PPaperPicks

Sharon Li

University of Wisconsin-Madison, Department of Computer Sciences, Madison, WI, USA

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

DBLP profile ↗ORCID 0000-0003-3479-4323 ↗Google Scholar ↗Homepage ↗

Venues

NeurIPS ×15ACL ×10ICLR ×8ICML ×8AAAI ×1CVPR ×1WWW ×1

Frequent coauthors

Hyeong Kyu Choi
DBLP profile ↗ORCID search ↗
×4
Changdae Oh
DBLP profile ↗ORCID search ↗
×4
Seongheon Park
DBLP profile ↗ORCID search ↗
×3
Xuefeng Du
DBLP profile ↗ORCID search ↗
×3
Pengyue Jia
DBLP profile ↗ORCID search ↗
×2
Samuel Yeh
DBLP profile ↗ORCID search ↗
×2
Wendi Li
DBLP profile ↗ORCID search ↗
×2
Shawn Im
DBLP profile ↗ORCID search ↗
×2
Leitian Tao
DBLP profile ↗ORCID search ↗
×2
Yu Wang
DBLP profile ↗ORCID search ↗
×1
Jihye Choi
DBLP profile ↗ORCID search ↗
×1
Shenzhi Yang
DBLP profile ↗ORCID search ↗
×1

