Summary of I-llm: Efficient Integer-only Inference For Fully-quantized Low-bit Large Language Models, by Xing Hu et al.
I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large Language Modelsby Xing Hu, Yuan Cheng, Dawei…
I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large Language Modelsby Xing Hu, Yuan Cheng, Dawei…
NUTS, NARS, and Speechby D. van der SluisFirst submitted to arxiv on: 28 May 2024CategoriesMain:…
Towards robust prediction of material properties for nuclear reactor design under scarce data – a…
Decentralized Directed Collaboration for Personalized Federated Learningby Yingqi Liu, Yifan Shi, Qinglun Li, Baoyuan Wu,…
An Information Theoretic Evaluation Metric For Strong Unlearningby Dongjae Jeon, Wonje Jeung, Taeheon Kim, Albert…
Resisting Stochastic Risks in Diffusion Planners with the Trajectory Aggregation Treeby Lang Feng, Pengjie Gu,…
Diffusion Rejection Samplingby Byeonghu Na, Yeongmin Kim, Minsang Park, Donghyeok Shin, Wanmo Kang, Il-Chul MoonFirst…
Crystal-LSBO: Automated Design of De Novo Crystals with Latent Space Bayesian Optimizationby Onur Boyar, Yanheng…
Achieving Exponential Asymptotic Optimality in Average-Reward Restless Bandits without Global Attractor Assumptionby Yige Hong, Qiaomin…
Improving Discrete Diffusion Models via Structured Preferential Generationby Severi Rissanen, Markus Heinonen, Arno SolinFirst submitted…