works on

From the 1 of 12 linked papers with an AI index.

collaborators

12 papers

cs.CL2026

ArogyaSutra: A Multi-Agent Framework for Multimodal Medical Reasoning in Indic Languages

Tanmoy Kanti Halder, Akash Ghosh, Subhadip Baidya +2

The paper introduces a large multilingual multimodal medical QA dataset (ArogyaBodha) and a multi‑agent actor‑critic framework (ArogyaSutra) to improve medical reasoning in Indian…

cs.LG2026

LAARA: Layer-Aware Adaptive Rank Allocation for Parameter-Efficient Fine-Tuning

Ashutosh Tripathi, Surya Deep Singh, Pranab Sahoo +1

Low-Rank Adaptation is widely used for parameter-efficient fine-tuning, yet existing methods typically assign the same adapter rank to every transformer layer despite their heterog…

cs.AI2026

CURE-Med: Curriculum-Informed Reinforcement Learning for Multilingual Medical Reasoning

Eric Onyame, Akash Ghosh, Subhadip Baidya +3

While large language models (LLMs) have shown to perform well on monolingual mathematical and commonsense reasoning, they remain unreliable for multilingual medical reasoning appli…

cs.CV2026

CarePilot: A Multi-Agent Framework for Long-Horizon Computer Task Automation in Healthcare

Akash Ghosh, Tajamul Ashraf, Rishu Kumar Singh +4

Multimodal agentic pipelines are transforming human-computer interaction by enabling efficient and accessible automation of complex, real-world tasks. However, recent efforts have…

cs.CV2026

Ask Me Again Differently: GRAS for Measuring Bias in Vision Language Models on Gender, Race, Age, and Skin Tone

Shaivi Malik, Hasnat Md Abdullah, Sriparna Saha +1

As Vision Language Models (VLMs) become integral to real-world applications, understanding their demographic biases is critical. We introduce GRAS, a benchmark for uncovering demog…

cs.LG2026

FedDUAL: A Dual-Strategy with Adaptive Loss and Dynamic Aggregation for Mitigating Data Heterogeneity in Federated Learning

Pranab Sahoo, Ashutosh Tripathi, Sriparna Saha +1

Federated Learning (FL) marks a transformative approach to distributed model training by combining locally optimized models from various clients into a unified global model. While…