KI-Forschungspapiere Täglich

PixelFlow: Pixel-Space Generative Models with Flow

InteractVLM: 3D Interaction Reasoning from 2D Foundational Models

SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learning

SAEs Can Improve Unlearning: Dynamic Sparse Autoencoder Guardrails for Precision Unlearning in LLMs

BlenderGym: Benchmarking Foundational Model Systems for Graphics Editing

Do PhD-level LLMs Truly Grasp Elementary Addition? Probing Rule Learning vs. Memorization in Large Language Models

Training-free Guidance in Text-to-Video Generation via Multimodal Planning and Structured Noise Initialization

UKBOB: One Billion MRI Labeled Masks for Generalizable 3D Medical Image Segmentation

In-2-4D: Inbetweening from Two Single-View Images to 4D Generation

ZipIR: Latent Pyramid Diffusion Transformer for High-Resolution Image Restoration

Visual Chronicles: Using Multimodal LLMs to Analyze Massive Collections of Images

FlexIP: Dynamic Control of Preservation and Personality for Customized Image Generation

Latent Diffusion Autoencoders: Toward Efficient and Meaningful Unsupervised Representation Learning in Medical Imaging

VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model

ModernBERT or DeBERTaV3? Examining Architecture and Data Influence on Transformer Encoder Models Performance

GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation

Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model

MineWorld: a Real-Time and Open-Source Interactive World Model on Minecraft

SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning

CoRAG: Collaborative Retrieval-Augmented Generation