KI-Forschungspapiere Täglich

NL-Eye: Abductive NLI for Images

Addition is All You Need for Energy-efficient Language Models

AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark

GenSim2: Scaling Robot Data Generation with Multi-modal and Reasoning LLMs

NRGBoost: Energy-Based Generative Boosted Trees

Horizon-Length Prediction: Advancing Fill-in-the-Middle Capabilities for Code Generation with Lookahead Planning

Erasing Conceptual Knowledge from Language Models

RoCoTex: A Robust Method for Consistent Texture Synthesis with Diffusion Models

Tutor CoPilot: A Human-AI Approach for Scaling Real-Time Expertise

Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding

MIGA: Mixture-of-Experts with Group Aggregation for Stock Market Prediction

CodeMMLU: A Multi-Task Benchmark for Assessing Code Understanding Capabilities of CodeLLMs

Selective Attention Improves Transformer

CANVAS: Commonsense-Aware Navigation System for Intuitive Human-Robot Interaction

A Comprehensive Survey of Mamba Architectures for Medical Image Analysis: Classification, Segmentation, Restoration and Beyond

MLP-KAN: Unifying Deep Representation and Function Learning