collaborators

8 papers

cs.CV2026

Pause and Think: A Dataset and Benchmark for Video-Grounded Assistive Action Suggestion

Shivam Singh, Saptarshi Majumder, Pratik Prabhanjan Brahma +2

Recent Vision-Language Models (VLMs) struggle with grounded reasoning, temporal consistency, and context aware planning in videos. We introduce pause-and-think-T, a reasoning-centr…

cs.CL2026

AdaptEvolve: Improving Efficiency of Evolutionary AI Agents through Adaptive Model Selection

Pretam Ray, Pratik Prabhanjan Brahma, Zicheng Liu +1

Evolutionary agentic systems intensify the trade-off between computational efficiency and reasoning capability by repeatedly invoking large language models (LLMs) during inference.…

cs.CV2026

DUET-VLM: Dual stage Unified Efficient Token reduction for VLM Training and Inference

Aditya Kumar Singh, Hitesh Kandala, Pratik Prabhanjan Brahma +2

Vision-language models (VLMs) have achieved remarkable multimodal understanding and reasoning capabilities, yet remain computationally expensive due to dense visual tokenization. E…

cond-mat.stat-mech2025

Hardware Acceleration of Frustrated Lattice Systems using Convolutional Restricted Boltzmann Machine

Pratik Brahma, Junghoon Han, Tamzid Razzaque +2

Geometric frustration gives rise to emergent quantum phenomena and exotic phases of matter. While Monte Carlo methods are traditionally used to simulate such systems, their samplin…

cs.CL2025

Instella: Fully Open Language Models with Stellar Performance

Jiang Liu, Jialian Wu, Xiaodong Yu +10

Large language models (LLMs) have demonstrated remarkable performance across a wide range of tasks, yet the majority of high-performing models remain closed-source or partially ope…

cs.CL2025

SAND-Math: Using LLMs to Generate Novel, Difficult and Useful Mathematics Questions and Answers

Chaitanya Manem, Pratik Prabhanjan Brahma, Prakamya Mishra +2

The demand for Large Language Models (LLMs) at multiple scales, capable of sophisticated and sound mathematical reasoning, continues to grow. However, the development of performant…