PPaperPicks

Yichen Zhu

Midea Group, AI Lab, Shanghai, Guangdong, China

17 papers at tracked venues · 9 at CORE A* · active 20242025

Venues

Frequent coauthors

Papers

  1. A Comprehensive Overhaul of Multimodal Assistant with Small Language Models
  2. ChatVLA-2: Vision-Language-Action Model with Open-World Reasoning
  3. ChatVLA: Unified Multimodal Understanding and Robot Control with Vision-Language-Action Model
  4. CoA-VLA: Improving Vision-Language-Action Models via Visual-Textual Chain-of-Affordance
  5. DiffusionVLA: Scaling Robot Foundation Models via Unified Diffusion and Autoregression
  6. Discrete Policy: Learning Disentangled Action Space for Multi-Task Robotic Manipulation
  7. Let Me Show You: Learning by Retrieving from Egocentric Video for Robotic Manipulation
    IROS 2025 · Yichen Zhu
  8. Scaling Diffusion Policy in Transformer to 1 Billion Parameters for Robotic Manipulation
  9. Any2Policy: Learning Visuomotor Policy with Any-Modality
    NeurIPS 2024 · Yichen Zhu
  10. EDT: An Efficient Diffusion Transformer Framework Inspired by Human-like Sketching
  11. EPSD: Early Pruning with Self-Distillation for Efficient Model Compression
  12. Exploring Gradient Explosion in Generative Adversarial Imitation Learning: A Probabilistic Perspective
  13. Language-Conditioned Robotic Manipulation with Fast and Slow Thinking
  14. MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models
  15. Object-Centric Instruction Augmentation for Robotic Manipulation
  16. Retrieval-Augmented Embodied Agents
    CVPR 2024 · Yichen Zhu
  17. Safety of Multimodal Large Language Models on Images and Text