AI研究論文デイリー

Learn Your Reference Model for Real Good Alignment

Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length

TransformerFAM: Feedback attention is working memory

Video2Game: Real-time, Interactive, Realistic and Browser-Compatible Environment from a Single Video

Compression Represents Intelligence Linearly

Ctrl-Adapter: An Efficient and Versatile Framework for Adapting Diverse Controls to Any Diffusion Model

HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing

On Speculative Decoding for Multimodal Large Language Models

Tango 2: Aligning Diffusion-based Text-to-Audio Generations through Direct Preference Optimization

TextHawk: Exploring Efficient Fine-Grained Perception of Multimodal Large Language Models

Taming Latent Diffusion Model for Neural Radiance Field Inpainting

CompGS: Efficient 3D Scene Representation via Compressed Gaussian Splatting