Related papers: SARE: Sample-wise Adaptive Reasoning for Training-…

Large language models (LLMs) have shown promise in generating program workflows for visual tasks. However, previous approaches often rely on closed-source models, lack systematic reasoning, and struggle with long-form video question…

While Vision-Language Models (VLMs) have shown promising progress in general multimodal tasks, they often struggle in industrial anomaly detection and reasoning, particularly in delivering interpretable explanations and generalizing to…

Recent advances in Visual Language Models (VLMs) have demonstrated exceptional performance in visual reasoning tasks. However, geo-localization presents unique challenges, requiring the extraction of multigranular visual cues from images…

Pre-trained visual language models (VLM) have shown excellent performance in image caption tasks. However, it sometimes shows insufficient reasoning ability. In contrast, large language models (LLMs) emerge with powerful reasoning…

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…

Few-shot recognition (FSR) aims to train a classification model with only a few labeled examples of each concept concerned by a downstream task, where data annotation cost can be prohibitively high. We develop methods to solve FSR by…

Large Vision Language Models (LVLMs) possess extensive text knowledge but struggles to utilize this knowledge for fine-grained image recognition, often failing to differentiate between visually similar categories. Existing fine-tuning…

Vision language models (VLMs) are increasingly capable of reasoning over images, but robust visual reasoning often requires re-grounding intermediate steps in the underlying visual evidence. Recent approaches typically rely on external…

Reinforcement Learning with Verifiable Reward (RLVR) is empirically shown to notably enhance the reasoning performance of large language models (LLMs), particularly in mathematics and programming. However, the mechanistic role of Sample…

Recent advances in instruction-tuned Large Vision-Language Models (LVLMs) have imbued the models with the ability to generate high-level, image-grounded explanations with ease. While such capability is largely attributed to the rich world…

Vocabulary-free fine-grained image recognition aims to distinguish visually similar categories within a meta-class without a fixed, human-defined label set. Existing solutions for this problem are limited by either the usage of a large and…

Large Vision-Language Models (LVLMs) have become pivotal at the intersection of computer vision and natural language processing. However, the full potential of LVLMs Retrieval-Augmented Generation (RAG) capabilities remains underutilized.…

While Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities for reasoning and self-correction at the textual level, these strengths provide minimal benefits for complex tasks centered on visual perception, such as…

We introduce FLARE, a family of vision language models (VLMs) with a fully vision-language alignment and integration paradigm. Unlike existing approaches that rely on single MLP projectors for modality alignment and defer cross-modal…

Recent studies posit that Reinforcement Learning with Verifiable Rewards (RLVR) primarily amplifies behaviors inherent to the pre-training distribution rather than inducing new capabilities, but these insights are predominantly limited to…

By combining natural language understanding, generation capabilities, and breadth of knowledge of large language models with image perception, recent large vision language models (LVLMs) have shown unprecedented visual reasoning…

Vision-language models (VLMs) have shown remarkable abilities by integrating large language models with visual inputs. However, they often fail to utilize visual evidence adequately, either depending on linguistic priors in vision-centric…

Effectively applying Vision-Language Models (VLMs) to Video Question Answering (VideoQA) hinges on selecting a concise yet comprehensive set of frames, as processing entire videos is computationally infeasible. However, current frame…

Despite recent advancements in Multi-modal Large Language Models (MLLMs) on diverse understanding tasks, these models struggle to solve problems which require extensive multi-step reasoning. This is primarily due to the progressive dilution…

Efficiently enhancing the reasoning capabilities of Vision-Language Models (VLMs) by merging them with Large Reasoning Models (LRMs) has emerged as a promising direction. However, existing methods typically operate at a coarse-grained layer…