Summary of Near: a Training-free Pre-estimator Of Machine Learning Model Performance, by Raphael T. Husistein et al.
NEAR: A Training-Free Pre-Estimator of Machine Learning Model Performanceby Raphael T. Husistein, Markus Reiher, Marco…
NEAR: A Training-Free Pre-Estimator of Machine Learning Model Performanceby Raphael T. Husistein, Markus Reiher, Marco…
Representation Learning of Geometric Treesby Zheng Zhang, Allen Zhang, Ruth Nelson, Giorgio Ascoli, Liang ZhaoFirst…
Constructing Domain-Specific Evaluation Sets for LLM-as-a-judgeby Ravi Raju, Swayambhoo Jain, Bo Li, Jonathan Li, Urmish…
The Limitations of Model Retraining in the Face of Performativityby Anmol Kabra, Kumar Kshitij PatelFirst…
Mitigating Degree Bias in Signed Graph Neural Networksby Fang He, Jinhai Deng, Ruizhan Xue, Maojun…
Inverse design with conditional cascaded diffusion modelsby Milad Habibi, Mark FugeFirst submitted to arxiv on:…
Unsupervised Transfer Learning via Adversarial Contrastive Trainingby Chenguang Duan, Yuling Jiao, Huazhen Lin, Wensen Ma,…
Where is the signal in tokenization space?by Renato Lui Geh, Honghua Zhang, Kareem Ahmed, Benjie…
A training regime to learn unified representations from complementary breast imaging modalitiesby Umang Sharma, Jungkyu…
ABQ-LLM: Arbitrary-Bit Quantized Inference Acceleration for Large Language Modelsby Chao Zeng, Songwei Liu, Yusheng Xie,…