AI研究論文每日精選

MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases

Genie: Generative Interactive Environments

Watermarking Makes Language Models Radioactive

Divide-or-Conquer? Which Part Should You Distill Your LLM?

GPTVQ: The Blessing of Dimensionality for LLM Quantization

ChunkAttention: Efficient Self-Attention with Prefix-Aware KV Cache and Two-Phase Partition

Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models

AgentOhana: Design Unified Data and Training Pipeline for Effective Agent Learning

Seamless Human Motion Composition with Blended Positional Encodings

API-BLEND: A Comprehensive Corpora for Training and Benchmarking API LLMs