Swift-SVD: Theoretical Optimality Meets Practical Efficiency in Low-Rank LLM Compression Paper • 2604.01609 • Published Apr 2 • 17
KV-CoRE: Benchmarking Data-Dependent Low-Rank Compressibility of KV-Caches in LLMs Paper • 2602.05929 • Published Feb 5 • 2
VQ-Seg: Vector-Quantized Token Perturbation for Semi-Supervised Medical Image Segmentation Paper • 2601.10124 • Published Jan 15 • 4