Related papers: Portus: Linking Alloy with SMT-based Finite Model …

In this paper, we present an early version of a SYCL-based FFT library, capable of running on all major vendor hardware, including CPUs and GPUs from AMD, ARM, Intel and NVIDIA. Although preliminary, the aim of this work is to seed further…

The enormous structural and chemical diversity of metal-organic frameworks (MOFs) forces researchers to actively use simulation techniques on an equal footing with experiments. MOFs are widely known for outstanding adsorption properties, so…

Structured outputs are essential for large language models (LLMs) in critical applications like agents and information extraction. Despite their capabilities, LLMs often generate outputs that deviate from predefined schemas, significantly…

Conventional spoken language translation (SLT) systems are pipeline based systems, where we have an Automatic Speech Recognition (ASR) system to convert the modality of source from speech to text and a Machine Translation (MT) systems to…

Supervised fine-tuning (SFT) has emerged as a crucial method for aligning large language models (LLMs) with human-annotated demonstrations. However, SFT, being an off-policy approach similar to behavior cloning, often struggles with…

Prior work in semantic parsing has shown that conventional seq2seq models fail at compositional generalization tasks. This limitation led to a resurgence of methods that model alignments between sentences and their corresponding meaning…

In the context of verification of data-aware processes (DAPs), a formal approach based on satisfiability modulo theories (SMT) has been considered to verify parameterised safety properties of so-called artifact-centric systems. This…

In recent years, large language models (LLMs) have demonstrated significant potential in complex reasoning tasks like mathematical problem-solving. However, existing research predominantly relies on reinforcement learning (RL) frameworks…

Modern circuit design process increasingly adopts high-level hardware construction languages and parameterized design methodologies to shorten development cycles and maintain high reusability, in contrast to traditional hardware description…

Adaptive Large Neighborhood Search (ALNS) is a prominent metaheuristic and a widely adopted approach for production and logistics optimization. However, it has long relied on hand-crafted components built on expert experience, which makes…

The combination of LLM agents with external tools enables models to solve complex tasks beyond their knowledge base. Human-designed tools are inflexible and restricted to solutions within the scope of pre-existing tools created by experts.…

Reasoning in language models is difficult to evaluate: natural-language traces are unverifiable, symbolic datasets are too small, and most benchmarks conflate heuristics with inference. We present FOL-Traces, the first large-scale dataset…

Post-training methods, especially Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), play an important role in improving large language models' (LLMs) complex reasoning abilities. However, the dominant two-stage pipeline (SFT…

This system description introduces an enhancement to the Yices2 SMT solver, enabling it to reason over non-linear polynomial systems over finite fields. Our reasoning approach fits into the model-constructing satisfiability (MCSat)…

The rapid development of Multimodal Large Language Models (MLLMs), such as GPT-4o, marks a significant step toward artificial general intelligence. Existing methods typically align vision encoders with LLMs via supervised fine-tuning (SFT),…

Multimodal embedding models aim to yield informative unified representations that empower diverse cross-modal tasks. Despite promising developments in the evolution from CLIP-based dual-tower architectures to large vision-language models,…

We address the problem of verifying safety properties of concurrent programs running over the Total Store Order (TSO) memory model. Known decision procedures for this model are based on complex encodings of store buffers as lossy channels.…

Federated fine-tuning (FFT) of large language models (LLMs) has recently emerged as a promising solution to enable domain-specific adaptation while preserving data privacy. Despite its benefits, FFT on resource-constrained clients relies on…

Used for centuries to enhance mechanical properties of materials, solid solution strengthening (SSS) is a classical metallurgical method in which small amounts of impurity elements are added to a base metal. Developed for dilute alloys,…

This research investigates the effectiveness of alignment techniques, Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and a combined SFT+DPO approach on improving the safety and helpfulness of the OPT-350M language…