KI-Forschungspapiere Täglich

rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking

Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Though

Agent Laboratory: Using LLM Agents as Research Assistants

URSA: Understanding and Verifying Chain-of-thought Reasoning in Multimodal Mathematics

LLM4SR: A Survey on Large Language Models for Scientific Research

InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflection

GeAR: Generation Augmented Retrieval

Chirpy3D: Continuous Part Latents for Creative 3D Bird Generation

SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Images

EpiCoder: Encompassing Diversity and Complexity in Code Generation

DPO Kernels: A Semantically-Aware, Kernel-Enhanced, and Divergence-Rich Paradigm for Direct Preference Optimization

Multi-task retriever fine-tuning for domain-specific and efficient RAG