RLRuntao Liu

Runtao Liu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Runtao Liu has a total of 19 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • DisRM: Reward Modeling as Discriminative Prediction

    by Runtao Liu, Jiahao Zhan, Yuxuan Guo, Yingqing He, Chen Wei, Alan Yuille, Qifeng Chen

  • Open Access

    UTMath: A Benchmark for Math Evaluation with Unit Test

    by Bo Yang, Qingping Yang, Yingwei Ma, Runtao Liu

    Bo Yang, Qingping Yang, Yingwei Ma, Runtao Liu. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.

  • Latent Guard: A Safety Framework for Text-to-Image Generation

    by Runtao Liu, Ashkan Khakzar, Jindong Gu, Qifeng Chen, Philip Torr, Fabio Pizzati


  • Open Access

    Unsupervised Sketch-to-Photo Synthesis

    by Runtao Liu, Qian Yu, Stella Yu

    Humans can envision a realistic photo given a free-hand sketch that is not only spatially imprecise and geometrically distorted but also without colors and visual details. We study unsupervised sketch-to-photo synthesis for the first time, learning from unpaired sketch-photo data where the target photo for a sketch is unknown during training. Existing works only deal with style change or spatial deformation alone, synthesizing photos from edge-aligned line drawings or transforming shapes within the same modality, e.g., color images. Our key insight is to decompose unsupervised sketch-to-photo synthesis into a two-stage translation task: First shape translation from sketches to grayscale photos and then content enrichment from grayscale to color photos. We also incorporate a self-supervised denoising objective and an attention module to handle abstraction and style variations that are inherent and specific to sketches. Our synthesis is sketch-faithful and photo-realistic to enable sketch-based image retrieval in practice. An exciting corollary product is a universal and promising sketch generator that captures human visual perception beyond the edge map of a photo.

  • Open Access

    CLEVR-Ref+: Diagnosing Visual Reasoning with Referring Expressions

    by Runtao Liu, Chenxi Liu, Yutong Bai, Alan Yuille

    Referring object detection and referring image segmentation are important tasks that require joint understanding of visual information and natural language. Yet there has been evidence that current benchmark datasets suffer from bias, and current state-of-the-art models cannot be easily evaluated on their intermediate reasoning process. To address these issues and complement similar efforts in visual question answering, we build CLEVR-Ref+, a synthetic diagnostic dataset for referring expression comprehension. The precise locations and attributes of the objects are readily available, and the referring expressions are automatically associated with functional programs. The synthetic nature allows control over dataset bias (through sampling strategy), and the modular programs enable intermediate reasoning ground truth without human annotators. In addition to evaluating several state-of-the-art models on CLEVR-Ref+, we also propose IEP-Ref, a module network approach that significantly outperforms other models on our dataset. In particular, we present two interesting and important findings using IEP-Ref: (1) the module trained to transform feature maps into segmentation masks can be attached to any intermediate module to reveal the entire reasoning process step-by-step; (2) even if all training data has at least one object referred, IEP-Ref can correctly predict no-foreground when presented with false-premise referring expressions. To the best of our knowledge, this is the first direct and quantitative proof that neural modules behave in the way they are intended.