KI-Forschungspapiere Täglich

The Lessons of Developing Process Reward Models in Mathematical Reasoning

Tensor Product Attention Is All You Need

Transformer^2: Self-adaptive LLMs

BIOMEDICA: An Open Biomedical Image-Caption Archive, Dataset, and Vision-Language Models Derived from Scientific Literature

MinMo: A Multimodal Large Language Model for Seamless Voice Interaction

VideoAuteur: Towards Long Narrative Video Generation

O1 Replication Journey -- Part 3: Inference-time Scaling for Medical Reasoning

WebWalker: Benchmarking LLMs in Web Traversal

SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training

UnCommon Objects in 3D

ChemAgent: Self-updating Library in Large Language Models Improves Chemical Reasoning

Evaluating Sample Utility for Data Selection by Mimicking Model Weights