Donglin Wang

papers

737

total citations

papers (22)

Pareto Self-Supervised Training for Few-Shot Learning

CVPR 2021arXiv

135

citations

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

AAAI 2025arXiv

110

citations

Prompt-Based Distribution Alignment for Unsupervised Domain Adaptation

AAAI 2024arXiv

citations

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

CVPR 2023arXiv

citations

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

ICLR 2025arXiv

citations

ReinboT: Amplifying Robot Visual-Language Manipulation with Reinforcement Learning

ICML 2025arXiv

citations

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

CVPR 2024arXiv

citations

CEIL: Generalized Contextual Imitation Learning

NEURIPS 2023arXiv

citations

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

NEURIPS 2025arXiv

citations

Unsupervised Domain Adaptation with Dynamics-Aware Rewards in Reinforcement Learning

NEURIPS 2021arXiv

citations

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

ICLR 2025arXiv

citations

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

NEURIPS 2023arXiv

citations

Expressive Forecasting of 3D Whole-Body Human Motions

AAAI 2024arXiv

citations

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

ICML 2025arXiv

citations

DIDI: Diffusion-Guided Diversity for Offline Behavioral Generation

ICML 2024arXiv

citations

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

AAAI 2025arXiv

citations

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

AAAI 2025arXiv

citations

Donglin Wang

papers (22)

Pareto Self-Supervised Training for Few-Shot Learning

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

Prompt-Based Distribution Alignment for Unsupervised Domain Adaptation

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

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

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

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

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

Reinformer: Max-Return Sequence Modeling for Offline RL

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

ReinboT: Amplifying Robot Visual-Language Manipulation with Reinforcement Learning

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

CEIL: Generalized Contextual Imitation Learning

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

Unsupervised Domain Adaptation with Dynamics-Aware Rewards in Reinforcement Learning

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

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

Expressive Forecasting of 3D Whole-Body Human Motions

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

DIDI: Diffusion-Guided Diversity for Offline Behavioral Generation

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

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

papers (22)

Pareto Self-Supervised Training for Few-Shot Learning

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

Prompt-Based Distribution Alignment for Unsupervised Domain Adaptation

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

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

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

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

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

Reinformer: Max-Return Sequence Modeling for Offline RL

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

ReinboT: Amplifying Robot Visual-Language Manipulation with Reinforcement Learning

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

CEIL: Generalized Contextual Imitation Learning

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

Unsupervised Domain Adaptation with Dynamics-Aware Rewards in Reinforcement Learning

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

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

Expressive Forecasting of 3D Whole-Body Human Motions

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

DIDI: Diffusion-Guided Diversity for Offline Behavioral Generation

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

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