AMXFP4: Taming Activation Outliers with Asymmetric Microscaling Floating-Point for 4-bit LLM Inferenceby Janghwan Lee, Jiwoong…
StreamAdapter: Efficient Test Time Adaptation from Contextual Streamsby Dilxat Muhtar, Yelong Shen, Yaming Yang, Xiaodong…
Analogical Reasoning Within a Conceptual Hyperspaceby Howard Goldowsky, Vasanth SarathyFirst submitted to arxiv on: 13…
Polymetis:Large Language Modeling for Multiple Material Domainsby Chao Huang, Huichen Xiao, Chen Chen, Chunyan Chen,…
Comment on Is Complexity an Illusion?by Gabriel SimmonsFirst submitted to arxiv on: 29 Oct 2024CategoriesMain:…
Scaling Properties of Diffusion Models for Perceptual Tasksby Rahul Ravishankar, Zeeshan Patel, Jathushan Rajasegaran, Jitendra…
On Active Privacy Auditing in Supervised Fine-tuning for White-Box Language Modelsby Qian Sun, Hanpeng Wu,…
Over-parameterized Student Model via Tensor Decomposition Boosted Knowledge Distillationby Yu-Liang Zhan, Zhong-Yi Lu, Hao Sun,…
Does This Summary Answer My Question? Modeling Query-Focused Summary Readers with Rational Speech Actsby Cesare…
Aligned Vector Quantization for Edge-Cloud Collabrative Vision-Language Modelsby Xiao Liu, Lijun Zhang, Deepak Ganesan, Hui…