Trending Research
MiniCPM-V: A GPT-4V Level MLLM on Your Phone
The recent surge of Multimodal Large Language Models (MLLMs) has fundamentally reshaped the landscape of AI research and industry, shedding light on a promising path toward the next AI milestone.
Ranked #7 on
Multiple-choice
on Neptune-Full
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.
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.
Monolith: Real Time Recommendation System With Collisionless Embedding Table
In this paper, we present Monolith, a system tailored for online training.
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.
Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos
This work presents Sa2VA, the first unified model for dense grounded understanding of both images and videos.
Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise
vgenai-netflix-eyeline-research/go-with-the-flow
•
•
The efficiency of our algorithm enables us to fine-tune modern video diffusion base models using warped noise with minimal overhead, and provide a one-stop solution for a wide range of user-friendly motion control: local object motion control, global camera movement control, and motion transfer.
UnCommon Objects in 3D
We introduce Uncommon Objects in 3D (uCO3D), a new object-centric dataset for 3D deep learning and 3D generative AI.
$\text{Transformer}^2$: Self-adaptive LLMs
Self-adaptive large language models (LLMs) aim to solve the challenges posed by traditional fine-tuning methods, which are often computationally intensive and static in their ability to handle diverse tasks.
Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Diffusion Transformer Networks
fudan-generative-vision/hallo3
•
•
Existing methodologies for animating portrait images face significant challenges, particularly in handling non-frontal perspectives, rendering dynamic objects around the portrait, and generating immersive, realistic backgrounds.
