5 papers
Learning to Help in Multi-Class Settings
Yu Wu, Yansong Li, Zeyu Dong +2
Deploying complex machine learning models on resource-constrained devices is challenging due to limited computational power, memory, and model retrainability. To address these limi…
Unraveling the Localized Latents: Learning Stratified Manifold Structures in LLM Embedding Space with Sparse Mixture-of-Experts
Xin Li, Anand Sarwate
However, real-world data often exhibit complex local structures that can be challenging for single-model approaches with a smooth global manifold in the embedding space to unravel.…
LSR-Adapt: Ultra-Efficient Parameter Tuning with Matrix Low Separation Rank Kernel Adaptation
Xin Li, Anand Sarwate
Imposing an effective structural assumption on neural network weight matrices has been the major paradigm for designing Parameter-Efficient Fine-Tuning (PEFT) systems for adapting…
Learning To Help: Training Models to Assist Legacy Devices
Yu Wu, Anand Sarwate
Machine learning models implemented in hardware on physical devices may be deployed for a long time. The computational abilities of the device may be limited and become outdated wi…
LASERS: LAtent Space Encoding for Representations with Sparsity for Generative Modeling
Xin Li, Anand Sarwate
Learning compact and meaningful latent space representations has been shown to be very useful in generative modeling tasks for visual data. One particular example is applying Vecto…