Energy-Efficient Uncertainty-Aware Biomass Composition Prediction at the Edgeby Muhammad Zawish, Paul Albert, Flavio Esposito, Steven…
CATP: Cross-Attention Token Pruning for Accuracy Preserved Multimodal Model Inferenceby Ruqi Liao, Chuqing Zhao, Jin…
Some Orders Are Important: Partially Preserving Orders in Top-Quality Planningby Michael Katz, Junkyu Lee, Jungkoo…
Streamlining Redundant Layers to Compress Large Language Modelsby Xiaodong Chen, Yuxuan Hu, Jing Zhang, Yanling…
Modeling Unified Semantic Discourse Structure for High-quality Headline Generationby Minghui Xu, Hao Fei, Fei Li,…
Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compressionby Junyuan Hong, Jinhao Duan,…
CoroNetGAN: Controlled Pruning of GANs via Hypernetworksby Aman Kumar, Khushboo Anand, Shubham Mandloi, Ashutosh Mishra,…
MoPE-CLIP: Structured Pruning for Efficient Vision-Language Models with Module-wise Pruning Error Metricby Haokun Lin, Haoli…
An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language…
DPPA: Pruning Method for Large Language Model to Model Mergingby Yaochen Zhu, Rui Xia, Jiajun…