Donglin Wang

Activation-wise Propagation: A One-Timestep Strategy for Spiking Neural Networks AAAI 2026 Balancing Signal and Variance: Adaptive Offline RL Post-Training for VLA Flow Models AAAI 2026 CUBic: Coordinated Unified Bimanual Perception and Control Framework CVPR 2026 Filter, Correlate, Compress: Training-Free Token Reduction for MLLM Acceleration AAAI 2026 HiF-VLA: Hindsight, Insight and Foresight through Motion Representation for Vision-Language-Action Models CVPR 2026 ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceiver AAAI 2026 Rethinking Target Label Conditioning in Adversarial Attacks: A 2D Tensor-Guided Generative Approach AAAI 2026 VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model AAAI 2026 CARP: Visuomotor Policy Learning via Coarse-to-Fine Autoregressive Prediction ICCV 2025 Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference AAAI 2025 CSL-L2M: Controllable Song-Level Lyric-to-Melody Generation Based on Conditional Transformer with Fine-Grained Lyric and Musical Controls AAAI 2025 GEVRM: Goal-Expressive Video Generation Model For Robust Visual Manipulation ICLR 2025 Long-VLA: Unleashing Long-Horizon Capability of Vision Language Action Model for Robot Manipulation CoRL 2025 MGDA: Model-based Goal Data Augmentation for Offline Goal-conditioned Weighted Supervised Learning AAAI 2025 ReinboT: Amplifying Robot Visual-Language Manipulation with Reinforcement Learning ICML 2025 Rethinking Latent Redundancy in Behavior Cloning: An Information Bottleneck Approach for Robot Manipulation ICML 2025 Score-Based Diffusion Policy Compatible with Reinforcement Learning via Optimal Transport ICML 2025 Stay Hungry, Keep Learning: Sustainable Plasticity for Deep Reinforcement Learning ICML 2025 VLAS: Vision-Language-Action Model with Speech Instructions for Customized Robot Manipulation ICLR 2025 Beyond OOD State Actions: Supported Cross-Domain Offline Reinforcement Learning AAAI 2024 DIDI: Diffusion-Guided Diversity for Offline Behavioral Generation ICML 2024 Expressive Forecasting of 3D Whole-Body Human Motions AAAI 2024 Learning Disentangled Identifiers for Action-Customized Text-to-Image Generation CVPR 2024 Nash CoT: Multi-Path Inference with Preference Equilibrium EMNLP 2024 PiTe: Pixel-Temporal Alignment for Large Video-Language Model ECCV 2024 Prompt-Based Distribution Alignment for Unsupervised Domain Adaptation AAAI 2024 QUAR-VLA: Vision-Language-Action Model for Quadruped Robots ECCV 2024 Reinformer: Max-Return Sequence Modeling for Offline RL ICML 2024 RL2AC: Reinforcement Learning-based Rapid Online Adaptive Control for Legged Robot Robust Locomotion RSS 2024 Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot Learning CVPR 2024 Behavior Proximal Policy Optimization ICLR 2023 Beyond Reward: Offline Preference-guided Policy Optimization ICML 2023 CEIL: Generalized Contextual Imitation Learning NeurIPS 2023 CLUE: Calibrated Latent Guidance for Offline Reinforcement Learning CoRL 2023 Design from Policies: Conservative Test-Time Adaptation for Offline Policy Optimization NeurIPS 2023 VoP: Text-Video Co-Operative Prompt Tuning for Cross-Modal Retrieval CVPR 2023 DARA: Dynamics-Aware Reward Augmentation in Offline Reinforcement Learning ICLR 2022 End-to-End Open-Set Semi-Supervised Node Classification with Out-of-Distribution Detection IJCAI 2022 Learn Goal-Conditioned Policy with Intrinsic Motivation for Deep Reinforcement Learning AAAI 2022 Learning to Evolve on Dynamic Graphs (Student Abstract) AAAI 2022 Tree Structure-Aware Few-Shot Image Classification via Hierarchical Aggregation ECCV 2022 A General Offline Reinforcement Learning Framework for Interactive Recommendation AAAI 2021 Attributes-Guided and Pure-Visual Attention Alignment for Few-Shot Recognition AAAI 2021 Deep Transfer Tensor Decomposition with Orthogonal Constraint for Recommender Systems AAAI 2021 Pareto Self-Supervised Training for Few-Shot Learning CVPR 2021 Unsupervised Domain Adaptation with Dynamics-Aware Rewards in Reinforcement Learning NeurIPS 2021 Independent Skill Transfer for Deep Reinforcement Learning IJCAI 2020