InfiniteHiP: Extending Language Model Context Up to 3 Million Tokens on a Single GPU Paper • 2502.08910 • Published 16 days ago • 142
Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Paper • 2502.06703 • Published 18 days ago • 140
TransMLA: Multi-head Latent Attention Is All You Need Paper • 2502.07864 • Published 17 days ago • 45