Related papers: Building Code with Dynamic Staging
LLM-conditioned segmentation has recently advanced rapidly by coupling large language models with iterative mask generation frameworks. However, we identify a persistent failure mode in current propose-then-select pipelines. Although…
To represent anything from mathematical concepts to real-world objects, we have to resort to an encoding. Encodings, such as written language, usually assume a decoder that understands a rich shared code. A semantic embedding is a form of…
This paper proposes a way to improve the performance of existing algorithms for text classification in domains with strong language semantics. We propose a domain adaptation layer learns weights to combine a generic and a domain specific…
Generating high-quality 3D assets from textual descriptions remains a pivotal challenge in computer graphics and vision research. Due to the scarcity of 3D data, state-of-the-art approaches utilize pre-trained 2D diffusion priors, optimized…
Deploying Deep Learning (DL) on embedded end devices is a scorching trend in pervasive computing. Since most Microcontrollers on embedded devices have limited computing power, it is necessary to add a DL accelerator. Embedded Field…
The label-embedded dictionary learning (DL) algorithms generate influential dictionaries by introducing discriminative information. However, there exists a limitation: All the label-embedded DL methods rely on the labels due that this way…
Understanding spoken language is a highly complex problem, which can be decomposed into several simpler tasks. In this paper, we focus on Spoken Language Understanding (SLU), the module of spoken dialog systems responsible for extracting a…
Any file is fundamentally a binary data stream. A practical solution was achieved to interpret binary data stream. A new scripting language named Data Format Scripting Language (DFSL) was developed to describe the physical layout of the…
Static word embeddings that represent words by a single vector cannot capture the variability of word meaning in different linguistic and extralinguistic contexts. Building on prior work on contextualized and dynamic word embeddings, we…
This report investigates enhancing semantic caching effectiveness by employing specialized, fine-tuned embedding models. Semantic caching relies on embedding similarity rather than exact key matching, presenting unique challenges in…
The escalating data scale in High-Energy Physics (HEP) fuels a growing aspiration for higher analytical efficiency. While Large Language Models (LLMs) offer a path toward automation via agentic AI, they struggle with complex scientific…
The process of designing neural architectures requires expert knowledge and extensive trial and error. While automated architecture search may simplify these requirements, the recurrent neural network (RNN) architectures generated by…
In recent years, machine learning has been widely adopted to automate the audio mixing process. Automatic mixing systems have been applied to various audio effects such as gain-adjustment, equalization, and reverberation. These systems can…
While fully-supervised deep learning yields good models for urban scene semantic segmentation, these models struggle to generalize to new environments with different lighting or weather conditions for instance. In addition, producing the…
Many software analysis methods have come to rely on machine learning approaches. Code segmentation - the process of decomposing source code into meaningful blocks - can augment these methods by featurizing code, reducing noise, and limiting…
In this paper, we present how we created a Domain Specific Language (DSL) dedicated to IP Multimedia Subsystem (IMS) at Ericsson. First, we introduce IMS and how developers are burdened by its complexity when integrating it in their…
Structured embedding transformations offer a promising approach for enhancing the efficiency and coherence of language model inference. The introduction of Structural Embedding Projection (SEP) provides a mechanism for refining token…
The advent of large language models (LLMs) has paved the way for a new era of programming tools with both significant capabilities and risks, as the generated code lacks guarantees of correctness and reliability. Developers using LLMs…
Effective retrieval in complex domains requires bridging the gap between structured metadata and unstructured content. Existing systems typically isolate these capabilities, relying on either symbolic filtering or vector similarity, failing…
Building deployment-ready LLM agents requires complex orchestration of tools, data sources, and control flow logic, yet existing systems tightly couple agent logic to specific programming languages and deployment models. We present a…