AI 연구 논문 데일리

StarCoder 2 and The Stack v2: The Next Generation

Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models

Beyond Language Models: Byte Models are Digital World Simulators

Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers

Humanoid Locomotion as Next Token Prediction

MOSAIC: A Modular System for Assistive and Interactive Cooking

DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models

Simple linear attention language models balance the recall-throughput tradeoff

Priority Sampling of Large Language Models for Compilers

Trajectory Consistency Distillation

ViewFusion: Towards Multi-View Consistency via Interpolated Denoising