Similar Items: LiVeAction: a Lightweight, Versatile, and Asymmetric Neural Codec Design for Real-time Operation
- Make Your LVLM KV Cache More Lightweight
- Where's the Plan? Locating Latent Planning in Language Models with Lightweight Mechanistic Interventions
- VideoNet: A Large-Scale Dataset for Domain-Specific Action Recognition
- SAVGO: Learning State-Action Value Geometry with Cosine Similarity for Continuous Control
- HyCOP: Hybrid Composition Operators for Interpretable Learning of PDEs
- Learning the Helmholtz equation operator with DeepONet for non-parametric 2D geometries