What's Missing in Screen-to-Action? Towards a UI-in-the-Loop Paradigm for Multimodal GUI Reasoning
Paper • 2604.06995 • Published • 1
Songze Li
CatCatCat36
AI & ML interests
Pre-trained Language Model, Knowledge Representation and Reasoning, Muti-modal Large Language Model, GUI Agents
Recent Activity
upvoted a paper 1 day ago
Scaling LLM Knowledge Boundaries via Distribution-Optimized Synthesis authored a paper 1 day ago
What's Missing in Screen-to-Action? Towards a UI-in-the-Loop Paradigm for Multimodal GUI ReasoningOrganizations
upvoted 4
papers 1 day ago
Scaling LLM Knowledge Boundaries via Distribution-Optimized Synthesis
Paper • 2606.23271 • Published • 1
Last Layer Logits to Logic: Empowering LLMs with Logic-Consistent Structured Knowledge Reasoning
Paper • 2511.07910 • Published • 1
Enrich-on-Graph: Query-Graph Alignment for Complex Reasoning with LLM Enriching
Paper • 2509.20810 • Published • 1