Xuefeng Li

Orcid: 0009-0007-3683-7901

Affiliations:
  • Shanghai Jiao Tong University (SJTU), Shanghai, China
  • Generative AI Research Lab (GAIR), Shanghai, China


According to our database1, Xuefeng Li authored at least 13 papers between 2024 and 2025.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2025
OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling.
CoRR, June, 2025

Generative AI Act II: Test Time Scaling Drives Cognition Engineering.
CoRR, April, 2025

ToRL: Scaling Tool-Integrated RL.
CoRR, March, 2025

LIMR: Less is More for RL Scaling.
CoRR, February, 2025

Progress or Regress? Self-Improvement Reversal in Post-training.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Evaluating Mathematical Reasoning Beyond Accuracy.
Proceedings of the AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25, 2025

2024
O1 Replication Journey - Part 2: Surpassing O1-preview through Simple Distillation, Big Progress or Bitter Lesson?
CoRR, 2024

O1 Replication Journey: A Strategic Progress Report - Part 1.
CoRR, 2024

OpenResearcher: Unleashing AI for Accelerated Scientific Research.
CoRR, 2024

MultiSPANS: A Multi-range Spatial-Temporal Transformer Network for Traffic Forecast via Structural Entropy Optimization.
Proceedings of the 17th ACM International Conference on Web Search and Data Mining, 2024

MathPile: A Billion-Token-Scale Pretraining Corpus for Math.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Reformatted Alignment.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024


  Loading...