5 papers
Refining Over Resampling: Test-Time Self-Correction for LLM Reasoning
Ahsan Bilal, Muhammad Ahmed Mohsin, Muhammad Umer +4
Test-time scaling improves LLM reasoning by using additional inference compute, but wider sampling alone can suffer from diminishing returns: new rollouts often repeat existing ans…
: Stratified Scaling Search for Test-Time in Diffusion Language Models
Ahsan Bilal, Muhammad Ahmed Mohsin, Muhammad Umer +6
Test-time scaling investigates whether a fixed diffusion language model (DLM) can generate better outputs when given more inference compute, without additional training. However, n…
MAGIC-MASK: Multi-Agent Guided Inter-Agent Collaboration with Mask-Based Explainability for Reinforcement Learning
Maisha Maliha, Dean Hougen
Understanding the decision-making process of Deep Reinforcement Learning agents remains a key challenge for deploying these systems in safety-critical and multi-agent environments.…
Neural Optimizer Equation, Decay Function, and Learning Rate Schedule Joint Evolution
Brandon Morgan, Dean Hougen
A major contributor to the quality of a deep learning model is the selection of the optimizer. We propose a new dual-joint search space in the realm of neural optimizer search (NOS…
Evolving Loss Functions for Specific Image Augmentation Techniques
Brandon Morgan, Dean Hougen
Previous work in Neural Loss Function Search (NLFS) has shown a lack of correlation between smaller surrogate functions and large convolutional neural networks with massive regular…