TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs Paper • 2607.17423 • Published Jul 19 • 167
Luigi/moss-transcribe-diarize-zhtw-gguf Automatic Speech Recognition • 6.93M • Updated Jul 23 • 119 • 1
RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation Paper • 2607.06558 • Published Jul 7 • 79