Ion Stoica

Berkeley College — United States

Computer Science · Physical Sciences

134h-index98.8kcitations724works2.62yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Cloud Computing and Resource Management(156), Caching and Content Delivery(137), Peer-to-Peer Network Technologies(100), Advanced Data Storage Technologies(95), Distributed systems and fault tolerance(90)

Publications723 total

TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times
arXiv (Cornell University)·2025Open Access
Let the Barbarians In: How AI Can Accelerate Systems Performance Research
arXiv (Cornell University)·2025Open Access
SonicMoE: Accelerating MoE with IO and Tile-aware Optimizations
arXiv (Cornell University)·2025Open Access
Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding
arXiv (Cornell University)·2025Open Access
SkyRL-Agent: Efficient RL Training for Multi-turn LLM Agent
arXiv (Cornell University)·2025Open Access
Rethinking the Cost of Distributed Caches for Datacenter Services
2025Open Access
Lost in Translation: The Search for Meaning in Network-Attached AI Accelerator Disaggregation
2025Open Access
EDIT-Bench: Evaluating LLM Abilities to Perform Real-World Instructed Code Edits
arXiv (Cornell University)·2025Open Access
RLBoost: Harvesting Preemptible Resources for Cost-Efficient Reinforcement Learning on LLMs
arXiv (Cornell University)·2025Open Access
Clinical significance of hematological parameters in the diagnosis and management of canine pyometra
Romanian Journal of Veterinary Sciences·2025Open Access
Efficient Long-context Language Model Training by Core Attention Disaggregation
arXiv (Cornell University)·2025Open Access
vAttention: Verified Sparse Attention
arXiv (Cornell University)·2025Open Access
Barbarians at the Gate: How AI is Upending Systems Research
arXiv (Cornell University)·2025Open Access
PrefillOnly: An Inference Engine for Prefill-only Workloads in Large Language Model Applications
2025· 1 citedOpen Access
Supporting Our AI Overlords: Redesigning Data Systems to be Agent-First
arXiv (Cornell University)·2025Open Access
Towards Efficient and Practical GPU Multitasking in the Era of LLM
arXiv (Cornell University)·2025Open Access
Advancing science- and evidence-based AI policy
Science·2025· 4 citedOpen Access
Radial Attention: $O(n\log n)$ Sparse Attention with Energy Decay for Long Video Generation
arXiv (Cornell University)·2025Open Access
VisionArena: 230K Real World User-VLM Conversations with Preference Labels
2025
LEANN: A Low-Storage Vector Index
arXiv (Cornell University)·2025Open Access
page 1 of 37Next →

Frequent Co-authors

Scott Shenker(20), Matei Zaharia(14), Robert Morris(6), David R. Karger(6), M. Frans Kaashoek(6), Joseph E. Gonzalez(6), Randy H. Katz(5), Mosharaf Chowdhury(5), Michael J. Franklin(5), Hari Balakrishnan(4), Anthony D. Joseph(4), Andy Konwinski(4), Tathagata Das(4), Frank Dabek(4), Ali Ghodsi(4), Sylvia Ratnasamy(4), Michael Armbrust(3), David A. Patterson(3), Reynold Xin(3), Ganesh Ananthanarayanan(3)