Yan Chen

Swapping to CTIFoundry allows smaller models to outperform flagship models, achieving higher accuracy with fewer tool calls in cyber threat intelligence investigations.

ConRub-Med achieves unprecedented accuracy in open-ended medical question answering by leveraging scalable, model-generated rubrics that outperform traditional expert-driven methods.

Unified image restoration methods can now be rigorously compared across real-world conditions, with 20 teams showcasing innovative solutions that push the boundaries of restoration accuracy.

SleepBand reveals that embedding physiological priors can significantly enhance the robustness of sleep staging models trained on a single dataset.

LLMs can significantly boost their emotional intelligence simply by role-playing conversations with themselves, iteratively refining their ability to both recognize and express emotions.

Training rPPG models on videos pre-screened by a multimodal LLM for signal quality and scene interference yields a substantial accuracy boost, finally unlocking the potential of unsupervised rPPG on "in-the-wild" data.

Video codecs, typically seen as just compression tools, can actually unlock 3x faster and 87% more efficient video analytics by guiding vision-language model inference.