Related papers: CompAgent: An Agentic Framework for Visual Complia…
While vision-language models (VLMs) have demonstrated remarkable performance across various tasks combining textual and visual information, they continue to struggle with fine-grained visual perception tasks that require detailed…
The dominant paradigm of monolithic scaling in Vision-Language Models (VLMs) is failing for understanding and reasoning in documents, yielding diminishing returns as it struggles with the inherent need of this domain for document-based…
Accurate visual understanding is imperative for advancing autonomous systems and intelligent robots. Despite the powerful capabilities of vision-language models (VLMs) in processing complex visual scenes, precisely recognizing obscured or…
Large Multimodal Models (LMMs) have ushered in a new era in artificial intelligence, merging capabilities in both language and vision to form highly capable Visual Foundation Agents. These agents are postulated to excel across a myriad of…
Large Language Model (LLM)-based agentic systems have shown growing promise in tackling complex, multi-step tasks through autonomous planning, reasoning, and interaction with external environments. However, the stochastic nature of LLM…
Emerging 6G networks rely on complex cross-layer optimization, yet manually translating high-level intents into mathematical formulations remains a bottleneck. While Large Language Models (LLMs) offer promise, monolithic approaches often…
We present a Collaborative Agent-Based Framework for Multi-Image Reasoning. Our approach tackles the challenge of interleaved multimodal reasoning across diverse datasets and task formats by employing a dual-agent system: a language-based…
Despite significant advancements in text-to-image models for generating high-quality images, these methods still struggle to ensure the controllability of text prompts over images in the context of complex text prompts, especially when it…
The rapid proliferation of large language model (LLM)-based agentic systems raises critical concerns regarding digital sovereignty, environmental sustainability, regulatory compliance, and ethical alignment. Whilst existing frameworks…
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…
Mathematical error detection in educational settings presents a significant challenge for Multimodal Large Language Models (MLLMs), requiring a sophisticated understanding of both visual and textual mathematical content along with complex…
Recent multimodal LLMs have shown promise in chart-based visual question answering, but their performance declines sharply on unannotated charts-those requiring precise visual interpretation rather than relying on textual shortcuts. To…
Image classification has traditionally relied on parameter-intensive model training, requiring large-scale annotated datasets and extensive fine tuning to achieve competitive performance. While recent vision language models (VLMs) alleviate…
Vision-Language Models (VLMs) often yield inconsistent descriptions of the same object across viewpoints, hindering the ability of embodied agents to construct consistent semantic representations over time. Previous methods resolved…
Multimodal large language models (MLLMs) that integrate visual and textual reasoning leverage chain-of-thought (CoT) prompting to tackle complex visual tasks, yet continue to exhibit visual hallucinations and an over-reliance on textual…
Large language model (LLM) agents are increasingly deployed to tackle complex tasks, often necessitating collaboration among multiple specialized agents. However, multi-agent collaboration introduces new challenges in planning,…
Recent advancements in Multi-modal Large Language Models (MLLMs) have significantly improved their performance in tasks combining vision and language. However, challenges persist in detailed multi-modal understanding, comprehension of…
Real-world visualization tasks involve complex, multi-modal requirements that extend beyond simple text-to-chart generation, requiring reference images, code examples, and iterative refinement. Current systems exhibit fundamental…
The increasing use of synthetic media, particularly deepfakes, is an emerging challenge for digital content verification. Although recent studies use both audio and visual information, most integrate these cues within a single model, which…
Large language models demonstrate remarkable reasoning capabilities but often produce unreliable or incorrect responses. Existing verification methods are typically model-specific or domain-restricted, requiring significant computational…