KI-Forschungspapiere Täglich

LongRecipe: Recipe for Efficient Long Context Generalization in Large Languge Models

OD-VAE: An Omni-dimensional Video Compressor for Improving Latent Video Diffusion Model

DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos

Follow-Your-Canvas: Higher-Resolution Video Outpainting with Extensive Content Generation

Compositional 3D-aware Video Generation with LLM Director

VideoLLaMB: Long-context Video Understanding with Recurrent Memory Bridges

Accurate Compression of Text-to-Image Diffusion Models via Vector Quantization

OLMoE: Open Mixture-of-Experts Language Models

LinFusion: 1 GPU, 1 Minute, 16K Image

Kvasir-VQA: A Text-Image Pair GI Tract Dataset

Diffusion Policy Policy Optimization

Density Adaptive Attention-based Speech Network: Enhancing Feature Understanding for Mental Health Disorders

PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action

ContextCite: Attributing Model Generation to Context

GenAgent: Build Collaborative AI Systems with Automated Workflow Generation -- Case Studies on ComfyUI

Know When to Fuse: Investigating Non-English Hybrid Retrieval in the Legal Domain

General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

FLUX that Plays Music

The MERIT Dataset: Modelling and Efficiently Rendering Interpretable Transcripts