pith. sign in

Junfeng Fang

Identifiers

  • name variant Junfeng Fang 0.60 · backfill

Papers (12)

  1. Learning to Act under Noise: Enhancing Agent Robustness via Noisy Environments cs.AI · 2026 · author #3
  2. UniVLR: Unifying Text and Vision in Visual Latent Reasoning for Multimodal LLMs cs.CV · 2026 · author #3
  3. Learning to Foresee: Unveiling the Unlocking Efficiency of On-Policy Distillation cs.CL · 2026 · author #12
  4. SOD: Step-wise On-policy Distillation for Small Language Model Agents cs.CL · 2026 · author #8
  5. SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation cs.CL · 2026 · author #8
  6. Rubric-based On-policy Distillation cs.LG · 2026 · author #1
  7. On the Implicit Reward Overfitting and the Low-rank Dynamics in RLVR cs.LG · 2026 · author #3
  8. MIRL: Mutual Information-Guided Reinforcement Learning for Vision-Language Models cs.CV · 2026 · author #5
  9. Mitigating Hallucinations in Large Vision-Language Models without Performance Degradation cs.CV · 2026 · author #2
  10. DRAFT: Task Decoupled Latent Reasoning for Agent Safety cs.LG · 2026 · author #2
  11. Revisiting Robustness for LLM Safety Alignment via Selective Geometry Control cs.LG · 2026 · author #5
  12. From System 1 to System 2: A Survey of Reasoning Large Language Models cs.AI · 2025 · author #17

Mentions

  • 2605.27209 #3 · arxiv_oai · confidence 0.70 Junfeng Fang
  • 2605.11739 #12 · arxiv_oai · confidence 0.70 Junfeng Fang
  • 2605.07711 #8 · arxiv_oai · confidence 0.70 Junfeng Fang
  • 2602.07340 #5 · arxiv_oai · confidence 0.70 Junfeng Fang

Frequent Coauthors