PPaperPicks

Hai Zhao

Shanghai Jiao Tong University, Department of Computer Science and Engineering, China

63 papers at tracked venues · 44 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0001-7290-0487 ↗Google Scholar ↗Homepage ↗

Venues

ACL ×31EMNLP ×15AAAI ×5NeurIPS ×4NAACL ×3ICML ×2ACM MM ×1ECAI ×1ICLR ×1

Frequent coauthors

Yao Yao
DBLP profile ↗ORCID search ↗
×4
Zouying Cao
DBLP profile ↗ORCID search ↗
×4
Yi Zhao
DBLP profile ↗ORCID search ↗
×4
Dongjie Yang
DBLP profile ↗ORCID search ↗
×4
Luohe Shi
DBLP profile ↗ORCID search ↗
×3
Xinbei Ma
DBLP profile ↗ORCID search ↗
×3
Weiqi Wu
DBLP profile ↗ORCID search ↗
×3
Junlong Li
DBLP profile ↗ORCID search ↗
×3
Jiajia Li
DBLP profile ↗ORCID search ↗
×2
Haoqi Yang
DBLP profile ↗ORCID search ↗
×2
Zuchao Li
DBLP profile ↗ORCID search ↗
×2
Zihong Zhang
DBLP profile ↗ORCID search ↗
×2

