Muhammad Jehanzeb Mirza

PRISMM-Bench: A Benchmark of Peer-Review Grounded Multimodal Inconsistencies

KV Cache Steering for Controlling Frozen LLMs

VisualOverload: Probing Visual Understanding of VLMs in Really Dense Scenes

TTRV: Test-Time Reinforcement Learning for Vision Language Models

AVRT: Audio-Visual Reasoning Transfer through Single-Modality Teachers

Can We Talk Models Into Seeing the World Differently?

Overflow Prevention Enhances Long-Context Recurrent LLMs

Mining your own secrets: Diffusion Classifier Scores for Continual Personalization of Text-to-Image Diffusion Models

Can Diffusion Models Disentangle? A Theoretical Perspective

GLOV: Guided Large Language Models as Implicit Optimizers for Vision Language Models

LiveXiv - A Multi-Modal live benchmark based on Arxiv papers content

Comparison Visual Instruction Tuning