AI研究論文デイリー

Qwen2.5 Technical Report

Progressive Multimodal Reasoning via Active Retrieval

MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval

How to Synthesize Text Data without Model Collapse?

LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks

Flowing from Words to Pixels: A Framework for Cross-Modality Evolution

LeviTor: 3D Trajectory Oriented Image-to-Video Synthesis

Affordance-Aware Object Insertion via Mask-Aware Dual Diffusion

AceMath: Advancing Frontier Math Reasoning with Post-Training and Reward Modeling

DI-PCG: Diffusion-based Efficient Inverse Procedural Content Generation for High-quality 3D Asset Creation

Descriptive Caption Enhancement with Visual Specialists for Multimodal Perception

UIP2P: Unsupervised Instruction-based Image Editing via Cycle Edit Consistency

AV-Link: Temporally-Aligned Diffusion Features for Cross-Modal Audio-Video Generation

TOMG-Bench: Evaluating LLMs on Text-based Open Molecule Generation

PixelMan: Consistent Object Editing with Diffusion Models via Pixel Manipulation and Generation

DateLogicQA: Benchmarking Temporal Biases in Large Language Models

Move-in-2D: 2D-Conditioned Human Motion Generation