Stronger Normalization-Free Transformers
12 月 12, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2512.10938v1 Announce Type: cross Abstract: Although normalization layers have long been viewed as indispensable components...
Stripe, Anthropic, and OpenAI are backing an effort to stop respiratory infections
6 月 24, 2026admin NUAI,Committee,新闻,Uncategorized(0)The common cold comes for us all—often more than once a year. And there is...
StreamTensor: A PyTorch-to-Accelerator Compiler that Streams LLM Intermediates Across FPGA Dataflows
10 月 6, 2025admin NUAI,Committee,新闻,Uncategorized(0)Why treat LLM inference as batched kernels to DRAM when a dataflow compiler can pipe...
Streaming Sequence-to-Sequence Learning with Delayed Streams Modeling
9 月 11, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2509.08753v1 Announce Type: new Abstract: We introduce Delayed Streams Modeling (DSM), a flexible formulation for...
Stopping Computation for Converged Tokens in Masked Diffusion-LM Decoding
2 月 9, 2026admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2602.06412v1 Announce Type: new Abstract: Masked Diffusion Language Models generate sequences via iterative sampling that...
Stop guessing why your LLMs break: Anthropic’s new tool shows you exactly what goes wrong
6 月 5, 2025admin NUAI,Committee,新闻,Uncategorized(0)Anthropic’s open-source circuit tracing tool can help developers debug, optimize, and control AI for reliable...
StepFun Releases Step 3.7 Flash: A 198B MoE Vision-Language Model for Coding Agents and Search Workflows
5 月 30, 2026admin NUAI,Committee,新闻,Uncategorized(0)StepFun today released Step 3.7 Flash, a multimodal Mixture-of-Experts model targeting agentic use cases. It...
StepFun AI Releases Step-Audio-R1: A New Audio LLM that Finally Benefits from Test Time Compute Scaling
11 月 30, 2025admin NUAI,Committee,新闻,Uncategorized(0)Why do current audio AI models often perform worse when they generate longer reasoning instead...
StepFun AI Releases Step-Audio 2 Mini: An Open-Source 8B Speech-to-Speech AI Model that Surpasses GPT-4o-Audio
9 月 1, 2025admin NUAI,Committee,新闻,Uncategorized(0)The StepFun AI team has released Step-Audio 2 Mini, an 8B parameter speech-to-speech large audio...
