Related papers: Train a Unified Multimodal Data Quality Classifier…

Image captioning requires numerous annotated image-text pairs, resulting in substantial annotation costs. Recently, large models (e.g. diffusion models and large language models) have excelled in producing high-quality images and text. This…

Although vision models such as Contrastive Language-Image Pre-Training (CLIP) show impressive generalization performance, their zero-shot robustness is still limited under Out-of-Distribution (OOD) scenarios without fine-tuning. Instead of…

Visual storytelling is an emerging field that combines images and narratives to create engaging and contextually rich stories. Despite its potential, generating coherent and emotionally resonant visual stories remains challenging due to the…

Recent advancements in Unified Multimodal Models (UMMs) have enabled remarkable image understanding and generation capabilities. However, while models like Gemini-2.5-Flash-Image show emerging abilities to reason over multiple related…

Dataset curation has become a basis for strong large language model (LLM) performance. While various rule-based filtering heuristics exist for English and multilingual datasets, model-based filtering techniques have primarily focused on…

Traditional multimodal learners find unified representations for tasks like visual question answering, but rely heavily on paired datasets. However, an overlooked yet potentially powerful question is: can one leverage auxiliary unpaired…

LLMs trained on massive datasets may inadvertently acquire sensitive information such as personal details and potentially harmful content. This risk is further heightened in multimodal LLMs as they integrate information from multiple…

Current instruction-based editing methods, such as InstructPix2Pix, often fail to produce satisfactory results in complex scenarios due to their dependence on the simple CLIP text encoder in diffusion models. To rectify this, this paper…

The hypothesis that pretrained large language models (LLMs) necessitate only minimal supervision during the fine-tuning (SFT) stage (Zhou et al., 2024) has been substantiated by recent advancements in data curation and selection research.…

We present ReMatch, a framework that leverages the generative strength of MLLMs for multimodal retrieval. Previous approaches treated an MLLM as a simple encoder, ignoring its generative nature, and under-utilising its compositional…

Unified multimodal models have shown promising results in multimodal content generation and editing but remain largely limited to the image domain. In this work, we present UniVideo, a versatile framework that extends unified modeling to…

Training Large Multimodality Models (LMMs) relies on descriptive image caption that connects image and language. Existing methods for generating such captions often rely on distilling the captions from pretrained LMMs, constructing them…

Multimodal large language models (MLLMs) have gained significant attention due to their strong multimodal understanding capability. However, existing works rely heavily on modality-specific encoders, which usually differ in architecture and…

Long-context language models unlock advanced capabilities in reasoning, code generation, and document summarization by leveraging dependencies across extended spans of text. However, a significant portion of readily available long-text data…

Multimodal Large Language Models (MLLMs) show impressive vision-language benchmark performance, yet growing concerns about data contamination (test set exposure during training) risk masking true generalization. This concern extends to…

Multimodal large language models (MLLMs) deployed on devices must adapt to continuously changing visual scenarios such as variations in background and perspective, to effectively perform complex visual tasks. To investigate catastrophic…

Multimodal Large Language Models (mLLMs) are trained on a large amount of text-image data. While most mLLMs are trained on caption-like data only, Alayrac et al. (2022) showed that additionally training them on interleaved sequences of text…

Contemporary news reporting increasingly features multimedia content, motivating research on multimedia event extraction. However, the task lacks annotated multimodal training data and artificially generated training data suffer from…

Image-text interleaved data, consisting of multiple images and texts arranged in a natural document format, aligns with the presentation paradigm of internet data and closely resembles human reading habits. Recent studies have shown that…

Multimodal large language models are typically trained in two stages: first pre-training on image-text pairs, and then fine-tuning using supervised vision-language instruction data. Recent studies have shown that large language models can…