Kunxi Li
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
🗺️
Taxonomy Completionist
(10)
Top co-authors
Research topics
Keywords
model compression
(1)
transfer learning
(1)
attention mechanism
(1)
knowledge distillation
(1)
multimodal learning
(1)
model merging
(1)
efficient inference
(1)
efficient computing
(1)
cross-modal alignment
(1)
multimodal large language model
(1)
kv cache
(1)
long context
(1)
kv cache eviction
(1)
long-context inference
(1)
modality adaptation
(1)
parameter adaptation
(1)
heterogeneous model
(1)
large language model
(1)
parameter adapter
(1)
kv cache optimization
(1)
Papers
AccKV: Towards Efficient Audio-Video LLMs Inference via Adaptive-Focusing and Cross-Calibration KV Cache Optimization
AAAI 2026
MadaKV: Adaptive Modality-Perception KV Cache Eviction for Efficient Multimodal Long-Context Inference
ACL 2025
MergeNet: Knowledge Migration Across Heterogeneous Models, Tasks, and Modalities
AAAI 2025