Related papers: Correct-by-Construction G-Code Generation: A Neuro…
Multimodal geometry reasoning requires models to jointly understand visual diagrams and perform structured symbolic inference, yet current vision--language models struggle with complex geometric constructions due to limited training data…
Autonomous systems that build structures from natural-language instructions need reliable spatial reasoning, yet large language models (LLMs) make systematic coordinate errors when generating three-dimensional block placements. We present a…
This paper investigates how hallucination rates in Large Language Models (LLMs) may be controlled via a symbolic data generation framework, exploring a fundamental relationship between the rate of certain mathematical errors and types of…
Utilizing large language models to generate codes has shown promising meaning in software development revolution. Despite the intelligence shown by the large language models, their specificity in code generation can still be improved due to…
Generating accurate circuit schematics from high-level natural language descriptions remains a persistent challenge in electronic design automation (EDA), as large language models (LLMs) frequently hallucinate components, violate strict…
Leveraging advanced reasoning capabilities and extensive world knowledge of large language models (LLMs) to construct generative agents for solving complex real-world problems is a major trend. However, LLMs inherently lack embodiment as…
Foundational verification considers the functional correctness of programming languages with formalized semantics and uses proof assistants (e.g., Coq, Isabelle) to certify proofs. The need for verifying complex programs compels it to…
State-of-the-art code generation frameworks rely on mental simulation, where LLMs internally trace execution to verify correctness. We expose a fundamental limitation: the Mental-Reality Gap -- where models hallucinate execution traces and…
This paper aims to design a unified Computer-Aided Design (CAD) generation system that can easily generate CAD models based on the user's inputs in the form of textual description, images, point clouds, or even a combination of them.…
Evaluations of large language models (LLMs) primarily emphasize convergent logical reasoning, where success is defined by producing a single correct proof. However, many real-world reasoning problems admit multiple valid derivations,…
LLMs deployed in high-stakes domains face fundamental reliability challenges: hallucinations, inconsistencies, and privacy vulnerabilities introduce unacceptable risks where errors carry legal, financial, or safety consequences. This paper…
Large language models (LLMs) show significant potential for clinical decision support (CDS), yet their black-box nature -- characterized by untraceable reasoning and probabilistic hallucinations -- poses severe challenges in acupuncture, a…
Visual reasoning tasks such as visual question answering (VQA) require an interplay of visual perception with reasoning about the question semantics grounded in perception. However, recent advances in this area are still primarily driven by…
Large language models (LLMs) have demonstrated remarkable capabilities in code generation across various domains. However, their effectiveness in generating simulation scripts for domain-specific environments like ns-3 remains…
Large language models (LLMs) have shown great potential for automatic code generation and form the basis for various tools such as GitHub Copilot. However, recent studies highlight that many LLM-generated code contains serious security…
Lane topology extraction involves detecting lanes and traffic elements and determining their relationships, a key perception task for mapless autonomous driving. This task requires complex reasoning, such as determining whether it is…
Structured reasoning over natural language inputs remains a core challenge in artificial intelligence, as it requires bridging the gap between unstructured linguistic expressions and formal logical representations. In this paper, we propose…
Natural language explanations (NLEs) are commonly used to provide plausible free-text explanations of a model's reasoning about its predictions. However, recent work has questioned their faithfulness, as they may not accurately reflect the…
While Temporal Logic provides a rigorous verification framework for robotics, it typically operates on trajectory-level signals and does not natively represent the object-centric geometric relations that are central to manipulation.…
LLMs can perform multi-step reasoning through Chain-of-Thought (CoT), but they cannot reliably verify their own logic. Even when they reach correct answers, the underlying reasoning may be flawed, undermining trust in high-stakes scenarios.…