KI-Forschungspapiere Täglich

MiniMax-01: Scaling Foundation Models with Lightning Attention

MangaNinja: Line Art Colorization with Precise Reference Following

3DIS-FLUX: simple and efficient multi-instance generation with DiT rendering

Padding Tone: A Mechanistic Analysis of Padding Tokens in T2I Models

Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Marks

Diffusion Adversarial Post-Training for One-Step Video Generation

A Multi-Modal AI Copilot for Single-Cell Analysis with Instruction Following

FramePainter: Endowing Interactive Image Editing with Video Diffusion Priors

Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens

HALoGEN: Fantastic LLM Hallucinations and Where to Find Them

PokerBench: Training Large Language Models to become Professional Poker Players

Tarsier2: Advancing Large Vision-Language Models from Detailed Video Description to Comprehensive Video Understanding

Enhancing Automated Interpretability with Output-Centric Feature Descriptions

OpenCSG Chinese Corpus: A Series of High-quality Chinese Datasets for LLM Training

Potential and Perils of Large Language Models as Judges of Unstructured Textual Data

MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training

AfriHate: A Multilingual Collection of Hate Speech and Abusive Language Datasets for African Languages

In-situ graph reasoning and knowledge expansion using Graph-PReFLexOR