < 1 in Visual Token Pruning: Beyond Naive Integration via Multi-Objective Balanced Covering

SpotDiff: Spatial Gene Expression Imputation Diffusion with Single-Cell RNA Sequencing Data Integration

ReCAP: Recursive Context-Aware Reasoning and Planning for Large Language Model Agents

Automatic Joint Structured Pruning and Quantization for Efficient Neural Network Training and Compression

Principled Penalty-based Methods for Bilevel Reinforcement Learning and RLHF

Achilles' Heel of Mamba: Essential difficulties of the Mamba architecture demonstrated by synthetic data

3DHumanEdit: Multi-modal Body Part-aware Conditioning Information Integration for 3D Human Manipulation

RetouchFormer: Semi-supervised High-Quality Face Retouching Transformer with Prior-Based Selective Self-Attention

AttriHuman-3D: Editable 3D Human Avatar Generation with Attribute Decomposition and Indexing

DistiLLM: Towards Streamlined Distillation for Large Language Models

SF-DQN: Provable Knowledge Transfer using Successor Feature for Deep Reinforcement Learning