Zihe Huang
3 papers · 2025–2026 · 2 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 · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(11)
Top co-authors
Research topics
Keywords
decision making
(1)
adversarial attack
(1)
image quality assessment
(1)
retrieval-augmented generation
(1)
feature integration
(1)
cross-modal interaction
(1)
visual modality
(1)
entity representation
(1)
multimodal knowledge graph
(1)
large language model agent
(1)
cross-modal integration
(1)
toxic content
(1)
llm detoxification
(1)
memory construction
(1)
entity feature integration
(1)
dynamic evolution
(1)
toxic subspace
(1)
Papers
Chain-of-Memory: Lightweight Memory Construction with Dynamic Evolution for LLM Agents
ACL 2026
Projecting Out the Malice: A Global Subspace Approach to LLM Detoxification
ACL 2026
Differentiated Vision: Unveiling Entity-Specific Visual Modality Requirements for Multimodal Knowledge Graph
EMNLP 2025