LoopSLM builds on looped Transformers for latent reasoning, reusing a decoder block to refine hidden states with acoustic grounding at every pass, and further narrows the perception-reasoning gap by separating learning to reason from learning to respond, enabling direct inference without CoT.
Gander is presented, a native multimodal duplex interaction model that builds on MiniCPM-o 4.5 and is further adapted for realtime interaction with an asynchronous agent loop and is released together with its models, code, and data to facilitate further research and development in the community.
Orantqing, Shengpeng Ji, Jun-Long Tong et al.· 3 citations
This work proposes X$^3-OPD, a cross-modal on-policy distillation framework that transfers reasoning capabilities from a powerful text teacher to an audio-language student, and extends cross-modal distillation beyond textually recoverable content to reasoning grounded in non-linguistic events, prosody, and conversation...
Dong-Jie Fu, Di Cao, Zi-Han Zhang et al.· Proceedings of the 2026 Conf...· 4 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.