2 papers
cs.MM2026
Mechanisms of Multimodal Synchronization: Insights from Decoder-Based Video-Text-to-Speech Synthesis
Akshita Gupta, Tatiana Likhomanenko, Karren Dai Yang +3
Unified decoder-only transformers have shown promise for multimodal generation, yet the mechanisms by which they synchronize modalities with heterogeneous sampling rates remain und…
cs.LG2026
Extending P: Spectral Conditions for Feature Learning Across Optimizers
Akshita Gupta, Marieme Ngom, Sam Foreman +1
Several variations of adaptive first-order and second-order optimization methods have been proposed to accelerate and scale the training of large language models. The performance o…