Related papers: Jasmine: A Simple, Performant and Scalable JAX-bas…
We present RoboManipBaselines, an open-source software framework for imitation learning research in robotic manipulation. The framework supports the entire imitation learning pipeline, including data collection, policy training, and…
The scope of neural code intelligence is rapidly expanding beyond text-based source code to encompass the rich visual outputs that programs generate. This visual dimension is critical for advanced applications like flexible content…
Automated Driving Systems (ADS) have rapidly evolved in recent years and their architecture becomes sophisticated. Ensuring robustness, reliability and safety of performance is particularly important. The main challenge in building an ADS…
Modern systems evolve in unpredictable environments and have to continuously adapt their behavior to changing conditions. The "DReAM" (Dynamic Reconfigurable Architecture Modeling) framework, has been designed for modeling reconfigurable…
We present SAINE, an Scientific Annotation and Inference ENgine based on a set of standard open-source software, such as Label Studio and MLflow. We show that our annotation engine can benefit the further development of a more accurate…
With the rapid advances of powerful multimodal models such as GPT-4o, Nano Banana, and Seedream 4.0 in Image Editing, the performance gap between closed-source and open-source models is widening, primarily due to the scarcity of…
Many graphics rendering algorithms used in both real-time games and virtual reality applications can get performance boosts by temporally reusing previous computations. However, algorithms based on temporal reuse are typically measured…
Restricted three-body codes have a proven ability to recreate much of the disturbed morphology of actual interacting galaxies. As more sophisticated n-body models were developed and computer speed increased, restricted three-body codes fell…
Low-precision formats such as float8 have been introduced in machine learning accelerated hardware to improve computational efficiency for large language models training and inference. Nevertheless, adoption by the ML community has been…
JavaScript Object Notation or JSON is a ubiquitous data exchange format on the Web. Ingesting JSON documents can become a performance bottleneck due to the sheer volume of data. We are thus motivated to make JSON parsing as fast as…
The code of nature, embedded in DNA and RNA genomes since the origin of life, holds immense potential to impact both humans and ecosystems through genome modeling. Genomic Foundation Models (GFMs) have emerged as a transformative approach…
Task-based execution frameworks, such as parallel programming libraries, computational workflow systems, and function-as-a-service platforms, enable the composition of distinct tasks into a single, unified application designed to achieve a…
Traditional approaches to training agents have generally involved a single, deterministic environment of minimal complexity to solve various tasks such as robot locomotion or computer vision. However, agents trained in static environments…
We design a family of program analyses for JavaScript that make no approximation in matching calls with returns, exceptions with handlers, and breaks with labels. We do so by starting from an established reduction semantics for JavaScript…
Applications with irregular data structures, data-dependent control flows and fine-grained data transfers (e.g., real-world graph computations) perform poorly on cache-based systems. We propose the UpDown accelerator that supports…
Mainstream Transformer-based large language models face major efficiency bottlenecks: training computation scales quadratically with sequence length, and inference memory grows linearly, limiting long-context processing. Building large…
In the evolving landscape of large language models (LLMs) tailored for software engineering, the need for benchmarks that accurately reflect real-world development scenarios is paramount. Current benchmarks are either too simplistic or fail…
World models provide a powerful framework for simulating environment dynamics conditioned on actions or instructions, enabling downstream tasks such as action planning or policy learning. Recent approaches leverage world models as learned…
The rapid development of quantum computing (QC) in the NISQ era urgently demands a low-level benchmark suite and insightful evaluation metrics for characterizing the properties of prototype NISQ devices, the efficiency of QC programming…
Understanding and reasoning about code semantics is essential for enhancing code LLMs' abilities to solve real-world software engineering (SE) tasks. Although several code reasoning benchmarks exist, most rely on synthetic datasets or…