相关论文: TRoVe: Discovering Error-Inducing Static Feature B…

When humans observe a physical system, they can easily locate objects, understand their interactions, and anticipate future behavior, even in settings with complicated and previously unseen interactions. For computers, however, learning…

Adapting pre-trained models to new tasks can exhibit varying effectiveness across datasets. Visual prompting, a state-of-the-art parameter-efficient transfer learning method, can significantly improve the performance of out-of-distribution…

Prolonged reinforcement learning with verifiable rewards (RLVR) has been shown to drive continuous improvements in the reasoning capabilities of large language models, but the training is often prone to instabilities, especially in…

Learning to model how the world changes as time elapses has proven a challenging problem for the computer vision community. We propose a self-supervised solution to this problem using temporal cycle consistency jointly in vision and…

Multimodal Large Language Models (MLLMs) suffer from high computational costs due to their massive size and the large number of visual tokens. In this paper, we investigate layer-wise redundancy in MLLMs by introducing a novel metric, Layer…

Existing Video Anomaly Detection (VAD) methods typically rely on task-specific training, leading to strong domain dependency and high training costs. Moreover, most existing methods output only scalar anomaly scores, providing limited…

Recently, reducing redundant visual tokens in vision-language models (VLMs) to accelerate VLM inference has emerged as a hot topic. However, most existing methods rely on heuristics constructed based on inter-visual-token similarity or…

We introduce a novel self-improving framework that enhances Embodied Visual Tracking (EVT) with Vision-Language Models (VLMs) to address the limitations of current active visual tracking systems in recovering from tracking failure. Our…

Existing Scene Text Recognition (STR) methods typically use a language model to optimize the joint probability of the 1D character sequence predicted by a visual recognition (VR) model, which ignore the 2D spatial context of visual…

We present a novel statistical framework for analyzing stereotypes in large language models (LLMs) by systematically estimating the bias and variation in their generation. Current alignment evaluation metrics often overlook stereotypes'…

Despite achieving remarkable performance on various vision-language tasks, Transformer-based Vision-Language Models (VLMs) suffer from redundancy in inputs and parameters, significantly hampering their efficiency in real-world applications.…

Reliable confidence estimation is critical when deploying vision models. We study error prediction: determining whether an image classifier's output is correct using only signals from a single forward pass. Motivated by internal-signal…

Continual Visual Instruction Tuning (CVIT) enables Multimodal Large Language Models to incrementally acquire new abilities. However, existing CVIT methods operate under a restrictive task-incremental setting, where each training phase…

As the Virtual Reality (VR) industry expands, the need for automated GUI testing is growing rapidly. Large Language Models (LLMs), capable of retaining information long-term and analyzing both visual and textual data, are emerging as a…

Vision-language models (VLMs) have recently emerged as powerful representation learning systems that align visual observations with natural language concepts, offering new opportunities for semantic reasoning in safety-critical autonomous…

Understanding the internal representations of large language models is crucial for ensuring their reliability and safety, with sparse autoencoders (SAEs) emerging as a promising interpretability approach. However, current SAE training…

Vision-Language-Action (VLA) models have recently emerged as a promising paradigm for generalist robotic control. Built upon vision-language model (VLM) architectures, VLAs predict actions conditioned on visual observations and language…

Vision-Language Models (VLMs) achieve strong cross-modal performance, yet recent evidence suggests they over-rely on textual descriptions while under-utilizing visual evidence -- a phenomenon termed ``text shortcut learning.'' We propose an…

Vision language models (VLMs) have seen growing adoption in recent years, but many still struggle with basic spatial reasoning errors. We hypothesize that this is due to VLMs adopting pre-trained vision backbones, specifically vision…

The increasing integration of Visual Language Models (VLMs) into AI systems necessitates robust model alignment, especially when handling multimodal content that combines text and images. Existing evaluation datasets heavily lean towards…