KI-Forschungspapiere Täglich

STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolution

Test-time Computing: from System-1 Thinking to System-2 Thinking

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning

Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction

Personalized Graph-Based Retrieval for Large Language Models

TransPixar: Advancing Text-to-Video Generation with Transparency

Scaling Laws for Floating Point Quantization Training

Through-The-Mask: Mask-based Motion Trajectories for Image-to-Video Generation

METAGENE-1: Metagenomic Foundation Model for Pandemic Monitoring

Auto-RT: Automatic Jailbreak Strategy Exploration for Red-Teaming Large Language Models

GS-DiT: Advancing Video Generation with Pseudo 4D Gaussian Fields through Efficient Dense 3D Point Tracking

DepthMaster: Taming Diffusion Models for Monocular Depth Estimation

PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models

ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use

Samba-asr state-of-the-art speech recognition leveraging structured state-space models

Ingredients: Blending Custom Photos with Video Diffusion Transformers

AutoPresent: Designing Structured Visuals from Scratch

Automated Generation of Challenging Multiple-Choice Questions for Vision Language Model Evaluation

ProTracker: Probabilistic Integration for Robust and Accurate Point Tracking