paper-with-me

Papers

MetaPoint: Unlocking Precise Spatial Control in Agentic Visual Generation

2026-06-03 · Dewei Zhou, Xinyu Huang, Xun Wang, Ji Xie, Yabo Zhang, Liang Li, Kunchang Li, Zongxin Yang, Yi Yang arxiv

Generative visual models fundamentally struggle with precise spatial control. This arises from a core disconnect: models can process textual descriptions of space but cannot directly map numerical coordinates onto the 2D image canvas. We introduce MetaPoint, a method that bridges this gap by representing a continuous 2D coordinate as a single, special token. Crucially, MetaPoint requires no new architectural components; it directly leverages the model's inherent positional encoding schemes to interpret these coordinates, treating our token as a virtual point on the canvas. This lightweight approach enables pixel-level control of an object's position with one token or its bounding box with two, all without requiring architectural changes or bespoke attention masking. The MetaPoint tokens are designed to be compositional, serving as spatial primitives. This allows a planner agent to decompose a high-level user request into a structured sequence of primitives for the generator. By providing a simple, precise, and scalable building block for spatial control, MetaPoint unlocks more powerful compositional generative agents and enables intuitive, interactive editing systems.

📄 PDF Abstract BibTeX arXiv:2606.05031

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

ToolVerse: Unlocking Massive Environments and Long-Horizon Tasks for Agentic Reinforcement Learning

2026-07-17 · Shuaiyu Zhou, Fengpeng Yue, Zengjie Hu, Yuanzhe Shen 외 arxiv

While LLM agents demonstrate strong reasoning abilities in compact and well-defined scenarios, they struggle to maintain robustness and effectiveness when faced with large-scale, diverse, and dynamic real-world environme…

Reinforcement Learning

Beyond Flatlands: Unlocking Spatial Intelligence by Decoupling 3D Reasoning from Numerical Regression

2025-11-14 · Zhongbin Guo, Jiahe Liu, Yushan Li, Wenyu Gao 외 arxiv

Existing Vision Language Models (VLMs) architecturally rooted in "flatland" perception, fundamentally struggle to comprehend real-world 3D spatial intelligence. This failure stems from a dual-bottleneck: input-stage conf…

Spatial Reasoning

PULSE: Agentic Investigation with Passive Sensing for Proactive Intervention in Cancer Survivorship

2026-05-17 · Zhiyuan Wang, Ariful Islam, Indrajeet Ghosh, Xinyu Chen 외 arxiv

Cancer survivors face elevated rates of depression, anxiety, and general emotional distress, yet the precise moments they most need support are often the moments when self-report is sparse, a phenomenon we term the diary…

Networking-Aware Energy Efficiency in Agentic AI Inference: A Survey

2026-04-09 · Xiaojing Chen, Haiqi Yu, Wei Ni, Dusit Niyato 외 arxiv

The rapid emergence of Large Language Models (LLMs) has catalyzed Agentic artificial intelligence (AI), autonomous systems integrating perception, reasoning, and action into closed-loop pipelines for continuous adaptatio…

Answer Only as Precisely as Justified: Calibrated Claim-Level Specificity Control for Agentic Systems

2026-04-19 · Tianyi Huang, Samuel Xu, Jason Tansong Dang, Samuel Yan 외 arxiv

Agentic systems often fail not by being entirely wrong, but by being too precise: a response may be generally useful while particular claims exceed what the evidence supports. We study this failure mode as overcommitment…