CaveAgent: Transforming LLMs into Stateful Runtime Operators Paper • 2601.01569 • Published Jan 4 • 20
SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention Paper • 2509.24006 • Published Sep 28, 2025 • 119
What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT Paper • 2509.19284 • Published Sep 23, 2025 • 23
Accelerating Retrieval-Augmented Language Model Serving with Speculation Paper • 2401.14021 • Published Jan 25, 2024 • 2
Less Is More: Training-Free Sparse Attention with Global Locality for Efficient Reasoning Paper • 2508.07101 • Published Aug 9, 2025 • 14
Beyond Context Limits: Subconscious Threads for Long-Horizon Reasoning Paper • 2507.16784 • Published Jul 22, 2025 • 123
TidalDecode: Fast and Accurate LLM Decoding with Position Persistent Sparse Attention Paper • 2410.05076 • Published Oct 7, 2024 • 8
