Zhonghua Jiang
4 papers · 2025–2026 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
๐ Interdisciplinary Bridge ๐งญ Keyword Pioneer ๐ Conference Polyglot (3) ๐ Cross-Pollinator (13) ๐ Renaissance Researcher (5)
๐บ๏ธ
Taxonomy Completionist
(18)
Conferences
AAAI (2)
ACL (1)
CVPR (1)
Top co-authors
Keywords
federated learning
(1)
attention mechanism
(1)
knowledge distillation
(1)
multimodal learning
(1)
efficient inference
(1)
neural rendering
(1)
model aggregation
(1)
distributed optimization
(1)
efficient computing
(1)
cross-modal alignment
(1)
3d gaussian splatting
(1)
real-time rendering
(1)
multimodal large language model
(1)
kv cache
(1)
long context
(1)
augmented reality
(1)
counterfactual learning
(1)
kv cache eviction
(1)
long-context inference
(1)
modality adaptation
(1)
Papers
AccKV: Towards Efficient Audio-Video LLMs Inference via Adaptive-Focusing and Cross-Calibration KV Cache Optimization
AAAI 2026
FedCFA: Alleviating Simpsonโs Paradox in Model Aggregation with Counterfactual Federated Learning
AAAI 2025
MadaKV: Adaptive Modality-Perception KV Cache Eviction for Efficient Multimodal Long-Context Inference
ACL 2025
TaoAvatar: Real-Time Lifelike Full-Body Talking Avatars for Augmented Reality via 3D Gaussian Splatting
CVPR 2025