Liang Lin

Bridge-WA achieves superior task performance by predicting where and how the world will change, enabling robots to focus on relevant scene dynamics rather than irrelevant visual details.

ICMPG achieves a groundbreaking balance between semantic fidelity and physical realism in motion synthesis, outperforming traditional methods in both standard and zero-shot scenarios.

Realistic pedestrian simulations can significantly improve the training and evaluation of human-aware navigation systems, bridging the gap between simulated and real-world interactions.

Strong proprietary models falter in grounding their predictions, revealing a critical flaw in current VideoQA systems that could reshape evaluation standards.

Real-robot trials are costly and slow, but DataLadder enables scalable evaluations and data generation through a seamless interplay between robots, simulations, and human feedback.

LVLMs can now perform visual search far more effectively thanks to a clever decoding strategy that harmonizes pre- and post-training capabilities.

Manifold optimization provides a surprisingly effective and geometrically consistent approach to fitting an unknown number of hyperplanes, outperforming traditional methods.

Overcome the scarcity of paired data in speech-preserving facial expression manipulation by personalizing visual-language model prompts with individual visual information and correlating changes in visual and semantic features.

Bridging the gap between human manipulation and robotic control, JoyAI-RA unlocks enhanced cross-embodiment behavior learning through multi-source pretraining.

Speakers expressing the same content with different emotions exhibit surprisingly consistent spatial-temporal correlations in their local facial animations, unlocking a new approach to speech-preserving facial expression manipulation.