Related papers: Improvements to ltlsynt
Fine-tuning large language models (LLMs) has become essential for adapting pretrained models to specific downstream tasks. In this paper, we propose Linear Chain Transformation (LinChain), a novel approach that introduces a sequence of…
Large language models (LLMs) have shown impressive performance on general-purpose tasks, yet adapting them to specific domains remains challenging due to the scarcity of high-quality domain data. Existing data synthesis tools often struggle…
In recent years, diffusion models have emerged as the most powerful approach in image synthesis. However, applying these models directly to video synthesis presents challenges, as it often leads to noticeable flickering contents. Although…
We study Latent Recurrent Transformer (LRT), a lightweight augmentation of autoregressive transformers that reuses a high-level source-layer hidden state from the previous token as recurrent memory for the next token. Because this source…
LLM Ensemble -- which involves the comprehensive use of multiple large language models (LLMs), each aimed at handling user queries during downstream inference, to benefit from their individual strengths -- has gained substantial attention…
Reactivity is central to Angular applications, yet subtle misuse of Observables, Signals, and change-detection often leads to performance regressions that are difficult to diagnose. Although Angular 17 introduced a unified, signal-first…
Conducting literature reviews for scientific papers is essential for understanding research, its limitations, and building on existing work. It is a tedious task which makes an automatic literature review generator appealing. Unfortunately,…
We present Natural Language Tools (NLT), a framework that replaces programmatic JSON tool calling in large language models (LLMs) with natural language outputs. By decoupling tool selection from response generation, NLT eliminates task…
This paper introduces an extended version of the Linear Temporal Logic (LTL) graphical interface. It is a sketch based interface built on the Android platform which makes the LTL control interface more straightforward and friendly to…
We present RTAMT, an online monitoring library for Signal Temporal Logic (STL) and its interface-aware variant (IA-STL), providing both discrete- and dense-time interpretation of the logic. We also introduce RTAMT4ROS, a tool that…
NLTK, the Natural Language Toolkit, is a suite of open source program modules, tutorials and problem sets, providing ready-to-use computational linguistics courseware. NLTK covers symbolic and statistical natural language processing, and is…
Large language models (LLMs) have shown promise in generating RTL code from natural-language descriptions, but existing methods remain static and struggle to adapt to evolving design requirements, potentially causing structural drift and…
Reactive synthesis is an automatic way to translate a human intention expressed in some logic into a system of some kind. This thesis has two parts, devoted to logic and to systems. In Part I, we develop two new approaches to CTL*…
Neural speech synthesis models have recently demonstrated the ability to synthesize high quality speech for text-to-speech and compression applications. These new models often require powerful GPUs to achieve real-time operation, so being…
Recent advancements in differentiable rendering and 3D reasoning have driven exciting results in novel view synthesis from a single image. Despite realistic results, methods are limited to relatively small view change. In order to…
Auto-regressive speech-text models pre-trained on interleaved text tokens and discretized speech tokens demonstrate strong speech understanding and generation, yet remain substantially less compute-efficient than text LLMs, partly due to…
Digital mobile systems must function with low power, small size and weight, and low cost. High-performance desktop microprocessors, with built-in floating point hardware, are not suitable in these cases. For embedded systems, it can be…
Recently, flow matching based speech synthesis has significantly enhanced the quality of synthesized speech while reducing the number of inference steps. In this paper, we introduce SlimSpeech, a lightweight and efficient speech synthesis…
Incremental processing allows interactive systems to respond based on partial inputs, which is a desirable property e.g. in dialogue agents. The currently popular Transformer architecture inherently processes sequences as a whole,…
Recent advancements in Natural Language Processing (NLP) have seen Large-scale Language Models (LLMs) excel at producing high-quality text for various purposes. Notably, in Text-To-Speech (TTS) systems, the integration of BERT for semantic…