Brief

Researchers are exploring novel methods for compressing large models and datasets to improve efficiency. Papers discuss unifying dataset pruning and distillation, bootstrapped tokenization for image generation, and activation-informed low-rank compression for LLMs and VLMs. Other work focuses on generic triple-latent sequence models, theoretical aspects of prediction under imperfect compression, and jointly optimizing architectural and quantization choices for LLM compression. AI

Researchers are developing new methods to improve recommendation systems by addressing limitations in current models. One approach, SaFeAU, enhances collaborative filtering by incorporating semantic factors to better handle sparse data and capture higher-order signals. Another area of focus is leveraging explicit user feedback, such as comments and reviews, to align recommendations with user preferences more accurately and reduce filter bubbles. Additionally, techniques like dataset distillation (FOSTER, Rec-Distill) and embedding control (ACE) are being explored to make large-scale recommendation models more efficient and effective for real-world deployment. AI