Papers

  1. GeoArena: Evaluating Open-World Geographic Reasoning in Large Vision-Language Models
    ACL 2026 ·
    Pengyue Jia
    DBLP profile ↗ORCID search ↗
  2. How Retrieved Context Shapes Internal Representations in RAG
    ACL 2026 ·
    Samuel Yeh
    DBLP profile ↗ORCID search ↗
  3. LAD: Learning Advantage Distribution for Reasoning
    ACL 2026 ·
    Wendi Li
    DBLP profile ↗ORCID search ↗
  4. ModeX: Evaluator-Free Best-of-N Selection for Open-Ended Generation
    ACL 2026 ·
    Hyeong Kyu Choi
    DBLP profile ↗ORCID search ↗
  5. Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities
    ACL 2026 ·
    Changdae Oh
    DBLP profile ↗ORCID search ↗
  6. VAUQ: Vision-Aware Uncertainty Quantification for LVLM Self-Evaluation
    ACL 2026 ·
    Seongheon Park
    DBLP profile ↗ORCID search ↗
  7. When Identity Skews Debate: Anonymization for Bias-Reduced Multi-Agent Reasoning
    ACL 2026 ·
    Hyeong Kyu Choi
    DBLP profile ↗ORCID search ↗
  8. Why Multimodal In-Context Learning Lags Behind? Unveiling the Inner Mechanisms and Bottlenecks
    ACL 2026 ·
    Yu Wang
    DBLP profile ↗ORCID search ↗
  9. CONDA: Adaptive Concept Bottleneck for Foundation Models Under Distribution Shifts
    ICLR 2025 ·
    Jihye Choi
    DBLP profile ↗ORCID search ↗
  10. Can DPO Learn Diverse Human Values? A Theoretical Scaling Law
    NeurIPS 2025 ·
    Shawn Im
    DBLP profile ↗ORCID search ↗
  11. Clean First, Align Later: Benchmarking Preference Data Cleaning for Reliable LLM Alignment
    NeurIPS 2025 ·
    Samuel Yeh
    DBLP profile ↗ORCID search ↗
  12. DaWin: Training-free Dynamic Weight Interpolation for Robust Adaptation
    ICLR 2025 ·
    Changdae Oh
    DBLP profile ↗ORCID search ↗
  13. Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?
    NeurIPS 2025 ·
    Hyeong Kyu Choi
    DBLP profile ↗ORCID search ↗
  14. GLSim: Detecting Object Hallucinations in LVLMs via Global-Local Similarity
    NeurIPS 2025 ·
    Seongheon Park
    DBLP profile ↗ORCID search ↗
  15. GeoRanker: Distance-Aware Ranking for Worldwide Image Geolocalization
    NeurIPS 2025 ·
    Pengyue Jia
    DBLP profile ↗ORCID search ↗
  16. Harnessing Feature Resonance under Arbitrary Target Alignment for Out-of-Distribution Node Detection
    NeurIPS 2025 ·
    Shenzhi Yang
    DBLP profile ↗ORCID search ↗
  17. How Contaminated Is Your Benchmark? Measuring Dataset Leakage in Large Language Models with Kernel Divergence
    ICML 2025 ·
    Hyeong Kyu Choi
    DBLP profile ↗ORCID search ↗
  18. Limited Preference Data? Learning Better Reward Model with Latent Space Synthesis
    NeurIPS 2025 ·
    Leitian Tao
    DBLP profile ↗ORCID search ↗
  19. MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent Systems
    NeurIPS 2025 ·
    Xuanming Zhang
    DBLP profile ↗ORCID search ↗
  20. Position: Challenges and Future Directions of Data-Centric AI Alignment
    ICML 2025 ·
    Min-Hsuan Yeh
    DBLP profile ↗ORCID search ↗
  21. Process Reward Model with Q-value Rankings
    ICLR 2025 ·
    Wendi Li
    DBLP profile ↗ORCID search ↗
  22. Prompt Candidates, then Distill: A Teacher-Student Framework for LLM-driven Data Annotation
    ACL 2025 ·
    Mingxuan Xia
    DBLP profile ↗ORCID search ↗
  23. Steer LLM Latents for Hallucination Detection
    ICML 2025 ·
    Seongheon Park
    DBLP profile ↗ORCID search ↗
  24. Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders
    NeurIPS 2025 ·
    James Oldfield
    DBLP profile ↗ORCID search ↗
  25. Understanding Multimodal LLMs Under Distribution Shifts: An Information-Theoretic Approach
    ICML 2025 ·
    Changdae Oh
    DBLP profile ↗ORCID search ↗
  26. Understanding and Mitigating Miscalibration in Prompt Tuning for Vision-Language Models
    ICML 2025 ·
    Shuoyuan Wang
    DBLP profile ↗ORCID search ↗
  27. Unsolvable Problem Detection: Robust Understanding Evaluation for Large Multimodal Models
    ACL 2025 ·
    Atsuyuki Miyai
    DBLP profile ↗ORCID search ↗
  28. Visual Instruction Bottleneck Tuning
    NeurIPS 2025 ·
    Changdae Oh
    DBLP profile ↗ORCID search ↗
  29. Your Pre-trained LLM is Secretly an Unsupervised Confidence Calibrator
    NeurIPS 2025 ·
    Beier Luo
    DBLP profile ↗ORCID search ↗
  30. Your Weak LLM is Secretly a Strong Teacher for Alignment
    ICLR 2025 ·
    Leitian Tao
    DBLP profile ↗ORCID search ↗
  31. ARGS: Alignment as Reward-Guided Search
    ICLR 2024 ·
    Maxim Khanov
    DBLP profile ↗ORCID search ↗
  32. BackdoorAlign: Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment
    NeurIPS 2024 ·
    Jiongxiao Wang
    DBLP profile ↗ORCID search ↗
  33. Bridging OOD Detection and Generalization: A Graph-Theoretic View
    NeurIPS 2024 ·
    Han Wang
    DBLP profile ↗ORCID search ↗
  34. ConjNorm: Tractable Density Estimation for Out-of-Distribution Detection
    ICLR 2024 ·
    Bo Peng
    DBLP profile ↗ORCID search ↗
  35. DCAI: Data-centric Artificial Intelligence
    WWW 2024 ·
    Wei Jin
    DBLP profile ↗ORCID search ↗
  36. HYPO: Hyperspherical Out-Of-Distribution Generalization
    ICLR 2024 ·
    Haoyue Bai
    DBLP profile ↗ORCID search ↗
  37. HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection
    NeurIPS 2024 ·
    Xuefeng Du
    DBLP profile ↗ORCID search ↗
  38. How Does Unlabeled Data Provably Help Out-of-Distribution Detection?
    ICLR 2024 ·
    Xuefeng Du
    DBLP profile ↗ORCID search ↗
  39. How to Overcome Curse-of-Dimensionality for Out-of-Distribution Detection?
    AAAI 2024 ·
    Soumya Suvra Ghosal
    DBLP profile ↗ORCID search ↗
  40. Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models
    NeurIPS 2024 ·
    Jiayu Wang
    DBLP profile ↗ORCID search ↗
  41. Targeted Representation Alignment for Open-World Semi-Supervised Learning
    CVPR 2024 ·
    Ruixuan Xiao
    DBLP profile ↗ORCID search ↗
  42. Understanding Retrieval-Augmented Task Adaptation for Vision-Language Models
    ICML 2024 ·
    Yifei Ming
    DBLP profile ↗ORCID search ↗
  43. Understanding the Learning Dynamics of Alignment with Human Feedback
    ICML 2024 ·
    Shawn Im
    DBLP profile ↗ORCID search ↗
  44. When and How Does In-Distribution Label Help Out-of-Distribution Detection?
    ICML 2024 ·
    Xuefeng Du
    DBLP profile ↗ORCID search ↗