Video-based AI systems are increasingly adopted in safety-critical domains such as autonomous driving and healthcare. However, interpreting their decisions remains challenging due to the inherent spatiotemporal complexity of video data and the opacit...
Efficiency, as a critical practical challenge for LLM-driven agentic and reasoning systems, is increasingly constrained by the inherent latency of autoregressive (AR) decoding. Speculative decoding mitigates this cost through a draft-verify scheme, y...
The rapid diffusion of "microblogging" services such as Twitter is ushering in a new era of possibilities for organizations to communicate with and engage their core stakeholders and the general public. To enhance understanding of the communicative f...
[NeurIPS 2023 Spotlight] Real-World Image Variation by Aligning Diffusion Inversion Chain (⭐ 153)
Text-to-image latent diffusion models (LDMs) have recently emerged as powerful generative models with great potential for solving inverse problems in imaging. However, leveraging such models in a Plug & Play (PnP), zero-shot manner remains challengin...
With the rapid development of diffusion models, text-to-image(T2I) models have made significant progress, showcasing impressive abilities in prompt following and image generation. Recently launched models such as FLUX.1 and Ideogram2.0, along with ot...
We propose a model for glioma patterns in a microlocal tumor environment under the influence of acidity, angiogenesis, and tissue anisotropy. The bottom-up model deduction eventually leads to a system of reaction-diffusion-taxis equations for glioma...
The paper discusses the potential of large vision-language models as objects of interest for empirical cultural studies. Focusing on the comparative analysis of outputs from two popular text-to-image synthesis models, DALL-E 2 and Stable Diffusion, t...
Deep learning models for skin disease classification require large, diverse, and well-annotated datasets. However, such resources are often limited due to privacy concerns, high annotation costs, and insufficient demographic representation. While tex...
We present an agent-based model to simulate gang territorial development motivated by graffiti marking on a two-dimensional discrete lattice. For simplicity, we assume that there are two rival gangs present, and they compete for territory. In this mo...
Mar 21, 2025 · A hybrid AI approach known as hybrid autoregressive transformer can generate realistic images with the same or better quality than state-of-the-art diffusion models, but that runs about nine …
4 days ago · AI algorithm enables tracking of vital white matter pathways Opening a new window on the brainstem, a new tool reliably and finely resolves distinct nerve bundles in live diffusion MRI scans, …
Single LDR to HDR reconstruction remains challenging for over-exposed regions where traditional methods often fail due to complete information loss. We present a training-free approach that enhances existing indirect and direct HDR reconstruction met...
Code release for "Avatars Grow Legs Generating Smooth Human Motion from Sparse Tracking Inputs with Diffusion Model", CVPR 2023 (⭐ 250)
Vacancy diffusion and clustering processes in body-centered-cubic (bcc) Fe are studied using the kinetic activation-relaxation technique (k-ART), an off-lattice kinetic Monte Carlo method with on-the-fly catalog building capabilities. For monovacanci...
【LLMs九层妖塔】分享 LLMs在自然语言处理（ChatGLM、Chinese-LLaMA-Alpaca、小羊驼 Vicuna、LLaMA、GPT4ALL等）、信息检索（langchain）、语言合成、语言识别、多模态等领域（Stable Diffusion、MiniGPT-4、VisualGLM-6B、Ziya-Visual等）等 实战与经验。 (⭐ 2156)
We perform mathematical anaysis of the biofilm development process. A model describing biomass growth is proposed: It arises from coupling three parabolic nonlinear equations: a biomass equation with degenerate and singular diffusion, a nutrient tran...
Automatic magnetic resonance (MR) image processing pipelines are widely used to study people with multiple sclerosis (PwMS), encompassing tasks such as lesion segmentation and brain parcellation. However, the presence of lesion often complicates thes...
Reconstructing sharp 3D representations from blurry multi-view images are long-standing problem in computer vision. Recent works attempt to enhance high-quality novel view synthesis from the motion blur by leveraging event-based cameras, benefiting f...
How can we reconstruct 3D hand poses when large portions of the hand are heavily occluded by itself or by objects? Humans often resolve such ambiguities by leveraging contextual knowledge -- such as affordances, where an object's shape and function s...