Related papers: WebSTAR: Scalable Data Synthesis for Computer Use …
Post-Training Multimodal Large Language Models (MLLMs) to build interactive agents holds promise across domains such as computer-use, web navigation, and robotics. A key challenge in scaling such post-training is lack of high-quality…
RRAM crossbars have been studied to construct in-memory accelerators for neural network applications due to their in-situ computing capability. However, prior RRAM-based accelerators show efficiency degradation when executing the popular…
Web-based activities span multiple webpages. However, conventional browsers with stacks of tabs cannot support operating and synthesizing large volumes of information across pages. While recent AI systems enable fully automated web browsing…
Modern computer vision systems increasingly encounter performance limitations in data-scarce domains, where collecting large-scale, high-quality labeled data is costly or impractical. While controllable diffusion models enable scalable…
End-to-end GUI agents for real desktop environments require large amounts of high-quality interaction data, yet collecting human demonstrations is expensive and existing synthetic pipelines often suffer from limited task diversity or noisy,…
Static "human data" faces inherent limitations: it is expensive to scale and bounded by the knowledge of its creators. Continuous learning from "experience data" - interactions between agents and their environments - promises to transcend…
The rapid advancement of AI and computer vision has significantly increased the demand for high-quality annotated datasets, particularly for semantic segmentation. However, creating such datasets is resource-intensive, requiring substantial…
Web applications are prime targets for cyberattacks as gateways to critical services and sensitive data. Traditional penetration testing is costly and expertise-intensive, making it difficult to scale with the growing web ecosystem. While…
With VLM-powered computer-using agents (CUAs) becoming increasingly capable at graphical user interface (GUI) navigation and manipulation, reliable step-level decision-making has emerged as a key bottleneck for real-world deployment. In…
With the rapid advancements in Large Language Models (LLMs), an increasing number of studies have leveraged LLMs as the cognitive core of agents to address complex task decision-making challenges. Specially, recent research has demonstrated…
While Multimodal Large Language Models have achieved human-like performance on many visual and textual reasoning tasks, their proficiency in fine-grained spatial understanding, such as route tracing on maps remains limited. Unlike humans,…
Computer Use Agents (CUAs) translate natural-language instructions into Graphical User Interface (GUI) actions such as clicks, keystrokes, and scrolls by relying on a Vision-Language Model (VLM) to interpret screenshots and predict grounded…
Training data collected in the wild often contain noisy labels and outliers that substantially degrade the performance and reliability of deep neural networks. While data cleaning is commonly applied as a separate preprocessing stage, such…
Data augmentation (DA) techniques aim to increase data variability, and thus train deep networks with better generalisation. The pioneering AutoAugment automated the search for optimal DA policies with reinforcement learning. However,…
Computer-assisted surgical (CAS) systems enhance surgical execution and outcomes by providing advanced support to surgeons. These systems often rely on deep learning models trained on complex, challenging-to-annotate data. While synthetic…
Recent studies in Vision-and-Language Navigation (VLN) train RL agents to execute natural-language navigation instructions in photorealistic environments, as a step towards robots that can follow human instructions. However, given the…
Despite the potential of language model-based agents to solve real-world tasks such as web navigation, current methods still struggle with long-horizon tasks with complex action trajectories. In contrast, humans can flexibly solve complex…
Data is the driving force of machine learning, with the amount and quality of training data often being more important for the performance of a system than architecture and training details. But collecting, processing and annotating real…
As quantum computing systems continue to scale up and become more clustered, efficiently compiling user quantum programs into high fidelity executable sequences on real hardware remains a key challenge for current quantum compilation…
Recent advances in continuous generative models, including multi-step approaches like diffusion and flow-matching (typically requiring 8-1000 sampling steps) and few-step methods such as consistency models (typically 1-8 steps), have…