Publications

A massive-scale benchmark for evaluating retrieval-augmented VQA across languages and modalities. (CVPR)

A novel cultural adversarial robustness suite designed to assess VLMs’ stability against perturbed geographical cues. (CVPR)

An uncertainty measure defined as the cross-entropy between predictive distribution and unknown true distribution. (ICLR)

A multilingual, rubric-agnostic reward reasoning model achieving the broadest language coverage in reward modeling to date. (ICLR)

A suite of dynamic guardian models offering novel flexibility by evaluating text based on user-defined policies. (ICLR)

A private text generation method that steers LLM generation using dataset vectors. (ICLR)

A framework for detecting duplicated regions in tampered biomedical images, leveraging affinity-guided attention. (ICLR)

A DPO that targets the most problematic parts of an output by assigning different preference weights. (ICLR)

A framework for multivariate time series forecasting using tabular foundation models. (ICLR)