Yu-Ran Wang

A 4B grounding foundation model achieves state-of-the-art visual grounding, outperforming larger models and boosting downstream robotic and autonomous driving performance by up to 24.8% in OOD settings.

Even top-tier vision-language models consistently invert a subject's left and right, exposing a blind spot in camera- versus subject-centric spatial reasoning that rubric-guided GRPO over anatomical priors can finally resolve.

Video generative priors only translate into robust physical control when paired with explicit world-to-action information routing and synchronized joint denoising rather than standard monolithic fine-tuning.

Motion-aligned latent dynamics enable robots to learn actionable behaviors from human videos without losing visual fidelity across different embodiments.

Integration of diverse robot policies can be streamlined from hours to minutes, revolutionizing how we deploy and evaluate robotic systems.

Sparse keypoints combined with dense correspondences enable robots to master complex rigid-deformable interactions with minimal demonstrations.

RefCaptioner not only outperforms existing models in video captioning but also enables precise grounding of visual elements to multiple reference images, enhancing factual accuracy.

Evolving contexts can transform the stability and effectiveness of on-policy distillation, leading to superior performance in open-ended tasks.

RoboDojo reveals that integrating simulation and real-world tasks can significantly enhance the evaluation of robot manipulation policies, bridging the gap between theoretical performance and practical deployment.

MagicSim revolutionizes robot learning by merging diverse world construction and execution into a single, efficient framework that enhances both evaluation and interaction capabilities.

AffordanceVLA transforms robotic manipulation by using structured affordance cues to create precise perception-action mappings, outperforming traditional models.

Ditching text-based chain-of-thought unlocks better audio-visual reasoning by interleaving textual steps with a unified latent space that preserves dense sensory information.

Finally, a robot can reliably pick out that specific shirt from a messy pile, thanks to a new vision-language pipeline that reasons about garment affordances.