UW (University of Washington)

flydust

authored a paper about 16 hours ago

CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models

Paper • 2406.12257 • Published Jun 18, 2024

Tim666

authored a paper about 2 months ago

Interleaved Scene Graph for Interleaved Text-and-Image Generation Assessment

Paper • 2411.17188 • Published Nov 26, 2024 • 21

Nitre

authored a paper about 2 months ago

SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory

Paper • 2411.11922 • Published Nov 18, 2024 • 18

flydust

authored a paper about 2 months ago

Stronger Models are NOT Stronger Teachers for Instruction Tuning

Paper • 2411.07133 • Published Nov 11, 2024 • 35

haotiz

authored 2 papers 3 months ago

Improve Vision Language Model Chain-of-thought Reasoning

Paper • 2410.16198 • Published Oct 21, 2024 • 22

MM-Ego: Towards Building Egocentric Multimodal LLMs

Paper • 2410.07177 • Published Oct 9, 2024 • 22

kellycyy

authored a paper 3 months ago

CulturalBench: a Robust, Diverse and Challenging Benchmark on Measuring the (Lack of) Cultural Knowledge of LLMs

Paper • 2410.02677 • Published Oct 3, 2024

haotiz

authored 3 papers 3 months ago

Revisit Large-Scale Image-Caption Data in Pre-training Multimodal Foundation Models

Paper • 2410.02740 • Published Oct 3, 2024 • 52

Contrastive Localized Language-Image Pre-Training

Paper • 2410.02746 • Published Oct 3, 2024 • 33

MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning

Paper • 2409.20566 • Published Sep 30, 2024 • 55

Tim666

authored 4 papers 5 months ago

Coarse Correspondence Elicit 3D Spacetime Understanding in Multimodal Language Model

Paper • 2408.00754 • Published Aug 1, 2024 • 22

Efficient Inference of Vision Instruction-Following Models with Elastic Cache

Paper • 2407.18121 • Published Jul 25, 2024 • 17

TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering

Paper • 2303.11897 • Published Mar 21, 2023

Unleashing Text-to-Image Diffusion Models for Visual Perception

Paper • 2303.02153 • Published Mar 3, 2023

flydust

authored a paper 6 months ago

ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat Templates

Paper • 2406.12935 • Published Jun 17, 2024 • 1

juliakharchenko

authored a paper 7 months ago

How Well Do LLMs Represent Values Across Cultures? Empirical Analysis of LLM Responses Based on Hofstede Cultural Dimensions

Paper • 2406.14805 • Published Jun 21, 2024 • 3

flydust

authored 3 papers 7 months ago

SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding

Paper • 2402.08983 • Published Feb 14, 2024 • 2

ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs

Paper • 2402.11753 • Published Feb 19, 2024 • 5

Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing

Paper • 2406.08464 • Published Jun 12, 2024 • 66

haotiz

authored a paper 9 months ago

Ferret-v2: An Improved Baseline for Referring and Grounding with Large Language Models

Paper • 2404.07973 • Published Apr 11, 2024 • 30

University of Washington

AI & ML interests

UW's activity

CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models

Interleaved Scene Graph for Interleaved Text-and-Image Generation Assessment

SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory

Stronger Models are NOT Stronger Teachers for Instruction Tuning

Improve Vision Language Model Chain-of-thought Reasoning

MM-Ego: Towards Building Egocentric Multimodal LLMs

CulturalBench: a Robust, Diverse and Challenging Benchmark on Measuring the (Lack of) Cultural Knowledge of LLMs

Revisit Large-Scale Image-Caption Data in Pre-training Multimodal Foundation Models

Contrastive Localized Language-Image Pre-Training

MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning

Coarse Correspondence Elicit 3D Spacetime Understanding in Multimodal Language Model

Efficient Inference of Vision Instruction-Following Models with Elastic Cache

TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering

Unleashing Text-to-Image Diffusion Models for Visual Perception

ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat Templates

How Well Do LLMs Represent Values Across Cultures? Empirical Analysis of LLM Responses Based on Hofstede Cultural Dimensions

SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding

ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs

Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing

Ferret-v2: An Improved Baseline for Referring and Grounding with Large Language Models

AI & ML interests

Team members 484

UW's activity