PPaperPicks

Zheng Lin

Chinese Academy of Sciences, Institute of Information Engineering, Bejing, China

34 papers at tracked venues · 28 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Breaking the Trade-Off Between Faithfulness and Expressiveness for Large Language Models
  2. ExDR: Explanation-driven Dynamic Retrieval Enhancement for Multimodal Fake News Detection
  3. IO-RAE: Information-Obfuscation Reversible Adversarial Example for Audio Privacy Protection
  4. LWGR: Lagrangian-Constrained Personalized World Knowledge for Generative Recommendation
  5. Test-time Prompt Intervention
  6. VecInfer: Efficient LLM Inference with Low-Bit KV Cache via Outlier-Suppressed Vector Quantization
  7. Adapt Once, Thrive with Updates: Transferable Parameter-Efficient Fine-Tuning on Evolving Base Models
  8. AutoPrompt: Automated Red-Teaming of Text-to-Image Models via LLM-Driven Adversarial Prompts
  9. BeamLoRA: Beam-Constraint Low-Rank Adaptation
  10. Bridging the Gap: Aligning Language Model Generation with Structured Information Extraction via Controllable State Transition
  11. CBP-Tuning: Efficient Local Customization for Black-box Large Language Models
  12. Categorical Attention: Fine-grained Language-guided Noise Filtering Network for Occluded Person Re-Identification
  13. DIVE into MoE: Diversity-Enhanced Reconstruction of Large Language Models from Dense into Mixture-of-Experts
  14. Incorporating Communication Style and Interaction of Speakers for Sarcasm Explanation in Dialogue
  15. Mitigating the Evolving Semantic Entanglement in Continual Learning of Vision-Language Models
  16. Multimodal Hypothetical Summary for Retrieval-based Multi-image Question Answering
  17. NeedleInATable: Exploring Long-Context Capability of Large Language Models towards Long-Structured Tables
  18. PIG: Privacy Jailbreak Attack on LLMs via Gradient-based Iterative In-Context Optimization
  19. Relation Also Knows: Rethinking the Recall and Editing of Factual Associations in Auto-Regressive Transformer Language Models
  20. Robust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attacks
  21. TableDreamer: Progressive and Weakness-guided Data Synthesis from Scratch for Table Instruction Tuning
  22. TailorKV: A Hybrid Framework for Long-Context Inference via Tailored KV Cache Optimization
  23. Trust-GRS: A Trustworthy Training Framework for Graph Neural Network Based Recommender Systems Against Shilling Attacks
  24. Two-Stage Adversarial Training for Deep Hashing via Representation Distillation
  25. Weights-Rotated Preference Optimization for Large Language Models
  26. A Pedestrian is Worth One Prompt: Towards Language Guidance Person Re- Identification
  27. Disrupting Diffusion: Token-Level Attention Erasure Attack against Diffusion-based Customization
  28. Light-PEFT: Lightening Parameter-Efficient Fine-Tuning via Early Pruning
  29. Multimodal Table Understanding
  30. Object Attribute Matters in Visual Question Answering
  31. Prediction Exposes Your Face: Black-Box Model Inversion via Prediction Alignment
  32. Pruning Large Language Models to Intra-module Low-rank Architecture with Transitional Activations
  33. Towards Flexible Evaluation for Generative Visual Question Answering
  34. Towards One-to-Many Visual Question Answering