Xiang Bo Deng

TRUST-CUA: Trustworthy Computer-Using Generalist Agents for Intelligent User Interfaces (Workshop)

Toby Jia-Jun Li, Segev Shlomov, Xiang Bo Deng, Ronen I. Brafman et autres

The Trust-CUA workshop brings the fast-growing area of computer-using agents (CUAs)– agents that operate across GUIs, browsers, APIs, and CLIs– to the core concerns of the IUI community: human-centered design, trust, and interactive control. We focus on methods, interfaces, and evaluations that …

us, il (code pays fourni par la source)

SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?

Xiang Bo Deng, Jeff Da, Edwin Pan, Yun He et autres

We introduce SWE-Bench Pro, a substantially more challenging benchmark that builds upon the best practices of SWE-BENCH [25], but is explicitly designed to capture realistic, complex, enterprise-level problems beyond the scope of SWE-BENCH. SWE-BENCH PRO contains 1,865 problems sourced from a diverse …

F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions

Qi Lv, Weijie Kong, Hao Li, Jia Zeng et autres

Executing language-conditioned tasks in dynamic visual environments remains a central challenge in embodied AI. Existing Vision-Language-Action (VLA) models predominantly adopt reactive state-to-action mappings, often leading to short-sighted behaviors and poor robustness in dynamic scenes. In this paper, we introduce F1, a pretrained …

WebGuard: Building a Generalizable Guardrail for Web Agents

Boyuan Zheng, Zeyi Liao, Zizuo Liu, Michael Lin et autres

The rapid development of autonomous web agents powered by Large Language Models (LLMs), while greatly elevating efficiency, exposes the frontier risk of taking unintended or harmful actions. This situation underscores an urgent need for effective safety measures, akin to access controls for …

Agent-RLVR: Training Software Engineering Agents via Guidance and Environment Rewards

Jeff Da, C. Wang, Xiang Bo Deng, Yuntao Ma et autres

Reinforcement Learning from Verifiable Rewards (RLVR) has been widely adopted as the de facto method for enhancing the reasoning capabilities of large language models and has demonstrated notable success in verifiable domains like math and competitive programming tasks. However, the efficacy of …

Few-Shot Vision-Language Action-Incremental Policy Learning

Mingchen Song, Xiang Bo Deng, Guoqiang Zhong, Qi Lv et autres

Recently, Transformer-based robotic manipulation methods utilize multi-view spatial representations and language instructions to learn robot motion trajectories by leveraging numerous robot demonstrations. However, the collection of robot data is extremely challenging, and existing methods lack the capability for continuous learning on new …

Addressing Multi-Label Learning with Partial Labels: From Sample Selection to Label Selection

Gengyu Lyu, Boliang Sun, Xiang Bo Deng, Songhe Feng

Multi-label Learning with Partial Labels (ML-PL) learns from training data, where each sample is annotated with part of positive labels while leaving the rest of positive labels unannotated. Existing methods mainly focus on extending multi-label losses to estimate unannotated labels, further inducing …

cn (code pays fourni par la source)

Graph-based Diffusion Model for Collaborative Filtering

Xuan Zhang, Xiang Bo Deng, Hongxing Yuan, Chunyu Wei et autres

Recently, diffusion-based recommendation methods have achieved impressive results. However, existing approaches predominantly treat each user's historical interactions as independent training samples, overlooking the potential of higher-order collaborative signals between users and items. Such signals, which encapsulate richer and more nuanced relationships, can …

Long-Range Z Z Interaction via Resonator-Induced Phase in Superconducting Qubits

Xiang Bo Deng, Wen Zheng, Xudong Liao, Haoyu Zhou et autres

Superconducting quantum computing emerges as one of the leading candidates for achieving quantum advantage. However, a prevailing challenge is the coding overhead due to limited quantum connectivity, constrained by nearest-neighbor coupling among superconducting qubits. Here, we propose a novel multimode coupling scheme …

cn (code pays fourni par la source)

HCTRL: Hierarchical Clustering Tree Reinforcement Learning Algorithm for Efficient Content Caching

Ruohan Shi, Qilin Fan, Xiuhua Li, Kai Wang et autres

cn (code pays fourni par la source)

Development of the Chinese Dual Auroral Radar Network and Preliminary Results

J. J. Zhang, Ailan Lan, Jingye Yan, Xiang Bo Deng et autres

cn, es, us, jp (code pays fourni par la source)

Long-Range $ZZ$ Interaction via Resonator-Induced Phase in Superconducting Qubits

Xiang Bo Deng, Wen Zheng, Xudong Liao, Haoyu Zhou et autres

Superconducting quantum computing emerges as one of leading candidates for achieving quantum advantage. However, a prevailing challenge is the coding overhead due to limited quantum connectivity, constrained by nearest-neighbor coupling among superconducting qubits. Here, we propose a novel multimode coupling scheme using …