Enhancing Neural Network Robustness Against Fault Injection Through Non-linear Weight Transformationsby Ninnart Fuengfusin, Hakaru TamukohFirst…
DIESEL – Dynamic Inference-Guidance via Evasion of Semantic Embeddings in LLMsby Ben Ganon, Alon Zolfi,…
UOE: Unlearning One Expert Is Enough For Mixture-of-experts LLMSby Haomin Zhuang, Yihua Zhang, Kehan Guo,…
Active Data Curation Effectively Distills Large-Scale Multimodal Modelsby Vishaal Udandarao, Nikhil Parthasarathy, Muhammad Ferjad Naeem,…
Preserving Deep Representations In One-Shot Pruning: A Hessian-Free Second-Order Optimization Frameworkby Ryan Lucas, Rahul MazumderFirst…
Continuous Autoregressive Models with Noise Augmentation Avoid Error Accumulationby Marco Pasini, Javier Nistal, Stefan Lattner,…
MiniKV: Pushing the Limits of LLM Inference via 2-Bit Layer-Discriminative KV Cacheby Akshat Sharma, Hangliang…
RPEE-HEADS: A Novel Benchmark for Pedestrian Head Detection in Crowd Videosby Mohamad Abubaker, Zubayda Alsadder,…
Improved implicit diffusion model with knowledge distillation to estimate the spatial distribution density of carbon…
Leaning Time-Varying Instruments for Identifying Causal Effects in Time-Series Databy Debo Cheng, Ziqi Xu, Jiuyong…