A trajectory engine is built that reconstructs real livestream sessions into structured causal supervision, yielding over 320 hours of optimization trajectories and a human-reviewed benchmark of 275 clips and 13,812 decision intervals, establishing livestream assistance as selective participation in a shared social str...
Shu-Jian Gao, Jia-Mei Yan, Yu-Chen Yang et al.· 0 citations
A critique-in-the-loop self-improvement method that incorporates critique-based supervision into the actor’s self-training process and improves the actor’s exploration efficiency and solution diversity, especially on challenging queries, leading to a stronger actor model.
Zhi-Heng Xi, Dingwen Yang, Jixuan Huang et al.· Proceedings of the Thirty-Fi...· 0 citations
VLZip is introduced, a framework that unifies visual and textual compression for high-fidelity reasoning within a pure Transformer, and establishes an efficient and powerful new standard for long-context multimodal AI.
Yu-Qi Zhang, Cheng Chen, Yuyu Guo et al.· 0 citations
This paper introduces TinyMem, a model built upon compact multimodal memory for long-form video action detection that outperforms a range of state-of-the-art models on AVA v2.2 while using 5 times fewer memory tokens than the baseline with dense visual memory embeddings.
Rui Tian, Qi Dai, Hang-Rui Hu et al.· IEEE Transactions on Pattern...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
