AI研究論文デイリー

mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding

LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

TnT-LLM: Text Mining at Scale with Large Language Models

Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models

AnimateDiff-Lightning: Cross-Model Diffusion Distillation

Vid2Robot: End-to-end Video-conditioned Policy Learning with Cross-Attention Transformers

Chart-based Reasoning: Transferring Capabilities from LLMs to VLMs

GaussianFlow: Splatting Gaussian Dynamics for 4D Content Creation

ComboVerse: Compositional 3D Assets Creation Using Spatially-Aware Diffusion Guidance

FouriScale: A Frequency Perspective on Training-Free High-Resolution Image Synthesis

FRESCO: Spatial-Temporal Correspondence for Zero-Shot Video Translation

GVGEN: Text-to-3D Generation with Volumetric Representation

TexDreamer: Towards Zero-Shot High-Fidelity 3D Human Texture Generation