Trending Research
FramePainter: Endowing Interactive Image Editing with Video Diffusion Priors
We highlight the effectiveness and efficiency of FramePainter across various of editing signals: it domainantly outperforms previous state-of-the-art methods with far less training data, achieving highly seamless and coherent editing of images, \eg, automatically adjust the reflection of the cup.
Stretching Each Dollar: Diffusion Training from Scratch on a Micro-Budget
sonyresearch/micro_diffusion
•
•
As scaling laws in generative AI push performance, they also simultaneously concentrate the development of these models among actors with large computational resources.
Tensor Product Attention Is All You Need
tensorgi/t6
•
•
Scaling language models to handle longer input sequences typically necessitates large key-value (KV) caches, resulting in substantial memory overhead during inference.
MiniRAG: Towards Extremely Simple Retrieval-Augmented Generation
The growing demand for efficient and lightweight Retrieval-Augmented Generation (RAG) systems has highlighted significant challenges when deploying Small Language Models (SLMs) in existing RAG frameworks.
UnCommon Objects in 3D
We introduce Uncommon Objects in 3D (uCO3D), a new object-centric dataset for 3D deep learning and 3D generative AI.
The GAN is dead; long live the GAN! A Modern GAN Baseline
brownvc/r3gan
•
•
There is a widely-spread claim that GANs are difficult to train, and GAN architectures in the literature are littered with empirical tricks.
Ranked #3 on
Image Generation
on ImageNet 32x32
SVFR: A Unified Framework for Generalized Video Face Restoration
wangzhiyaoo/svfr
•
•
In this paper, we propose a novel approach for the Generalized Video Face Restoration (GVFR) task, which integrates video BFR, inpainting, and colorization tasks that we empirically show to benefit each other.
Agentless: Demystifying LLM-based Software Engineering Agents
However, the complexity of these agent-based approaches, together with the limited abilities of current LLMs, raises the following question: Do we really have to employ complex autonomous software agents?
LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs
The benchmark presents a diverse set of challenges with eight different categories ranging from complex visual perception to scientific reasoning with over 4k reasoning steps in total, enabling robust evaluation of LLMs' abilities to perform accurate and interpretable visual reasoning across multiple steps.
KAG: Boosting LLMs in Professional Domains via Knowledge Augmented Generation
The recently developed retrieval-augmented generation (RAG) technology has enabled the efficient construction of domain-specific applications.
