Mamba-3: 지수-사다리꼴 이산화, 복소 SSM, MIMO를 통한 표현력 높은 상태 공간 모델
논문 링크: arXiv 2603.15569 저자: Tri Dao, Albert Gu 소속: Together AI / Carnegie Mellon University
Recent Posts
MM-Zero: 데이터 없이 스스로 진화하는 멀티모델 비전-언어 모델
논문 링크: arXiv 2603.09206 저자: Zongxia Li, Hongyang Du, Chengsong Huang, Xiyang Wu, Lantao Yu, Yicheng He, Jing Xie, Xiaomin Wu, Zhichao Liu, Jiarui Zhang...
Less is Enough: LLM의 특성 공간에서 다양한 데이터 합성하기
https://arxiv.org/abs/2602.10388
OPUS: LLM 사전 학습에서 매 반복마다 효율적이고 원칙에 입각한 데이터 선택을 향하여
https://arxiv.org/abs/2602.05400
Attention Is Not What You Need: Grassmann Flows as an Attention-Free Alternative for Sequence Modeling
논문 링크: arXiv 2512.19428 저자: Zhang Chong
Real-Time Object Detection Meets DINOv3
https://intellindust-ai-lab.github.io/projects/DEIMv2/
Object Detection Model Leaderboard
https://leaderboard.roboflow.com/
Mamba YOLO: A Simple Baseline for Object Detection with State Space Model
https://arxiv.org/abs/2406.05835
YOLO-Master: MOE-Accelerated with Specialized Transformers for Enhanced Real-time Detection
https://arxiv.org/abs/2512.23273
LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection
https://arxiv.org/abs/2406.03459