activity
20242026
collaborators

16 papers

cs.DC2026

DeltaServe: Host-Agnostic Co-Serving of Inference and Fine-Tuning for LLMs

Jiaxuan Chen, Jianshu She, Ye Yuan +5

LLM serving systems are provisioned for peak load to meet strict latency targets, leaving substantial GPU compute idle whenever traffic falls below peak. We present DeltaServe, a h…

cs.LG2026

Reduced-Order Models: The Mother of World Models

Rajat Ghosh

World models -- compressed latent representations of an environment that support action-conditioned prediction and planning -- are typically presented as a product of modern self-s…

cs.CL2026

Pluralis v0.1: Towards a Multicultural, Multimodal, Multilingual Benchmark for AI Risk and Reliability

Alicia Parrish, Rajat Shinde, Sanket Badhe +57

Current AI safety evaluation and benchmarking frameworks predominantly rely on Western-centric culture-agnostic defaults that mask critical regional laws, socio-linguistic nuances,…

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

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.LG2026

Croissant Baker: Metadata Generation for Discoverable, Governable, and Reusable ML Datasets

Rafi Al Attrach, Rajna Fani, Sebastian Lobentanzer +17

Croissant has emerged as the metadata standard for machine learning datasets, providing a structured, JSON-LD-based format that makes dataset discovery, automated ingestion, and re…