UBTree: Parallel Tree Drafting via Unigram and Bigram Models for Speculative Decoding Paper • 2609.39972 • Published 24 days ago • 39
SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention Paper • 2509.24006 • Published Sep 28, 2025 • 119
Efficient Attention Mechanisms for Large Language Models: A Survey Paper • 2507.19595 • Published Jul 25, 2025 • 7
FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling Paper • 2502.14856 • Published Feb 20, 2025 • 8