Shaochen Zhong
14 papers · 2022–2026 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π Conference Polyglot (5) πΊοΈ Taxonomy Completionist (15) π Renaissance Researcher (5) π Interdisciplinary Bridge π§ Keyword Pioneer
π
Cross-Pollinator
(11)
π€
Dynamic Duo
(10)
π
Century Club
(13)
β‘
Prolific Year
(5)
β
The Questioner
(2)
Conferences
ICML (5)
EMNLP (4)
ICLR (2)
ACL (1)
CVPR (1)
EACL (1)
Top co-authors
Research topics
Keywords
large language model
(5)
model compression
(4)
long context
(2)
language model evaluation
(1)
token efficiency
(1)
backdoor attack
(1)
model merging
(1)
low-rank adaptation
(1)
evaluation benchmark
(1)
context window
(1)
kv cache compression
(1)
reasoning model
(1)
hidden state analysis
(1)
transformer optimization
(1)
prompt compression
(1)
language model
(1)
structured pruning
(1)
faithful explanation
(1)
taylor expansion
(1)
privacy preservation
(1)
Papers
FaithLM: Towards Faithful Explanations for Large Language Models
EACL 2026
Flexible Group Count Enables Hassle-Free Structured Pruning
CVPR 2025
MQuAKE-Remastered: Multi-Hop Knowledge Editing Can Only Be Advanced with Reliable Evaluations
ICLR 2025
Word Salad Chopper: Reasoning Models Waste A Ton Of Decoding Budget On Useless Repetitions, Self-Knowingly
EMNLP 2025
LoRATK: LoRA Once, Backdoor Everywhere in the Share-and-Play Ecosystem
EMNLP 2025
100-LongBench: Are de facto Long-Context Benchmarks Literally Evaluating Long-Context Ability?
ACL 2025
GNNs Also Deserve Editing, and They Need It More Than Once
ICML 2024
Taylor Unswift: Secured Weight Release for Large Language Models via Taylor Expansion
EMNLP 2024
Knowledge Graphs Can be Learned with Just Intersection Features
ICML 2024
KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache
ICML 2024
TVE: Learning Meta-attribution for Transferable Vision Explainer
ICML 2024
KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches
EMNLP 2024
Soft Prompt Recovers Compressed LLMs, Transferably
ICML 2024
Revisit Kernel Pruning with Lottery Regulated Grouped Convolutions
ICLR 2022