Speed Always Wins: A Survey on Efficient Architectures for Large Language Models Paper • 2508.09834 • Published Aug 13, 2025 • 53
view article Article A Review on the Evolvement of Load Balancing Strategy in MoE LLMs: Pitfalls and Lessons NormalUhr • Feb 4, 2025 • 38
ComfyUI-Copilot: An Intelligent Assistant for Automated Workflow Development Paper • 2506.05010 • Published Jun 5, 2025 • 82
UMoE: Unifying Attention and FFN with Shared Experts Paper • 2505.07260 • Published May 12, 2025 • 10
UMoE: Unifying Attention and FFN with Shared Experts Paper • 2505.07260 • Published May 12, 2025 • 10
UMoE: Unifying Attention and FFN with Shared Experts Paper • 2505.07260 • Published May 12, 2025 • 10 • 2
Enabling Intelligent Interactions between an Agent and an LLM: A Reinforcement Learning Approach Paper • 2306.03604 • Published Jun 6, 2023 • 1
Enhancing Efficiency in Sparse Models with Sparser Selection Paper • 2403.18926 • Published Feb 27, 2024
Once is Enough: A Light-Weight Cross-Attention for Fast Sentence Pair Modeling Paper • 2210.05261 • Published Oct 11, 2022
FilmAgent: A Multi-Agent Framework for End-to-End Film Automation in Virtual 3D Spaces Paper • 2501.12909 • Published Jan 22, 2025 • 74
Running Agents 1.24k Edge TTS Text To Speech 👁 1.24k Generate speech audio from text with custom voice settings