collaborators

5 papers

cs.CV2025

xGen-MM (BLIP-3): A Family of Open Large Multimodal Models

Le Xue, Manli Shu, Anas Awadalla +30

This paper introduces BLIP-3, an open framework for developing Large Multimodal Models (LMMs). The framework comprises meticulously curated datasets, a training recipe, model archi…

cs.CV2025

DyMU: Dynamic Merging and Virtual Unmerging for Efficient VLMs

Zhenhailong Wang, Senthil Purushwalkam, Caiming Xiong +3

We present DyMU, an efficient, training-free framework that dynamically reduces the computational burden of vision-language models (VLMs) while maintaining high task performance. O…

cs.CL2025

FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"

Yifei Ming, Senthil Purushwalkam, Shrey Pandit +4

Ensuring faithfulness to context in large language models (LLMs) and retrieval-augmented generation (RAG) systems is crucial for reliable deployment in real-world applications, as…

cs.CV2024

BLIP3-KALE: Knowledge Augmented Large-Scale Dense Captions

Anas Awadalla, Le Xue, Manli Shu +13

We introduce BLIP3-KALE, a dataset of 218 million image-text pairs that bridges the gap between descriptive synthetic captions and factual web-scale alt-text. KALE augments synthet…

cs.CV2024

Trust but Verify: Programmatic VLM Evaluation in the Wild

Viraj Prabhu, Senthil Purushwalkam, An Yan +2

Vision-Language Models (VLMs) often generate plausible but incorrect responses to visual queries. However, reliably quantifying the effect of such hallucinations in free-form respo…