Related papers: ChartZero: Synthetic Priors Enable Zero Shot Chart…
Long-horizon Flexible Job-Shop Scheduling~(FJSP) presents a formidable combinatorial challenge due to complex, interdependent decisions spanning extended time horizons. While learning-based Rolling Horizon Optimization~(RHO) has emerged as…
A major obstacle to the wide-spread adoption of neural retrieval models is that they require large supervised training sets to surpass traditional term-based techniques, which are constructed from raw corpora. In this paper, we propose an…
Learning-based stereo matching and depth estimation networks currently excel on public benchmarks with impressive results. However, state-of-the-art networks often fail to generalize from synthetic imagery to more challenging real data…
Piano audio-to-score transcription (A2S) is an important yet underexplored task with extensive applications for music composition, practice, and analysis. However, existing end-to-end piano A2S systems faced difficulties in retrieving…
Large, high-quality annotated corpora remain scarce in document-level entity and relation extraction in zero-shot or few-shot settings. In this paper, we present a fully automatic, LLM-based pipeline for synthetic data generation and…
Existing dehazing approaches struggle to process real-world hazy images owing to the lack of paired real data and robust priors. In this work, we present a new paradigm for real image dehazing from the perspectives of synthesizing more…
Text-to-image (T2I) models offer great potential for creating virtually limitless synthetic data, a valuable resource compared to fixed and finite real datasets. Previous works evaluate the utility of synthetic data from T2I models on three…
Automatic synthesis of hardware components from declarative specifications is an ambitious endeavor in computer aided design. Existing synthesis algorithms are often implemented with Binary Decision Diagrams (BDDs), inheriting their…
Automatic data extraction from charts is challenging for two reasons: there exist many relations among objects in a chart, which is not a common consideration in general computer vision problems; and different types of charts may not be…
Recent advances in search-augmented large reasoning models (LRMs) enable the retrieval of external knowledge to reduce hallucinations in multistep reasoning. However, their ability to operate on graph-structured data, prevalent in domains…
Constructing a static call graph requires trade-offs between soundness and precision. Program analysis techniques for constructing call graphs are unfortunately usually imprecise. To address this problem, researchers have recently proposed…
Objective: Modelling the associations from high-throughput experimental molecular data has provided unprecedented insights into biological pathways and signalling mechanisms. Graphical models and networks have especially proven to be useful…
Zero-shot quantization (ZSQ) is promising for compressing and accelerating deep neural networks when the data for training full-precision models are inaccessible. In ZSQ, network quantization is performed using synthetic samples, thus, the…
Building a semantic parser quickly in a new domain is a fundamental challenge for conversational interfaces, as current semantic parsers require expensive supervision and lack the ability to generalize to new domains. In this paper, we…
The rise of graph-structured data has driven interest in graph learning and synthetic data generation. While successful in text and image domains, synthetic graph generation remains challenging -- especially for real-world graphs with…
Semantic parsing datasets are expensive to collect. Moreover, even the questions pertinent to a given domain, which are the input of a semantic parsing system, might not be readily available, especially in cross-domain semantic parsing.…
The financial industry is increasingly seeking robust methods to address the challenges posed by data scarcity and low signal-to-noise ratios, which limit the application of deep learning techniques in stock market analysis. This paper…
Vision-Language Models (VLMs) have shown promise in generating plotting code from chart images, yet achieving structural fidelity remains challenging. Existing approaches largely rely on supervised fine-tuning, encouraging surface-level…
Charts are very popular for analyzing data, visualizing key insights and answering complex reasoning questions about data. To facilitate chart-based data analysis using natural language, several downstream tasks have been introduced…
Visual grouping -- operationalized through tasks such as instance segmentation, visual grounding, and object detection -- enables applications ranging from robotic perception to photo editing. These fundamental problems in computer vision…