Better Models, Faster Training: Sigmoid Attention for single-cell Foundation Models Paper • 2604.27124 • Published 9 days ago • 10
Meta-learning In-Context Enables Training-Free Cross Subject Brain Decoding Paper • 2604.08537 • Published 29 days ago • 9
CityRAG: Stepping Into a City via Spatially-Grounded Video Generation Paper • 2604.19741 • Published 17 days ago • 17
LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model Paper • 2604.20796 • Published 16 days ago • 239
BubbleRAG: Evidence-Driven Retrieval-Augmented Generation for Black-Box Knowledge Graphs Paper • 2603.20309 • Published Mar 19 • 21
LMCache: An Efficient KV Cache Layer for Enterprise-Scale LLM Inference Paper • 2510.09665 • Published Oct 8, 2025 • 5
Runtime error Agents Featured 136 Qwen3-ASR Demo 🎙 136 Transcribe audio to text with multi-language timestamps