pith. the verified trust layer for science. sign in

Xiaoye Qu

Identifiers

  • name variant Xiaoye Qu 0.60 · backfill

Papers (8)

  1. $\pi$-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows cs.AI · 2026 · author #11
  2. Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling cs.AI · 2026 · author #20
  3. Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs cs.CV · 2026 · author #2
  4. VCE: A zero-cost hallucination mitigation method of LVLMs via visual contrastive editing cs.CV · 2026 · author #4
  5. A Survey of Reinforcement Learning for Large Reasoning Models cs.CL · 2025 · author #28
  6. Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers cs.CV · 2025 · author #6
  7. OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learning cs.CV · 2025 · author #10
  8. Learning to Reason under Off-Policy Guidance cs.LG · 2025 · author #6

Mentions

  • 2509.08827 #28 · arxiv_oai · confidence 0.70 Xiaoye Qu
  • 2505.08617 #10 · arxiv_oai · confidence 0.70 Xiaoye Qu
  • 2504.14945 #6 · arxiv_oai · confidence 0.70 Xiaoye Qu

Frequent Coauthors