AI研究论文每日精选

An Introduction to Vision-Language Modeling

Transformers Can Do Arithmetic with the Right Embeddings

Matryoshka Multimodal Models

Zamba: A Compact 7B SSM Hybrid Model

NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models

I2VEdit: First-Frame-Guided Video Editing via Image-to-Video Diffusion Models

Human4DiT: Free-view Human Video Generation with 4D Diffusion Transformer

Trans-LoRA: towards data-free Transferable Parameter Efficient Finetuning

Looking Backward: Streaming Video-to-Video Translation with Feature Banks

Collaborative Video Diffusion: Consistent Multi-video Generation with Camera Control

Part123: Part-aware 3D Reconstruction from a Single-view Image

EM Distillation for One-step Diffusion Models

Vidu4D: Single Generated Video to High-Fidelity 4D Reconstruction with Dynamic Gaussian Surfels

LoGAH: Predicting 774-Million-Parameter Transformers using Graph HyperNetworks with 1/100 Parameters

Greedy Growing Enables High-Resolution Pixel-Based Diffusion Models