← Back to all news
arXiv Computation and Language By Hao Qiu, Junyan Wang, Zheyuan Liu, Lei Fan, Hong Jia, Lianbo Guo, Zhulin Tao

ManGo: Manga Active Narrative Grounding Optimization

Read the original on arXiv Computation and Language →

ManGo is an unsupervised framework for manga visual question answering that actively selects panels, extracts concise clues, and decides when to stop, creating a compact evidence sketch before answering. It introduces Active Narrative Sketching (ANS) and optimizes its behavior using group-relative policy training with two rewards: answer preference from listwise self-ranking and path consistency from stable ordered panel trajectories. Experiments on standard manga understanding benchmarks demonstrate that ManGo achieves state‑of‑the‑art performance across different settings.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Related stories

arXiv AI
Sep 15

Navigating Sparse Evidence: Agentic Visual RAG via Explicit Context Selection and Consolidation

The paper introduces SCoRE, an agentic framework for Visual Retrieval-Augmented Generation that explicitly selects and consolidates visual evidence before generating answers. It addresses two key challenges: sparse, scattered evidence and noisy exploration trajectories that obscure reasoning. By maintaining a textual ledger of relevant observations and reloading original images for a logical evidence sequence, SCoRE decouples reasoning from exploration and enforces strict visual grounding, with training that rewards evidence coverage, compactness, and answer correctness.

By Yucheng Shen, Lingyong Yan, Jiulong Wu, Shuaiqiang Wang, Jianmin WU, Dawei Yin, Min Cao
ragagentsreinforcement-learningefficiency
More like this →
arXiv AI
Jul 22

PlotTwist: A Creative Plot Generation Framework with Small Language Models

arXiv:2603. 16410v2 Announce Type: replace-cross Abstract: Creative plot generation presents a fundamental challenge for language models: transforming a concise premise into a coherent narrative that sustains global coherence, character development, pacing, tone consistency, and emotional progression.

By Abhinav Thorat, Ravi Kolla, Jyotin Goel, Madhav Kataria, Niranjan Pedanekar
llmsagentsreinforcement-learningsafety
More like this →
arXiv AI
Sep 3

DocHop: Benchmarking Out-of-domain Multi-hop Reasoning in Information-Dense Documents

DocHop is a new benchmark that tests multimodal large language models on integrated chart‑context reasoning within document‑style images. The benchmark presents narrative text that imposes multi‑step compositional constraints, while charts supply the data needed to answer questions grounded in semantic reference labels. It contains 2,074 examples across six task categories, generated via a stochastic logic‑first pipeline that controls reasoning depth and visual density, and shows a large performance gap between humans (over 90% accuracy) and the best models (62.83%).

By Zhuoran Yu, Le Thien Phuc Nguyen, Jaden Park, Xinyi Gu, Zexue He, Soochahn Lee, Rogerio Feris, Yong Jae Lee
llmsnlpmultimodalbenchmarks
More like this →