Author

Koustuv Sinha

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

On BatchNorm Forward Modes in Value-Based Reinforcement Learning

Batch normalization (BN) substantially improves sample efficiency in continuous-control actor-critic methods such as CrossQ, yet recent studies report performance degradation in discrete-action value learning on Atari. These failures are surprising because discrete Q-networks lack the action-input distribution mismatch...

Daniel Palenicek, Mikael Henaff, Scott Fujimoto et al. · 0 citations

#artificial intelligence May 2025

Multi-Modal Language Models as Text-to-Image Model Evaluators

MT2IE is presented, an evaluation framework in which a single multimodal large language model (MLLM) acts as an evaluator agent, iteratively generating the evaluation prompts and scoring the resulting images, showing that MT2IE's image-text consistency scores have higher correlation with human judgment than metrics pre...

Jiahui Chen, Candace Ross, Reyhane Askari-Hemmat et al. · arXiv.org · 4 citations · ⚡1