相关论文: COSMIC: Generalized Refusal Direction Identificati…

Robot planning in partially observable environments, where not all objects are known or visible, is a challenging problem, as it requires reasoning under uncertainty through partially observable Markov decision processes. During the…

Leveraging Large Language Models as Recommenders (LLMRec) has gained significant attention and introduced fresh perspectives in user preference modeling. Existing LLMRec approaches prioritize text semantics, usually neglecting the valuable…

Understanding large-scale, complex software systems is a major challenge for developers, who spend a significant portion of their time on program comprehension. Traditional tools such as static visualizations and reverse engineering…

Vision-language models (VLMs), such as CLIP and SigLIP, have found remarkable success in classification, retrieval, and generative tasks. For this, VLMs deterministically map images and text descriptions to a joint latent space in which…

Machine unlearning aims to remove specific information, e.g. sensitive or undesirable content, from large language models (LLMs) while preserving overall performance. We propose an inference-time unlearning algorithm that uses contrastive…

Large Language Models (LLMs) have recently emerged as promising tools for recommendation thanks to their advanced textual understanding ability and context-awareness. Despite the current practice of training and evaluating LLM-based…

With rapid advances in code generation, reasoning, and problem-solving, Large Language Models (LLMs) are increasingly applied in robotics. Most existing work focuses on high-level tasks such as task decomposition. A few studies have…

Controlling multiple behavioral attributes in large language models (LLMs) at inference time is a challenging problem due to interference between attributes and the limitations of linear steering methods, which assume additive behavior in…

Reasoning over very long inputs remains difficult for large language models (LLMs). Common workarounds either shrink the input via retrieval (risking missed evidence), enlarge the context window (straining selectivity), or stage multiple…

Human action recognition (HAR) with multi-modal inputs (RGB-D, skeleton, point cloud) can achieve high accuracy but typically relies on large labeled datasets and degrades sharply when sensors fail or are noisy. We present Robust…

Large language models (LLMs) have demonstrated remarkable capabilities in simulating human behaviour and social intelligence. However, they risk perpetuating societal biases, especially when demographic information is involved. We introduce…

Recent advances in large language models (LLMs) have intensified the need to understand and reliably curb their harmful behaviours. We introduce a multidimensional framework for probing and steering harmful content in model internals. For…

Recovering the structure of causal graphical models from observational data is an essential yet challenging task for causal discovery in scientific scenarios. Domain-specific causal discovery usually relies on expert validation or prior…

We propose a method to teach multiple large language models (LLM) to collaborate by interleaving their generations at the token level. We model the decision of which LLM generates the next token as a latent variable. By optimizing the…

The field of large language models (LLMs) has grown rapidly in recent years, driven by the desire for better efficiency, interpretability, and safe use. Building on the novel approach of "activation engineering," this study explores…

Human intention-based systems enable robots to perceive and interpret user actions to interact with humans and adapt to their behavior proactively. Therefore, intention prediction is pivotal in creating a natural interaction with social…

Multimodal learning from document data has achieved great success lately as it allows to pre-train semantically meaningful features as a prior into a learnable downstream task. In this paper, we approach the document classification problem…

Despite the success of Large Language Models (LLMs) across various fields, their potential to generate untruthful, biased and harmful responses poses significant risks, particularly in critical applications. This highlights the urgent need…

Large Language Models (LLMs) are prone to generating fluent but incorrect content, known as confabulation, which poses increasing risks in multi-turn or agentic applications where outputs may be reused as context. In this work, we…

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…