pith. sign in

Deqing Yang

Identifiers

  • name variant Deqing Yang 0.60 · backfill

Papers (7)

  1. Deep Research as Rubric for Reinforcement Learning cs.CL · 2026 · author #12
  2. ProRL: Effective Reinforcement Learning for Proactive Recommendation via Rectified Policy Gradient Estimation cs.LG · 2026 · author #8
  3. M3D-Stereo: A Multiple-Medium and Multiple-Degradation Dataset for Stereo Image Restoration cs.CV · 2026 · author #1
  4. Good Reasoning Makes Good Demonstrations: Implicit Reasoning Quality Supervision via In-Context Reinforcement Learning cs.LG · 2026 · author #8
  5. Outcome-Grounded Advantage Reshaping for Fine-Grained Credit Assignment in Mathematical Reasoning cs.CL · 2026 · author #8
  6. Confidence Estimation for LLMs in Multi-turn Interactions cs.CL · 2026 · author #7
  7. What Makes an Ideal Quote? Recommending "Unexpected yet Rational" Quotations via Novelty cs.IR · 2025 · author #6

Mentions

  • 2603.09803 #8 · arxiv_oai · confidence 0.70 Deqing Yang
  • 2601.07408 #8 · arxiv_oai · confidence 0.70 Deqing Yang
  • 2606.01091 #12 · arxiv_oai · confidence 0.70 Deqing Yang
  • 2605.28293 #8 · arxiv_oai · confidence 0.70 Deqing Yang

Frequent Coauthors