English
Related papers

Related papers: Manifold-Guided Attention Steering

200 papers

The design choices in the Transformer attention mechanism, including weak inductive bias and quadratic computational complexity, have limited its application for modeling long sequences. In this paper, we introduce Mega, a simple,…

Machine Learning · Computer Science 2023-01-31 Xuezhe Ma , Chunting Zhou , Xiang Kong , Junxian He , Liangke Gui , Graham Neubig , Jonathan May , Luke Zettlemoyer

Large Language Models (LLMs) are increasingly deployed in high-stakes decision-making contexts. While prior work has shown that LLMs exhibit cognitive biases behaviorally, whether these biases correspond to identifiable internal…

Artificial Intelligence · Computer Science 2026-04-03 Fan Huang , Songheng Zhang , Haewoon Kwak , Jisun An

Large language models (LLMs) can be controlled at inference time through prompts (in-context learning) and internal activations (activation steering). Different accounts have been proposed to explain these methods, yet their common goal of…

Machine Learning · Computer Science 2026-03-13 Eric Bigelow , Daniel Wurgaft , YingQiao Wang , Noah Goodman , Tomer Ullman , Hidenori Tanaka , Ekdeep Singh Lubana

The reasoning segmentation task, which demands a nuanced comprehension of intricate queries to accurately pinpoint object regions, is attracting increasing attention. However, Multi-modal Large Language Models (MLLM) often find it difficult…

Computer Vision and Pattern Recognition · Computer Science 2024-07-12 Xiaoyi Bao , Siyang Sun , Shuailei Ma , Kecheng Zheng , Yuxin Guo , Guosheng Zhao , Yun Zheng , Xingang Wang

Large reasoning models (LRMs) achieve strong performance through extended reasoning traces, but they often exhibit overthinking behavior for low-complexity queries. Existing efforts to mitigate this issue are fundamentally limited by…

Machine Learning · Computer Science 2026-02-27 Zihang Xu , Haozhi Xie , Ziqi Miao , Wuxuan Gong , Chen Qian , Lijun Li

Large Language Models (LLMs) exhibit impressive capabilities but often hallucinate, confidently providing incorrect answers instead of admitting ignorance. Prior work has shown that models encode linear representations of their own…

Computation and Language · Computer Science 2025-12-09 Wannan , Yang , Xinchi Qiu , Lei Yu , Yuchen Zhang , Aobo Yang , Narine Kokhlikyan , Nicola Cancedda , Diego Garcia-Olano

Masked autoencoders (MAEs) have established themselves as a powerful method for unsupervised pre-training for computer vision tasks. While vanilla MAEs put equal emphasis on reconstructing the individual parts of the image, we propose to…

Computer Vision and Pattern Recognition · Computer Science 2024-02-26 Leon Sick , Dominik Engel , Pedro Hermosilla , Timo Ropinski

Recent progress in Multimodal Large Language Models (MLLMs) has unlocked powerful cross-modal reasoning abilities, but also raised new safety concerns, particularly when faced with adversarial multimodal inputs. To improve the safety of…

Computation and Language · Computer Science 2025-09-24 Lyucheng Wu , Mengru Wang , Ziwen Xu , Tri Cao , Nay Oo , Bryan Hooi , Shumin Deng

Retrieval-Augmented Generation (RAG) has demonstrated significant effectiveness in enhancing large language models (LLMs) for complex multi-hop question answering (QA). For multi-hop QA tasks, current iterative approaches predominantly rely…

Computation and Language · Computer Science 2026-01-19 Yuling Shi , Maolin Sun , Zijun Liu , Mo Yang , Yixiong Fang , Tianran Sun , Xiaodong Gu

Activation-based steering enables Large Language Models (LLMs) to exhibit targeted behaviors by intervening on intermediate activations without retraining. Despite its widespread use, the mechanistic factors that govern when steering…

Computation and Language · Computer Science 2026-03-13 Mehdi Jafari , Hao Xue , Flora Salim

This work examines whether activating latent subspaces in language models (LLMs) can steer scientific code generation toward a specific programming language. Five causal LLMs were first evaluated on scientific coding prompts to quantify…

Artificial Intelligence · Computer Science 2025-06-24 Vansh Sharma , Venkat Raman

Eye gaze can provide rich information on human psychological activities, and has garnered significant attention in the field of Human-Robot Interaction (HRI). However, existing gaze estimation methods merely predict either the gaze…

Computer Vision and Pattern Recognition · Computer Science 2025-05-23 Haoming Huang , Musen Zhang , Jianxin Yang , Zhen Li , Jinkai Li , Yao Guo

Large language models (LLMs) have demonstrated impressive capabilities in various reasoning tasks, aided by techniques like chain-of-thought prompting that elicits verbalized reasoning. However, LLMs often generate text with obvious…

Artificial Intelligence · Computer Science 2024-12-06 Zhihui Xie , Jizhou Guo , Tong Yu , Shuai Li

Improving decision-making capabilities in Autonomous Intelligent Vehicles (AIVs) has been a heated topic in recent years. Despite advancements, training machines to capture regions of interest for comprehensive scene understanding, like…

Artificial Intelligence · Computer Science 2025-04-09 Zhuoli Zhuang , Cheng-You Lu , Yu-Cheng Fred Chang , Yu-Kai Wang , Thomas Do , Chin-Teng Lin

One of the remarkable properties of robust computer vision models is that their input-gradients are often aligned with human perception, referred to in the literature as perceptually-aligned gradients (PAGs). Despite only being trained for…

Machine Learning · Computer Science 2024-03-12 Suraj Srinivas , Sebastian Bordt , Hima Lakkaraju

Large language models (LLMs) often exhibit undesirable behaviors, such as safety violations and hallucinations. Although inference-time steering offers a cost-effective way to adjust model behavior without updating its parameters, existing…

Machine Learning · Computer Science 2026-04-20 Zixuan Weng , Jinghuai Zhang , Kunlin Cai , Ying Li , Peiran Wang , Yuan Tian

The field of mechanistic interpretability in pre-trained transformer models has demonstrated substantial evidence supporting the ''linear representation hypothesis'', which is the idea that high level concepts are encoded as vectors in the…

Machine Learning · Computer Science 2025-10-08 Damjan Kalajdzievski

Large multimodal models (LMMs) are increasingly integrated into autonomous driving systems for user interaction. However, their limitations in fine-grained spatial reasoning pose challenges for system interpretability and user trust. We…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Imran Kabir , Md Alimoor Reza , Syed Billah

Masked diffusion models (MDMs), which leverage bidirectional attention and a denoising process, are narrowing the performance gap with autoregressive models (ARMs). However, their internal attention mechanisms remain under-explored. This…

Machine Learning · Computer Science 2026-01-14 Xin Dai , Pengcheng Huang , Zhenghao Liu , Shuo Wang , Yukun Yan , Chaojun Xiao , Yu Gu , Ge Yu , Maosong Sun

Latent space steering methods provide a practical approach to controlling large language models by applying steering vectors to intermediate activations, guiding outputs toward desired behaviors while avoiding retraining. Despite their…

Machine Learning · Computer Science 2026-01-13 Shawn Im , Sharon Li