Papers

  1. BoYaEval: Evaluating Multimodal Large Language Models on Understanding Ancient Chinese Musical Scores
    ACL 2026 ·
    Jiajia Li
    DBLP profile ↗ORCID search ↗
  2. Faster MoE LLM Inference for Extremely Large Models
    ACL 2026 ·
    Haoqi Yang
    DBLP profile ↗ORCID search ↗
  3. GoT-R1: Internalizing Graph-of-Thought via Structural Reinforcement for High-Density Reasoning
    ACL 2026 ·
    Zuchao Li
    DBLP profile ↗ORCID search ↗
  4. PAR: Training-Free Positional Perturbation and Attention Recycling for Faithful OCR
    ACL 2026 ·
    Yao Yao
    DBLP profile ↗ORCID search ↗
  5. ParaCook: On Time-Efficient Planning for Multi-Agent Systems
    ACL 2026 ·
    Shiqi Zhang
    DBLP profile ↗ORCID search ↗
  6. RACER: Retrieval-Augmented Contextual Rapid Speculative Decoding
    ACL 2026 ·
    Zihong Zhang
    DBLP profile ↗ORCID search ↗
  7. Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution
    ACL 2026 ·
    Zouying Cao
    DBLP profile ↗ORCID search ↗
  8. Scaling LLM Speculative Decoding: Non-Autoregressive Forecasting in Large-Batch Scenarios
    AAAI 2026 ·
    Luohe Shi
    DBLP profile ↗ORCID search ↗
  9. TrigReason: Trigger-Based Collaboration between Small and Large Reasoning Models
    ACL 2026 ·
    Yi Zhao
    DBLP profile ↗ORCID search ↗
  10. Can Large Language Models Be Good Language Teachers?
    EMNLP 2025 ·
    LiQing Xu
    DBLP profile ↗ORCID search ↗
  11. Caution for the Environment: Multimodal LLM Agents are Susceptible to Environmental Distractions
    ACL 2025 ·
    Xinbei Ma
    DBLP profile ↗ORCID search ↗
  12. CoViPAL: Layer-wise Contextualized Visual Token Pruning for Large Vision-Language Models
    EMNLP 2025 ·
    Zicong Tang
    DBLP profile ↗ORCID search ↗
  13. DAC: A Dynamic Attention-aware Approach for Task-Agnostic Prompt Compression
    ACL 2025 ·
    Yi Zhao
    DBLP profile ↗ORCID search ↗
  14. Dialogue-RAG: Enhancing Retrieval for LLMs via Node-Linking Utterance Rewriting
    ACL 2025 ·
    Qiwei Li
    DBLP profile ↗ORCID search ↗
  15. Evolving Chinese Spelling Correction with Corrector-Verifier Collaboration
    EMNLP 2025 ·
    Linfeng Liu
    DBLP profile ↗ORCID search ↗
  16. Faster In-Context Learning for LLMs via N-Gram Trie Speculative Decoding
    EMNLP 2025 ·
    Jinglin Chen
    DBLP profile ↗ORCID search ↗
  17. From Parameters to Performance: A Data-Driven Study on LLM Structure and Development
    EMNLP 2025 ·
    Suqing Wang
    DBLP profile ↗ORCID search ↗
  18. Game Development as Human-LLM Interaction
    ACL 2025 ·
    Jiale Hong
    DBLP profile ↗ORCID search ↗
  19. IAM: Efficient Inference through Attention Mapping between Different-scale LLMs
    ACL 2025 ·
    Yi Zhao
    DBLP profile ↗ORCID search ↗
  20. KV-Latent: Dimensional-level KV Cache Reduction with Frequency-aware Rotary Positional Embedding
    ACL 2025 ·
    Luohe Shi
    DBLP profile ↗ORCID search ↗
  21. LESA: Learnable LLM Layer Scaling-Up
    ACL 2025 ·
    Yifei Yang
    DBLP profile ↗ORCID search ↗
  22. MEGen: Generative Backdoor into Large Language Models via Model Editing
    ACL 2025 ·
    Jiyang Qiu
    DBLP profile ↗ORCID search ↗
  23. Open-Theatre: An Open-Source Toolkit for LLM-based Interactive Drama
    EMNLP 2025 ·
    Tianyang Xu
    DBLP profile ↗ORCID search ↗
  24. PGPO: Enhancing Agent Reasoning via Pseudocode-style Planning Guided Preference Optimization
    ACL 2025 ·
    Zouying Cao
    DBLP profile ↗ORCID search ↗
  25. SCANS: Mitigating the Exaggerated Safety for LLMs via Safety-Conscious Activation Steering
    AAAI 2025 ·
    Zouying Cao
    DBLP profile ↗ORCID search ↗
  26. Segment First or Comprehend First? Explore the Limit of Unsupervised Word Segmentation with Large Language Models
    ACL 2025 ·
    Zihong Zhang
    DBLP profile ↗ORCID search ↗
  27. SmallKV: Small Model Assisted Compensation of KV Cache Compression for Efficient LLM Inference
    NeurIPS 2025 ·
    Yi Zhao
    DBLP profile ↗ORCID search ↗
  28. ToM: Leveraging Tree-oriented MapReduce for Long-Context Reasoning in Large Language Models
    EMNLP 2025 ·
    Jiani Guo
    DBLP profile ↗ORCID search ↗
  29. Towards Enhanced Immersion and Agency for LLM-based Interactive Drama
    ACL 2025 ·
    Hongqiu Wu
    DBLP profile ↗ORCID search ↗
  30. Unfolding the Headline: Iterative Self-Questioning for News Retrieval and Timeline Summarization
    NAACL 2025 ·
    Weiqi Wu
    DBLP profile ↗ORCID search ↗
