AI研究論文デイリー

LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding

How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites

Make Your LLM Fully Utilize the Context

Interactive3D: Create What You Want by Interactive 3D Generation

ConsistentID: Portrait Generation with Multimodal Fine-Grained Identity Preserving

Tele-FLM Technical Report

List Items One by One: A New Data Source and Learning Paradigm for Multimodal LLMs

Revisiting Text-to-Image Evaluation with Gecko: On Metrics, Prompts, and Human Ratings

NeRF-XL: Scaling NeRFs with Multiple GPUs

SEED-Bench-2-Plus: Benchmarking Multimodal Large Language Models with Text-Rich Visual Comprehension