PPaperPicks

Yi R. Fung

Hong Kong University of Science and Technology, Department of Computer Science and Engineering, Hong Kong

26 papers at tracked venues · 17 at CORE A* · active 2024–2026

DBLP profile ↗ORCID search ↗Google Scholar ↗Homepage ↗

Venues

ACL ×14EMNLP ×6NAACL ×2AAAI ×1ICLR ×1MLSys ×1NeurIPS ×1

Frequent coauthors

Zhiyuan Fan
DBLP profile ↗ORCID search ↗
×3
Yee Man Choi
DBLP profile ↗ORCID search ↗
×1
Jiayu Liu
DBLP profile ↗ORCID search ↗
×1
Zheyu Fan
DBLP profile ↗ORCID search ↗
×1
Dadi Guo
DBLP profile ↗ORCID search ↗
×1
Qi He
DBLP profile ↗ORCID search ↗
×1
Yumeng Wang
DBLP profile ↗ORCID search ↗
×1
Ruida Wang
DBLP profile ↗ORCID search ↗
×1
Junsheng Huang
DBLP profile ↗ORCID search ↗
×1
Zhitao He
DBLP profile ↗ORCID search ↗
×1
Minghao Liu
DBLP profile ↗ORCID search ↗
×1
Hengzhi Li
DBLP profile ↗ORCID search ↗
×1

Papers

  1. CiteGuard: Faithful Citation Attribution for LLMs via Retrieval-Augmented Validation
    ACL 2026 ·
    Yee Man Choi
    DBLP profile ↗ORCID search ↗
  2. CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents
    ACL 2026 ·
    Jiayu Liu
    DBLP profile ↗ORCID search ↗
  3. EMCompress: Video-LLMs with Endomorphic Multimodal Compression
    ACL 2026 ·
    Zheyu Fan
    DBLP profile ↗ORCID search ↗
  4. Learning Diverse Responses with Prefix-Conditioned Supervised Fine-Tuning
    ACL 2026 ·
    Zhiyuan Fan
    DBLP profile ↗ORCID search ↗
  5. Mathematical Proof as a Litmus Test: Revealing Failure Modes of Advanced Large Reasoning Models
    ACL 2026 ·
    Dadi Guo
    DBLP profile ↗ORCID search ↗
  6. Scaling Human-Centric Trustworthy Foundation Model via Advanced Reasoning and Agentic Frameworks
    AAAI 2026 · Yi Ren Fung
  7. Veri-R1: Toward Precise and Faithful Claim Verification via Online Reinforcement Learning
    ACL 2026 ·
    Qi He
    DBLP profile ↗ORCID search ↗
  8. CALM: Unleashing the Cross-Lingual Self-Aligning Ability of Language Model Question Answering
    NAACL 2025 ·
    Yumeng Wang
    DBLP profile ↗ORCID search ↗
  9. End-to-End Optimization for Multimodal Retrieval-Augmented Generation via Reward Backpropagation
    EMNLP 2025 ·
    Zhiyuan Fan
    DBLP profile ↗ORCID search ↗
  10. Let's Reason Formally: Natural-Formal Hybrid Reasoning Enhances LLM's Math Capability
    EMNLP 2025 ·
    Ruida Wang
    DBLP profile ↗ORCID search ↗
  11. MAC-Tuning: LLM Multi-Compositional Problem Reasoning with Enhanced Knowledge Boundary Awareness
    EMNLP 2025 ·
    Junsheng Huang
    DBLP profile ↗ORCID search ↗
  12. MMBoundary: Advancing MLLM Knowledge Boundary Awareness through Reasoning Step Confidence Calibration
    ACL 2025 ·
    Zhitao He
    DBLP profile ↗ORCID search ↗
  13. MedEBench: Diagnosing Reliability in Text-Guided Medical Image Editing
    EMNLP 2025 ·
    Minghao Liu
    DBLP profile ↗ORCID search ↗
  14. MimeQA: Towards Socially-Intelligent Nonverbal Foundation Models
    NeurIPS 2025 ·
    Hengzhi Li
    DBLP profile ↗ORCID search ↗
  15. Self-Correction is More than Refinement: A Learning Framework for Visual and Language Reasoning Tasks
    ACL 2025 ·
    Jiayi He
    DBLP profile ↗ORCID search ↗
  16. Spa: Scaling Graph Neural Network Training on Large graphs via Probabilistic splitting
    MLSys 2025 ·
    Sandeep Polisetty
    DBLP profile ↗ORCID search ↗
  17. TAMP: Token-Adaptive Layerwise Pruning in Multimodal Large Language Models
    ACL 2025 ·
    Jaewoo Lee
    DBLP profile ↗ORCID search ↗
  18. The Law of Knowledge Overshadowing: Towards Understanding, Predicting and Preventing LLM Hallucination
    ACL 2025 ·
    Yuji Zhang
    DBLP profile ↗ORCID search ↗
  19. Unveiling the Lack of LVLM Robustness to Fundamental Visual Variations: Why and Path Forward
    ACL 2025 ·
    Zhiyuan Fan
    DBLP profile ↗ORCID search ↗
  20. VLM2-Bench: A Closer Look at How Well VLMs Implicitly Link Explicit Matching Visual Cues
    ACL 2025 ·
    Jianshu Zhang
    DBLP profile ↗ORCID search ↗
  21. CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets
    ICLR 2024 ·
    Lifan Yuan
    DBLP profile ↗ORCID search ↗
  22. Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning
    ACL 2024 ·
    Kung-Hsiang Huang
    DBLP profile ↗ORCID search ↗
  23. MACAROON: Training Vision-Language Models To Be Your Engaged Partners
    EMNLP 2024 ·
    Shujin Wu
    DBLP profile ↗ORCID search ↗
  24. R-Tuning: Instructing Large Language Models to Say 'I Don't Know'
    NAACL 2024 ·
    Hanning Zhang
    DBLP profile ↗ORCID search ↗
  25. Schema-Guided Culture-Aware Complex Event Simulation with Multi-Agent Role-Play
    EMNLP 2024 ·
    Sha Li
    DBLP profile ↗ORCID search ↗
  26. Word Embeddings Are Steers for Language Models
    ACL 2024 ·
    Chi Han
    DBLP profile ↗ORCID search ↗