Related papers: Pre$^3$: Enabling Deterministic Pushdown Automata …

We present LTM3D, a Latent Token space Modeling framework for conditional 3D shape generation that integrates the strengths of diffusion and auto-regressive (AR) models. While diffusion-based methods effectively model continuous latent…

We apply topological data analysis (TDA) to speech classification problems and to the introspection of a pretrained speech model, HuBERT. To this end, we introduce a number of topological and algebraic features derived from Transformer…

Advanced reasoning typically requires Chain-of-Thought prompting, which is accurate but incurs prohibitive latency and substantial test-time inference costs. The standard alternative, fine-tuning smaller models, often sacrifices…

Speculative decoding accelerates Large Language Models (LLMs) inference by using a lightweight draft model to propose candidate tokens that are verified in parallel by the target model. However, existing draft model training objectives are…

Drug-target interaction (DTI) prediction is of great significance for drug discovery and drug repurposing. With the accumulation of a large volume of valuable data, data-driven methods have been increasingly harnessed to predict DTIs,…

Recently, prompt tuning \cite{lester2021power} has gradually become a new paradigm for NLP, which only depends on the representation of the words by freezing the parameters of pre-trained language models (PLMs) to obtain remarkable…

LLM-based data generation for real-world tabular data can be challenged by the lack of sufficient semantic context in feature names used to describe columns. We hypothesize that enriching prompts with domain-specific insights can improve…

To ensure that text generated by large language models (LLMs) is in an expected format, constrained decoding proposes to enforce strict formal language constraints during generation. However, as we show in this work, not only do such…

Current large language model (LLM) applications often employ multi-component prompts, comprising both system and user prompts, to guide model behaviors. While recent advancements have demonstrated the efficacy of automatically optimizing…

In recent years, Large Language Models (LLMs) have emerged as a prominent area of interest across various research domains, including Process Mining (PM). Current applications in PM have predominantly centered on prompt engineering…

Row-level lineage explains what input rows produce an output row through a data processing pipeline, having many applications like data debugging, auditing, data integration, etc. Prior work on lineage falls in two lines: eager lineage…

Language Reasoning Models (LRMs) achieve strong performance by scaling test-time computation but often suffer from ``overthinking'', producing excessively long reasoning traces that increase latency and memory usage. Existing LRMs typically…

Large Language Models (LLMs) have been widely adopted in commercial code completion engines, significantly enhancing coding efficiency and productivity. However, LLMs may generate code with quality issues that violate coding standards and…

We propose Prefix-Adaptive Decoding (PREADD), a flexible method for controlled text generation. Unlike existing methods that use auxiliary expert models to control for attributes, PREADD does not require an external model, instead relying…

Large Language Models (LLMs) have become more prevalent in long-context applications such as interactive chatbots, document analysis, and agent workflows, but it is challenging to serve long-context requests with low latency and high…

Autoformalization, the process of transforming informal mathematical language into formal specifications and proofs remains a difficult task for state-of-the-art (large) language models. Existing works point to competing explanations for…

Speculative Decoding (SD) is a widely used approach to accelerate the inference of large language models (LLMs) without reducing generation quality. It operates by first using a compact model to draft multiple tokens efficiently, followed…

Large Language Model (LLM)-based generative recommendation has achieved notable success, yet its practical deployment is costly particularly due to excessive inference latency caused by autoregressive decoding. For lossless LLM decoding…

Fine-tuning Large Language Models (LLMs) is now a common approach for text classification in a wide range of applications. When labeled documents are scarce, active learning helps save annotation efforts but requires retraining of massive…

Matrix-level low-rank compression is a promising way to reduce the cost of large language models, but running compression and evaluating the resulting models on language tasks can be prohibitively expensive. Can compression-induced…