English
Related papers

Related papers: Spherical Steering: Geometry-Aware Activation Rota…

200 papers

Non-prehensile manipulation is challenging due to complex contact interactions between objects, the environment, and robots. Model-based approaches can efficiently generate complex trajectories of robots and objects under contact…

Robotics · Computer Science 2025-08-07 Yuki Shirai , Kei Ota , Devesh K. Jha , Diego Romeres

Time series foundation models (TSFMs) promise to be powerful tools for a wide range of applications. However, their internal representations and learned concepts are still not well understood. In this study, we investigate the structure and…

Machine Learning · Computer Science 2025-06-09 Michał Wiliński , Mononito Goswami , Willa Potosnak , Nina Żukowska , Artur Dubrawski

Speculative Decoding has emerged as a popular technique for accelerating inference in Large Language Models. However, most existing approaches yield only modest improvements in production serving systems. Methods that achieve substantial…

Computation and Language · Computer Science 2026-01-08 Michele Marzollo , Jiawei Zhuang , Niklas Roemer , Niklas Zwingenberger , Lorenz K. Müller , Lukas Cavigelli

Imitation learning has shown great potential for enabling robots to acquire complex manipulation behaviors. However, these algorithms suffer from high sample complexity in long-horizon tasks, where compounding errors accumulate over the…

Robotics · Computer Science 2024-08-20 Tian Gao , Soroush Nasiriany , Huihan Liu , Quantao Yang , Yuke Zhu

Deploying LLMs in real-world applications requires controllable output that satisfies multiple desiderata at the same time. While existing work extensively addresses LLM steering for a single behavior, \textit{compositional steering} --…

Computation and Language · Computer Science 2026-04-21 Gorjan Radevski , Kiril Gashteovski , Giwon Hong , Carolin Lawrence , Goran Glavaš

Large language model (LLM) steering has emerged as a promising paradigm for controlling model behavior at inference time through targeted manipulation of hidden states, offering a lightweight alternative to expensive retraining. However,…

Computation and Language · Computer Science 2026-03-03 Haolei Xu , Xinyu Mei , Yuchen Yan , Rui Zhou , Wenqi Zhang , Weiming Lu , Yueting Zhuang , Yongliang Shen

Symmetries, e.g. rotational and translational invariances for the class of mechanical systems, allow to characterize solution trajectories of nonlinear dynamical systems. Thus, the restriction to symmetry-induced dynamics, e.g. by using the…

Optimization and Control · Mathematics 2019-06-24 Kathrin Flaßkamp , Sina Ober-Blöbaum , Karl Worthmann

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

Low-dimensional projections of text embeddings support visual analysis of document collections, but their spatial organization may not reflect the relationships an analyst intends to examine. Existing semantic interaction approaches encode…

Human-Computer Interaction · Computer Science 2026-05-05 Wei Liu , Eric Krokos , Kirsten Whitley , Rebecca Faust , Chris North

Learned Sparse Retrieval (LSR) is an effective IR approach that exploits pre-trained language models for encoding text into a learned bag of words. Several efforts in the literature have shown that sparsity is key to enabling a good…

Information Retrieval · Computer Science 2025-05-06 Franco Maria Nardini , Thong Nguyen , Cosimo Rulli , Rossano Venturini , Andrew Yates

Large Language Models (LLMs) encode vast amounts of parametric knowledge during pre-training. As world knowledge evolves, effective deployment increasingly depends on their ability to faithfully follow externally retrieved context. When…

Computation and Language · Computer Science 2026-01-13 Nikhil Anand , Shwetha Somasundaram , Anirudh Phukan , Apoorv Saxena , Koyel Mukherjee

Large language models sometimes assert falsehoods despite internally representing the correct answer, failures of honesty rather than accuracy, which undermines auditability and safety. Existing approaches largely optimize factual…

Machine Learning · Computer Science 2025-12-09 Gracjan Góral , Marysia Winkels , Steven Basart

Recent advances in Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in solving complex tasks such as mathematics and coding. However, these models frequently exhibit a phenomenon known as overthinking during…

Machine Learning · Computer Science 2025-11-18 Yao Huang , Huanran Chen , Shouwei Ruan , Yichi Zhang , Xingxing Wei , Yinpeng Dong

Large language models (LLMs) require precise behavior control for safe and effective deployment across diverse applications. Activation steering offers a promising approach for LLMs' behavioral control. We focus on the question of how…

Artificial Intelligence · Computer Science 2026-01-13 Tetiana Bas , Krystian Novak

How large language models (LLMs) align with the neural representation and computation of human language is a central question in cognitive science. Using representational geometry as a mechanistic lens, we addressed this by tracking…

Neurons and Cognition · Quantitative Biology 2026-02-10 Yixuan Liu , Zhiyuan Ma , Likai Tang , Runmin Gan , Xinche Zhang , Jinhao Li , Chao Xie , Sen Song

Controlling the behavior of large language models (LLMs) at inference time is essential for aligning outputs with human abilities and safety requirements. \emph{Activation steering} provides a lightweight alternative to prompt engineering…

Artificial Intelligence · Computer Science 2026-01-30 Diaoulé Diallo , Katharina Dworatzyk , Sophie Jentzsch , Peer Schütt , Sabine Theis , Tobias Hecking

Providing high-quality feedback to Large Language Models (LLMs) on a diverse training distribution can be difficult and expensive, and providing feedback only on a narrow distribution can result in unintended generalizations. To better…

Computation and Language · Computer Science 2026-03-02 Constanza Fierro , Fabien Roger

Imitation learning frameworks for robotic manipulation have drawn attention in the recent development of language model grounded robotics. However, the success of the frameworks largely depends on the coverage of the demonstration cases:…

Robotics · Computer Science 2025-03-10 Tong Mu , Yihao Liu , Mehran Armand

Large language models (LLMs) have achieved remarkable performance across many generation tasks. Nevertheless, effectively aligning them with desired behaviors remains a significant challenge. Activation steering is an effective and…

Computation and Language · Computer Science 2025-10-02 Zifeng Cheng , Jinwei Gan , Zhiwei Jiang , Cong Wang , Yafeng Yin , Xiang Luo , Yuchen Fu , Qing Gu

Shared-autonomy imitation learning lets a human correct a robot in real time, mitigating covariate-shift errors. Yet existing approaches ignore two critical factors: (i) the operator's cognitive load and (ii) the risk created by delayed or…

Robotics · Computer Science 2025-06-18 Taewoo Kim , Donghyung Kim , Minsu Jang , Jaehong Kim