-
Thinking with Anchors, our work on grounded and efficient document reasoning with ADOPD 2026, is now available on arXiv.
-
The interactive demo for
Context Learning is now available.
-
Chimera, our hybrid visual diffusion transformer with a Chinchilla-style scaling recipe, is now available.
-
FLARE, our framework for converting hybrid autoregressive models into diffusion language models, is now available.
-
LaViDa-O, our unified diffusion model for multimodal understanding and generation, appears at ICLR 2026.
-
LaViDa-R1, our reasoning model for unified multimodal diffusion, appears at ICML 2026.
-
MENTOR, an efficient framework for controllable multimodal image generation, appears in Findings of ACL 2026.
-
Doc-AGround, our work on visual grounding for text-rich images, appears in Findings of ACL 2026.
-
UniTemp, a framework for video generation in any temporal order, is now available.
-
Sparse-LaViDa, our efficient sparse multimodal diffusion model, appears at CVPR 2026.
-
FastCar, our work on efficient autoregressive video generation for edge devices, appears at ICLR 2026.
-
OIDA-QA, our multimodal benchmark for opioid-industry document analysis, appears at AAAI 2026.
-
Two papers get accepted to ICLR 2025.
-
One paper gets accepted to NAACL 2025.
-
Two papers get accepted to AAAI 2025.
-
Two papers get accepted to WACV 2025.
-
Two papers get accepted to EMNLP 2024.
-
One paper gets accepted to ACL Findings 2024.
-
One paper gets accepted to ICML 2024.
-
One paper gets accepted to NAACL 2024.
-
One paper get accepted to ICLR (Mathematical and Empirical Understanding of Foundation Models) 2024.
-
Two papers get accepted to CVPR 2024.
-
Three papers (ADoPD, LRM, SOHES) get accepted to ICLR 2024 (1 Oral, 2 Poster).
-
Two papers (Document OOD Detection and Document CLIP) get accepted by EMNLP 2023.
-
One paper on entity segmentation gets accepted to NeurIPS 2023 (Spotlight).
-
One paper gets accepted to ICCV 2023 (Oral).
-
I will be serving as an Area Chair of WACV 2024.
-
One paper gets accepted to AAAI 2023.
-
One paper (Entity Segmentation) gets accepted to PAMI.
-
One paper gets accepted to AAAI 2023.
-
One paper (Differential Privacy in Learning Language Models) gets accepted to BigData 2022.
-
One paper gets accepted to WACV 2023.
-
Our most recent Doc-series paper (SelfDoc->UniDoc->MGDoc) gets accepted to EMNLP 2022.
-
One paper (OOD Detection) gets accepted to NeurIPS 2022.
-
Three papers get accepted to ECCV 2022.
-
One paper gets accepted to Interspeech 2022.
-
One paper gets accepted to NAACL 2022.
-
Three papers get accepted to CVPR 2022.
-
One paper (Adaptive Axis Attentions) gets accepted to ACL 2022 Findings.
-
One paper gets accepted to WWW 2022.
-
Two papers get accepted to AAAI 2022.
-
The second Doc-series paper (SelfDoc->UniDoc) gets accepted to NeurIPS 2021.
-
One paper gets accepted to NAACL 2021.
-
Three papers (SelfDoc is our first Doc-series paper) get accepted to CVPR 2021.
-
My FIRST summer intern Peizhao’s work on “Document Representation Learning” got accepted by CVPR 2021.
-
One paper gets accepted to NeurIPS 2020.
-
One paper on video captioning gets accepted to Neurcomputing.
-
One paper gets accepted to ECCV 2020.
-
Started work at Adobe Research.
-
Successfully passed my oral defense!
-
One paper gets accepted to ICCV 2019.
-
One paper gets accepted to ACM MM 2019.
-
One paper gets accepted to CVPR 2019.