3 papers
cs.LG2026
Spectral-Target Physical Latent Structuring for JEPA-Style World Models
Penghao Zhu, Salvatore Penachio, Kaustav Mukherjee +1
Latent world models have become increasingly popular as a method to predict and plan in latent space rather than pixel space. Recent architectures, such as LeWorldModel (LeWM), joi…
cs.SD2026
Multi-Task Learning for Non-Canonical Phoneme Recognition via Articulatory Feature Decomposition
Sophia Riaz, Haoze Zheng, Amos Roche +5
Pathological and more broadly non-canonical speech present significant challenges for automatic phoneme recognition due to systematic deviations from canonical pronunciation and li…
cs.CL2025
Mnemosyne: An Unsupervised, Human-Inspired Long-Term Memory Architecture for Edge-Based LLMs
Aneesh Jonelagadda, Christina Hahn, Haoze Zheng +1
Long-term memory is essential for natural, realistic dialogue. However, current large language model (LLM) memory systems rely on either brute-force context expansion or static ret…