64 citations · 188 across the 16 of their papers we have counts for
16 papers
Qwen-CUA: Native Computer Use for (almost) Everything
Dunjie Lu, Shuai Bai, Tianyi Bai +42
Native computer use offers a general interface for agents to operate almost any software available to people, but requires long-horizon state tracking, large-scale interactive expe…
ShotCrop: Cropping Human-Centric Images into Cinematic Triple-Shot Compositions
Dehong Kong, Lina Lei, Lingtao Zheng +10
Prior work on aesthetic composition typically produces a single aesthetically pleasing crop, overlooking the narrative value of composing multiple shots from one scene. In practice…
OpenCUA: Open Foundations for Computer-Use Agents
Xinyuan Wang, Bowen Wang, Dunjie Lu +39
Vision-language models have demonstrated impressive capabilities as computer-use agents (CUAs) capable of automating diverse computer tasks. As their commercial potential grows, cr…
Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction
Vaishnavh Nagarajan, Chen Henry Wu, Charles Ding +1
We design a suite of minimal algorithmic tasks that are a loose abstraction of open-ended real-world tasks. This allows us to cleanly and controllably quantify the creative limits…
Dissecting Adversarial Robustness of Multimodal LM Agents
Chen Henry Wu, Rishi Shah, Jing Yu Koh +3
As language models (LMs) are used to build autonomous agents in real environments, ensuring their adversarial robustness becomes a critical challenge. Unlike chatbots, agents are c…
ITI-GEN: Inclusive Text-to-Image Generation
Cheng Zhang, Xuanbai Chen, Siqi Chai +4
Text-to-image generative models often reflect the biases of the training data, leading to unequal representations of underrepresented groups. This study investigates inclusive text…
Text2Reward: Reward Shaping with Language Models for Reinforcement Learning
Tianbao Xie, Siheng Zhao, Chen Henry Wu +5
Designing reward functions is a longstanding challenge in reinforcement learning (RL); it requires specialized knowledge or domain data, leading to high costs for development. To a…
Zero-shot Model Diagnosis
Jinqi Luo, Zhaoning Wang, Chen Henry Wu +2
When it comes to deploying deep vision models, the behavior of these systems must be explicable to ensure confidence in their reliability and fairness. A common approach to evaluat…
Generative Visual Prompt: Unifying Distributional Control of Pre-Trained Generative Models
Chen Henry Wu, Saman Motamed, Shaunak Srivastava +1
Generative models (e.g., GANs, diffusion models) learn the underlying data distribution in an unsupervised manner. However, many applications of interest require sampling from a pa…
Unifying Diffusion Models' Latent Space, with Applications to CycleDiffusion and Guidance
Chen Henry Wu, Fernando De la Torre
Diffusion models have achieved unprecedented performance in generative modeling. The commonly-adopted formulation of the latent code of diffusion models is a sequence of gradually…
Selective Annotation Makes Language Models Better Few-Shot Learners
Hongjin Su, Jungo Kasai, Chen Henry Wu +8
Many recent approaches to natural language tasks are built on the remarkable abilities of large language models. Large language models can perform in-context learning, where they l…
UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models
Tianbao Xie, Chen Henry Wu, Peng Shi +20
Structured knowledge grounding (SKG) leverages structured knowledge to complete user requests, such as semantic parsing over databases and question answering over knowledge bases.…
Summ^N: A Multi-Stage Summarization Framework for Long Input Dialogues and Documents
Yusen Zhang, Ansong Ni, Ziming Mao +6
Text summarization helps readers capture salient information from documents, news, interviews, and meetings. However, most state-of-the-art pretrained language models (LM) are unab…
DYLE: Dynamic Latent Extraction for Abstractive Long-Input Summarization
Ziming Mao, Chen Henry Wu, Ansong Ni +7
Transformer-based models have achieved state-of-the-art performance on short-input summarization. However, they still struggle with summarizing longer text. In this paper, we prese…
EVA: An Open-Domain Chinese Dialogue System with Large-Scale Generative Pre-Training
Hao Zhou, Pei Ke, Zheng Zhang +11
Although pre-trained language models have remarkably enhanced the generation ability of dialogue systems, open-domain Chinese dialogue systems are still limited by the dialogue dat…
A Hierarchical Reinforced Sequence Operation Method for Unsupervised Text Style Transfer
Chen Wu, Xuancheng Ren, Fuli Luo +1
Unsupervised text style transfer aims to alter text styles while preserving the content, without aligned data for supervision. Existing seq2seq methods face three challenges: 1) th…