E-commerce live streaming requires omni-modal understanding of noisy, temporally extended streams, where product facts are distributed across speech, video frames, product images, overlaid text, and user queries. We present TLive-Omni, an omni-modal understanding model tailored to live-commerce scenarios. It maps image...
Large language models deployed as personalized assistants must reason over long, evolving interaction histories. However, in long-term dialogue reasoning, relevant evidence is scattered across sessions, preferences may be revised over time, and standard long-context training fails to address these challenges under data...
Na-En Xu, Wan-Qing Cui, Yi-Bo Hu et al.· 0 citations
Safety-Flag is introduced, which places seven widely used safety benchmarks (BeaverTails, XSTest, Ethics, WildGuard, Aegis, ToxiChat, and ToxiGen) into a single balanced flag / do-not-flag protocol.
Harness-Aware Training (HAT), which trains compact models to adapt to changing Harnesses through reinforcement learning in augmented environments, is proposed and deployed in Taobao Live's digital-avatar service.
T. Sun, Wen-Hao Lin, Yong-Dong Luo et al.· 1 citation
It is shown that a score-mechanism shift silently breaks conformal prediction in multi-agent LLM systems, where coverage falls from a calibrated 90% to 74% under unanimous-wrong peers at the standard alpha = 0.10 operating point.
Yi-Bo Hu, Han-Yuan Su· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
