AI研究論文デイリー

MOSAIC: Modeling Social AI for Content Dissemination and Regulation in Multi-Agent Simulations

Kimi-VL Technical Report

TAPNext: Tracking Any Point (TAP) as Next Token Prediction

Pangu Ultra: Pushing the Limits of Dense Large Language Models on Ascend NPUs

DeepSeek-R1 Thoughtology: Let's <think> about LLM Reasoning

VCR-Bench: A Comprehensive Evaluation Framework for Video Chain-of-Thought Reasoning

Compass Control: Multi Object Orientation Control for Text-to-Image Generation

MonoPlace3D: Learning 3D-Aware Object Placement for 3D Monocular Detection

VisualCloze: A Universal Image Generation Framework via Visual In-Context Learning

Towards Visual Text Grounding of Multimodal Large Language Model

SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement

Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction

HoloPart: Generative 3D Part Amodal Segmentation

MM-IFEngine: Towards Multimodal Instruction Following

Scaling Laws for Native Multimodal Models Scaling Laws for Native Multimodal Models

C3PO: Critical-Layer, Core-Expert, Collaborative Pathway Optimization for Test-Time Expert Re-Mixing