相关论文: F-IDEs with Features and VCs Designed to Assist Hu…

Fashion-image editing represents a challenging computer vision task, where the goal is to incorporate selected apparel into a given input image. Most existing techniques, known as Virtual Try-On methods, deal with this task by first…

Vision-and-Language Navigation in Continuous Environments (VLN-CE) is one of the most intuitive yet challenging embodied AI tasks. Agents are tasked to navigate towards a target goal by executing a set of low-level actions, following a…

The practical impact of deep learning on complex supervised learning problems has been significant, so much so that almost every Artificial Intelligence problem, or at least a portion thereof, has been somehow recast as a deep learning…

Test or prove? These two approaches to software verification have long been presented as opposites. One is dynamic, the other static: a test executes the program, a proof only analyzes the program text. A different perspective is emerging,…

We call on the Document AI (DocAI) community to reevaluate current methodologies and embrace the challenge of creating more practically-oriented benchmarks. Document Understanding Dataset and Evaluation (DUDE) seeks to remediate the halted…

Legal reasoning requires both precise interpretation of statutory language and consistent application of complex rules, presenting significant challenges for AI systems. This paper introduces a modular multi-agent framework that decomposes…

Advanced test-time computing strategies are essential for scaling reasoning models, but their effectiveness is capped by the models' poor self-evaluation. We propose a pairwise Explanatory Verifier, trained via reinforcement learning…

Training large language models (LLMs) with synthetic reasoning data has become a popular approach to enhancing their reasoning capabilities, while a key factor influencing the effectiveness of this paradigm is the quality of the generated…

High-quality datasets are critical for training and evaluating reliable NLP models. In tasks like natural language inference (NLI), human label variation (HLV) arises when multiple labels are valid for the same instance, making it difficult…

This paper is a brief introduction to our recently initiated project named VERIFAI: Traceability and verification of natural language requirements. The project addresses the challenges in the traceability and verification of formal…

Code completion is a popular software development tool integrated into all major IDEs. Many neural language models have achieved promising results in completion suggestion prediction on synthetic benchmarks. However, a recent study When…

Human intelligence is multimodal; we integrate visual, linguistic, and acoustic signals to maintain a holistic worldview. Most current pretraining methods, however, are limited to one or two modalities. We present i-Code, a self-supervised…

We present OpenComputer, a verifier-grounded framework for constructing verifiable software worlds for computer-use agents. OpenComputer integrates four components: (1) app-specific state verifiers that expose structured inspection…

Rule-based systems remain central in safety-critical domains but often struggle with scalability, brittleness, and goal misspecification. These limitations can lead to reward hacking and failures in formal verification, as AI systems tend…

AI code generation tools have expanded software creation beyond professional developers, giving rise to vibe coding, a practice in which users generate software via natural-language prompts, evaluate outputs primarily by execution. Prior…

The requirements engineering (RE) phase is pivotal in developing high-quality software. Integrating advanced modelling techniques with large language models (LLMs) and formal verification in a logical style can significantly enhance this…

Multimodal Large Language Models (MLLMs) struggle with precise reasoning for structured visuals like charts and diagrams, as pixel-based perception lacks a mechanism for verification. To address this, we propose to leverage derendering --…

Transformer-based language models for automatic code completion have shown great promise so far, yet the evaluation of these models rarely uses real data. This study provides both quantitative and qualitative assessments of three public…

Training models through self-play alone (without any human data) has been a longstanding goal in AI, but its effectiveness for training large language models remains unclear, particularly in code generation where rewards based on unit tests…

We introduce Reinforcement Learning (RL) with Adaptive Verifiable Environments (RLVE), an approach using verifiable environments that procedurally generate problems and provide algorithmically verifiable rewards, to scale up RL for language…