Bin Wang

StreamOPD achieves near teacher-level performance in streaming video understanding without relying on memory or retrieval, reshaping the landscape of post-training techniques.

Existing document parsers may score high on benchmarks, but they still falter on real-world tables, with a top parser achieving only 85.03 TEDS.

Achieving 93.02% accuracy in molecular structure recognition, MinerU.Chem outperforms existing systems, unlocking new possibilities for AI-driven chemistry research.

Adversarial attacks on vision-language agents reveal critical vulnerabilities, with multi-view optimization strategies proving significantly more effective than isolated approaches.

A novel Circadian Rhythm Score reveals that nearly all predictive power can be captured from multi-domain behaviors, transforming depression screening and intervention strategies.

Real-world inter-channel correlations can significantly enhance long-term time series forecasting, as shown by McWC's superior performance on diverse datasets.

Structured allocentric representations can boost spatial reasoning in foundation models by up to 18%, even in the absence of visual inputs.

Today's visual generation models are often evaluated on the wrong things, leading to inflated performance claims that mask critical failures in spatial reasoning, temporal consistency, and causal understanding.