相关论文: Exploring the Potential of Encoder-free Architectu…

Large Language Models (LLMs) achieve strong performance across tasks, but face storage and compute challenges on edge devices. We propose EntroLLM, a compression framework combining mixed quantization and entropy coding to reduce storage…

Machine learning for tabular data remains constrained by poor schema generalization, a challenge rooted in the lack of semantic understanding of structured variables. This challenge is particularly acute in domains like clinical medicine,…

Large language models (LLMs) have made significant advances in complex reasoning tasks, yet they remain bottlenecked by two core challenges: architectural inefficiency due to reliance on Transformers, and a lack of structured fine-tuning…

We study model merging as a practical alternative to conventional adaptation strategies for code-mixed NLP. Starting from a multilingual base model, we: (i) perform continued pre-training (CPT) on unlabeled code-mixed text to obtain an…

Despite significant progress in 3D point cloud segmentation, existing methods primarily address specific tasks and depend on explicit instructions to identify targets, lacking the capability to infer and understand implicit user intentions…

3D Vision-Language Models (VLMs), such as PointLLM and GPT4Point, have shown strong reasoning and generalization abilities in 3D understanding tasks. However, their adversarial robustness remains largely unexplored. Prior work in 2D VLMs…

Recent advances in 3D scene-language understanding have leveraged Large Language Models (LLMs) for 3D reasoning by transferring their general reasoning ability to 3D multi-modal contexts. However, existing methods typically adopt standard…

While deep learning-based methods have demonstrated outstanding results in numerous domains, some important functionalities are missing. Resolution scalability is one of them. In this work, we introduce a novel architecture, dubbed…

Large Vision-Language Models (VLMs) exhibit impressive multi-modal capabilities but suffer from prohibitive computational and memory demands, due to their long visual token sequences and massive parameter sizes. To address these issues,…

Embodied multimodal large models (EMLMs) have gained significant attention in recent years due to their potential to bridge the gap between perception, cognition, and action in complex, real-world environments. This comprehensive review…

Large Language Models (LLMs) have so far impressed the world, with unprecedented capabilities that emerge in models at large scales. On the vision side, transformer models (i.e., ViT) are following the same trend, achieving the best…

Recent advancements in building domain-specific large language models (LLMs) have shown remarkable success, especially in tasks requiring reasoning abilities like logical inference over complex relationships and multi-step problem solving.…

Visual encoding constitutes the basis of large multimodal models (LMMs) in understanding the visual world. Conventional LMMs process images in fixed sizes and limited resolutions, while recent explorations in this direction are limited in…

The pre-trained point cloud model based on Masked Point Modeling (MPM) has exhibited substantial improvements across various tasks. However, these models heavily rely on the Transformer, leading to quadratic complexity and limited decoder,…

Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in representing and understanding diverse modalities. However, they typically focus on modality alignment in a pairwise manner while overlooking structural…

Fine-tuning Large Language Models (LLMs) with multimodal encoders on modality-specific data expands the modalities that LLMs can handle, leading to the formation of Multimodal LLMs (MLLMs). However, this paradigm heavily relies on…

Multilingual understanding models (or encoder-based), pre-trained via masked language modeling, have achieved promising results on many language understanding tasks (e.g., mBERT). However, these non-autoregressive (NAR) models still…

Vision-language pretraining has advanced image-text alignment, yet progress in radiology remains constrained by the heterogeneity of clinical reports, including abbreviations, impression-only notes, and stylistic variability. Unlike…

A language model (LM) is a mapping from a linguistic context to an output token. However, much remains to be known about this mapping, including how its geometric properties relate to its function. We take a high-level geometric approach to…

We propose EMMA, an efficient and unified architecture for multimodal understanding, generation and editing. Specifically, EMMA primarily consists of 1) An efficient autoencoder with a 32x compression ratio, which significantly reduces the…