8 papers
DocAtlas: Long-Document Understanding as Mutable-State Interaction
Hongchen Wei, Yuanzhe Wang, Bei Liu +8
Long-document understanding requires models to find and combine evidence across many pages, layouts, tables, figures, and charts. Existing retrieval-augmented systems usually selec…
XL-DocBench: Benchmarking Evidence-Grounded Extra-Long Document Understanding
Hongchen Wei, Yuanzhe Wang, Bei Liu +9
Real-world document tasks often ask professionals to answer questions from annual reports, regulations, clinical guidelines, and technical manuals that span hundreds or thousands o…
SciDiagramEdit: Learning to Edit Scientific Diagrams from Paper Revisions
Yasheng Sun, Zezi Zeng, Yifan Yang +4
The paper introduces SciDiagramEdit, a system that learns to edit scientific figures based on natural-language revision instructions by training on before-and-after figure pairs fr…
RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources
Yijia Fan, Zonglin Di, Zimo Wen +8
The paper introduces RESOURCE2SKILL, a framework that converts multimodal human-created resources such as tutorial videos, code repositories, and articles into executable skills or…
PDCR: Perception-Decomposed Confidence Reward for Vision-Language Reasoning
Hee Suk Yoon, Eunseop Yoon, Ji Woo Hong +6
Reinforcement Learning with Verifiable Rewards (RLVR) traditionally relies on a sparse, outcome-based signal. Recent work shows that providing a fine-grained, model-intrinsic signa…
Covering Human Action Space for Computer Use: Data Synthesis and Benchmark
Miaosen Zhang, Xiaohan Zhao, Zhihong Tan +14
Computer-use agents (CUAs) automate on-screen work, as illustrated by GPT-5.4 and Claude. Yet their reliability on complex, low-frequency interactions is still poor, limiting user…