Related papers: SAGE: A Visual Language Model for Anomaly Detectio…

Detecting visual anomalies in diverse, multi-class real-world images is a significant challenge. We introduce \ours, a novel unsupervised multi-class visual anomaly detection framework. It integrates a Latent Diffusion Model (LDM) with a…

Domain-specific intelligence demands specialized knowledge and sophisticated reasoning for problem-solving, posing significant challenges for large language models (LLMs) that struggle with knowledge hallucination and inadequate reasoning…

Visual token compression is widely used to accelerate large vision-language models (LVLMs) by pruning or merging visual tokens, yet its adversarial robustness remains unexplored. We show that existing encoder-based attacks cannot fully…

Sparse Autoencoders (SAEs) have recently gained attention as a means to improve the interpretability and steerability of Large Language Models (LLMs), both of which are essential for AI safety. In this work, we extend the application of…

Reasoning Vision-Language Models (VLMs) have shown promising performance on complex multimodal tasks. However, they still face significant challenges: they are highly sensitive to reasoning errors, require large volumes of annotated data or…

Reasoning has emerged as a pivotal capability in Large Language Models (LLMs). Through Reinforcement Learning (RL), typically Group Relative Policy Optimization (GRPO), these models are able to solve complex tasks such as mathematics and…

Reinforcement Learning (RL) agents often struggle to generalize knowledge to new tasks, even those structurally similar to ones they have mastered. Although recent approaches have attempted to mitigate this issue via zero-shot transfer,…

Vision language models (VLM) have demonstrated remarkable performance across various downstream tasks. However, understanding fine-grained visual-linguistic concepts, such as attributes and inter-object relationships, remains a significant…

Existing visual reasoning datasets such as Visual Question Answering (VQA), often suffer from biases conditioned on the question, image or answer distributions. The recently proposed CLEVR dataset addresses these limitations and requires…

The rapid advancement of AI-powered smart glasses-one of the hottest wearable devices-has unlocked new frontiers for multimodal interaction, with Visual Question Answering (VQA) over external knowledge sources emerging as a core…

A recent trend in vision-language models (VLMs) has been to enhance their spatial cognition for embodied domains. Despite progress, existing evaluations have been limited both in paradigm and in coverage, hindering rapid, iterative model…

While Machine Learning has become crucial for Industry 4.0, its opaque nature hinders trust and impedes the transformation of valuable insights into actionable decision, a challenge exacerbated in the evolving Industry 5.0 with its…

Expressway video anomaly detection is essential for safety management. However, identifying anomalies across diverse scenes remains challenging, particularly for far-field targets exhibiting subtle abnormal vehicle motions. While…

Reinforcement learning (RL) has demonstrated notable success in post-training large language models (LLMs) as agents for tasks such as computer use, tool calling, and coding. However, exploration remains a central challenge in RL for LLM…

Current multimodal models often suffer from shallow reasoning, leading to errors caused by incomplete or inconsistent thought processes. To address this limitation, we propose Self-Verification and Self-Rectification (SVSR), a unified…

Recent years have witnessed a significant increase in the performance of Vision and Language tasks. Foundational Vision-Language Models (VLMs), such as CLIP, have been leveraged in multiple settings and demonstrated remarkable performance…

Visual retrieval-augmented generation (VRAG) augments vision-language models (VLMs) with external visual knowledge to ground reasoning and reduce hallucinations. Yet current VRAG systems often fail to reliably perceive and integrate…

Existing methods for explainable artificial intelligence (XAI), including popular feature importance measures such as SAGE, are mostly restricted to the batch learning scenario. However, machine learning is often applied in dynamic…

Diffusion models manifest evident benefits across diverse domains, yet their high sampling cost, requiring dozens of sequential model evaluations, remains a major limitation. Prior efforts mainly accelerate sampling via optimized solvers or…

Vision-Language Models (VLMs) have emerged as a promising approach to address the data scarcity challenge in robotics, enabling the development of generalizable visuomotor control policies. While models like OpenVLA showcase the potential…