Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free Paper • 2505.06708 • Published May 10, 2025 • 9
OpenTSLM: Time-Series Language Models for Reasoning over Multivariate Medical Text- and Time-Series Data Paper • 2510.02410 • Published Oct 2, 2025 • 18
TimesFM Release Collection TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting. • 6 items • Updated Oct 4, 2025 • 29
view article Article A Review on the Evolvement of Load Balancing Strategy in MoE LLMs: Pitfalls and Lessons Feb 4, 2025 • 28
view article Article Blazingly fast whisper transcriptions with Inference Endpoints +4 May 13, 2025 • 81
view article Article Assisted Generation: a new direction toward low-latency text generation May 11, 2023 • 74
view article Article Benchmarking Assisted Generation with Gemma 3 and Qwen 2.5: A Code-First Guide Mar 12, 2025 • 5