Cover Image

No Training Wheels: Steering Vectors for Bias Correction at Inference Time

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Gupta, Aviral, Sethi, Armaan, Sethi, Ameesh
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Computation and Language Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Listen Then See: Video Alignment with Speaker Attention
by: Agrawal, Aviral, et al.
Published: (2024)

Efficient Whole Slide Image Classification through Fisher Vector Representation
by: Gupta, Ravi Kant, et al.
Published: (2024)

Scalable Whole Slide Image Representation Using K-Mean Clustering and Fisher Vector Aggregation
by: Gupta, Ravi Kant, et al.
Published: (2025)

Network Inversion of Convolutional Neural Nets
by: Suhail, Pirzada, et al.
Published: (2024)

BiPrompt: Bilateral Prompt Optimization for Visual and Textual Debiasing in Vision-Language Models
by: Gupta, Sunny, et al.
Published: (2026)

Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models
by: Gan, Woody Haosheng, et al.
Published: (2025)

A General Framework for Inference-time Scaling and Steering of Diffusion Models
by: Singhal, Raghav, et al.
Published: (2025)

Mitigating Instance-Dependent Label Noise: Integrating Self-Supervised Pretraining with Pseudo-Label Refinement
by: Bala, Gouranga, et al.
Published: (2024)

IDAL: Improved Domain Adaptive Learning for Natural Images Dataset
by: Gupta, Ravi Kant, et al.
Published: (2025)

Network Inversion for Generating Confidently Classified Counterfeits
by: Suhail, Pirzada, et al.
Published: (2025)

Activation Matching for Explanation Generation
by: Suhail, Pirzada, et al.
Published: (2025)

Shortcut Learning Susceptibility in Vision Classifiers
by: Suhail, Pirzada, et al.
Published: (2025)

Privacy Preserving Properties of Vision Classifiers
by: Suhail, Pirzada, et al.
Published: (2025)

TIE: A Training-Inversion-Exclusion Framework for Visually Interpretable and Uncertainty-Guided Out-of-Distribution Detection
by: Suhail, Pirzada, et al.
Published: (2025)

Spectrally-Guided Diffusion Noise Schedules
by: Esteves, Carlos, et al.
Published: (2026)

Clustered Patch Embeddings for Permutation-Invariant Classification of Whole Slide Images
by: Gupta, Ravi Kant, et al.
Published: (2024)

Transformer-VQ: Linear-Time Transformers via Vector Quantization
by: Lingle, Lucas D.
Published: (2023)

Network Inversion and Its Applications
by: Suhail, Pirzada, et al.
Published: (2024)

Network Inversion for Uncertainty-Aware Out-of-Distribution Detection
by: Suhail, Pirzada, et al.
Published: (2025)

IM-Unpack: Training and Inference with Arbitrarily Low Precision Integers
by: Zeng, Zhanpeng, et al.
Published: (2024)

TabPFN Through The Looking Glass: An interpretability study of TabPFN and its internal representations
by: Gupta, Aviral, et al.
Published: (2026)

Test-Time Training Done Right
by: Zhang, Tianyuan, et al.
Published: (2025)

Sparse-IFT: Sparse Iso-FLOP Transformations for Maximizing Training Efficiency
by: Thangarasa, Vithursan, et al.
Published: (2023)

DiffuSAM: Diffusion Guided Zero-Shot Object Grounding for Remote Sensing Imagery
by: Sethi, Geet, et al.
Published: (2026)

BiasConnect: Investigating Bias Interactions in Text-to-Image Models
by: Shukla, Pushkar, et al.
Published: (2025)

ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time
by: Ding, Yi, et al.
Published: (2024)

Spectral Image Tokenizer
by: Esteves, Carlos, et al.
Published: (2024)

DeepCoT: Deep Continual Transformers for Real-Time Inference on Data Streams
by: Picón, Ginés Carreto, et al.
Published: (2025)

Scaling Inference-Time Search with Vision Value Model for Improved Visual Comprehension
by: Wang, Xiyao, et al.
Published: (2024)

Learning to Steer: Input-dependent Steering for Multimodal LLMs
by: Parekh, Jayneel, et al.
Published: (2025)

Low-Resource Video Super-Resolution using Memory, Wavelets, and Deformable Convolutions
by: Viswanathan, Kavitha, et al.
Published: (2025)

Evaluating the Correctness of Inference Patterns Used by LLMs for Judgment
by: Chen, Lu, et al.
Published: (2024)

Network Inversion for Training-Like Data Reconstruction
by: Suhail, Pirzada, et al.
Published: (2024)

Unleashing the Potential of Model Bias for Generalized Category Discovery
by: An, Wenbin, et al.
Published: (2024)

The Instinctive Bias: Spurious Images lead to Illusion in MLLMs
by: Han, Tianyang, et al.
Published: (2024)

Words in Motion: Extracting Interpretable Control Vectors for Motion Transformers
by: Tas, Omer Sahin, et al.
Published: (2024)

Examining the Robustness of Homogeneity Bias to Hyperparameter Adjustments in GPT-4
by: Lee, Messi H. J.
Published: (2025)

FairImagen: Post-Processing for Bias Mitigation in Text-to-Image Models
by: Fu, Zihao, et al.
Published: (2025)

When are Lemons Purple? The Concept Association Bias of Vision-Language Models
by: Yamada, Yutaro, et al.
Published: (2022)

The Cost of Context: Mitigating Textual Bias in Multimodal Retrieval-Augmented Generation
by: Jung, Hoin, et al.
Published: (2026)