activity
20242026
collaborators

6 papers

cs.CV2026

FlowCast: Trajectory Forecasting for Scalable Zero-Cost Speculative Flow Matching

Divya Jyoti Bajpai, Shubham Agarwal, Apoorv Saxena +3

Flow Matching (FM) has recently emerged as a powerful approach for high-quality visual generation. However, their prohibitively slow inference due to a large number of denoising st…

cs.CV2025

Argus: Quality-Aware High-Throughput Text-to-Image Inference Serving System

Shubham Agarwal, Subrata Mitra, Saud Iqbal

Text-to-image (T2I) models have gained significant popularity. Most of these are diffusion models with unique computational characteristics, distinct from both traditional small-sc…

cs.CL2025

RCStat: A Statistical Framework for using Relative Contextualization in Transformers

Debabrata Mahapatra, Shubham Agarwal, Apoorv Saxena +1

Prior work on input-token importance in auto-regressive transformers has relied on Softmax-normalized attention weights, which obscure the richer structure of pre-Softmax query-key…

cs.DC2025

Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generation

Shubham Agarwal, Sai Sundaresan, Subrata Mitra +6

Retrieval-Augmented Generation (RAG) is often used with Large Language Models (LLMs) to infuse domain knowledge or user-specific information. In RAG, given a user query, a retrieve…

cs.LG2025

Prompt-Aware Scheduling for Efficient Text-to-Image Inferencing System

Shubham Agarwal, Saud Iqbal, Subrata Mitra

Traditional ML models utilize controlled approximations during high loads, employing faster, but less accurate models in a process called accuracy scaling. However, this method is…

cs.AI2024

ScaleViz: Scaling Visualization Recommendation Models on Large Data

Ghazi Shazan Ahmad, Shubham Agarwal, Subrata Mitra +4

Automated visualization recommendations (vis-rec) help users to derive crucial insights from new datasets. Typically, such automated vis-rec models first calculate a large number o…