New KV cache compaction technique cuts LLM memory 50x without accuracy loss

MIT researchers developed Attention Matching, a KV cache compaction technique that compresses LLM memory by 50x in seconds — ...
IEEE

Leveraging Simplex Gradient Variance and Bias Reduction for Black-Box Optimization of Noisy and Costly Functions

Gradient variance errors in gradient-based search methods are largely mitigated using momentum, however the bias gradient errors may fail the numerical search methods in reaching the true optimum. We ...
IEEE

Adversarial Examples for Image Cropping: Gradient-Based and Bayesian-Optimized Approaches for Effective Adversarial Attack

Abstract: In this study, we propose novel approaches for generating adversarial examples targeting machine learning-based image cropping systems. Image cropping is crucial for meeting display space ...