Xinyi Wan
5 papers · 2024–2026 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Silver
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(16)
Venues
Top co-authors
Research topics
Keywords
large language model
(3)
pipeline parallelism
(3)
activation memory
(2)
throughput optimization
(2)
distributed training
(2)
memory optimization
(1)
vector index
(1)
semantic retrieval
(1)
evidence retrieval
(1)
multi-agent framework
(1)
multi-agent system
(1)
human action emulation
(1)
semantic caching
(1)
hybrid parallelism
(1)
knowledge caching
(1)
bubble reduction
(1)
optimizer synchronization
(1)
backward computation
(1)
acceleration
(1)
throughput
(1)
Papers
Cortex: Achieving Low-Latency, Cost-Efficient Remote Data Access For LLM via Semantic-Aware Knowledge Caching
NSDI 2026
EMULATE: A Multi-Agent Framework for Determining the Veracity of Atomic Claims by Emulating Human Actions
ACL 2025
PipeOffload: Improving Scalability of Pipeline Parallelism with Memory Optimization
ICML 2025
Pipeline Parallelism with Controllable Memory
NeurIPS 2024
Zero Bubble (Almost) Pipeline Parallelism
ICLR 2024