Related papers: BRIDGE: Building Representations In Domain Guided …

Program synthesis techniques construct or infer programs from user-provided specifications, such as input-output examples. Yet most specifications, especially those given by end-users, leave the synthesis problem radically ill-posed,…

Multimodal large language models (MLLMs) extend the success of language models to visual understanding, and recent efforts have sought to build unified MLLMs that support both understanding and generation. However, constructing such models…

Time-series Generation (TSG) is a prominent research area with broad applications in simulations, data augmentation, and counterfactual analysis. While existing methods have shown promise in unconditional single-domain TSG, real-world…

High-quality labeled datasets are fundamental for training and evaluating machine learning models, yet domains such as healthcare and Requirements Engineering (RE) face persistent barriers due to data scarcity, privacy constraints, or…

Automated proof generation for formal software verification remains largely unresolved despite advances in large language models (LLMs). While LLMs perform well in NLP, vision, and code generation, formal verification still requires…

Recent advancements in Large Language Models (LLMs) have revealed a significant performance gap between closed-source and open-source models, particularly in tasks requiring complex reasoning and precise instruction following. This paper…

Translating human-written mathematical theorems and proofs from natural language (NL) into formal languages (FLs) like Lean 4 has long been a significant challenge for AI. Most state-of-the-art methods either focus on theorem-only NL-to-FL…

Large language models have become proficient at generating functional code, but ensuring the output truly matches the programmer's intent remains difficult. Testing improves trust, yet for safety-critical applications, formal verification…

Large Language Models (LLMs) demonstrate strong proficiency in generating code for high-resource programming languages (HRPLs) like Python but struggle significantly with low-resource programming languages (LRPLs) such as Racket or D. This…

Mathematical reasoning remains challenging for LLMs due to complex logic and the need for precise computation. Existing methods enhance LLM reasoning by synthesizing datasets through problem rephrasing, but face issues with generation…

Even with impressive advances in automated formal methods, certain problems in system verification and synthesis remain challenging. Examples include the verification of quantitative properties of software involving constraints on timing…

Large language models have demonstrated remarkable capabilities across diverse reasoning tasks, yet their performance on algorithmic reasoning remains limited. To handle this limitation, we propose PRIME (Policy-Reinforced Iterative…

Large Language Models (LLMs) often struggle with complex mathematical reasoning, where prose-based generation leads to unverified and arithmetically unsound solutions. Current prompting strategies like Chain of Thought still operate within…

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…

Multimodal retrieval systems struggle to resolve image-text queries against text-only corpora: the best vision-language encoder achieves only 27.6 nDCG@10 on MM-BRIGHT, underperforming strong text-only retrievers. We argue the bottleneck is…

Prompt-based continual learning (CL) provides a parameter-efficient approach for adapting large language models (LLMs) across task sequences. However, most existing methods rely on task-aware inference and maintain a growing set of…

The evolution of Large Language Models (LLMs) from static instruction-followers to autonomous agents necessitates operating within complex, stateful environments to achieve precise state-transition objectives. However, this paradigm is…

Modern Large Language Model (LLM) systems are assembled from third-party artifacts such as pre-trained weights, fine-tuning adapters, datasets, dependency packages, and container images, fetched through automated pipelines. This speed comes…

Automated assessment of open-ended student responses is a critical capability for scaling personalized feedback in education. While large language models (LLMs) have shown promise in grading tasks via in-context learning (ICL), their…

In the past few years, Large Language Models (LLMs) have exploded in usefulness and popularity for code generation tasks. However, LLMs still struggle with accuracy and are unsuitable for high-risk applications without additional oversight…