KI-Forschungspapiere Täglich

Embodied-RAG: General non-parametric Embodied Memory for Retrieval and Generation

One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos

Flex3D: Feed-Forward 3D Generation With Flexible Reconstruction Model And Input View Curation

TPI-LLM: Serving 70B-scale LLMs Efficiently on Low-resource Edge Devices

ACE: All-round Creator and Editor Following Instructions via Diffusion Transformer

SyntheOcc: Synthesize Geometric-Controlled Street View Images through 3D Semantic MPIs

DressRecon: Freeform 4D Human Reconstruction from Monocular Video

What the Harm? Quantifying the Tangible Impact of Gender Bias in Machine Translation with a Human-centered Study

Law of the Weakest Link: Cross Capabilities of Large Language Models

Atlas-Chat: Adapting Large Language Models for Low-Resource Moroccan Arabic Dialect

Visual Context Window Extension: A New Perspective for Long Video Understanding

Posterior-Mean Rectified Flow: Towards Minimum MSE Photo-Realistic Image Restoration

Illustrious: an Open Advanced Illustration Model

Helpful DoggyBot: Open-World Object Fetching using Legged Robots and Vision-Language Models