Auto-FlexSwitch achieves efficient dynamic model merging by decomposing task vectors into sparse masks, signs, and scalars, then making the compression learnable via gating and adaptive bit selection with KNN-based retrieval.
Remote sensing image scene classifica- tion: Benchmark and state of the art
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
A two-stage physics-guided framework synthesizes soft-boundary shadow pairs and performs cascaded umbra-penumbra deshadowing, generalizing from synthetic aerospace data to real imagery.
Collaborative LLM inference on LEO satellite networks via model splitting, pipeline parallelism, and adaptive compression reduces inference delay by up to 42% and communication overhead by up to 71% with less than 1% accuracy loss.
citing papers explorer
-
Auto-FlexSwitch: Efficient Dynamic Model Merging via Learnable Task Vector Compression
Auto-FlexSwitch achieves efficient dynamic model merging by decomposing task vectors into sparse masks, signs, and scalars, then making the compression learnable via gating and adaptive bit selection with KNN-based retrieval.
-
AeroDeshadow: Physics-Guided Shadow Synthesis and Penumbra-Aware Deshadowing for Aerospace Imagery
A two-stage physics-guided framework synthesizes soft-boundary shadow pairs and performs cascaded umbra-penumbra deshadowing, generalizing from synthetic aerospace data to real imagery.
-
Communication-Efficient Collaborative LLM Inference over LEO Satellite Networks
Collaborative LLM inference on LEO satellite networks via model splitting, pipeline parallelism, and adaptive compression reduces inference delay by up to 42% and communication overhead by up to 71% with less than 1% accuracy loss.