PPaperPicks

Yi Lu

23 papers at tracked venues · 14 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. CoGR-MoE: Concept-Guided Expert Routing with Consistent Selection and Flexible Reasoning for Visual Question Answering
  2. ReviewGrounder: Improving Review Substantiveness with Rubric-Guided, Tool-Integrated Agents
  3. SWE-QA-Pro: A Representative Benchmark and Scalable Training Recipe for Repository-Level Code Understanding
  4. Unlearning in Cross-Modal Retrieval via Prior-Prototype Guided Partitioned Dampening
    AAAI 2026 · Yi Lu
  5. Graph-Guided Dual-Level Augmentation for 3D Scene Segmentation
  6. Mitigating Object Hallucinations in MLLMs via Multi-Frequency Perturbations
  7. MotionPRO: Exploring the Role of Pressure in Human MoCap and Beyond
  8. RSVP: Reasoning Segmentation via Visual Prompting and Multi-modal Chain-of-Thought
    ACL 2025 · Yi Lu
  9. Understanding Parametric and Contextual Knowledge Reconciliation within Large Language Models
  10. VEU-Bench: Towards Comprehensive Understanding of Video Editing
  11. Video Repurposing from User Generated Content: A Large-scale Dataset and Benchmark
  12. VisualLens: Personalization through Task-Agnostic Visual History
  13. APDDv2: Aesthetics of Paintings and Drawings Dataset with Artist Labeled Scores and Comments
  14. Codecfake: An Initial Dataset for Detecting LLM-based Deepfake Audio
  15. Generalized Fake Audio Detection via Deep Stable Learning
  16. Genuine-Focused Learning using Mask AutoEncoder for Generalized Fake Audio Detection
  17. LONGAGENT: Achieving Question Answering for 128k-Token-Long Documents through Multi-Agent Collaboration
  18. Leveraging RGB-Pressure for Whole-body Human-to-Humanoid Motion Imitation
    ACM MM 2024 · Yi Lu
  19. LongHeads: Multi-Head Attention is Secretly a Long Context Processor
    EMNLP 2024 · Yi Lu
  20. Making Harmful Behaviors Unlearnable for Large Language Models
  21. PPPR: Portable Plug-in Prompt Refiner for Text to Audio Generation
  22. Paintings and Drawings Aesthetics Assessment with Rich Attributes for Various Artistic Categories
  23. Self-Demos: Eliciting Out-of-Demonstration Generalizability in Large Language Models