KI-Forschungspapiere Täglich

Neural Network Diffusion

Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models

Video ReCap: Recursive Captioning of Hour-Long Videos

Instruction-tuned Language Models are Better Knowledge Learners

VideoPrism: A Foundational Visual Encoder for Video Understanding

The FinBen: An Holistic Financial Benchmark for Large Language Models

Improving Robustness for Joint Optimization of Camera Poses and Decomposed Low-Rank Tensorial Radiance Fields

MVDiffusion++: A Dense High-resolution Multi-view Diffusion Model for Single or Sparse-view 3D Object Reconstruction

FlashTex: Fast Relightable Mesh Texturing with LightControlNet

A Touch, Vision, and Language Dataset for Multimodal Alignment

How Easy is It to Fool Your Multimodal LLMs? An Empirical Analysis on Deceptive Prompts

TofuEval: Evaluating Hallucinations of LLMs on Topic-Focused Dialogue Summarization

RealCompo: Dynamic Equilibrium between Realism and Compositionality Improves Text-to-Image Diffusion Models