English
Related papers

Related papers: Interpretability Transfer from Language to Vision …

200 papers

Vision-Language-Action (VLA) policies translate language and visual inputs into robot actions, where their hidden representations directly shape closed-loop behavior. However, mechanistic interpretability tools from language and…

Robotics · Computer Science 2026-05-19 Xinchen Jin , Aditya Chatterjee , Pranav Kumar , Rohan Paleja

While large language models provide strong compositional reasoning, existing reasoning segmentation pipelines fail to transparently connect this reasoning to visual perception. Current methods, such as latent query alignment, are end-to-end…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Zhenyu Lu , Liupeng Li , Jinpeng Wang , Haoqian Kang , Yan Feng , Ke Chen , Yaowei Wang

Although significant progress has been made in few-shot learning, most of existing few-shot image classification methods require supervised pre-training on a large amount of samples of base classes, which limits their generalization ability…

Computer Vision and Pattern Recognition · Computer Science 2023-01-23 Fang Peng , Xiaoshan Yang , Linhui Xiao , Yaowei Wang , Changsheng Xu

Translating the internal representations and computations of models into concepts that humans can understand is a key goal of interpretability. While recent dictionary learning methods such as Sparse Autoencoders (SAEs) provide a promising…

Computation and Language · Computer Science 2026-02-27 Usha Bhalla , Alex Oesterling , Claudio Mayrink Verdun , Himabindu Lakkaraju , Flavio P. Calmon

Vision-language (VL) learning requires extensive visual perception capabilities, such as fine-grained object recognition and spatial perception. Recent works typically rely on training huge models on massive datasets to develop these…

Computer Vision and Pattern Recognition · Computer Science 2025-04-02 Yuanchen Wu , Junlong Du , Ke Yan , Shouhong Ding , Xiaoqiang Li

Sparse Autoencoders (SAEs) are widely used to steer large language models (LLMs), based on the assumption that their interpretable features naturally enable effective model behavior steering. Yet, a fundamental question remains unanswered:…

Machine Learning · Computer Science 2025-10-07 Xu Wang , Yan Hu , Benyou Wang , Difan Zou

Recently, the Vision Transformer (ViT), which applied the transformer structure to the image classification task, has outperformed convolutional neural networks. However, the high performance of the ViT results from pre-training using a…

Computer Vision and Pattern Recognition · Computer Science 2021-12-28 Seung Hoon Lee , Seunghyun Lee , Byung Cheol Song

Current multimodal large language models (MLLMs) face a critical challenge in modality alignment, often exhibiting a bias towards textual information at the expense of other modalities like vision. This paper conducts a systematic…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Mingxiao Li , Na Su , Fang Qu , Zhizhou Zhong , Ziyang Chen , Yuan Li , Zhaopeng Tu , Xiaolong Li

Advances in self-supervised encoders have improved Visual Speech Recognition (VSR). Recent approaches integrating these encoders with LLM decoders improves transcription accuracy; however, it remains unclear whether these gains stem from…

Sound · Computer Science 2026-01-21 Rishabh Jain , Naomi Harte

Referring image segmentation is a fundamental vision-language task that aims to segment out an object referred to by a natural language expression from an image. One of the key challenges behind this task is leveraging the referring…

Computer Vision and Pattern Recognition · Computer Science 2022-04-07 Zhao Yang , Jiaqi Wang , Yansong Tang , Kai Chen , Hengshuang Zhao , Philip H. S. Torr

Steering has emerged as a promising approach in controlling large language models (LLMs) without modifying model parameters. However, most existing steering methods rely on large-scale datasets to learn clear behavioral information, which…

Machine Learning · Computer Science 2025-10-06 Anyi Wang , Xuansheng Wu , Dong Shu , Yunpu Ma , Ninghao Liu

Radiological services are experiencing unprecedented demand, leading to increased interest in automating radiology report generation. Existing Vision-Language Models (VLMs) suffer from hallucinations, lack interpretability, and require…

Computer Vision and Pattern Recognition · Computer Science 2024-10-07 Ahmed Abdulaal , Hugo Fry , Nina Montaña-Brown , Ayodeji Ijishakin , Jack Gao , Stephanie Hyland , Daniel C. Alexander , Daniel C. Castro

Large vision-language models (LVLMs) have achieved remarkable performance on multimodal tasks. However, they still suffer from hallucinations, generating text inconsistent with visual input, posing significant risks in real-world…

Computer Vision and Pattern Recognition · Computer Science 2025-09-16 Zhenglin Hua , Jinghan He , Zijun Yao , Tianxu Han , Haiyun Guo , Yuheng Jia , Junfeng Fang

Most existing visual search systems are deployed based upon fixed kinds of visual features, which prohibits the feature reusing across different systems or when upgrading systems with a new type of feature. Such a setting is obviously…

Computer Vision and Pattern Recognition · Computer Science 2019-04-01 Jie Hu , Rongrong Ji , Hong Liu , Shengchuan Zhang , Cheng Deng , Qi Tian

Understanding the internal activations of Vision Transformers (ViTs) is critical for building interpretable and trustworthy models. While Sparse Autoencoders (SAEs) have been used to extract human-interpretable features, they operate on…

Computer Vision and Pattern Recognition · Computer Science 2026-04-16 Gerasimos Chatzoudis , Konstantinos D. Polyzos , Zhuowei Li , Difei Gu , Gemma E. Moran , Hao Wang , Dimitris N. Metaxas

In this thesis, we develop methods to enhance the interpretability of recent representation learning techniques in natural language processing (NLP) while accounting for the unavailability of annotated data. We choose to leverage…

Computation and Language · Computer Science 2023-05-05 Ghazi Felhi

Vision-Language Models (VLMs) have achieved impressive performance in cross-modal understanding across textual and visual inputs, yet existing benchmarks predominantly focus on pure-text queries. In real-world scenarios, language also…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Qing'an Liu , Juntong Feng , Yuhao Wang , Xinzhe Han , Yujie Cheng , Yue Zhu , Haiwen Diao , Yunzhi Zhuge , Huchuan Lu

Large Language Models (LLMs) have transformed natural language processing, yet their internal mechanisms remain largely opaque. Recently, mechanistic interpretability has attracted significant attention from the research community as a…

Machine Learning · Computer Science 2025-09-24 Dong Shu , Xuansheng Wu , Haiyan Zhao , Daking Rai , Ziyu Yao , Ninghao Liu , Mengnan Du

The architecture of multimodal large language models (MLLMs) commonly connects a vision encoder, often based on CLIP-ViT, to a large language model. While CLIP-ViT works well for capturing global image features, it struggles to model local…

Computer Vision and Pattern Recognition · Computer Science 2025-07-08 Haoran Lou , Chunxiao Fan , Ziyan Liu , Yuexin Wu , Xinliang Wang

It has been long known that sparsity is an effective inductive bias for learning efficient representation of data in vectors with fixed dimensionality, and it has been explored in many areas of representation learning. Of particular…

Computation and Language · Computer Science 2021-04-20 Victor Prokhorov , Yingzhen Li , Ehsan Shareghi , Nigel Collier