Yueting Zhuang

This work proposes EvoSkill-GUI, a training-free framework in which each skill is a structured multi-file package containing retrieval metadata, executable plans, backup localization, failure-recovery rules, accessibility utilities, and failure cases.

Scaling task complexity across 280 standardized manipulation variants reveals that today's leading VLA models fundamentally collapse under fine-grained spatial ambiguity and memory-intensive sequential planning.

Treating robot skill calls as runtime-verified execution proposals rather than blind action predictions enables self-correcting VLA autonomy that reaches 97.4% success on LIBERO.

TTPO achieves label-supervised performance without any ground-truth labels, outperforming traditional methods on key benchmarks.

Generating over 203,000 unique web interaction trajectories, BrowserForge significantly boosts model performance on real-world tasks by leveraging the vastness of the open web.

Decoupling perception from reasoning in visual tasks leads to a remarkable 93.2% accuracy on V-Star, showcasing a new paradigm for fine-grained visual reasoning.

Uncertainty-driven zoom-in boosts GUI grounding accuracy by up to 13.4% without any retraining, showing that targeted attention to model uncertainty can significantly improve performance.

Forget noisy pseudo-labels: SpatialEvo unlocks self-supervised 3D spatial reasoning by generating perfectly accurate training data directly from scene geometry.

Offloading memory and computation to a copilot lets a 7B parameter GUI agent outperform larger models on long-horizon tasks, suggesting a path to more efficient and capable GUI automation.

Object-centric vision could be the key to unlocking LMMs' potential for precise object manipulation and fine-grained spatial reasoning, capabilities currently beyond their reach.

Finally, a unified open-source framework lets you train, evaluate, and deploy GUI agents across real devices and chat platforms, closing the gap between research and real-world application.

Even frontier models like Claude Sonnet 4.6 stumble when asked to infer user preferences and proactively assist in mobile tasks, achieving less than 50% success despite excelling at explicit task execution.

Multimodal models can "see" the image but still fail at reasoning because the visual input distracts the routing mechanism from activating the right experts.

LLM agents can internalize skills via in-context RL, achieving zero-shot autonomous behavior without the token overhead and retrieval noise of traditional methods.

Current multimodal systems struggle with logical flow in visual sequences because they neglect visual logic, but LogiStory tackles this head-on, turning narrative coherence into an explicit objective.

By adversarially co-evolving code and test LLMs, Code-A1 achieves code generation performance on par with human-annotated training, while simultaneously boosting the LLM's ability to find bugs.