THUNLP
PulseAugur coverage of THUNLP — every cluster mentioning THUNLP across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
Latent Compaction technique compresses LLM KV caches using test-time training
Researchers have developed a new technique called Latent Compaction, which uses test-time training to compress key-value (KV) caches in large language models. This method learns a document-specific compact cache by opti…
-
面壁智能开源StaffDeck，打造企业AI数字员工
面壁智能 (Mianmian Intelligence) has launched StaffDeck, an open-source platform designed to transform AI agents into reliable "digital employees" for businesses. Unlike typical AI agents that struggle with complex workflow…
-
Consumer-grade graphics cards can quickly get started! MiniCPM-o 4.5 from Mianbi Intelligent releases technical report
MiniCPM-o 4.5 is a new 9B parameter omni-modal large language model designed for real-time, full-duplex interaction. It can simultaneously process and generate audio, video, and text, enabling proactive behaviors and co…