Hongye Jin
8 papers · 2023–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (18) π Cross-Pollinator (12) π Renaissance Researcher (5) π Interdisciplinary Bridge π§ Keyword Pioneer
π
Conference Polyglot
(5)
β‘
Prolific Year
(5)
β
The Questioner
(2)
Conferences
EMNLP (2)
ICML (2)
NIPS (2)
ACL (1)
NAACL (1)
Top co-authors
Research topics
Keywords
large language model
(4)
evaluation benchmark
(2)
long context
(2)
model compression
(2)
domain generalization
(1)
language model evaluation
(1)
privacy preservation
(1)
model editing
(1)
gradient descent
(1)
distribution shift
(1)
node prediction
(1)
language model
(1)
context length
(1)
context window
(1)
kv cache compression
(1)
transformer optimization
(1)
prompt compression
(1)
gradient rewiring
(1)
editable training
(1)
demographic parity
(1)
Papers
100-LongBench: Are de facto Long-Context Benchmarks Literally Evaluating Long-Context Ability?
ACL 2025
LongLeader: A Comprehensive Leaderboard for Large Language Models in Long-context Scenarios
NAACL 2025
Taylor Unswift: Secured Weight Release for Large Language Models via Taylor Expansion
EMNLP 2024
LLM Maybe LongLM: SelfExtend LLM Context Window Without Tuning
ICML 2024
KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache
ICML 2024
KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches
EMNLP 2024
Gradient Rewiring for Editable Graph Neural Network Training
NIPS 2024
Chasing Fairness Under Distribution Shift: A Model Weight Perturbation Approach
NIPS 2023