Author

Saurabh Goyal

2 papers indexed here

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.

#artificial intelligence Preprint Sep 2026

DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent Training

This work proposes DRACO: Distributing Rubric-based Advantage for Credit Optimization, which generates rubrics dynamically during training to track the policy's evolving capability, scores those rubrics once per completed trajectory, and redistributes that judgment over the steps responsible for annotated rubrics to pr...

Shubham Gandhi, Saurabh Goyal, K. Kate et al. · 5 citations

#artificial intelligence Dec 2025

Kascade: A Practical Sparse Attention Method for Long-Context LLM Inference

Kascade is a training-free sparse attention method that leverages known observations such as 1) post-softmax attention is intrinsically sparse, and 2) the identity of high-weight keys is stable across nearby layers to achieve high accuracy on long-context LLM inference.

Dhruv Deshmukh, Saurabh Goyal, Nipun Kwatra et al. · arXiv.org · 10 citations