Why Vision Language Models Ignore What They See with Munawar Hayat - #758

Why Vision Language Models Ignore What They See with Munawar Hayat - #758

December 9, 2025 · 58 min · Episode 758

About this episode

Munawar Hayat discusses challenges and innovations in Vision-Language Models and generative AI.

In this episode, we’re joined by Munawar Hayat, researcher at Qualcomm AI Research, to discuss a series of papers presented at NeurIPS 2025 focusing on multimodal and generative AI. We dive into the persistent challenge of object hallucination in Vision-Language Models (VLMs), why models often discard visual information in favor of pre-trained language priors, and how his team used attention-guided alignment to enforce better visual grounding. We also explore a novel approach to generalized contrastive learning designed to solve complex, composed retrieval tasks—such as searching via combined text and image queries—without increasing inference costs. Finally, we cover the difficulties generative models face when rendering multiple human subjects, and the new "MultiHuman Testbench" his team created to measure and mitigate issues like identity leakage and attribute blending. Throughout the discussion, we examine how these innovations align with the need for efficient, on-device AI deployment. The complete show notes for this episode can be found at https://twimlai.com/go/758.

People in this episode

Host: Sam Charrington

Guest: Munawar Hayat

Topics covered

Keywords

Mentioned in this episode

Organizations: Qualcomm AI Research

More episodes of The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)

Explore listener stats, chart rankings, contacts and more on the The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence) podcast page.