17 papers
Thinking with Anchors: Grounded and Efficient Document Reasoning
Sichen Zhu, Yuchen Zhu, Wenzhuo Xu +13
Existing document understanding benchmarks have largely focused on locating page elements, yet real-world document intelligence requires models to reason jointly about region seman…
Spinning Straw into Gold: Relabeling LLM Agent Trajectories in Hindsight for Successful Demonstrations
Zichao Li, Gang Wu, Zichao Wang +5
Large language model agents operate in partially observable, long-horizon settings where obtaining supervision remains a major bottleneck. We address this by utilizing a source of…
GUI-AIMA: Aligning Intrinsic Multimodal Attention with a Context Anchor for GUI Grounding
Shijie Zhou, Viet Dac Lai, Hao Tan +4
Graphical user interface (GUI) grounding is a key capability for computer-use agents, mapping natural-language instructions to actionable regions on the screen. Existing Multimodal…
Text-Conditioned Background Generation for Editable Multi-Layer Documents
Taewon Kang, Joseph K J, Chris Tensmeyer +4
We present a framework for document-centric background generation with multi-page editing and thematic continuity. To ensure text regions remain readable, we employ a latent maskin…
FLARE: Diffusion for Hybrid Language Model
Yuchen Zhu, Jing Shi, Chongjian Ge +9
Autoregressive (AR) large language models (LLMs) have achieved broad practical success, but sequential decoding remains a key bottleneck for low-latency deployment. Recent efficien…
Conformalized Percentile Interval: Finite Sample Validity and Improved Conditional Performance
Ran Zou, Wanrong Zhu, Bin Nan
Conformal prediction provides distribution-free predictive intervals with finite-sample marginal coverage. However, achieving conditional validity and interval efficiency (in terms…