Author

Ion Stoica

Observed name: Stoica, Ion

Institutions: Berkeley College, Tsinghua–Berkeley Shenzhen Institute, Orano (United States), University of California, Davis, University of California, Berkeley

Observed institutions: Berkeley College, Tsinghua–Berkeley Shenzhen Institute, Orano (United States), University of California, Davis, University of California, Berkeley

ORCID: 0000-0002-5373-0088

Observed ORCID: 0000-0002-5373-0088

OpenAlex ID: A5123536079

EvoX: Meta-Evolution for Automated Discovery

2026 · Liu, Shu, Agarwal, Shubham, et al. · arXiv (Cornell University) · 1

PDF

mKernel: Fast Multi-GPU, Multi-Node Fused Kernels

2026 · Mao, Ziming, Zhang, Yihan, et al. · arXiv (Cornell University)

PDF

Breaking the Tradeoff: Elastic and Isolated GPU Sharing with Ghost

2026 · Liu, Yicheng, Qiao, Yifan, et al. · Zenodo (CERN European Organization for Nuclear Research)

CommBench: Can LLMs Write Correct and Efficient GPU Communication Code?

2026 · Ma, Shuang, Li, Yuyi, et al. · arXiv (Cornell University)

PDF

Antiproof: Synthesizing Vulnerability Detectors and Proofs of Exploitability

2026 · Shakevsky, Alon, Villa, Corban, et al. · arXiv (Cornell University)

PDF

Arena-T2I Hard: Benchmarking and Improving Faithfulness with Dependency-Aware Checklist

2026 · Ban, Yuanhao, Xie, Tong, et al. · arXiv (Cornell University)

PDF

HERALD: High-Throughput Block Diffusion LLM Serving via CPU-GPU Cooperative KV Cache Retrieval

2026 · Kwon, Omin, Kim, Doyeon, et al. · arXiv (Cornell University)

PDF

Uncovering Intra-expert Activation Sparsity for Efficient Mixture-of-Expert Model Execution

2026 · Park, Jongseok, Kim, Sunga, et al. · arXiv (Cornell University)

PDF

Unleashing Scalable Context Parallelism for Foundation Models Pre-Training via FCP

2026 · Zhao, Yilong, Nie, Xiaonan, et al. · arXiv (Cornell University)

PDF

ClawEnvKit: Automatic Environment Generation for Claw-Like Agents

2026 · Li, Xirui, Li, Ming, et al. · arXiv (Cornell University)

PDF

UCCL-Zip: Lossless Compression Supercharged GPU Communication

2026 · Ma, Shuang, Lao, Chon Lam, et al. · arXiv (Cornell University)

PDF

M$^2$RNN: Non-Linear RNNs with Matrix-Valued States for Scalable Language Modeling

2026 · Mishra, Mayank, Tan, Shawn, et al. · arXiv (Cornell University)

PDF

Flash-KMeans: Fast and Memory-Efficient Exact K-Means

2026 · Yang, Shuo, Xi, Haocheng, et al. · arXiv (Cornell University)

PDF

SageBwd: A Trainable Low-bit Attention

2026 · Zhang, Jintao, Chen, Marco, et al. · arXiv (Cornell University)

PDF

SLA2: Sparse-Linear Attention with Learnable Routing and Quantization-aware Training

2026 · Zhang, Jintao, Wang, Haoxu, et al. · arXiv (Cornell University)

PDF

Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization

2026 · Xi, Haocheng, Yang, Shuo, et al. · arXiv (Cornell University)

PDF

Qrita: High-performance Top-k and Top-p using Pivot-based Truncation and Selection

2026 · Park, Jongseok, Kim, Sunga, et al. · arXiv (Cornell University)

PDF

VisGym: Diverse, Customizable, Scalable Environments for Multimodal Agents

2026 · Wang, Zirui, Zhang, Junyi, et al. · arXiv (Cornell University)

PDF

SVG-EAR: Parameter-Free Linear Compensation for Sparse Video Generation via Error-aware Routing

2026 · Xuanyi Zhou, Qiuyang Mang, et al. · Lecture notes in computer science

PDF

Speculative Decoding: Performance or Illusion?

2025 · Liu, Xiaoxuan, Yu, Jiaxiang, et al. · arXiv (Cornell University)

PDF

RedunCut: Measurement-Driven Sampling and Accuracy Performance Modeling for Low-Cost Live Video Analytics

2025 · Sela, Gur-Eyal, Agrawal, Kumar Krishna, et al. · arXiv (Cornell University)

PDF

Works count: 26

Citation count: 7

H-index: 1

I10-index: