Poster Thu, Sep 10, 2026 • 7:30 AM – 9:30 AM PDT ExHall # 151

CoLT: Teaching Multi-Modal Models to Think with Chain of Latent Thoughts

Lianyu Hu ⋅ shengqian qin ⋅ Zeqin Liao ⋅ Qing Guo ⋅ Liang Wan ⋅ Wei Feng ⋅ Yang Liu

Keywords: Video Understanding, Generation and Multimodal Learning