Related papers: Are We Making Progress in Multimodal Domain Genera…

Recently, multimodal graph learning (MGL) has garnered significant attention for integrating diverse modality information and structured context to support various network applications. However, real-world graphs are often isolated due to…

Multimodal learning has become a prominent research area, with the potential of substantial performance gains by combining information across modalities. At the same time, model development has trended toward increasingly complex deep…

Recent advances in Retrieval-Augmented Generation (RAG) have significantly improved response accuracy and relevance by incorporating external knowledge into Large Language Models (LLMs). However, existing RAG methods primarily focus on…

The misuse of advanced generative AI models has resulted in the widespread proliferation of falsified data, particularly forged human-centric audiovisual content, which poses substantial societal risks (e.g., financial fraud and social…

Tabular Foundation Models have recently established the state of the art in supervised tabular learning, by leveraging pretraining to learn generalizable representations of numerical and categorical structured data. However, they lack…

Existing MLLM benchmarks face significant challenges in evaluating Unified MLLMs (U-MLLMs) due to: 1) lack of standardized benchmarks for traditional tasks, leading to inconsistent comparisons; 2) absence of benchmarks for mixed-modality…

Multimodal emotion recognition plays a crucial role in enhancing user experience in human-computer interaction. Over the past few decades, researchers have proposed a series of algorithms and achieved impressive progress. Although each…

The explosive growth of various types of big data and advances in AI technologies have catalyzed a new type of workloads called multi-modal DNNs. Multi-modal DNNs are capable of interpreting and reasoning about information from multiple…

Multimodal learning, which integrates diverse data sources such as images, text, and structured data, has proven superior to unimodal counterparts in high-stakes decision-making. However, while performance gains remain the gold standard for…

Reward models play an essential role in training vision-language models (VLMs) by assessing output quality to enable aligning with human preferences. Despite their importance, the research community lacks comprehensive open benchmarks for…

The popularity of multimodal large language models (MLLMs) has triggered a recent surge in research efforts dedicated to evaluating these models. Nevertheless, existing evaluation studies of MLLMs primarily focus on the comprehension and…

Multimodal Large Language models (MLLMs) have shown promise in web-related tasks, but evaluating their performance in the web domain remains a challenge due to the lack of comprehensive benchmarks. Existing benchmarks are either designed…

Adaptive multimodal reasoning has emerged as a promising frontier in Vision-Language Models (VLMs), aiming to dynamically modulate between tool-augmented visual reasoning and text reasoning to enhance both effectiveness and efficiency.…

Machine learning typically relies on the assumption that training and testing distributions are identical and that data is centrally stored for training and testing. However, in real-world scenarios, distributions may differ significantly…

With the rapid growth of academic publications, peer review has become an essential yet time-consuming responsibility within the research community. Large Language Models (LLMs) have increasingly been adopted to assist in the generation of…

Multimodal Large Languages models have been progressing from uni-modal understanding toward unifying visual, audio and language modalities, collectively termed omni models. However, the correlation between uni-modal and omni-modal remains…

A critical yet frequently overlooked challenge in the field of deepfake detection is the lack of a standardized, unified, comprehensive benchmark. This issue leads to unfair performance comparisons and potentially misleading results.…

Recent multimodal image generators such as GPT-4o, Gemini 2.0 Flash, and Gemini 2.5 Pro excel at following complex instructions, editing images and maintaining concept consistency. However, they are still evaluated by disjoint toolkits:…

Despite impressive performance on standard benchmarks, multimodal large language models (MLLMs) face critical challenges in real-world clinical environments where medical images inevitably suffer various quality degradations. Existing…

Multimodal Large Language Models are primarily trained and evaluated on aligned image-text pairs, which leaves their ability to detect and resolve real-world inconsistencies largely unexplored. In open-domain applications visual and textual…