SEA-VL Phase 2: Multimodal Vision-Language Models for SEA Collection Anthropogenic Regional Adaptation in Multimodal Vision-Language Model • 27 items • Updated 2 days ago • 5
SIM1: Physics-Aligned Simulator as Zero-Shot Data Scaler in Deformable Worlds Paper • 2604.08544 • Published 10 days ago • 16
Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale Paper • 2603.25040 • Published 24 days ago • 131
M2RNN Collection Note that the 7B models are MoE with 1.1B active parameters and 400M models are dense models • 14 items • Updated Mar 12 • 7
V_{0.5}: Generalist Value Model as a Prior for Sparse RL Rollouts Paper • 2603.10848 • Published Mar 11 • 14
OpenEarthAgent Collection The OpenEarthAgent Collection brings together the OpenEarthAgent model and its accompanying large-scale tool-augmented geospatial reasoning data. • 2 items • Updated Feb 20 • 5
GLiClass-Instruct Collection Multi-task efficient zero-shot sequence classification models • 3 items • Updated Feb 17 • 5
LateOn-Code 💻 Collection State-of-the-art late interaction code retrieval models • 6 items • Updated 11 days ago • 17
MiniCPM4 Collection MiniCPM4: Ultra-Efficient LLMs on End Devices • 30 items • Updated 13 days ago • 84