  31. What Limits Bidirectional Model's Generative Capabilities? A Uni-Bi-Directional Mixture-of-Expert Method For Bidirectional Fine-tuning
    ICML 2025 ·
    Zuchao Li
    DBLP profile ↗ORCID search ↗
  32. Wide-Horizon Thinking and Simulation-Based Evaluation for Real-World LLM Planning with Multifaceted Constraints
    NeurIPS 2025 ·
    Dongjie Yang
    DBLP profile ↗ORCID search ↗
  33. X-TURING: Towards an Enhanced and Efficient Turing Test for Long-Term Dialogue Agents
    ACL 2025 ·
    Weiqi Wu
    DBLP profile ↗ORCID search ↗
  34. XQuant: Achieving Ultra-Low Bit KV Cache Quantization with Cross-Layer Compression
    EMNLP 2025 ·
    Haoqi Yang
    DBLP profile ↗ORCID search ↗
  35. A Coin Has Two Sides: A Novel Detector-Corrector Framework for Chinese Spelling Correction
    ECAI 2024 ·
    Xiangke Zeng
    DBLP profile ↗ORCID search ↗
  36. A Novel Energy Based Model Mechanism for Multi-Modal Aspect-Based Sentiment Analysis
    AAAI 2024 ·
    Tianshuo Peng
    DBLP profile ↗ORCID search ↗
  37. Are LLMs Aware that Some Questions are not Open-ended?
    EMNLP 2024 ·
    Dongjie Yang
    DBLP profile ↗ORCID search ↗
  38. CMMLU: Measuring massive multitask language understanding in Chinese
    ACL 2024 ·
    Haonan Li
    DBLP profile ↗ORCID search ↗
  39. Chinese Spelling Correction as Rephrasing Language Model
    AAAI 2024 ·
    Linfeng Liu
    DBLP profile ↗ORCID search ↗
  40. Chinese Spelling Corrector Is Just a Language Learner
    ACL 2024 ·
    Lai Jiang
    DBLP profile ↗ORCID search ↗
  41. CoCo-Agent: A Comprehensive Cognitive MLLM Agent for Smartphone GUI Automation
    ACL 2024 ·
    Xinbei Ma
    DBLP profile ↗ORCID search ↗
  42. Dissecting Human and LLM Preferences
    ACL 2024 ·
    Junlong Li
    DBLP profile ↗ORCID search ↗
  43. Fact-Driven Logical Reasoning for Machine Reading Comprehension
    AAAI 2024 ·
    Siru Ouyang
    DBLP profile ↗ORCID search ↗
  44. From Role-Play to Drama-Interaction: An LLM Solution
    ACL 2024 ·
    Weiqi Wu
    DBLP profile ↗ORCID search ↗
  45. GKT: A Novel Guidance-Based Knowledge Transfer Framework For Efficient Cloud-edge Collaboration LLM Deployment
    ACL 2024 ·
    Yao Yao
    DBLP profile ↗ORCID search ↗
  46. GLaPE: Gold Label-agnostic Prompt Evaluation for Large Language Models
    EMNLP 2024 ·
    Xuanchang Zhang
    DBLP profile ↗ORCID search ↗
  47. Generative Judge for Evaluating Alignment
    ICLR 2024 ·
    Junlong Li
    DBLP profile ↗ORCID search ↗
  48. GoT: Effective Graph-of-Thought Reasoning in Language Models
    NAACL 2024 ·
    Yao Yao
    DBLP profile ↗ORCID search ↗
  49. Head-wise Shareable Attention for Large Language Models
    EMNLP 2024 ·
    Zouying Cao
    DBLP profile ↗ORCID search ↗
  50. Hypergraph based Understanding for Document Semantic Entity Recognition
    ACL 2024 ·
    Qiwei Li
    DBLP profile ↗ORCID search ↗
  51. Instruction-Driven Game Engine: A Poker Case Study
    EMNLP 2024 ·
    Hongqiu Wu
    DBLP profile ↗ORCID search ↗
  52. LaCo: Large Language Model Pruning via Layer Collapse
    EMNLP 2024 ·
    Yifei Yang
    DBLP profile ↗ORCID search ↗
  53. Multi-modal Auto-regressive Modeling via Visual Tokens
    ACM MM 2024 ·
    Tianshuo Peng
    DBLP profile ↗ORCID search ↗
  54. On the Robustness of Editing Large Language Models
    EMNLP 2024 ·
    Xinbei Ma
    DBLP profile ↗ORCID search ↗
  55. PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference
    ACL 2024 ·
    Dongjie Yang
    DBLP profile ↗ORCID search ↗
  56. Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models
    NeurIPS 2024 ·
    Luohe Shi
    DBLP profile ↗ORCID search ↗
  57. Selective Prefix Tuning for Pre-trained Language Models
    ACL 2024 ·
    Hongyi Zhang
    DBLP profile ↗ORCID search ↗
  58. Self-Prompting Large Language Models for Zero-Shot Open-Domain QA
    NAACL 2024 ·
    Junlong Li
    DBLP profile ↗ORCID search ↗
  59. SirLLM: Streaming Infinite Retentive LLM
    ACL 2024 ·
    Yao Yao
    DBLP profile ↗ORCID search ↗
  60. Sparse is Enough in Fine-tuning Pre-trained Large Language Models
    ICML 2024 ·
    Weixi Song
    DBLP profile ↗ORCID search ↗
  61. The Music Maestro or The Musically Challenged, A Massive Music Evaluation Benchmark for Large Language Models
    ACL 2024 ·
    Jiajia Li
    DBLP profile ↗ORCID search ↗
  62. VHASR: A Multimodal Speech Recognition System With Vision Hotwords
    EMNLP 2024 ·
    Jiliang Hu
    DBLP profile ↗ORCID search ↗
  63. Vript: A Video Is Worth Thousands of Words
    NeurIPS 2024 ·
    Dongjie Yang
    DBLP profile ↗ORCID search ↗