Get started
Author

Shrey Pandit

Observed name: Pandit, Shrey
OpenAlex ID: A5124020904
FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"
2024 · Ming, Yifei, Purushwalkam, Senthil, et al. · arXiv (Cornell University) · 3
PDF
CodeUpdateArena: Benchmarking Knowledge Editing on API Updates
2024 · Liu, Zeyu Leo, Pandit, Shrey, et al. · arXiv (Cornell University) · 3
PDF
SFR-RAG: Towards Contextually Faithful LLMs
2024 · Nguyen, Xuan-Phi, Pandit, Shrey, et al. · arXiv (Cornell University) · 2
PDF
Flattening Every Memory Peak in Long-Context Mixture-of-Experts Training
2026 · Pandit, Shrey, Nguyen, Xuan-Phi, et al. · arXiv (Cornell University)
PDF
Privileged Likelihood Is Not Automatically Value: Three Checks for Token Credit in On-Policy Self-Distillation
2026 · Nguyen, Xuan-Phi, Liu, Zeyu Leo, et al. · arXiv (Cornell University)
PDF
Mixture-of-Parallelisms: Towards Memory-Efficient Training Stack for Mixture-of-Experts Models
2026 · Nguyen, Xuan-Phi, Pandit, Shrey, et al. · arXiv (Cornell University)
PDF
Hard2Verify: A Step-Level Verification Benchmark for Open-Ended Frontier Math
2026 · Association for Computational Linguistics 2026, Joty, Shafiq, et al. · Underline Science Inc.
Least-Loaded Expert Parallelism: Load Balancing An Imbalanced Mixture-of-Experts
2026 · Nguyen, Xuan-Phi, Pandit, Shrey, et al. · arXiv (Cornell University)
PDF
Hard2Verify: A Step-Level Verification Benchmark for Open-Ended Frontier Math
2026 · Shrey Pandit, Austin Xu, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
SFR-DeepResearch: Towards Effective Reinforcement Learning for Autonomously Reasoning Single Agents
2025 · Nguyen, Xuan-Phi, Pandit, Shrey, et al. · arXiv (Cornell University)
PDF
Works count: 11
Citation count: 8
H-index: 2
I10-index:
Year
Topic
Type