PPaperPicks

Zuchao Li

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

Venues

Frequent coauthors

Papers

  1. BoYaEval: Evaluating Multimodal Large Language Models on Understanding Ancient Chinese Musical Scores
  2. End-to-End Contrastive Language-Speech Pretraining Model for Long-Form Spoken Question Answering
  3. Faster MoE LLM Inference for Extremely Large Models
  4. From AR to Diffusion: Efficiently Adapting Large Language Models with Strictly Causal and Elastic Horizons
  5. Ghost in the Transformer: Detecting Model Reuse with Invariant Spectral Signatures
  6. GoT-R1: Internalizing Graph-of-Thought via Structural Reinforcement for High-Density Reasoning
    ACL 2026 · Zuchao Li
  7. PAR: Training-Free Positional Perturbation and Attention Recycling for Faithful OCR
  8. RACER: Retrieval-Augmented Contextual Rapid Speculative Decoding
  9. Scaling LLM Speculative Decoding: Non-Autoregressive Forecasting in Large-Batch Scenarios
  10. TRACE: Traversal Retrieval-Augmented Chain of Evidence for Document Understanding
  11. TrigReason: Trigger-Based Collaboration between Small and Large Reasoning Models
  12. VCB Bench: An Evaluation Benchmark for Audio-Grounded Large Language Model Conversational Agents
  13. Vista-LLM: Decoupled Query-Guided Visual Token Pruning for Efficient Long-Video Large Language Models
  14. AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders
  15. Can Large Language Models Be Good Language Teachers?
  16. CoViPAL: Layer-wise Contextualized Visual Token Pruning for Large Vision-Language Models
  17. DAC: A Dynamic Attention-aware Approach for Task-Agnostic Prompt Compression
  18. Dialogue-RAG: Enhancing Retrieval for LLMs via Node-Linking Utterance Rewriting
  19. Faster In-Context Learning for LLMs via N-Gram Trie Speculative Decoding
  20. From Parameters to Performance: A Data-Driven Study on LLM Structure and Development
  21. IAM: Efficient Inference through Attention Mapping between Different-scale LLMs
  22. Imitate Before Detect: Aligning Machine Stylistic Preference for Machine-Revised Text Detection
  23. KV-Latent: Dimensional-level KV Cache Reduction with Frequency-aware Rotary Positional Embedding
  24. Label Drop for Multi-Aspect Relation Modeling in Universal Information Extraction
  25. NOTA: Multimodal Music Notation Understanding for Visual Large Language Model
  26. Segment First or Comprehend First? Explore the Limit of Unsupervised Word Segmentation with Large Language Models
  27. SmallKV: Small Model Assisted Compensation of KV Cache Compression for Efficient LLM Inference
  28. SongSong: A Time Phonograph for Chinese SongCi Music from Thousand of Years Away
  29. SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers
  30. Teaching Your Models to Understand Code via Focal Preference Alignment
  31. ToM: Leveraging Tree-oriented MapReduce for Long-Context Reasoning in Large Language Models
  32. What Limits Bidirectional Model's Generative Capabilities? A Uni-Bi-Directional Mixture-of-Expert Method For Bidirectional Fine-tuning
    ICML 2025 · Zuchao Li
  33. XQuant: Achieving Ultra-Low Bit KV Cache Quantization with Cross-Layer Compression
  34. A Coin Has Two Sides: A Novel Detector-Corrector Framework for Chinese Spelling Correction
  35. A Novel Energy Based Model Mechanism for Multi-Modal Aspect-Based Sentiment Analysis
  36. GKT: A Novel Guidance-Based Knowledge Transfer Framework For Efficient Cloud-edge Collaboration LLM Deployment
  37. GoT: Effective Graph-of-Thought Reasoning in Language Models
  38. Hypergraph based Understanding for Document Semantic Entity Recognition
  39. Multi-Modal Latent Space Learning for Chain-of-Thought Reasoning in Language Models
  40. Multi-modal Auto-regressive Modeling via Visual Tokens
  41. N-gram Unsupervised Compoundation and Feature Injection for Better Symbolic Music Understanding
  42. Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models
  43. Selective Prefix Tuning for Pre-trained Language Models
  44. SirLLM: Streaming Infinite Retentive LLM
  45. Sparse is Enough in Fine-tuning Pre-trained Large Language Models
  46. The Music Maestro or The Musically Challenged, A Massive Music Evaluation Benchmark for Large Language Models
  47. VHASR: A Multimodal Speech Recognition System With Vision Hotwords