activity
20232026
most citedDMLR: Data-centric Machine Learning Research -- Past, Present and Future

6 citations · 16 across the 15 of their papers we have counts for

collaborators
Showing cs.LGShow all

9 papers · 1 filter

cs.LG2026

Predictable GRPO: A Closed-Form Model of Training Dynamics

Rajat Ghosh, Datta Nimmaturi, Aryan Singhal +4

We develop a first-principles reduced-order model of these dynamics. Under a single mean-field assumption that summarizes the policy by its expected reward, we reduce the GRPO upda…

cs.LG2026

Action Shapley: A Training Data Selection Metric for World Model in Reinforcement Learning

Rajat Ghosh, Debojyoti Dutta

Numerous offline and model-based reinforcement learning systems incorporate world models to emulate the inherent environments. A world model is particularly important in scenarios…

cs.LG2025

Go-UT-Bench: A Fine-Tuning Dataset for LLM-Based Unit Test Generation in Go

Yashshi Pipalani, Hritik Raj, Rajat Ghosh +2

Training data imbalance poses a major challenge for code LLMs. Most available data heavily over represents raw opensource code while underrepresenting broader software engineering…

cs.LG2025

A Multi-Agent Framework for Stateful Inference-Time Search

Arshika Lalan, Rajat Ghosh, Aditya Kolsur +1

Recent work explores agentic inference-time techniques to perform structured, multi-step reasoning. However, stateless inference often struggles on multi-step tasks due to the abse…

cs.LG2025

BAR Conjecture: the Feasibility of Inference Budget-Constrained LLM Services with Authenticity and Reasoning

Jinan Zhou, Rajat Ghosh, Vaishnavi Bhargava +2

When designing LLM services, practitioners care about three key properties: inference-time budget, factual authenticity, and reasoning capacity. However, our analysis shows that no…

cs.LG2025

Predictive Scaling Laws for Efficient GRPO Training of Large Reasoning Models

Datta Nimmaturi, Vaishnavi Bhargava, Rajat Ghosh +2

Fine-tuning large language models (LLMs) for reasoning tasks using reinforcement learning methods like Group Relative Policy Optimization (GRPO) is computationally expensive. To ad…