English
Related papers

Related papers: Steerable but Not Decodable: Function Vectors Oper…

200 papers

Vision-Language Models (VLMs) achieve strong results on multimodal tasks such as visual question answering, yet they can still fail even when the correct visual evidence is present. In this work, we systematically investigate whether these…

Artificial Intelligence · Computer Science 2025-10-21 Zhining Liu , Ziyi Chen , Hui Liu , Chen Luo , Xianfeng Tang , Suhang Wang , Joy Zeng , Zhenwei Dai , Zhan Shi , Tianxin Wei , Benoit Dumoulin , Hanghang Tong

Vision language models (VLMs) exhibit vast knowledge of the physical world, including intuition of physical and spatial properties, affordances, and motion. With fine-tuning, VLMs can also natively produce robot trajectories. We demonstrate…

Robotics · Computer Science 2025-05-16 William Xie , Max Conway , Yutong Zhang , Nikolaus Correll

Unsupervised learning of latent variable models (LVMs) is widely used to represent data in machine learning. When such models reflect the ground truth factors and the mechanisms mapping them to observations, there is reason to expect that…

Machine Learning · Statistics 2023-01-23 Simon Buchholz , Michel Besserve , Bernhard Schölkopf

This work introduces SteerVLM, a lightweight steering module designed to guide Vision-Language Models (VLMs) towards outputs that better adhere to desired instructions. Our approach learns from the latent embeddings of paired prompts…

Computer Vision and Pattern Recognition · Computer Science 2025-10-31 Anushka Sivakumar , Andrew Zhang , Zaber Hakim , Chris Thomas

Vision-Language Models (VLMs) combine a vision encoder and a large language model (LLM) through alignment training, showing strong performance on multimodal tasks. A central component in this architecture is the projection layer, which maps…

Computer Vision and Pattern Recognition · Computer Science 2025-09-10 Raehyuk Jung , Seungjun Yu , Hyunjung Shim

Large Language Models (LLMs) often generate inconsistent responses when prompted with semantically equivalent paraphrased inputs. Recently, activation steering, a technique that modulates LLMs' behaviours by adjusting their latent…

Computation and Language · Computer Science 2025-01-23 Jingyuan Yang , Rongjun Li , Weixuan Wang , Ziyu Zhou , Zhiyong Feng , Wei Peng

Pretrained Vision Transformers (ViTs) such as DINOv2 and MAE provide generic image features that can be applied to a variety of downstream tasks such as retrieval, classification, and segmentation. However, such representations tend to…

Computer Vision and Pattern Recognition · Computer Science 2026-04-03 Jona Ruthardt , Manu Gaur , Deva Ramanan , Makarand Tapaswi , Yuki M. Asano

Vision-language models (VLMs) exhibit a systematic bias when confronted with classic optical illusions: they overwhelmingly predict the illusion as "real" regardless of whether the image has been counterfactually modified. We present a…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 Xuesong Wang , Harry Wang

Despite the remarkable success of Multimodal Large Language Models (MLLMs) across diverse tasks, the internal mechanisms governing how they encode and ground distinct visual concepts remain poorly understood. To bridge this gap, we propose…

Artificial Intelligence · Computer Science 2026-05-08 Zehao Deng , Tianjie Ju , Zheng Wu , Liangbo He , Jun Lan , Huijia Zhu , Weiqiang Wang , Zhuosheng Zhang

Recent advances in automated theorem proving use Large Language Models (LLMs) to translate informal mathematical statements into formal proofs. However, informal cues are often ambiguous or lack strict logical structure, making it hard for…

Machine Learning · Computer Science 2025-10-14 Shashank Kirtania , Arun Iyer

Remarkable progress in 2D Vision-Language Models (VLMs) has spurred interest in extending them to 3D settings for tasks like 3D Question Answering, Dense Captioning, and Visual Grounding. Unlike 2D VLMs that typically process images through…

Computer Vision and Pattern Recognition · Computer Science 2025-06-09 Haoyuan Li , Yanpeng Zhou , Yufei Gao , Tao Tang , Jianhua Han , Yujie Yuan , Dave Zhenyu Chen , Jiawang Bian , Hang Xu , Xiaodan Liang

Large language models (LLMs) exhibit impressive in-context learning (ICL) capability, enabling them to perform new tasks using only a few demonstrations in the prompt. Two different mechanisms have been proposed to explain ICL: induction…

Machine Learning · Computer Science 2025-05-05 Kayo Yin , Jacob Steinhardt

Activation steering methods in large language models (LLMs) have emerged as an effective way to perform targeted updates to enhance generated language without requiring large amounts of adaptation data. We ask whether the features…

Computation and Language · Computer Science 2025-11-05 Masha Fedzechkina , Eleonora Gualdoni , Sinead Williamson , Katherine Metcalf , Skyler Seto , Barry-John Theobald

Object hallucination critically undermines the reliability of Multimodal Large Language Models, often stemming from a fundamental failure in cognitive introspection, where models blindly trust linguistic priors over specific visual…

Computer Vision and Pattern Recognition · Computer Science 2026-01-09 Shuliang Liu , Songbo Yang , Dong Fang , Sihang Jia , Yuqi Tang , Lingfeng Su , Ruoshui Peng , Yibo Yan , Xin Zou , Xuming Hu

Reliable confidence estimation is critical when deploying vision models. We study error prediction: determining whether an image classifier's output is correct using only signals from a single forward pass. Motivated by internal-signal…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Ido Beigelman , Moti Freiman

Despite significant progress in alignment, large language models (LLMs) remain vulnerable to adversarial attacks that elicit harmful behaviors. Activation steering techniques offer a promising inference-time intervention approach, but…

Machine Learning · Computer Science 2026-01-28 Quy-Anh Dang , Chris Ngo

Large language models (LLMs) increasingly exhibit behaviors suggesting awareness of their evaluation context, often adapting their reasoning strategies in benchmark settings. Prior work has shown that such evaluation awareness can distort…

Computation and Language · Computer Science 2026-05-12 Yanshi Li , Xueru Bai , Shuman Liu , Haibo Zhang , Anxiang Zeng

Activation steering is a practical post-training model alignment technique to enhance the utility of Large Language Models (LLMs). Prior to deploying a model as a service, developers can steer a pre-trained model toward specific behavioral…

Cryptography and Security · Computer Science 2026-02-06 Chen Xiong , Zhiyuan He , Pin-Yu Chen , Ching-Yun Ko , Tsung-Yi Ho

While open sourced Vision-Language Models (VLMs) have proliferated, selecting the optimal pretrained model for a specific downstream task remains challenging. Exhaustive evaluation is often infeasible due to computational constraints and…

Artificial Intelligence · Computer Science 2026-02-03 Wei Yang , Hong Xie , Tao Tan , Xin Li , Defu Lian , Enhong Chen

Large Language Models (LLMs) are widely used by software engineers for programming tasks. However, research shows that LLMs often lack a deep understanding of program semantics. Even minor changes to syntax, such as renaming variables, can…

Computation and Language · Computer Science 2025-10-06 Francesca Lucchetti , Arjun Guha