Related papers: Deciding Boolean Separation Logic via Small Models…

We propose a novel approach to conformal prediction for generative language models (LMs). Standard conformal prediction produces prediction sets -- in place of single predictions -- that have rigorous, statistical performance guarantees. LM…

Spatial reasoning over text is challenging as the models not only need to extract the direct spatial information from the text but also reason over those and infer implicit spatial relations. Recent studies highlight the struggles even…

We investigate the relationship between two independently developed termination techniques. On the one hand, sized-types based termination (SBT) uses types annotated with size expressions and Girard's reducibility candidates, and applies on…

Separation logic is often praised for its ability to closely mimic the locality of state updates when reasoning about them at the level of assertions. The prover only needs to concern themselves with the footprint of the computation at…

Tokenizing raw texts into word units is an essential pre-processing step for critical tasks in the NLP pipeline such as tagging, parsing, named entity recognition, and more. For most languages, this tokenization step straightforward.…

Speculative decoding, which combines a draft model with a target model, has emerged as an effective approach to accelerate large language model (LLM) inference. However, existing methods often face a trade-off between the acceptance rate…

Symbolic execution is a well established method for test input generation. Despite of having achieved tremendous success over numerical domains, existing symbolic execution techniques for heap-based programs are limited due to the lack of a…

Recently, significant progress has been made on semantic segmentation. However, the success of supervised semantic segmentation typically relies on a large amount of labelled data, which is time-consuming and costly to obtain. Inspired by…

Semantic segmentation plays a crucial role in enabling machines to understand and interpret visual scenes at a pixel level. While traditional segmentation methods have achieved remarkable success, their generalization to diverse scenes and…

Separation logics are a family of extensions of Hoare logic for reasoning about programs that mutate memory. These logics are "abstract" because they are independent of any particular concrete memory model. Their assertion languages, called…

Explicit Chain-of-Thought improves the reasoning performance of large language models but often incurs high inference cost due to verbose token-level traces. While recent approaches reduce this overhead via concise prompting or step…

Prior methods to text segmentation are mostly at token level. Despite the adequacy, this nature limits their full potential to capture the long-term dependencies among segments. In this work, we propose a novel framework that incrementally…

The Split and Rephrase (SPRP) task, which consists in splitting complex sentences into a sequence of shorter grammatical sentences, while preserving the original meaning, can facilitate the processing of complex texts for humans and…

We present quantitative separation logic ($\mathsf{QSL}$). In contrast to classical separation logic, $\mathsf{QSL}$ employs quantities which evaluate to real numbers instead of predicates which evaluate to Boolean values. The connectives…

Despite recent advancements in domain adaptation techniques for large language models, these methods remain computationally intensive, and the resulting models can still exhibit hallucination issues. Most existing adaptation methods do not…

Semantic segmentation is a fundamental task in medical image analysis, aiding medical decision-making by helping radiologists distinguish objects in an image. Research in this field has been driven by deep learning applications, which have…

Accurate semantic segmentation models typically require significant computational resources, inhibiting their use in practical applications. Recent works rely on well-crafted lightweight models to achieve fast inference. However, these…

Despite their strong performance on reasoning tasks, large reasoning models (LRMs) often suffer from overthinking, producing unnecessarily long outputs and incurring high end-to-end latency, a significant limitation to their real-world…

Split learning (SL) has been recently proposed as a way to enable resource-constrained devices to train multi-parameter neural networks (NNs) and participate in federated learning (FL). In a nutshell, SL splits the NN model into parts, and…

The ability of generative large language models (LLMs) to perform in-context learning has given rise to a large body of research into how best to prompt models for various natural language processing tasks. Machine Translation (MT) has been…