Accepted abstracts (2026)

2026

1. How Sampling Shapes LLM Alignment: From One-Shot Optima to Iterative Dynamics

   Yurong Chen, Yu He, Michael I. Jordan, and Fan Yao

   2026

   Bib

   @article{paper19,
     title = {How Sampling Shapes LLM Alignment: From One-Shot Optima to Iterative Dynamics},
     author = {Chen, Yurong and He, Yu and Jordan, Michael I. and Yao, Fan},
     year = {2026}
   }

2. INFUSER: Influence-Guided Self-Evolution Improves Reasoning

   Siyu Chen, Miao Lu, Beining Wu, Heejune Sheen, Fengzhuo Zhang, Shuangning Li, Zhiyuan Li, Jose Blanchet, Tianhao Wang, and Zhuoran Yang

   2026

   Bib

   @article{paper20,
     title = {INFUSER: Influence-Guided Self-Evolution Improves Reasoning},
     author = {Chen, Siyu and Lu, Miao and Wu, Beining and Sheen, Heejune and Zhang, Fengzhuo and Li, Shuangning and Li, Zhiyuan and Blanchet, Jose and Wang, Tianhao and Yang, Zhuoran},
     year = {2026}
   }

3. Behavior Cloning is Not All You Need: The Optimality of On-Policy Distillation for Noisy Expert Feedback

   Ved Sriraman, Peihan Liu, Daniel Hsu, and Adam Block

   2026

   Bib

   @article{paper21,
     title = {Behavior Cloning is Not All You Need: The Optimality of On-Policy Distillation for Noisy Expert Feedback},
     author = {Sriraman, Ved and Liu, Peihan and Hsu, Daniel and Block, Adam},
     year = {2026}
   }

4. Pass@k Learning from Suboptimal Demonstrations

   Chandramauli Chakraborty and Cong Ma

   2026

   Bib

   @article{paper22,
     title = {{Pass@k} Learning from Suboptimal Demonstrations},
     author = {Chakraborty, Chandramauli and Ma, Cong},
     year = {2026}
   }

5. On the Emergence of Implicit Curriculum in RLVR Learning Dynamics

   Yu Huang, Zixin Wen, Yuejie Chi, Yuting Wei, Aarti Singh, Yingbin Liang, and Yuxin Chen

   2026

   Bib

   @article{paper23,
     title = {On the Emergence of Implicit Curriculum in RLVR Learning Dynamics},
     author = {Huang, Yu and Wen, Zixin and Chi, Yuejie and Wei, Yuting and Singh, Aarti and Liang, Yingbin and Chen, Yuxin},
     year = {2026}
   }

6. VGB for Masked Diffusion Model: Efficient Test-time Scaling for Reward Satisfaction and Sample Editing

   Kijung Jeon, Thuy-Duong Vuong, and Molei Tao

   2026

   Bib

   @article{paper24,
     title = {VGB for Masked Diffusion Model: Efficient Test-time Scaling for Reward Satisfaction and Sample Editing},
     author = {Jeon, Kijung and Vuong, Thuy-Duong and Tao, Molei},
     year = {2026}
   }

7. Betting Loss Beyond Realizability: Limits of Squared Error and Variance-Adaptive L^1 Bound

   Yinan Li and Kwang-Sung Jun

   2026

   Bib

   @article{paper25,
     title = {Betting Loss Beyond Realizability: Limits of Squared Error and Variance-Adaptive $L^1$ Bound},
     author = {Li, Yinan and Jun, Kwang-Sung},
     year = {2026}
   }

8. Reinforcement Learning from Rich Feedback with Distributional DAgger

   Rishabh Agrawal, Jacob Fein-Ashley, and Paria Rashidinejad

   2026

   Bib

   @article{paper26,
     title = {Reinforcement Learning from Rich Feedback with Distributional DAgger},
     author = {Agrawal, Rishabh and Fein-Ashley, Jacob and Rashidinejad, Paria},
     year = {2026}
   }

9. Policy optimization goes beyond sharpening of base models

   Audrey Huang, Sadhika Malladi, Akshay Krishnamurthy, Nan Jiang, and Dylan J Foster

   2026

   Bib

   @article{paper27,
     title = {Policy optimization goes beyond sharpening of base models},
     author = {Huang, Audrey and Malladi, Sadhika and Krishnamurthy, Akshay and Jiang, Nan and Foster, Dylan J},
     year = {2026}
   }

10. Reasoning with Sampling: Cutting at Decision Points

    Felix Zhou, Anay Mehrotra, and Quanquan C. Liu

    2026

    Bib

    @article{paper28,
      title = {Reasoning with Sampling: Cutting at Decision Points},
      author = {Zhou, Felix and Mehrotra, Anay and Liu, Quanquan C.},
      year = {2026}
    }

11. Adaptive Generate-Rank-Verify: Inference-Time Search with Costly Verification

    Shaddin Dughmi, Mahdi Haghifam, and Yusuf Hakan Kalayci

    2026

    Bib

    @article{paper29,
      title = {Adaptive Generate-Rank-Verify: Inference-Time Search with Costly Verification},
      author = {Dughmi, Shaddin and Haghifam, Mahdi and Kalayci, Yusuf Hakan},
      year = {2026}
    }