4 papers
MHVF: Training-Free GUI Grounding via Verification-Guided Multi-Hypothesis Search
Minghua Chen, Xingming Liao, Weiqiang Zhong +1
GUI grounding enables web agents to translate natural-language instructions into actionable interface locations. However, dense layouts and small, visually similar controls can lea…
MARINER: A 3E-Driven Benchmark for Fine-Grained Perception and Complex Reasoning in Open-Water Environments
Xingming Liao, Ning Chen, Muying Shu +5
Fine-grained visual understanding and high-level reasoning in real-world open-water environments remain under-explored due to the lack of dedicated benchmarks. We introduce MARINER…
Chameleon: Benchmarking Detection and Backtracking on Commercial-Grade AI-Generated Videos
Xingming Liao, Meiyu Zeng, Canyu Chen +3
The proliferation of AI-Generated Content (AIGC), especially deepfake videos, poses a severe threat to social trust by enabling fraud, privacy violations and disinformation. Existi…
Composited-Nested-Learning with Data Augmentation for Nested Named Entity Recognition
Xingming Liao, Nankai Lin, Haowen Li +3
Nested Named Entity Recognition (NNER) focuses on addressing overlapped entity recognition. Compared to Flat Named Entity Recognition (FNER), annotated resources are scarce in the…