Zhiyu Lin
7 papers · 2021–2026 · 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 ↓
π
Conference Polyglot Β· Silver
π
Academic Marathon Β· Sprint
π
Interdisciplinary Bridge Β· Bronze
πΊοΈ
Taxonomy Completionist
(18)
π£
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Keywords
instruction following
(2)
adversarial robustness
(2)
image classification
(2)
data augmentation
(1)
prosody analysis
(1)
code generation
(1)
convolutional neural network
(1)
multimodal large language model
(1)
frequency domain
(1)
jailbreak attack
(1)
spectral density
(1)
security evaluation
(1)
language generation
(1)
evolutionary optimization
(1)
prompt injection
(1)
story generation
(1)
robustness testing
(1)
controllable text generation
(1)
reasoning behavior
(1)
malicious code generation
(1)
Papers
S2S-Arena: Evaluating Paralinguistic Instruction Following in Speech-to-Speech Models
ACL 2026
ThinkPilot: Steering Reasoning Models via Automated Think-prefixes Optimization
EACL 2026
LLMs Caught in the Crossfire: Malware Requests and Jailbreak Challenges
ACL 2025
WebUIBench: A Comprehensive Benchmark for Evaluating Multimodal Large Language Models in WebUI-to-Code
ACL 2025
Revisiting Visual Model Robustness: A Frequency Long-Tailed Distribution View
NeurIPS 2023
Investigating and Explaining the Frequency Bias in Image Classification
IJCAI 2022
Plug-and-Blend: A Framework for Controllable Story Generation with Blended Control Codes
NAACL 2021