15 papers
MOBA-VL: Event-Localized Multi-Turn Reinforcement Learning for Real-Time MOBA Commentary
Shengyun Zhong, Xinkang Zhao, Ziyuan Chu +1
Real-time commentary for Multiplayer Online Battle Arena (MOBA) esports requires a vision-language model (VLM) to narrate a live match second by second, both fluently and accuratel…
CaptchaArena: A Large-Scale, Fine-Grained Dataset for Training Computer-Use Agents on Interactive CAPTCHAs
Zhenhao Zhang, Zhaoyu Fan, Haohan Ying +5
Interactive CAPTCHAs remain challenging for computer-use agents, while existing datasets face trade-offs among type coverage, interaction fidelity, and trajectory supervision. To a…
No Free Checker: A Survey of Verifiers for Robot Policies
Yang Wan, Xihang Yue, Zhirui Liu +7
A verifier for robot policies reads a candidate behavior and returns a score for how well it did, used both to evaluate vision-language-action policies and to train them. Verifiers…
From Interaction Traces to Persistent Skills: Online Evolution for Computer-Use Agents
Longtao Hu, Xiao Liang, Linchao Zhu
Computer-use agents can execute increasingly complex tasks in graphical interfaces, but their interaction experience is typically transient: procedural knowledge acquired from one…
SeekJudge: A Practical Reward Framework for Reinforcement Learning in Computer-Use Agents
Yang Wan, Zhenhao Zhang, Jierui Wang +2
Deciding whether a trajectory actually fulfills its instruction determines how we measure computer-use agents on long-horizon graphical-user-interface tasks and how we train them w…
VISTA: View-Consistent Self-Verified Training for GUI Grounding
Xinyu Qiu, Yunzhu Zhang, Heng Jia +3
When applying Group Relative Policy Optimization (GRPO) for GUI Grounding, rollouts are sampled from a single screenshot view; groups often become either all failures on difficult…
A Fixed-Point Neural Operator for Size- and Functional-Transferable Hamiltonian Prediction
Yunhong Lou, Xihang Yue, Xinran Wei +2
Predicting the Kohn-Sham Hamiltonian with machine learning can accelerate density functional theory while retaining access to molecular orbitals, energy levels, and electronic-stru…
GPD: Guided Progressive Distillation for Fast and High-Quality Video Generation
Xiao Liang, Yunzhu Zhang, Linchao Zhu
Diffusion models have achieved remarkable success in video generation; however, the high computational cost of the denoising process remains a major bottleneck. Existing approaches…
Mitigating Conversational Inertia in Multi-Turn Agents
Yang Wan, Zheng Cao, Zhenhao Zhang +4
Large language models excel as few-shot learners when provided with appropriate demonstrations, yet this strength becomes problematic in multiturn agent scenarios, where LLMs erron…
MTC-VAE: Multi-Level Temporal Compression with Content Awareness
Yubo Dong, Linchao Zhu
Latent Video Diffusion Models (LVDMs) rely on Variational Autoencoders (VAEs) to compress videos into compact latent representations. For continuous Variational Autoencoders (VAEs)…
Unified Generation and Self-Verification for Vision-Language Models via Advantage Decoupled Preference Optimization
Xinyu Qiu, Heng Jia, Zhengwen Zeng +4
Parallel test-time scaling typically trains separate generation and verification models, incurring high training and inference costs. We propose Advantage Decoupled Preference Opti…
MVP: Multiple View Prediction Improves GUI Grounding
Yunzhu Zhang, Zeyu Pan, Zhengwen Zeng +3
GUI grounding, which translates natural language instructions into precise pixel coordinates, is essential for developing practical GUI agents. However, we observe that existing gr…
H3R: Hybrid Multi-view Correspondence for Generalizable 3D Reconstruction
Heng Jia, Linchao Zhu, Na Zhao
Despite recent advances in feed-forward 3D Gaussian Splatting, generalizable 3D reconstruction remains challenging, particularly in multi-view correspondence modeling. Existing app…
Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks
Hongyuan Tao, Ying Zhang, Zhenhao Tang +12
Recent advances in Large Language Models (LLMs) have shown promise in function-level code generation, yet repository-level software engineering tasks remain challenging. Current so…
High-Fidelity Facial Albedo Estimation via Texture Quantization
Zimin Ran, Xingyu Ren, Xiang An +6
Recent 3D face reconstruction methods have made significant progress in shape estimation, but high-fidelity facial albedo reconstruction remains challenging. Existing methods depen…