Donglin Wang

22

Papers

365

Total Citations

Papers (22)

Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference

Prompt-Based Distribution Alignment for Unsupervised Domain Adaptation

VLAS: Vision-Language-Action Model with Speech Instructions for Customized Robot Manipulation

Beyond OOD State Actions: Supported Cross-Domain Offline Reinforcement Learning

CARP: Visuomotor Policy Learning via Coarse-to-Fine Autoregressive Prediction

Learning Disentangled Identifiers for Action-Customized Text-to-Image Generation

ReinboT: Amplifying Robot Visual-Language Manipulation with Reinforcement Learning

SSR: Enhancing Depth Perception in Vision-Language Models via Rationale-Guided Spatial Reasoning

GEVRM: Goal-Expressive Video Generation Model For Robust Visual Manipulation

Expressive Forecasting of 3D Whole-Body Human Motions

Score-Based Diffusion Policy Compatible with Reinforcement Learning via Optimal Transport

MGDA: Model-based Goal Data Augmentation for Offline Goal-conditioned Weighted Supervised Learning

Tree Structure-Aware Few-Shot Image Classification via Hierarchical Aggregation

DIDI: Diffusion-Guided Diversity for Offline Behavioral Generation

Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot Learning

CSL-L2M: Controllable Song-Level Lyric-to-Melody Generation Based on Conditional Transformer with Fine-Grained Lyric and Musical Controls

Reinformer: Max-Return Sequence Modeling for Offline RL

Pareto Self-Supervised Training for Few-Shot Learning

VoP: Text-Video Co-Operative Prompt Tuning for Cross-Modal Retrieval

Unsupervised Domain Adaptation with Dynamics-Aware Rewards in Reinforcement Learning

Design from Policies: Conservative Test-Time Adaptation for Offline Policy Optimization

CEIL: Generalized Contextual Imitation Learning