AI研究論文デイリー

Enabling Versatile Controls for Video Diffusion Models

TaoAvatar: Real-Time Lifelike Full-Body Talking Avatars for Augmented Reality via 3D Gaussian Splatting

MARS: A Multi-Agent Framework Incorporating Socratic Guidance for Automated Prompt Optimization

When Less is Enough: Adaptive Token Reduction for Efficient Image Representation

FFaceNeRF: Few-shot Face Editing in Neural Radiance Fields

Single Image Iterative Subject-driven Generation and Editing

A Comprehensive Survey on Long Context Language Modeling

Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation

Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Model

MathFlow: Enhancing the Perceptual Flow of MLLMs for Visual Mathematical Problems

OpenVLThinker: An Early Exploration to Complex Vision-Language Reasoning via Iterative Self-Improvement

GAEA: A Geolocation Aware Conversational Model

ETVA: Evaluation of Text-to-Video Alignment via Fine-grained Question Generation and Answering

Modifying Large Language Model Post-Training for Diverse Creative Writing

FastCuRL: Curriculum Reinforcement Learning with Progressive Context Extension for Efficient Training R1-like Reasoning Models

RoboFactory: Exploring Embodied Agent Collaboration with Compositional Constraints

When Preferences Diverge: Aligning Diffusion Models with Minority-Aware Adaptive DPO

Can Large Vision Language Models Read Maps Like a Human?

MAPS: A Multi-Agent Framework Based on Big Seven Personality and Socratic Guidance for Multimodal Scientific Problem Solving

From Head to Tail: Towards Balanced Representation in Large Vision-Language Models through Adaptive Data Calibration

PVChat: Personalized Video Chat with One-Shot Learning

Implicit Bias-Like Patterns in Reasoning Models