TL;DR
VisPlay is introduced, a self-evolving RL framework that enables VLMs to autonomously improve their reasoning capabilities from massive unlabeled image data and establishes a scalable path toward self-evolving multimodal intelligence.
Trace is introduced, a taxonomy-guided environment for multidomain visual reasoning that factorizes task construction into a scene grammar and an executable task program, separating visual realization from answer computation, providing evidence that broad procedural training can transfer beyond the generated task distr...
Modality-Informed Reciprocal Reasoning Optimization (MIRROR), a reinforcement learning approach for improving multimodal reasoning via self supervision, is developed and improves over standard RL and yields more accurate and consistent behavior across modalities.
This work investigates whether VLMs can be trained to reason about AI-generated image edits using reinforcement learning (RL) rather than explicit reasoning supervision, and introduces effective intersection over union (eff-IoU), a unified metric to jointly evaluate detection and localization.
DeepVoyager-VL is proposed, a long-horizon multimodal deep-search framework for vision-in-the-loop search that constructs a multimodal event graph to drive data synthesis, yielding problems with intermediate visual dependencies and long reasoning chains.
Video-FLAIR is introduced, a training framework that learns to select the appropriate reasoning mode for each query using reinforcement learning, and yields a supervision signal for learning adaptive reasoning without per-query annotations.
A coherent map of the rapidly expanding landscape of visual RL is provided to provide researchers and practitioners with a coherent map of the rapidly expanding landscape of visual RL and to highlight promising directions for future inquiry.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
