pith. sign in

Sharon Li

Identifiers

  • name variant Sharon Li 0.60 · backfill

Papers (21)

  1. Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents cs.LG · 2026 · author #6
  2. OpenHalDet: A Unified Benchmark for Hallucination Detection across Diverse Generation Scenarios cs.CL · 2026 · author #14
  3. Hide-and-Seek in Trajectories: Discovering Failure Signals for VLA Runtime Monitoring cs.RO · 2026 · author #7
  4. Cyclical Entropy Eruption: Entropy Dynamics in Agent Reinforcement Learning cs.LG · 2026 · author #3
  5. DECOR: Auditing LLM Deception via Information Manipulation Theory cs.CL · 2026 · author #5
  6. Auditing Agent Harness Safety cs.CL · 2026 · author #9
  7. Why Multimodal In-Context Learning Lags Behind? Unveiling the Inner Mechanisms and Bottlenecks cs.CV · 2026 · author #2
  8. TorchUMM: A Unified Multimodal Model Codebase for Evaluation, Analysis, and Post-training cs.AI · 2026 · author #8
  9. Can LLMs Learn to Reason Robustly under Noisy Supervision? cs.LG · 2026 · author #4
  10. Combating Data Laundering in LLM Training cs.CR · 2026 · author #3
  11. VAUQ: Vision-Aware Uncertainty Quantification for LVLM Self-Evaluation cs.CV · 2026 · author #5
  12. How Retrieved Context Shapes Internal Representations in RAG cs.CL · 2026 · author #2
  13. Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities cs.AI · 2026 · author #11
  14. How Do Transformers Learn to Associate Tokens: Gradient Leading Terms Bring Mechanistic Interpretability cs.CL · 2026 · author #4
  15. ModeX: Evaluator-Free Best-of-N Selection for Open-Ended Generation cs.CL · 2026 · author #2
  16. When Identity Skews Debate: Anonymization for Bias-Reduced Multi-Agent Reasoning cs.AI · 2025 · author #3
  17. Detecting Distillation Data from Reasoning Models cs.CL · 2025 · author #3
  18. Unsupervised Domain Adaptation for Binary Classification with an Unobservable Source Subpopulation stat.ML · 2025 · author #6
  19. GeoArena: Evaluating Open-World Geographic Reasoning in Large Vision-Language Models cs.CV · 2025 · author #4
  20. GeoRanker: Distance-Aware Ranking for Worldwide Image Geolocalization cs.CV · 2025 · author #5
  21. Distributional Statistics Restore Training Data Auditability in One-step Distilled Diffusion Models cs.LG · 2025 · author #3

Mentions

  • 2606.26080 #6 · arxiv_oai · confidence 0.70 Sharon Li
  • 2505.13731 #5 · arxiv_oai · confidence 0.70 Sharon Li
  • 2606.06959 #14 · arxiv_oai · confidence 0.70 Sharon Li
  • 2605.30834 #7 · arxiv_oai · confidence 0.70 Sharon Li
  • 2604.01904 #3 · arxiv_oai · confidence 0.70 Sharon Li
  • 2605.27954 #3 · arxiv_oai · confidence 0.70 Sharon Li
  • 2604.10784 #8 · arxiv_oai · confidence 0.70 Sharon Li
  • 2605.19270 #5 · arxiv_oai · confidence 0.70 Sharon Li
  • 2605.14271 #9 · arxiv_oai · confidence 0.70 Sharon Li

Frequent Coauthors