Get started
Author

Xiaotong Ji

Observed name: Ji, Xiaotong
OpenAlex ID: A5124441334
The $\mathbf{Y}$-Combinator for LLMs: Solving Long-Context Rot with $λ$-Calculus
2026 · Roy, Amartya, Tutunov, Rasul, et al. · arXiv (Cornell University) · 1
PDF
iSDFT: Information-Proximal Self-Distillation for Continual Learning in LLMs
2026 · Khamis, Ahmed Khaled, Ji, Xiaotong, et al. · arXiv (Cornell University)
PDF
Risk-Controlled Lean-as-Judge for Natural-Language Mathematical Reasoning
2026 · Bourigault, Pauline, Ji, Xiaotong, et al. · arXiv (Cornell University)
PDF
The Model Knows, the Decoder Finds: Future Value Guided Particle Power Sampling
2026 · Nguyen, Tu, Zimmer, Matthieu, et al. · arXiv (Cornell University)
PDF
Decoding as Optimisation on the Probability Simplex: From Top-K to Top-P (Nucleus) to Best-of-K Samplers
2026 · Ji, Xiaotong, Tutunov, Rasul, et al. · arXiv (Cornell University)
PDF
Multi-Task GRPO: Reliable LLM Reasoning Across Tasks
2026 · Ramesh, Shyam Sundhar, Ji, Xiaotong, et al. · arXiv (Cornell University)
PDF
Scalable Power Sampling: Unlocking Efficient, Training-Free Reasoning for LLMs via Distribution Sharpening
2026 · Ji, Xiaotong, Tutunov, Rasul, et al. · arXiv (Cornell University)
PDF
Works count: 7
Citation count: 1
H-index: 1
I10-index:
Year
Topic
Type