Related papers: Liquidsoap: a High-Level Programming Language for …
Procedural content generation uses algorithmic techniques to create large amounts of new content for games at much lower production costs. In newer approaches, procedural content generation utilizes machine learning. However, these methods…
Video continues to dominate network traffic, yet operators today have poor visibility into the number, duration, and resolutions of the video streams traversing their domain. Current approaches are inaccurate, expensive, or unscalable, as…
Existing digital manufacturing methods can be broadly divided into subtractive approaches, where material is removed from a bulk to reveal the desired form, and additive methods, in which material is introduced voxel-by-voxel to create an…
Event processing will play an increasingly important role in constructing enterprise applications that can immediately react to business critical events. Various technologies have been proposed in recent years, such as event processing,…
Compiling high-level programs to target high-speed packet-processing pipelines is a challenging combinatorial optimization problem. The compiler must configure the pipeline's resources to match the high-level semantics of the program, while…
We describe a system for large-scale audiovisual translation and dubbing, which translates videos from one language to another. The source language's speech content is transcribed to text, translated, and automatically synthesized into…
The dominant programming languages support only linear text to express ideas. Visual languages offer graphical representations for entire programs, when viewed with special tools. Hybrid languages, with support from existing tools, allow…
The goal of this work is to reconstruct high quality speech from lip motions alone, a task also known as lip-to-speech. A key challenge of lip-to-speech systems is the one-to-many mapping caused by (1) the existence of homophenes and (2)…
Extracting real-time insights from multi-modal data streams from various domains such as healthcare, intelligent transportation, and satellite remote sensing remains a challenge. High computational demands and limited knowledge scope…
We define a broad class of deterministic stream functions and show they can be implemented as homomorphisms into a "state" monoid. The homomorphism laws are simpler than the conditions of previous semantic frameworks for stream program…
A Flow is a collection of component models ("Agents") which constructs the solution to a complex problem via iterative communication. Flows have emerged as state of the art architectures for code generation, and are the raison d'etre for…
Floodsub is a simple, robust and popular peer-to-peer publish/subscribe (pubsub) protocol, where nodes can arbitrarily leave or join the network, subscribe to or unsubscribe from topics and forward newly received messages to all of their…
Current software development is often quite code-centric and aimed at short-term deliverables, due to various contextual forces (such as the need for new revenue streams from many individual buyers). We're interested in software where…
The proliferation of deep learning in natural language processing (NLP) has led to the development and release of innovative technologies capable of understanding and generating human language with remarkable proficiency. Atinuke, a…
Advances in multi-modal generative models are enabling new applications, from storytelling to automated media synthesis. Most current workloads generate simple outputs (e.g., image generation from a prompt) in batch mode, often requiring…
Controllable speech generation methods typically rely on single or fixed prompts, hindering creativity and flexibility. These limitations make it difficult to meet specific user needs in certain scenarios, such as adjusting the style while…
Recent Large Language Models have been enhanced with vision capabilities, enabling them to comprehend images, videos, and interleaved vision-language content. However, the learning methods of these large multimodal models typically treat…
Recent advancements in discrete token-based speech generation have highlighted the importance of token-to-waveform generation for audio quality, particularly in real-time interactions. Traditional frameworks integrating semantic tokens with…
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…
Simulation is an invaluable tool for developing and evaluating controllers for self-driving cars. Current simulation frameworks are driven by highly-specialist domain specific languages, and so a natural language interface would greatly…