SparseDecoding: Decoding-Aware Pruning for Accurate and Efficient LLM Inference Paper • 2610.12327 • Published 3 days ago • 25
SparseDecoding: Decoding-Aware Pruning for Accurate and Efficient LLM Inference Paper • 2610.12327 • Published 3 days ago • 25
OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers Paper • 2607.04033 • Published Jul 4 • 55
MMLongBench: Benchmarking Long-Context Vision-Language Models Effectively and Thoroughly Paper • 2505.10610 • Published May 15, 2025 • 56