KI-Forschungspapiere Täglich

Edit Away and My Face Will not Stay: Personal Biometric Defense against Malicious Generative Editing

ROICtrl: Boosting Instance Control for Visual Generation

Interleaved Scene Graph for Interleaved Text-and-Image Generation Assessment

DreamCache: Finetuning-Free Lightweight Personalized Image Generation via Feature Caching

3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes

Identity-Preserving Text-to-Video Generation by Frequency Decomposition

CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models

Draft Model Knows When to Stop: A Self-Verification Length Policy for Speculative Decoding

Video-Guided Foley Sound Generation with Multimodal Controls

MARVEL-40M+: Multi-Level Visual Elaboration for High-Fidelity Text-to-3D Content Creation

Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient

DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving

Make-It-Animatable: An Efficient Framework for Authoring Animation-Ready 3D Characters

VideoLLM Knows When to Speak: Enhancing Time-Sensitive Video Comprehension with Video-Text Duet Interaction Format

UniPose: A Unified Multimodal Framework for Human Pose Comprehension, Generation and Editing

Adaptive Blind All-in-One Image Restoration

Optimizing Brain Tumor Segmentation with MedNeXt: BraTS 2024 SSA and Pediatrics

Large Language Model-Brained GUI Agents: A Survey

Diffusion Self-Distillation for Zero-Shot Customized Image Generation

Training and Evaluating Language Models with Template-based Data Generation

Omegance: A Single Parameter for Various Granularities in Diffusion-Based Synthesis

ChatRex: Taming Multimodal LLM for Joint Perception and Understanding