Jacob Fein-Ashley

Jacob Fein-Ashley

PhD Student at USC

Advised by Professor Paria Rashidinejad

Publications

Reinforcement Learning from Rich Feedback with Distributional DAgger
Rishabh Agrawal, Jacob Fein-Ashley, and Paria Rashidinejad
arXiv
Solve the Loop: Attractor Models for Language and Reasoning
Jacob Fein-Ashley and Paria Rashidinejad
arXiv
Latent Denoising Improves Visual Alignment in Large Multimodal Models
Dhruv Parikh, Jacob Fein-Ashley, Rajgopal Kannan, and Viktor Prasanna
arXiv
Bridging Hidden States in Vision-Language Models
Benjamin Fein-Ashley and Jacob Fein-Ashley
arXiv
Mixture of Thoughts: Learning to Aggregate What Experts Think, Not Just What They Say
Jacob Fein-Ashley, Dhruv Parikh, Rajgopal Kannan, and Viktor Prasanna
arXiv
ClusterViG: Efficient Globally Aware Vision GNNs via Image Partitioning
Dhruv Parikh, Jacob Fein-Ashley, Tian Ye, Rajgopal Kannan, and Viktor Prasanna
IEEE MCNA'25 — Best Paper Award
IEEE
SPECTRE: An FFT-Based Efficient Drop-In Replacement to Self-Attention for Long Contexts
Jacob Fein-Ashley, Neelesh Gupta, Rajgopal Kannan, and Viktor Prasanna
arXiv