While current KGE methods have shown success, many are limited to the graph structure alone, neglecting the wealth of open-world knowledge surrounding entities not explicitly depicted in the KG, which is manually created in most cases.

While this refusal behavior is widespread across chat models, its underlying mechanisms remain poorly understood. In this work, we show that refusal is mediated by a one-dimensional subspace, across 13 popular open-source chat models up to 72B parameters in size.

The current paradigm of evaluating Large Language Models (LLMs) through static benchmarks comes with significant limitations, such as vulnerability to data contamination and a lack of adaptability to the evolving capabilities of LLMs.

Large multimodal models (LMMs) combine unimodal encoders and large language models (LLMs) to perform multimodal tasks.

Illustration is a fundamental mode of human expression and communication.

However, the complexity and duration of procedural activities inherently increase the likelihood of making errors.

While efforts have been made to explain computer vision models, these approaches often fall short of providing direct and human-understandable explanations.

Vision Language Models (VLMs) have demonstrated remarkable performance in 2D vision and language tasks. However, their ability to reason about spatial arrangements remains limited. In this work, we introduce Spatial Region GPT (SpatialRGPT) to enhance VLMs' spatial perception and reasoning capabilities.

Membership Inference Attacks (MIA) aim to infer whether a target data record has been utilized for model training or not.