AI研究論文デイリー

DSBench: How Far Are Data Science Agents to Becoming Data Science Experts?

Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale

Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers

IFAdapter: Instance Feature Control for Grounded Text-to-Image Generation

Source2Synth: Synthetic Data Generation and Curation Grounded in Real Data Sources

TextBoost: Towards One-Shot Personalization of Text-to-Image Models via Fine-tuning Text Encoder

DreamHOI: Subject-Driven Generation of 3D Human-Object Interactions with Diffusion Priors

PiTe: Pixel-Temporal Alignment for Large Video-Language Model

FlashSplat: 2D to 3D Gaussian Splatting Segmentation Solved Optimally

Can OOD Object Detectors Learn from Foundation Models?