SC25 Home
Close

Organization

Independent Researcher
Contributors
Yufan Xu
Presentations
Paper
Towards Efficient LLM Inference via Collective and Adaptive Speculative Decoding
11:15am - 11:37am CST Wednesday, 19 November 2025 261-262-265-266
Applications
Architectures & Networks
HPC for Machine Learning
Livestreamed
Recorded
TP
Paper
Zero-Value Code Specialization via Profile-Guided Control Data Flow Analysis
11:37am - 12:00pm CST Tuesday, 18 November 2025 263-264
Performance Measurement, Modeling, & Tools
Livestreamed
Recorded
TP