Copertina

Debias your Large Multi-Modal Model at Test-Time via Non-Contrastive Visual Attribute Steering

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ratzlaff, Neale, Olson, Matthew Lyle, Hinck, Musashi, Aflalo, Estelle, Tseng, Shao-Yen, Lal, Vasudev, Howard, Phillip
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computer Vision and Pattern Recognition Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Debiasing Large Vision-Language Models by Ablating Protected Attribute Representations
di: Ratzlaff, Neale, et al.
Pubblicazione: (2024)

Steering Large Language Models to Evaluate and Amplify Creativity
di: Olson, Matthew Lyle, et al.
Pubblicazione: (2024)

Probing the Representational Power of Sparse Autoencoders in Vision Models
di: Olson, Matthew Lyle, et al.
Pubblicazione: (2025)

Analyzing Hierarchical Structure in Vision Models with Sparse Autoencoders
di: Olson, Matthew Lyle, et al.
Pubblicazione: (2025)

LieCraft: A Multi-Agent Framework for Evaluating Deceptive Capabilities in Language Models
di: Olson, Matthew Lyle, et al.
Pubblicazione: (2026)

Probing Semantic Routing in Large Mixture-of-Expert Models
di: Olson, Matthew Lyle, et al.
Pubblicazione: (2025)

LLaVA-Gemma: Accelerating Multimodal Foundation Models with a Compact Language Model
di: Hinck, Musashi, et al.
Pubblicazione: (2024)

Training-Free Mitigation of Language Reasoning Degradation After Multimodal Instruction Tuning
di: Ratzlaff, Neale, et al.
Pubblicazione: (2024)

Learning from Reasoning Failures via Synthetic Data Generation
di: Stan, Gabriela Ben Melech, et al.
Pubblicazione: (2025)

Why do LLaVA Vision-Language Models Reply to Images in English?
di: Hinck, Musashi, et al.
Pubblicazione: (2024)

ClimDetect: A Benchmark Dataset for Climate Change Detection and Attribution
di: Yu, Sungduk, et al.
Pubblicazione: (2024)

LVLM-Interpret: An Interpretability Tool for Large Vision-Language Models
di: Stan, Gabriela Ben Melech, et al.
Pubblicazione: (2024)

FastRM: An efficient and automatic explainability framework for multimodal generative models
di: Stan, Gabriela Ben-Melech, et al.
Pubblicazione: (2024)

FiVL: A Framework for Improved Vision-Language Alignment through the Lens of Training, Evaluation and Explainability
di: Aflalo, Estelle, et al.
Pubblicazione: (2024)

A Causal World Model Underlying Next Token Prediction: Exploring GPT in a Controlled Environment
di: Rohekar, Raanan Y., et al.
Pubblicazione: (2024)

DPO Learning with LLMs-Judge Signal for Computer Use Agents
di: Luo, Man, et al.
Pubblicazione: (2025)

NeuroPrompts: An Adaptive Framework to Optimize Prompts for Text-to-Image Generation
di: Rosenman, Shachar, et al.
Pubblicazione: (2023)

Cultural Awareness in Vision-Language Models: A Cross-Country Exploration
di: Madasu, Avinash, et al.
Pubblicazione: (2025)

Pruning the Paradox: How CLIP's Most Informative Heads Enhance Performance While Amplifying Bias
di: Madasu, Avinash, et al.
Pubblicazione: (2025)

Quantifying and Enabling the Interpretability of CLIP-like Models
di: Madasu, Avinash, et al.
Pubblicazione: (2024)

Is Your Paper Being Reviewed by an LLM? Benchmarking AI Text Detection in Peer Review
di: Yu, Sungduk, et al.
Pubblicazione: (2025)

Is Your Paper Being Reviewed by an LLM? Investigating AI Text Detectability in Peer Review
di: Yu, Sungduk, et al.
Pubblicazione: (2024)

Using Imperfect Surrogates for Downstream Inference: Design-based Supervised Learning for Social Science Applications of Large Language Models
di: Egami, Naoki, et al.
Pubblicazione: (2023)

AutoPersuade: A Framework for Evaluating and Explaining Persuasive Arguments
di: Saenger, Till Raphael, et al.
Pubblicazione: (2024)

NeuroComparatives: Neuro-Symbolic Distillation of Comparative Knowledge
di: Howard, Phillip, et al.
Pubblicazione: (2023)

SocialCounterfactuals: Probing and Mitigating Intersectional Social Biases in Vision-Language Models with Counterfactual Examples
di: Howard, Phillip, et al.
Pubblicazione: (2023)

ICSVR: Investigating Compositional and Syntactic Understanding in Video Retrieval Models
di: Madasu, Avinash, et al.
Pubblicazione: (2023)

SK-VQA: Synthetic Knowledge Generation at Scale for Training Context-Augmented Multimodal LLMs
di: Su, Xin, et al.
Pubblicazione: (2024)

Getting it Right: Improving Spatial Consistency in Text-to-Image Models
di: Chatterjee, Agneet, et al.
Pubblicazione: (2024)

IssueBench: Millions of Realistic Prompts for Measuring Issue Bias in LLM Writing Assistance
di: Röttger, Paul, et al.
Pubblicazione: (2025)

Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models
di: Röttger, Paul, et al.
Pubblicazione: (2024)

L-MAGIC: Language Model Assisted Generation of Images with Coherence
di: Cai, Zhipeng, et al.
Pubblicazione: (2024)

Advocating with your story: Compelling our legislators to act
di: Zoe Tseng
Pubblicazione: (2025)

Utilizando Recursos Computacionais (Planilha) na Compreensão dos Números Racionais
di: Rosane Ratzlaff da Rosa
Pubblicazione: (2008)

LVLM-Compress-Bench: Benchmarking the Broader Impact of Large Vision-Language Model Compression
di: Kundu, Souvik, et al.
Pubblicazione: (2025)

Controlling your Attributes in Voice
di: Li, Xuyuan, et al.
Pubblicazione: (2025)

Geometry-Aware CLIP Retrieval via Local Cross-Modal Alignment and Steering
di: Prakash, Nirmalendu, et al.
Pubblicazione: (2026)

Debias-CLR: A Contrastive Learning Based Debiasing Method for Algorithmic Fairness in Healthcare Applications
di: Agarwal, Ankita, et al.
Pubblicazione: (2024)

Interaction-Enabled Two- and Three-Fold Exceptional Points
di: Kato, Musashi, et al.
Pubblicazione: (2026)

SegDebias: Test-Time Bias Mitigation for ViT-Based CLIP via Segmentation
di: Wu, Fangyu, et al.
Pubblicazione: (2025)