KI-Forschungspapiere Täglich

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

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

A Comprehensive Survey on Long Context Language Modeling

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

RoboFactory: Exploring Embodied Agent Collaboration with Compositional Constraints

Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation

Modifying Large Language Model Post-Training for Diverse Creative Writing

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

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

Enabling Versatile Controls for Video Diffusion Models

Single Image Iterative Subject-driven Generation and Editing

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

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

Can Large Vision Language Models Read Maps Like a Human?

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

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

PVChat: Personalized Video Chat with One-Shot Learning

Implicit Bias-Like Patterns in Reasoning Models

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

GAEA: A Geolocation Aware Conversational Model

FFaceNeRF: Few-shot Face Editing in Neural Radiance Fields

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