相关论文: Steerable but Not Decodable: Function Vectors Oper…

Language provides a natural interface to specify and evaluate performance on visual tasks. To realize this possibility, vision language models (VLMs) must successfully integrate visual and linguistic information. Our work compares VLMs to a…

Identifying control-friendly models of nonlinear systems remains one of the major challenges at the intersection of system identification and control. The Linear Parameter-Varying (LPV) framework offers a promising solution, but existing…

Vision-Language-Action (VLA) models are increasingly expected to not only complete robot tasks, but also follow human instructions about how those tasks should be executed. However, existing robot datasets usually pair trajectories with…

Researchers have been studying approaches to steer the behavior of Large Language Models (LLMs) and build personalized LLMs tailored for various applications. While fine-tuning seems to be a direct solution, it requires substantial…

Sparse autoencoders (SAEs) improve interpretability in multimodal models, but it remains unclear whether SAE features form modular, composable units for reasoning-an assumption underlying many intervention-based steering methods. We test…

Shouldn't language and vision features be treated equally in vision-language (VL) tasks? Many VL approaches treat the language component as an afterthought, using simple language models that are either built upon fixed word embeddings…

Understanding a program's runtime reasoning behavior, meaning how intermediate states and control flows lead to final execution results, is essential for reliable code generation, debugging, and automated reasoning. Although large language…

As Vision-Language Models (VLMs) grow in sophistication, their ability to perform reasoning is coming under increasing supervision. While they excel at many tasks, their grasp of fundamental scientific principles, such as physics, remains…

Recent advances in Multimodal Large Language Models (MLLMs) have significantly improved performance on tasks such as visual grounding and visual question answering. However, the reasoning processes of these models remain largely opaque;…

Vision Language Models (VLMs) have achieved remarkable success by integrating visual encoders with large language models (LLMs). While VLMs process dense image tokens across deep transformer stacks (incurring substantial computational…

Encoder-decoder models such as FLAN-T5 are finetuned to follow instructions, but often fail when the instructions conflict with memorized continuations ingrained during training. To understand this behavior, we adapt DoLa to FLAN-T5 and…

Embedding models have been crucial in enabling various downstream tasks such as semantic similarity, information retrieval, and clustering. Recently, there has been a surge of interest in developing universal text embedding models that can…

In this article, we investigate vision-language models (VLM) as reasoners. The ability to form abstractions underlies mathematical reasoning, problem-solving, and other Math AI tasks. Several formalisms have been given to these underlying…

Large language models (LLMs) increasingly serve as automated evaluators, yet they suffer from "self-preference bias": a tendency to favor their own outputs over those of other models. This bias undermines fairness and reliability in…

Neural decoding, the process of understanding how brain activity corresponds to different stimuli, has been a primary objective in cognitive sciences. Over the past three decades, advances in functional Magnetic Resonance Imaging (fMRI) and…

Recent transformer-based methods achieve notable gains in the Human-object Interaction Detection (HOID) task by leveraging the detection of DETR and the prior knowledge of Vision-Language Model (VLM). However, these methods suffer from…

This paper investigates how Large Language Models (LLMs) represent non-English tokens -- a question that remains underexplored despite recent progress. We propose a lightweight intervention method using representation steering, where a…

Linear activation steering is a powerful approach for eliciting the capabilities of large language models and specializing their behavior using limited labeled data. While effective, existing methods often apply a fixed steering strength to…

Multimodal Large Language Models (MLLMs) struggle with tasks that require reasoning about 2D object orientation in images, as documented in prior work. Tong et al. and Nichols et al. hypothesize that these failures originate in the visual…

Vision-Language-Action (VLA) models combine perception, language, and motor control in a single architecture, yet how they translate multimodal inputs into actions remains poorly understood. We apply activation injection, sparse…