How I Study AI - Learn AI Papers & Lectures the Easy Way

LongVideo-R1: Smart Navigation for Low-cost Long Video Understanding

Intermediate

Jihao Qiu, Lingxi Xie et al.Feb 24arXiv

LongVideo-R1 is a smart video-watching agent that jumps to the right moments in long videos instead of scanning everything.

#long video understanding#video navigation#multimodal large language model

FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs

Intermediate

Qian Chen, Jinlan Fu et al.Jan 20arXiv

FutureOmni is the first benchmark that tests if multimodal AI models can predict what happens next from both sound and video, not just explain what already happened.

#multimodal LLM#audio-visual reasoning#future forecasting

Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding

Intermediate

Christopher Clark, Jieyu Zhang et al.Jan 15arXiv

Molmo2 is a family of vision-language models that can watch videos, understand them, and point to or track things over time using fully open weights, data, and code.

#vision-language model#video grounding#pointing and tracking

Papers3

LongVideo-R1: Smart Navigation for Low-cost Long Video Understanding

FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs

Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding