相关论文: Logics-Parsing-Omni Technical Report

Understanding human instructions to identify the target objects is vital for perception systems. In recent years, the advancements of Large Language Models (LLMs) have introduced new possibilities for image segmentation. In this work, we…

Multimodal large language models (MLLMs) have made significant progress in vision-language understanding, yet effectively aligning different modalities remains a fundamental challenge. We present a framework that unifies multimodal…

With the proliferation of images in online content, language-guided image retrieval (LGIR) has emerged as a research hotspot over the past decade, encompassing a variety of subtasks with diverse input forms. While the development of large…

Recent advances in Large Multi-modal Models (LMMs) have demonstrated their remarkable success as general-purpose multi-modal assistants, with particular focuses on holistic image- and video-language understanding. Conversely, less attention…

Compositional visual reasoning has emerged as a key research frontier in multimodal AI, aiming to endow machines with the human-like ability to decompose visual scenes, ground intermediate concepts, and perform multi-step logical inference.…

The practical deployment of medical vision-language models (Med-VLMs) necessitates seamless integration of textual data with diverse visual modalities, including 2D/3D images and videos, yet existing models typically employ separate…

Multimodal Large Language Models (MLLMs) have achieved significant advances in integrating visual and linguistic information, yet their ability to reason about complex and real-world scenarios remains limited. The existing benchmarks are…

Although Multimodal Large Language Models (MLLMs) demonstrate strong omni-modal perception, their ability to forecast future events from audio-visual cues remains largely unexplored, as existing benchmarks focus mainly on retrospective…

The emergence of large multimodal models (LMMs) has brought significant advancements to pathology. Previous research has primarily focused on separately training patch-level and whole-slide image (WSI)-level models, limiting the integration…

Open-world 3D scene understanding is a critical challenge that involves recognizing and distinguishing diverse objects and categories from 3D data, such as point clouds, without relying on manual annotations. Traditional methods struggle…

While multimodal LLMs (MLLMs) demonstrate remarkable reasoning progress, their application in specialized scientific domains like physics reveals significant gaps in current evaluation benchmarks. Specifically, existing benchmarks often…

Recent large language models (LLMs) have advanced table understanding capabilities but rely on converting tables into text sequences. While multimodal large language models (MLLMs) enable direct visual processing, they face limitations in…

As large-scale models evolve, language instructions are increasingly utilized in multi-modal tasks. Due to human language habits, these instructions often contain ambiguities in real-world scenarios, necessitating the integration of visual…

To extend the reinforcement learning post-training paradigm to omni-modal models for concurrently bolstering video-audio understanding and collaborative reasoning, we propose OmniJigsaw, a generic self-supervised framework built upon a…

Amodal completion, the task of inferring invisible object parts, faces significant challenges in maintaining semantic consistency and structural integrity. Prior progressive approaches are inherently limited by inference instability and…

Large Multimodal Models (LMMs) have become increasingly versatile, accompanied by impressive Optical Character Recognition (OCR) related capabilities. Existing OCR-related benchmarks emphasize evaluating LMMs' abilities of relatively simple…

Large Language Models have demonstrated remarkable reasoning capability in complex textual tasks. However, multimodal reasoning, which requires integrating visual and textual information, remains a significant challenge. Existing…

Understanding a visualization is a multi-level process. A reader must extract and extrapolate from numeric facts, understand how those facts apply to both the context of the data and other potential contexts, and draw or evaluate…

Despite the progress of image segmentation for accurate visual entity segmentation, completing the diverse requirements of image editing applications for different-level region-of-interest selections remains unsolved. In this paper, we…

We introduce WorldSense, the first benchmark to assess the multi-modal video understanding, that simultaneously encompasses visual, audio, and text inputs. In contrast to existing benchmarks, our WorldSense has several features:…