[ICLR2024] A Unified Sampling Framework for Solver Searching of Diffusion Probab

[ICLR2025] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformer

[ICLR26] Cache-to-Cache: Direct Semantic Communication Between Large Language Mo

[HPEC2024] GLITCHES: GPU-FPGA LLM Inference Through a Collaborative Heterogeneou

[ICLR 26] NI Sampling: Accelerating Discrete DIffusion Sampling by Token Order

[MLSys2024] FlashDecoding++: Faster Large Language Model Inference with Asynchro

[lEEE RA-L] OmniDrones: An Efficient and Flexible Platform for Reinforcement

[AAAI2025] Enhancing Contrastive Learning Inspired by the Philosophy of ‘the Bli

[NeurIPS24] DiTFastAttn: Attention Compression for Diffusion Transformer Models

[ICRA26] JuggleRL: Mastering Ball Juggling with a Quadrotor via Deep Reinforceme

《稀疏存内计算电脑与架构》-岳金山

[EuroSys 26] STAlloc: Enhancing Memory Efficiency in Large-Scale Model Training

大语言模型量化简介

JuggleRL: Mastering Ball Juggling with a Quadrotor via Deep Reinforcement Learni

[NeurIPS 2024] Can LLMs Learn by Teaching for Better Reasoning? A Preliminary S

[EuroSys 26] Efficient and Adaptable Overlapping for Computation and Communicati

[ICLR26] PM-KVQ: Progressive Mixed-precision KV Cache Quantization for Long-CoT

生成模型的算法/模型层加速工作介绍

神经网络加速器网站简介 (中文)

[CoRL 2025] Mastering Multi-Drone Volleyball through Hierarchical Co-Self-Play R