Tag
Introduces Video-MME-Logical, a controlled benchmark for evaluating video temporal-logical reasoning in multimodal large language models, revealing a substantial human-model gap.
VideoKR introduces a large-scale video reasoning dataset and benchmark designed to enhance knowledge-intensive video understanding through expert-domain content and human-in-the-loop example generation. The dataset contains 315K video reasoning examples over 145K expert-domain videos.
This paper introduces a paradigm where Vision-Language Models (VLMs) act as test-time teachers to guide Video Generation Models (VGMs) via differentiable rewards and LoRA optimization, achieving a 16.7-point average improvement on video reasoning benchmarks.
VideoRLVR optimizes video diffusion models for verifiable reasoning tasks using reinforcement learning with rule-based rewards, achieving better performance than supervised methods in constraint-satisfying video generation.
Perceptron Inc. has released Perceptron Mk1, a frontier AI model designed for video and embodied reasoning tasks.
CollabVR is a research paper proposing a closed-loop framework that collaboratively integrates vision-language models with video generation models to improve visual reasoning and correct failures in real-time.
LiconStudio releases a LoRA adapter for LTX-2.3 fine-tuned on the VBVR dataset to enhance video generation with improved prompt understanding, motion dynamics, and temporal consistency for complex video reasoning tasks.
This paper introduces the Very Big Video Reasoning (VBVR) dataset and benchmark, a large-scale resource with over one million video clips across 200 reasoning tasks, enabling systematic study of spatiotemporal reasoning and showing early signs of emergent generalization.