One Token per Multimodal Evidence: Latent Memory for Resource-Constrained QA Paper • 2606.10572 • Published Jun 9 • 17
Agentic Fusion of Large Atomic and Language Models to Accelerate Superconductors Discovery Paper • 2604.23758 • Published Apr 29 • 8
Lingshu-Cell: A generative cellular world model for transcriptome modeling toward virtual cells Paper • 2603.25240 • Published Mar 26 • 79
SofT-GRPO: Surpassing Discrete-Token LLM Reinforcement Learning via Gumbel-Reparameterized Soft-Thinking Policy Optimization Paper • 2511.06411 • Published Nov 9, 2025 • 18
ReasonMed: A 370K Multi-Agent Generated Dataset for Advancing Medical Reasoning Paper • 2506.09513 • Published Jun 11, 2025 • 103
