최신 연구 논문

Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning

MiMo-VL Technical Report

Self-supervised learning of molecular representations from millions of tandem mass spectra using DreaMS

Prot42: a Novel Family of Protein Language Models for Target-aware Protein Binder Generation

GraftIQ: Hybrid multi-class neural network integrating clinical insight for multi-outcome prediction in liver transplant recipients

OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models

SynthRL: Scaling Visual Reasoning with Verifiable Data Synthesis

VS-Bench: Evaluating VLMs for Strategic Reasoning and Decision-Making in Multi-Agent Environments

CSVQA: A Chinese Multimodal Benchmark for Evaluating STEM Reasoning Capabilities of VLMs

UniWorld: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation