ViBR reproduces 72% of bugs from video reports by segmenting actions with CLIP similarity and using VLMs for region-aware GUI state comparison, outperforming prior heuristics-based methods.
arXiv preprint arXiv:2109.03144 (2021) 1, 4, 5
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
verdicts
UNVERDICTED 5representative citing papers
StrucTab achieves SOTA table parsing performance by unifying structural subtasks through sequential reasoning and using decomposed RL rewards in Uni-TabRL, plus a new TableVerse-5K benchmark.
GOT is a unified end-to-end model that treats all man-made optical signals as characters and handles multiple OCR tasks including formatted output and interactive region recognition via prompts.
PaddleOCR 3.0 releases compact open-source models for OCR, document structure parsing, and information extraction that rival billion-parameter VLMs.
PP-OCRv6 introduces three tiers of lightweight OCR models (1.5M–34.5M parameters) built on unified MetaFormer blocks with reparameterization that claim superior accuracy to PP-OCRv5 and billion-scale VLMs on in-house benchmarks.
citing papers explorer
-
ViBR: Automated Bug Replay from Video-based Reports using Vision-Language Models
ViBR reproduces 72% of bugs from video reports by segmenting actions with CLIP similarity and using VLMs for region-aware GUI state comparison, outperforming prior heuristics-based methods.
-
StrucTab: A Structured Optimization Framework for Table Parsing
StrucTab achieves SOTA table parsing performance by unifying structural subtasks through sequential reasoning and using decomposed RL rewards in Uni-TabRL, plus a new TableVerse-5K benchmark.
-
General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
GOT is a unified end-to-end model that treats all man-made optical signals as characters and handles multiple OCR tasks including formatted output and interactive region recognition via prompts.
-
PaddleOCR 3.0 Technical Report
PaddleOCR 3.0 releases compact open-source models for OCR, document structure parsing, and information extraction that rival billion-parameter VLMs.
-
PP-OCRv6: From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks
PP-OCRv6 introduces three tiers of lightweight OCR models (1.5M–34.5M parameters) built on unified MetaFormer blocks with reparameterization that claim superior accuracy to PP-OCRv5 and billion-scale VLMs on in-house benchmarks.