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 — ...
Decrypt

Google Nano Banana 2 vs ByteDance Seedream 5.0 Lite: Which AI Image Generator Is Best?

A hands-on comparison between the two shows how the latest image models differ on price, speed, and creative control.
IEEE

Multi-Scale Semantic Compression for Robust Collaborative CNN Inference in Low-SNR Environments: An Attention-Enhanced UNet Autoencoder

Abstract: In collaborative inference scenarios, semantic communication replaces raw data transmission by conveying task-oriented semantic features to improve bandwidth efficiency. However, under noisy ...
GitHub

SVG-T2I: Scaling up Text-to-Image Latent Diffusion Model

Important Note: This repository implements SVG-T2I, a text-to-image diffusion framework that performs visual generation directly in Visual Foundation Model (VFM) representation space, rather than ...
IEEE

Knowledge Base Autoencoder Framework: A Novel Approach for Continuous Phase Shift Compression in RIS-Aided Comunications

Abstract: In a communication system assisted by reconfigurable intelligent surfaces (RIS), phase optimization on RIS is not feasible by itself because of its passive nature. Therefore, the base ...