9 papers
Curvature-Weighted Capacity Allocation: A Minimum Description Length Framework for Layer-Adaptive Large Language Model Optimization
Theophilus Amaefuna, Hitesh Vaidya, Anshuman Chhabra +1
Layer-wise capacity in large language models is highly non-uniform: some layers contribute disproportionately to loss reduction, whereas others are nearly redundant. Existing layer…
A Human-in-the-Loop Framework for Efficient Prompt Selection in Microscopy Vision-Language Models
Abhiram Kandiyana, Ankur Mali, Lawrence O. Hall +2
Deep-learning pipelines for microscopy image classification often require expensive, labor- and time-intensive expert annotation to produce high-quality ground truth for training.…
Surprisal-Rényi Free Energy
Shion Matsumoto, Raul Castillo, Benjamin Prada +1
The forward and reverse Kullback-Leibler (KL) divergences arise as limiting objectives in learning and inference yet induce markedly different inductive biases that cannot be expla…
Realizable Circuit Complexity: Embedding Computation in Space-Time
Benjamin Prada, Ankur Mali
Classical circuit complexity characterizes parallel computation in purely combinatorial terms, ignoring the physical constraints that govern real hardware. The standard classes $\m…
Integral Signatures of Activation Functions: A 9-Dimensional Taxonomy and Stability Theory for Deep Learning
Ankur Mali, Lawrence Hall, Jake Williams +1
Activation functions govern the expressivity and stability of neural networks, yet existing comparisons remain largely heuristic. We propose a rigorous framework for their classifi…
Rethinking Reasoning in LLMs: Neuro-Symbolic Local RetoMaton Beyond ICL and CoT
Rushitha Santhoshi Mamidala, Anshuman Chhabra, Ankur Mali
Prompt-based reasoning strategies such as Chain-of-Thought (CoT) and In-Context Learning (ICL) have become widely used for eliciting reasoning capabilities in large language models…