Profiles2021-2026ORCID 0000-0002-8188-3735
Donglin Wang
Westlake University
35Papers
28Last author
38Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers35
- Balancing Signal and Variance: Adaptive Offline RL Post-Training for VLA Flow ModelsAuthor 7 of 7AAAI 2026 · 11 citations
- Activation-wise Propagation: A One-Timestep Strategy for Spiking Neural NetworksAuthor 4 of 4AAAI 2026
- Dyn-VPP: Video Prediction Policy Optimization for Improved Visual DynamicsAuthor 17 of 17ICML 2026
- Rethinking Target Label Conditioning in Adversarial Attacks: A 2D Tensor-Guided Generative ApproachAuthor 4 of 4AAAI 2026
- Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient InferenceAuthor 6 of 6AAAI 2025 · 125 citations
- SSR: Enhancing Depth Perception in Vision-Language Models via Rationale-Guided Spatial ReasoningAuthor 8 of 8NeurIPS 2025 · 46 citations
- CARP: Visuomotor Policy Learning via Coarse-to-Fine Autoregressive PredictionAuthor 8 of 8ICCV 2025 · 3 citations
- CSL-L2M: Controllable Song-Level Lyric-to-Melody Generation Based on Conditional Transformer with Fine-Grained Lyric and Musical ControlsAuthor 2 of 2AAAI 2025 · 1 citation
- GEVRM: Goal-Expressive Video Generation Model For Robust Visual ManipulationAuthor 5 of 5ICLR 2025
- MGDA: Model-based Goal Data Augmentation for Offline Goal-conditioned Weighted Supervised LearningAuthor 3 of 3AAAI 2025
- ReinboT: Amplifying Robot Visual-Language Manipulation with Reinforcement LearningAuthor 6 of 6ICML 2025
- Rethinking Latent Redundancy in Behavior Cloning: An Information Bottleneck Approach for Robot ManipulationAuthor 5 of 6ICML 2025
- Score-Based Diffusion Policy Compatible with Reinforcement Learning via Optimal TransportAuthor 4 of 4ICML 2025
- VLAS: Vision-Language-Action Model with Speech Instructions for Customized Robot ManipulationAuthor 7 of 7ICLR 2025
- Beyond OOD State Actions: Supported Cross-Domain Offline Reinforcement LearningAuthor 7 of 7AAAI 2024 · 30 citations
- Reinformer: Max-Return Sequence Modeling for Offline RLAuthor 5 of 5ICML 2024 · 29 citations
- ProFD: Prompt-Guided Feature Disentangling for Occluded Person Re-IdentificationAuthor 6 of 6ACM MM 2024 · 18 citations
- DIDI: Diffusion-Guided Diversity for Offline Behavioral GenerationAuthor 4 of 4ICML 2024 · 3 citations
- Nash CoT: Multi-Path Inference with Preference EquilibriumAuthor 5 of 5EMNLP 2024 · 1 citation
- Learning Disentangled Identifiers for Action-Customized Text-to-Image GenerationAuthor 7 of 7CVPR 2024
- Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot LearningAuthor 6 of 6CVPR 2024
- Beyond Reward: Offline Preference-guided Policy OptimizationAuthor 5 of 5ICML 2023 · 41 citations
- CEIL: Generalized Contextual Imitation LearningAuthor 5 of 6NeurIPS 2023 · 23 citations
- Design from Policies: Conservative Test-Time Adaptation for Offline Policy OptimizationAuthor 5 of 6NeurIPS 2023 · 15 citations
- Behavior Proximal Policy OptimizationAuthor 4 of 5ICLR 2023 · 8 citations
- VoP: Text-Video Co-Operative Prompt Tuning for Cross-Modal RetrievalAuthor 7 of 7CVPR 2023
- DARA: Dynamics-Aware Reward Augmentation in Offline Reinforcement LearningAuthor 3 of 3ICLR 2022 · 47 citations
- Learning on Graphs with Out-of-Distribution NodesAuthor 2 of 2KDD 2022 · 28 citations
- Learn Goal-Conditioned Policy with Intrinsic Motivation for Deep Reinforcement LearningAuthor 2 of 4AAAI 2022 · 27 citations
- A General Offline Reinforcement Learning Framework for Interactive RecommendationAuthor 2 of 2AAAI 2021 · 82 citations
Showing the 30 most recent indexed papers.
