Shenggan Cheng
4 papers · 2020–2025 · 3 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 ↓
๐
Conference Polyglot ยท Bronze
๐
Academic Marathon ยท Sprint
๐
Interdisciplinary Bridge ยท Bronze
Top co-authors
Research topics
Keywords
mathematical reasoning
(1)
code generation
(1)
memory optimization
(1)
activation memory
(1)
throughput improvement
(1)
communication cost
(1)
fine tuning
(1)
long sequence
(1)
random seed
(1)
deep learning inference
(1)
chunk strategy
(1)
loras
(1)
fusion
(1)
dynamic sequence parallelism
(1)
embedded sequence parallelism
(1)
multi-dimensional transformers
(1)
resharding strategy
(1)
Papers
DSP: Dynamic Sequence Parallelism for Multi-Dimensional Transformers
ICML 2025
SeedLoRA: A Fusion Approach to Efficient LLM Fine-Tuning
ICML 2025
AutoChunk: Automated Activation Chunk for Memory-Efficient Deep Learning Inference
ICLR 2024
FTL: A universal framework for training low-bit DNNs via Feature Transfer
ECCV 2020