Soujanya Poria

Demystifying Deep Search: A Holistic Evaluation with Hint-free Multi-Hop Questions and Factorised Metrics

Measuring and Mitigating Rapport Bias of Large Language Models under Multi-Agent Social Interactions

TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching and Clap-Ranked Preference Optimization

OffTopicEval: When Large Language Models Enter the Wrong Chat, Almost Always!

Training Vision-Language Process Reward Models for Test-Time Scaling in Multimodal Reasoning: Key Insights and Lessons Learned

Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse

MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypotheses

M-Longdoc: A Benchmark For Multimodal Super-Long Document Understanding And A Retrieval-Aware Tuning Framework

Two Are Better than One: Context Window Extension with Multi-Grained Self-Injection