3 papers
cs.CV2026
PalmLeaf-VQA: A Multi-Script Visual Question Answering Benchmark for Historical Palm-Leaf Manuscript Understanding Across Diverse Regions
Nimol Thuon, Jun Du, Panhapin Theang
Historical manuscripts remain largely absent from modern vision-language benchmarks, leaving open how well multimodal large language models (MLLMs) handle culturally diverse, degra…
cs.IR2026
HeadRank: Decoding-Free Passage Reranking via Preference-Aligned Attention Heads
Juyuan Wang, Chenxing Wang, Yuchen Fang +8
Decoding-free reranking methods that read relevance signals directly from LLM attention weights offer significant latency advantages over autoregressive approaches, yet suffer from…
cs.CL2025
KH-FUNSD: A Hierarchical and Fine-Grained Layout Analysis Dataset for Low-Resource Khmer Business Document
Nimol Thuon, Jun Du
Automated document layout analysis remains a major challenge for low-resource, non-Latin scripts. Khmer is a language spoken daily by over 17 million people in Cambodia, receiving…