Xinrong Zhang
6 papers · 2024–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
π
Conference Polyglot
(4)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(15)
π§
Keyword Pioneer
π
Cross-Pollinator
(15)
Conferences
EMNLP (2)
NAACL (2)
ACL (1)
ICLR (1)
Top co-authors
Keywords
large language model
(2)
text generation
(1)
context understanding
(1)
parallel processing
(1)
distributed training
(1)
memory efficiency
(1)
language model
(1)
pipeline parallelism
(1)
evaluation benchmark
(1)
token processing
(1)
context window
(1)
inference acceleration
(1)
training throughput
(1)
speculative decoding
(1)
data cleaning
(1)
long context
(1)
sequence processing
(1)
human-ai interaction
(1)
dialogue system
(1)
parallel decoding
(1)
Papers
Seq1F1B: Efficient Sequence-Level Pipeline Parallelism for Large Language Model Training
NAACL 2025
AutoClean: LLMs Can Prepare Their Training Corpus
NAACL 2025
βBench: Extending Long Context Evaluation Beyond 100K Tokens
ACL 2024
Beyond the Turn-Based Game: Enabling Real-Time Conversations with Duplex Models
EMNLP 2024
Ouroboros: Generating Longer Drafts Phrase by Phrase for Faster Speculative Decoding
EMNLP 2024
Predicting Emergent Abilities with Infinite Resolution Evaluation
ICLR 2024