相关论文: QiMeng-MuPa: Mutual-Supervised Learning for Sequen…

Transformers are the cornerstone of modern large language models, but their quadratic computational complexity limits efficiency in long-sequence processing. Recent advancements in Mamba, a state space model (SSM) with linear complexity,…

Multilingual large language models (LLMs) are great translators, but this is largely limited to high-resource languages. For many LLMs, translating in and out of low-resource languages remains a challenging task. To maximize data efficiency…

Nowadays, the paradigm of parallel computing is changing. CUDA is now a popular programming model for general purpose computations on GPUs and a great number of applications were ported to CUDA obtaining speedups of orders of magnitude…

Numba is a game-changing compiler for high-performance computing with Python. It produces machine code that runs outside of the single-threaded Python interpreter and that fully utilizes the resources of modern CPUs. This means support for…

Autoregressive decoding in large language models (LLMs) requires $\mathcal{O}(n)$ sequential steps for $n$ tokens, fundamentally limiting inference throughput. Recent diffusion-based LLMs (dLLMs) enable parallel token generation through…

An existing hybrid MPI-OpenMP scheme is augmented with a CUDA-based fine grain parallelization approach for multidimensional distributed Fourier transforms, in a well-characterized pseudospectral fluid turbulence code. Basics of the hybrid…

Speculative backpropagation has emerged as a promising technique to accelerate the training of neural networks by overlapping the forward and backward passes. Leveraging speculative weight updates when error gradients fall within a specific…

We present Sequential Policy Optimization for Simultaneous Machine Translation (SeqPO-SiMT), a new policy optimization framework that defines the simultaneous machine translation (SiMT) task as a sequential decision making problem,…

Recent advancements in Large Language Model (LLM)-based Natural Language Generation evaluation have largely focused on single-example prompting, resulting in significant token overhead and computational inefficiencies. In this work, we…

As quantum computing advances toward fault-tolerance through quantum error correction, modular chiplet architectures have emerged to provide the massive qubit counts required while overcoming fabrication limits of monolithic chips. However,…

Recent papers in neural machine translation have proposed the strict use of attention mechanisms over previous standards such as recurrent and convolutional neural networks (RNNs and CNNs). We propose that by running traditionally stacked…

Parallel programs in high performance computing (HPC) continue to grow in complexity and scale in the exascale era. The diversity in hardware and parallel programming models make developing, optimizing, and maintaining parallel software…

Practical guidance on training Large Language Models (LLMs) to leverage Code Interpreter across diverse tasks remains lacking. We present R1-Code-Interpreter, an extension of a text-only LLM trained via multi-turn supervised fine-tuning…

Scaling inference-time computation has enabled Large Language Models (LLMs) to achieve strong reasoning performance, but inherently sequential decoding leads to substantial latency, especially on complex tasks. Recent work on adaptive…

State Space Models (SSMs) with selective scan (Mamba) have been adapted into efficient vision models. Mamba, unlike Vision Transformers, achieves linear complexity for token interactions through a recurrent hidden state process. This…

Back-translation is an effective strategy to improve the performance of Neural Machine Translation~(NMT) by generating pseudo-parallel data. However, several recent works have found that better translation quality of the pseudo-parallel…

The aim of parallel computing is to increase an application performance by executing the application on multiple processors. OpenMP is an API that supports multi platform shared memory programming model and shared-memory programs are…

Manual parallelization of code remains a significant challenge due to the complexities of modern software systems and the widespread adoption of multi-core architectures. This paper introduces OMPar, an AI-driven tool designed to automate…

Universal Multimodal embedding models built on Multimodal Large Language Models (MLLMs) have traditionally employed contrastive learning, which aligns representations of query-target pairs across different modalities. Yet, despite its…

Model parallelism has become a necessity for training modern large-scale deep language models. In this work, we identify a new and orthogonal dimension from existing model parallel approaches: it is possible to perform pipeline parallelism…