4 papers
Visualizing LLM Latent Space Geometry Through Dimensionality Reduction
Alex Ning, Vainateya Rangaraju, Yen-Ling Kuo
Large language models (LLMs) achieve state-of-the-art results across many natural language tasks, but their internal mechanisms remain difficult to interpret. In this work, we extr…
Recurrent convolutional neural networks for modeling non-adiabatic dynamics of quantum-classical systems
Alex P. Ning, Lingyu Yang, Gia-Wei Chern
Recurrent neural networks (RNNs) have recently been extensively applied to model the time-evolution in fluid dynamics, weather predictions, and even chaotic systems thanks to their…
Learning When to Stop: Adaptive Latent Reasoning via Reinforcement Learning
Alex Ning, Yen-Ling Kuo, Gabe Gomes
Latent reasoning represents a new development in Transformer language models that has shown potential in compressing reasoning lengths compared to chain-of-thought reasoning. By di…
Change-of-Basis Pruning via Rotational Invariance
Alex Ning, Vainateya Rangaraju
Structured pruning removes entire neurons or channels, but its effectiveness depends on how importance is distributed across the representation space. Change-of-basis (CoB) pruning…