Related papers: Contextualized Data-Wrangling Code Generation in C…

Code generation maps a program description to executable source code in a programming language. Existing approaches mainly rely on a recurrent neural network (RNN) as the decoder. However, we find that a program contains significantly more…

Generating images conditioned on multiple visual references is critical for real-world applications such as multi-subject composition, narrative illustration, and novel view synthesis, yet current models suffer from severe performance…

Reasoning capability is pivotal for Large Language Models (LLMs) to solve complex tasks, yet achieving reliable and scalable reasoning remains challenging. While Chain-of-Thought (CoT) prompting has become a mainstream approach, existing…

Contextual Partitioning introduces an innovative approach to enhancing the architectural design of large-scale computational models through the dynamic segmentation of parameters into context-aware regions. This methodology emphasizes the…

Code intelligence leverages machine learning techniques to extract knowledge from extensive code corpora, with the aim of developing intelligent tools to improve the quality and productivity of computer programming. Currently, there is…

Image captioning is one of the straightforward tasks that can take advantage of large-scale web-crawled data which provides rich knowledge about the visual world for a captioning model. However, since web-crawled data contains image-text…

Context-bounded analysis has been shown to be both efficient and effective at finding bugs in concurrent programs. According to its original definition, context-bounded analysis explores all behaviors of a concurrent program up to some…

Recent diffusion models achieve strong photorealism and fluency in video generation, yet remain fragile under abstract, sparse or complex conditions, leading to poor performance in professional production workflows such as storyboard…

To adequately test modern code generation systems, evaluation benchmarks must execute and test the code generated by the system. However, these execution and testing requirements have largely limited benchmarks to settings where code is…

Large Language Models (LLMs) and Code-LLMs (CLLMs) have significantly improved code generation, but, they frequently face difficulties when dealing with challenging and complex problems. Retrieval-Augmented Generation (RAG) addresses this…

Effective code generation requires both model capability and a problem representation that carefully structures how models reason and plan. Existing approaches augment reasoning steps or inject specific structure into how models think, but…

Open-ended learning frames intelligence as emerging from continual interaction with an ever-expanding space of environments. While recent advances have utilized foundation models to programmatically generate diverse environments, these…

Since the rise of neural natural-language-to-code models (NL->Code) that can generate long expressions and statements rather than a single next-token, one of the major problems has been reliably evaluating their generated output. In this…

Accurate document layout analysis is a key requirement for high-quality PDF document conversion. With the recent availability of public, large ground-truth datasets such as PubLayNet and DocBank, deep-learning models have proven to be very…

Retrieval-Augmented Generation (RAG) allows overcoming the limited knowledge of LLMs by extending the input with external information. As a consequence, the contextual inputs to the model become much longer which slows down decoding time…

Recent neural models have shown significant progress on the problem of generating short descriptive texts conditioned on a small number of database records. In this work, we suggest a slightly more difficult data-to-text generation task,…

Interleaved image-text generation has emerged as a crucial multimodal task, aiming at creating sequences of interleaved visual and textual content given a query. Despite notable advancements in recent multimodal large language models…

Data management and analysis tasks are often carried out using spreadsheet software. A popular feature in most spreadsheet platforms is the ability to define data-dependent formatting rules. These rules can express actions such as "color…

Training on verifiable symbolic data is a promising way to expand the reasoning frontier of language models beyond what standard pre-training corpora provide. Yet existing procedural generators often rely on fixed puzzles or templates and…

Automating the development of machine learning algorithms has the potential to unlock new breakthroughs. However, our ability to improve and evaluate algorithm discovery systems has thus far been limited by existing task suites. They suffer…