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

How do vision transformers (ViTs) represent and process the world? This paper addresses this long-standing question through the first systematic analysis of 6.6K features across all layers, extracted via sparse autoencoders, and by…

Though vision transformers (ViTs) have achieved state-of-the-art performance in a variety of settings, they exhibit surprising failures when performing tasks involving visual relations. This begs the question: how do ViTs attempt to perform…

Federated Learning (FL) is a distributed learning paradigm that can learn a global or personalized model from decentralized datasets on edge devices. However, in the computer vision domain, model performance in FL is far behind centralized…

While large language models (LLMs) have seen unprecedented advancements in capabilities and applications across a variety of use-cases, safety alignment of these models is still an area of active research. The fragile nature of LLMs, even…

Vision-Language Action (VLAs) models promise to extend the remarkable success of vision-language models (VLMs) to robotics. Yet, unlike VLMs in the vision-language domain, VLAs for robotics require finetuning to contend with varying…

The deployment of vision-language models remains constrained by substantial computational requirements. We present \textbf{FrEVL}, a framework exploring whether frozen pretrained embeddings can support effective vision-language…

Large language models (LLMs) often encode cognitive behaviors unpredictably across prompts, layers, and contexts, making them difficult to diagnose and control. We present CBMAS, a diagnostic framework for continuous activation steering,…

Reasoning encompasses two typical types: deductive reasoning and inductive reasoning. Despite extensive research into the reasoning capabilities of Large Language Models (LLMs), most studies have failed to rigorously differentiate between…

Vision-language models (VLMs) are powerful but remain opaque black boxes. We introduce the first framework for transparent circuit tracing in VLMs to systematically analyze multimodal reasoning. By utilizing transcoders, attribution graphs,…

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…

Vision Language Models (VLMs) can produce unintended and harmful content when exposed to adversarial attacks, particularly because their vision capabilities create new vulnerabilities. Existing defenses, such as input preprocessing,…

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} --…

In recent years, many interpretability methods have been proposed to help interpret the internal states of Transformer-models, at different levels of precision and complexity. Here, to analyze encoder-decoder Transformers, we propose a…

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…

The integration of Large Language Models (LLMs) into autonomous driving has attracted growing interest for their strong reasoning and semantic understanding abilities, which are essential for handling complex decision-making and long-tail…

Masked diffusion language models (MDLMs) generate text via iterative masked-token denoising, enabling mask-parallel decoding and distinct controllability and efficiency tradeoffs from autoregressive LLMs. Yet, efficient representation-level…

A popular approach to post-training control of large language models (LLMs) is the steering of intermediate latent representations. Namely, identify a well-chosen direction depending on the task at hand and perturbs representations along…

Activation steering has emerged as a powerful tool to shape LLM behavior without the need for weight updates. While its inherent brittleness and unreliability are well-documented, its safety implications remain underexplored. In this work,…

Medical vision-language models (VLMs) offer promise for clinical decision support, yet their reliability under distribution shifts remains a major concern for safe deployment. These models often learn task-agnostic correlations due to…

Vision-Language Models (VLMs) exhibit puzzling failures in multi-object visual tasks, such as hallucinating non-existent elements or failing to identify the most similar objects among distractions. While these errors mirror human cognitive…