Related papers: Visual-Redundancy-Controlled Parallel Decoding for…

Large vision-language models (LVLMs) achieve strong multimodal understanding, but their inference cost grows rapidly with the number of visual tokens, especially for high-resolution images and long videos. Existing attention-based methods…

Multi-view representation learning aims to derive robust representations that are both view-consistent and view-specific from diverse data sources. This paper presents an in-depth analysis of existing approaches in this domain, highlighting…

Recent large-scale vision-language models (VLMs) have shown remarkable text-to-image generation capabilities, yet their visual fidelity remains constrained by the discrete image tokenization, which poses a major challenge. Although several…

Current Multimodal Large Language Model (MLLM) architectures face a critical tradeoff between performance and efficiency: decoder-only architectures achieve higher performance but lower efficiency, while cross-attention-based architectures…

Despite the remarkable capabilities of Large Vision Language Models (LVLMs), they still lack detailed knowledge about specific entities. Retrieval-augmented Generation (RAG) is a widely adopted solution that enhances LVLMs by providing…

The vision tokens in multimodal large language models usually exhibit significant spatial and temporal redundancy and take up most of the input tokens, which harms their inference efficiency. To solve this problem, some recent works were…

By treating visual tokens from visual encoders as text tokens, Multimodal Large Language Models (MLLMs) have achieved remarkable progress across diverse visual understanding tasks, leveraging the robust architectures of Large Language…

Diffusion-based large multimodal models, such as LLaDA-V, have demonstrated impressive capabilities in vision-language understanding and generation. However, their bidirectional attention mechanism and diffusion-style iterative denoising…

The excessive use of visual tokens in existing Multimoal Large Language Models (MLLMs) often exhibits obvious redundancy and brings in prohibitively expensive computation. To gain insights into this problem, we first conduct extensive…

Large-scale contrastive pre-training produces powerful Vision-and-Language Models (VLMs) capable of generating representations (embeddings) effective for a wide variety of visual and multimodal tasks. However, these pretrained embeddings…

Recent progress in multimodal large language models (MLLMs) has highlighted the challenge of efficiently bridging pre-trained Vision-Language Models (VLMs) with Diffusion Models. While methods using a fixed number of learnable query tokens…

Diffusion large language models (dLLMs) enable parallel text generation by iteratively denoising a fully masked sequence, unmasking a subset of masked tokens at each step. Existing decoding strategies rely on static confidence metrics…

Current Video Large Language Models (Video LLMs) typically encode frames via a vision encoder and employ an autoregressive (AR) LLM for understanding and generation. However, this AR paradigm inevitably faces a dual efficiency bottleneck:…

Masked diffusion models have recently emerged as a flexible framework for discrete generative modeling. However, a key limitation of standard masked diffusion is its inability to effectively capture dependencies among tokens that are…

Unified visual grounding pursues a simple and generic technical route to leverage multi-task data with less task-specific design. The most advanced methods typically present boxes and masks as vertex sequences to model referring detection…

Multimodal latent reasoning has emerged as a promising paradigm that replaces explicit Chain-of-Thought (CoT) decoding with implicit feature propagation, simultaneously enhancing representation informativeness and reducing inference…

Diffusion language models enable parallel token generation through block-wise decoding, but their irreversible commitments can lead to stagnation, where the reverse diffusion process fails to make further progress under a suboptimal…

Vision capabilities in vision large language models (VLLMs) have consistently lagged behind their linguistic capabilities. In particular, numerous benchmark studies have demonstrated that VLLMs struggle when fine-grained visual information…

Multi-task visual grounding involves the simultaneous execution of localization and segmentation in images based on textual expressions. The majority of advanced methods predominantly focus on transformer-based multimodal fusion, aiming to…

Despite the remarkable capabilities of Multimodal Large Language Models (MLLMs), they still suffer from visual fading in long-context scenarios. Specifically, the attention to visual tokens diminishes as the text sequence lengthens, leading…