ChartQA
PulseAugur coverage of ChartQA — every cluster mentioning ChartQA across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New system enhances document Q&A with visual retrieval and evidence threading
Researchers have developed a novel system for question answering on long-context documents, particularly those with visual elements like charts and infographics. The system, named VisRAG-Ret, utilizes a frozen Qwen2.5-V…
-
New STEER method enhances AI's scientific chart understanding
Researchers have developed a new method called STEER (Structure-Token Evidence-anchored Reasoning) to improve how large vision-language models understand scientific charts. Current models often treat charts like regular…
-
New framework ChartProbe boosts VLM visual reasoning by training simpler skills
Researchers have developed ChartProbe, a diagnostic framework designed to improve visual reasoning in vision-language models (VLMs). This framework isolates and trains simpler skills like perception and grounding, rathe…
-
New benchmark SynthDocBench reveals VLM failures in long-context document understanding
Researchers have introduced SynthDocBench, a novel synthetic benchmark designed to evaluate the long-context visual document understanding capabilities of vision-language models (VLMs). Unlike existing benchmarks, Synth…
-
New system routes chart questions to save VLM costs
Researchers have developed SAFE-Cascade, a system designed to optimize chart question answering by adaptively routing queries between a text-only language model and a more powerful vision-language model (VLM). This appr…
-
New VLM Self-Ensembling Method Improves Chart Data Extraction Accuracy
Researchers have developed a self-ensembling method for vision-language models (VLMs) to improve the extraction of data from chart images. This technique involves generating multiple tabular outputs from the same VLM fo…
-
New Benchmark Evaluates VLMs on Extracting Data from Epidemic Curves
Researchers have introduced EpiCurveBench, a new benchmark designed to evaluate vision-language models (VLMs) on the task of extracting data from epidemic curve charts. This benchmark includes 1,000 real-world epidemic …
-
Perceptual Flow Network and VGR enhance visual reasoning in LLMs
Researchers have developed a Perceptual Flow Network (PFlowNet) to improve visual reasoning in Large-Vision Language Models (LVLMs). PFlowNet decouples perception from reasoning and uses variational reinforcement learni…
-
New benchmarks DRAGON and OmniSch test LMMs on diagram reasoning
Researchers have introduced DRAGON, a new benchmark designed to evaluate how well vision-language models (VLMs) can ground their reasoning in specific visual evidence within diagrams. This benchmark addresses the limita…