Jiaheng Zhang
8 papers · 2025–2026 · 6 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 ↓
🌍
Conference Polyglot · Silver
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(16)
⭐
Rising Star
(8)
⚡
Prolific Year · Productive
Top co-authors
Research topics
Keywords
large language model
(2)
diffusion language model
(2)
backdoor defense
(2)
uncertainty quantification
(1)
distributed learning
(1)
image synthesis
(1)
text-to-image synthesis
(1)
ai safety
(1)
iterative refinement
(1)
backdoor attack
(1)
adversarial attack
(1)
diffusion model
(1)
text-to-image diffusion
(1)
jailbreak attack
(1)
neuron activation
(1)
defense mechanism
(1)
multi-step reasoning
(1)
process reward model
(1)
test-time scaling
(1)
model safety
(1)
Papers
Batman: Benign Knowledge Alignment Through Malicious Null Space in Federated Backdoor Attack
CVPR 2026
Beyond Hard Masks: Progressive Token Evolution for Diffusion Language Models
ACL 2026
Efficient Self-Evaluation for Diffusion Language Models via Sequence Regeneration
ACL 2026
Efficient Test-Time Scaling of Multi-Step Reasoning by Probing Internal States of Large Language Models
ACL 2026
ExtendAttack: Attacking Servers of LRMs via Extending Reasoning
AAAI 2026
Efficient Input-level Backdoor Defense on Text-to-Image Synthesis via Neuron Activation Variation
ICCV 2025
FlipAttack: Jailbreak LLMs via Flipping
ICML 2025
Safety in Large Reasoning Models: A Survey
EMNLP 2025