PPaperPicks

Zhifang Sui

28 papers at tracked venues · 20 at CORE A* · active 2024–2026

DBLP profile ↗ORCID search ↗

Venues

ACL ×14EMNLP ×7AAAI ×4CVPR ×1ICLR ×1NAACL ×1

Frequent coauthors

Rui Li
DBLP profile ↗ORCID search ↗
×3
Jingyuan Ma
DBLP profile ↗ORCID search ↗
×2
Yixin Yang
DBLP profile ↗ORCID search ↗
×2
Xiaochen Wang
DBLP profile ↗ORCID search ↗
×2
Zhe Yang
DBLP profile ↗ORCID search ↗
×2
Yudong Wang
DBLP profile ↗ORCID search ↗
×2
Qingxiu Dong
DBLP profile ↗ORCID search ↗
×2
Peiyi Wang
DBLP profile ↗ORCID search ↗
×2
Zhengyu Chen
DBLP profile ↗ORCID search ↗
×1
Yi Jing
DBLP profile ↗ORCID search ↗
×1
Zheng Li
DBLP profile ↗ORCID search ↗
×1
Rui Li
DBLP profile ↗ORCID search ↗
×1

Papers

  1. From Mathematical Reasoning to Code: Generalization of Process Reward Models in Test-Time Scaling
    AAAI 2026 ·
    Zhengyu Chen
    DBLP profile ↗ORCID search ↗
  2. HAUNTATTACK: When Attack Follows Reasoning as a Shadow
    ACL 2026 ·
    Jingyuan Ma
    DBLP profile ↗ORCID search ↗
  3. HistLens: Mapping Idea Change across Concepts and Corpora
    ACL 2026 ·
    Yi Jing
    DBLP profile ↗ORCID search ↗
  4. Large Language Models Struggle with Unreasonability in Math Problems
    AAAI 2026 ·
    Jingyuan Ma
    DBLP profile ↗ORCID search ↗
  5. RICo: Refined In-Context Contribution for Automatic Instruction-Tuning Data Selection
    AAAI 2026 ·
    Yixin Yang
    DBLP profile ↗ORCID search ↗
  6. SelfBudgeter: Adaptive Token Allocation for Efficient LLM Reasoning
    ACL 2026 ·
    Zheng Li
    DBLP profile ↗ORCID search ↗
  7. SenseJudge: Human-Centric Preference-Driven Judgment Framework
    ACL 2026 ·
    Rui Li
    DBLP profile ↗ORCID search ↗
  8. Towards Stable and Effective Reinforcement Learning for Mixture-of-Experts
    ACL 2026 ·
    Di Zhang
    DBLP profile ↗ORCID search ↗
  9. A Probabilistic Inference Scaling Theory for LLM Self-Correction
    EMNLP 2025 ·
    Zhe Yang
    DBLP profile ↗ORCID search ↗
  10. AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization
    CVPR 2025 ·
    Yiyang Du
    DBLP profile ↗ORCID search ↗
  11. Beyond Single Frames: Can LMMs Comprehend Implicit Narratives in Comic Strip?
    EMNLP 2025 ·
    Xiaochen Wang
    DBLP profile ↗ORCID search ↗
  12. Confidence v.s. Critique: A Decomposition of Self-Correction Capability for LLMs
    ACL 2025 ·
    Zhe Yang
    DBLP profile ↗ORCID search ↗
  13. Exploring Activation Patterns of Parameters in Language Models
    AAAI 2025 ·
    Yudong Wang
    DBLP profile ↗ORCID search ↗
  14. How Far are LLMs from Being Our Digital Twins? A Benchmark for Persona-Based Behavior Chain Simulation
    ACL 2025 ·
    Rui Li
    DBLP profile ↗ORCID search ↗
  15. SG-FSM: A Self-Guiding Zero-Shot Prompting Paradigm for Multi-Hop Question Answering Based on Finite State Machine
    NAACL 2025 ·
    Xiaochen Wang
    DBLP profile ↗ORCID search ↗
  16. Self-Boosting Large Language Models with Synthetic Preference Data
    ICLR 2025 ·
    Qingxiu Dong
    DBLP profile ↗ORCID search ↗
  17. Towards Harmonized Uncertainty Estimation for Large Language Models
    ACL 2025 ·
    Rui Li
    DBLP profile ↗ORCID search ↗
  18. A Survey on In-context Learning
    EMNLP 2024 ·
    Qingxiu Dong
    DBLP profile ↗ORCID search ↗
  19. Achilles-Bench: A Challenging Benchmark for Low-Resource Evaluation
    ACL 2024 ·
    Yudong Wang
    DBLP profile ↗ORCID search ↗
  20. Be a Multitude to Itself: A Prompt Evolution Framework for Red Teaming
    EMNLP 2024 ·
    Rui Li
    DBLP profile ↗ORCID search ↗
  21. Can Large Language Models Always Solve Easy Problems if They Can Solve Harder Ones?
    EMNLP 2024 ·
    Zhe Yang
    DBLP profile ↗ORCID search ↗
  22. Can Large Multimodal Models Uncover Deep Semantics Behind Images?
    ACL 2024 ·
    Yixin Yang
    DBLP profile ↗ORCID search ↗
  23. DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models
    ACL 2024 ·
    Damai Dai
    DBLP profile ↗ORCID search ↗
  24. Large Language Models are not Fair Evaluators
    ACL 2024 ·
    Peiyi Wang
    DBLP profile ↗ORCID search ↗
  25. Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations
    ACL 2024 ·
    Peiyi Wang
    DBLP profile ↗ORCID search ↗
  26. ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors
    EMNLP 2024 ·
    Zhexin Zhang
    DBLP profile ↗ORCID search ↗
  27. Taking a Deep Breath: Enhancing Language Modeling of Large Language Models with Sentinel Tokens
    EMNLP 2024 ·
    Weiyao Luo
    DBLP profile ↗ORCID search ↗
  28. Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding
    ACL 2024 ·
    Heming Xia
    DBLP profile ↗ORCID search ↗