TimeViper: A Hybrid Mamba-Transformer Vision-Language Model for Efficient Long Video Understanding Paper • 2511.16595 • Published 21 days ago • 9
Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains Paper • 2505.16552 • Published May 22 • 1
REVISOR: Beyond Textual Reflection, Towards Multimodal Introspective Reasoning in Long-Form Video Understanding Paper • 2511.13026 • Published 24 days ago • 25