Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis

This paper does not describe a new method; instead, it provides a thorough exploration of an important yet understudied design space related to recent advances in text-to-image synthesis -- specifically, the deep fusion of large language models (LLMs) and diffusion transformers (DiTs) for multi-modal generation. Previous studies mainly focused on overall system performance rather than detailed comparisons with alternative methods, and key design details and training recipes were often left undisclosed. These gaps create uncertainty about the real potential of this approach. To fill these gaps, we conduct an empirical study on text-to-image generation, performing controlled comparisons with established baselines, analyzing important design choices, and providing a clear, reproducible recipe for training at scale. We hope this work offers meaningful data points and practical guidelines for future research in multi-modal generation.

VividMed: Vision Language Model with Versatile Visual Grounding for Medicine

Recent advancements in Vision Language Models (VLMs) have demonstrated remarkable promise in generating visually grounded responses. However, their application in the medical domain is hindered by unique challenges. For instance, most VLMs rely on a single method of visual grounding, whereas complex medical tasks demand more versatile approaches. Additionally, while most VLMs process only 2D images, a large portion of medical images are 3D. The lack of medical data further compounds these obstacles. To address these challenges, we present VividMed, a vision language model with versatile visual grounding for medicine. Our model supports generating both semantic segmentation masks and instance-level bounding boxes, and accommodates various imaging modalities, including both 2D and 3D data. We design a three-stage training procedure and an automatic data synthesis pipeline based on open datasets and models. Besides visual grounding tasks, VividMed also excels in other common downstream tasks, including Visual Question Answering (VQA) and report generation. Ablation studies empirically show that the integration of visual grounding ability leads to improved performance on these tasks. Our code is publicly available at https://github.com/function2-llx/MMMM.

CORE4D: A 4D Human-Object-Human Interaction Dataset for Collaborative Object REarrangement

Understanding how humans cooperatively rearrange household objects is critical for VR/AR and human-robot interaction. However, in-depth studies on modeling these behaviors are under-researched due to the lack of relevant datasets. We fill this gap by presenting CORE4D, a novel large-scale 4D human-object-human interaction dataset focusing on collaborative object rearrangement, which encompasses diverse compositions of various object geometries, collaboration modes, and 3D scenes. With 1K human-object-human motion sequences captured in the real world, we enrich CORE4D by contributing an iterative collaboration retargeting strategy to augment motions to a variety of novel objects. Leveraging this approach, CORE4D comprises a total of 11K collaboration sequences spanning 3K real and virtual object shapes. Benefiting from extensive motion patterns provided by CORE4D, we benchmark two tasks aiming at generating human-object interaction: human-object motion forecasting and interaction synthesis. Extensive experiments demonstrate the effectiveness of our collaboration retargeting strategy and indicate that CORE4D has posed new challenges to existing human-object interaction generation methodologies. Our dataset and code are available at https://github.com/leolyliu/CORE4D-Instructions.

ObscurePrompt: Jailbreaking Large Language Models via Obscure Input

Recently, Large Language Models (LLMs) have garnered significant attention for their exceptional natural language processing capabilities. However, concerns about their trustworthiness remain unresolved, particularly in addressing "jailbreaking" attacks on aligned LLMs. Previous research predominantly relies on scenarios with white-box LLMs or specific and fixed prompt templates, which are often impractical and lack broad applicability. In this paper, we introduce a straightforward and novel method, named ObscurePrompt, for jailbreaking LLMs, inspired by the observed fragile alignments in Out-of-Distribution (OOD) data. Specifically, we first formulate the decision boundary in the jailbreaking process and then explore how obscure text affects LLM's ethical decision boundary. ObscurePrompt starts with constructing a base prompt that integrates well-known jailbreaking techniques. Powerful LLMs are then utilized to obscure the original prompt through iterative transformations, aiming to bolster the attack's robustness. Comprehensive experiments show that our approach substantially improves upon previous methods in terms of attack effectiveness, maintaining efficacy against two prevalent defense mechanisms. We believe that our work can offer fresh insights for future research on enhancing LLM alignment.

Pre-trained Universal Medical Image Transformer

Self-supervised learning has emerged as a viable method to leverage the abundance of unlabeled medical imaging data, addressing the challenge of labeled data scarcity in medical image analysis. In particular, masked image modeling (MIM) with visual token reconstruction has shown promising results in the general computer vision (CV) domain and serves as a candidate for medical image analysis. However, the presence of heterogeneous 2D and 3D medical images often limits the volume and diversity of training data that can be effectively used for a single model structure. In this work, we propose a spatially adaptive convolution (SAC) module, which adaptively adjusts convolution parameters based on the voxel spacing of the input images. Employing this SAC module, we build a universal visual tokenizer and a universal Vision Transformer (ViT) capable of effectively processing a wide range of medical images with various imaging modalities and spatial properties. Moreover, in order to enhance the robustness of the visual tokenizer's reconstruction objective for MIM, we suggest to generalize the discrete token output of the visual tokenizer to a probabilistic soft token. We show that the generalized soft token representation can be effectively integrated with the prior distribution regularization through a constructive interpretation. As a result, we pre-train a universal visual tokenizer followed by a universal ViT via visual token reconstruction on 55 public medical image datasets, comprising over 9 million 2D slices (including over 48,000 3D images). This represents the largest, most comprehensive, and diverse dataset for pre-training 3D medical image models to our knowledge. Experimental results on downstream medical image classification and segmentation tasks demonstrate the superior performance of our model and improved label efficiency.