Author

Shrey Pandit

University of Texas at Austin

h-index 9 Homepage View on Semantic Scholar

We have 2 of 20 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Sep 2026

Flattening Every Memory Peak in Long-Context Mixture-of-Experts Training

Four parallelism plans are left unbounded by the parallelism plans in common use, and each grows differently: expert dispatch with the routing matrix, the vocabulary projection with tokens times vocabulary, gradient checkpoint boundaries with depth times sequence length, and optimizer state with parameter count.

Shrey Pandit, Xuan-Phi Nguyen, Yiran Zhao et al. · 0 citations

Preprint Aug 2026

Privileged Likelihood Is Not Automatically Value: Three Checks for Token Credit in On-Policy Self-Distillation

The results suggest that dense credit assignment through distillation can be effective when its likelihood-based scores are empirically validated as meaningful proxies for outcome-relevant credit, when this alignment does not hold.

Xuan-Phi Nguyen, Z. Liu, Yang Li et al. · 3 citations