KI-Forschungspapiere Täglich

RepText: Rendering Visual Text via Replicating

Clinical knowledge in LLMs does not translate to human interactions

LLM-Powered GUI Agents in Phone Automation: Surveying Progress and Prospects

SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoning

CipherBank: Exploring the Boundary of LLM Reasoning Capabilities through Cryptography Challenges

Benchmarking Multimodal Mathematical Reasoning with Explicit Visual Dependency

MMInference: Accelerating Pre-filling for Long-Context VLMs via Modality-Aware Permutation Sparse Attention

Versatile Framework for Song Generation with Prompt-based Control

Group Downsampling with Equivariant Anti-aliasing

NORA: A Small Open-Sourced Generalist Vision Language Action Model for Embodied Tasks

TrustGeoGen: Scalable and Formal-Verified Data Engine for Trustworthy Multi-modal Geometric Problem Solving

Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory

ICL CIPHERS: Quantifying "Learning'' in In-Context Learning via Substitution Ciphers

ChiseLLM: Unleashing the Power of Reasoning LLMs for Chisel Agile Hardware Development