2024 "transformer models" Papers
9 papers found
Case-Based or Rule-Based: How Do Transformers Do the Math?
Yi Hu, Xiaojuan Tang, Haotong Yang et al.
ICML 2024posterarXiv:2402.17709
Delving into Differentially Private Transformer
Youlong Ding, Xueyang Wu, Yining meng et al.
ICML 2024posterarXiv:2405.18194
FrameQuant: Flexible Low-Bit Quantization for Transformers
Harshavardhan Adepu, Zhanpeng Zeng, Li Zhang et al.
ICML 2024posterarXiv:2403.06082
Interpretability Illusions in the Generalization of Simplified Models
Dan Friedman, Andrew Lampinen, Lucas Dixon et al.
ICML 2024posterarXiv:2312.03656
Learning Associative Memories with Gradient Descent
Vivien Cabannnes, Berfin Simsek, Alberto Bietti
ICML 2024poster
MoMo: Momentum Models for Adaptive Learning Rates
Fabian Schaipp, Ruben Ohana, Michael Eickenberg et al.
ICML 2024posterarXiv:2305.07583
Towards an Understanding of Stepwise Inference in Transformers: A Synthetic Graph Navigation Model
Mikail Khona, Maya Okawa, Jan Hula et al.
ICML 2024posterarXiv:2402.07757
Vectorized Conditional Neural Fields: A Framework for Solving Time-dependent Parametric Partial Differential Equations
Jan Hagnberger, Marimuthu Kalimuthu, Daniel Musekamp et al.
ICML 2024oralarXiv:2406.03919
What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation
Aaditya Singh, Ted Moskovitz, Feilx Hill et al.
ICML 2024spotlightarXiv:2404.07129