Learning quantization-aware linear paths in weight space yields a midpoint whose direct quantization matches quantization-aware training performance without using straight-through estimators.
qualitatively characterizing neural network optimization problems
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
Rotary positional encodings reduce the symmetry group of functional equivalence in attention compared to sinusoidal encodings, increasing expressivity and altering linear mode connectivity patterns.
Scalar embeddings of neural network training trajectories treated as temporal networks preserve main dynamical features including Lyapunov exponents, enable definition of a characteristic decorrelation time, and show asymptotic state spacings compatible with a skew lognormal distribution.
Representations learned by large AI models are converging toward a shared statistical model of reality.
citing papers explorer
-
Functional Equivalence in Attention: A Comprehensive Study with Applications to Linear Mode Connectivity
Rotary positional encodings reduce the symmetry group of functional equivalence in attention compared to sinusoidal encodings, increasing expressivity and altering linear mode connectivity patterns.
-
Scalar Representations of Neural Network Training Dynamics
Scalar embeddings of neural network training trajectories treated as temporal networks preserve main dynamical features including Lyapunov exponents, enable definition of a characteristic decorrelation time, and show asymptotic state spacings compatible with a skew lognormal distribution.