English
Related papers

Related papers: RadixMLP -- Intra-batch Deduplication for Causal T…

200 papers

Diffusion large language models (dLLMs) have recently drawn considerable attention within the research community as a promising alternative to autoregressive generation, offering parallel token prediction and lower inference latency. Yet,…

Computation and Language · Computer Science 2025-10-01 Zigeng Chen , Gongfan Fang , Xinyin Ma , Ruonan Yu , Xinchao Wang

All simulation approaches eventually face limits in computational scalability when applied to large spatiotemporal domains. This challenge becomes especially apparent in molecular-level particle simulations, where high spatial and temporal…

Computational Physics · Physics 2025-10-23 Matthias Busch , Gregor Häfner , Jiayu Xie , Marius Tacke , Marcus Müller , Christian J. Cyron , Roland C. Aydin

LLM serving is increasingly dominated by decode attention, which is a memory-bound operation due to massive KV cache loading from global memory. Meanwhile, real-world workloads exhibit substantial, hierarchical shared prefixes across…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-03-17 Jinjun Yi , Zhixin Zhao , Yitao Hu , Ke Yan , Weiwei Sun , Hao Wang , Laiping Zhao , Yuhao Zhang , Wenxin Li , Keqiu Li

Recent advances with large language models (LLM) illustrate their diverse capabilities. We propose a novel algorithm, staged speculative decoding, to accelerate LLM inference in small-batch, on-device scenarios. We address the low…

Artificial Intelligence · Computer Science 2023-08-10 Benjamin Spector , Chris Re

Matrix multiplication performance has long been the major bottleneck to scaling deep learning workloads, which has stimulated the design of new accelerators that use increasingly low-precision number formats. However, improvements in matrix…

Machine Learning · Computer Science 2026-03-16 Callum McLean , Luke Y. Prince , Alexandre Payot , Paul Balança , Carlo Luschi

Fueled by advances in both robust optimization theory and reinforcement learning (RL), robust Markov Decision Processes (RMDPs) have garnered increasing attention due to their powerful capability for sequential decision-making under…

Optimization and Control · Mathematics 2025-07-08 Wenfan Ou , Sheng Bi

This work presents self-rewarding sequential Monte Carlo (SMC), an inference-time scaling algorithm enabling effective sampling of masked diffusion language models (MDLMs). Our algorithm stems from the observation that most existing MDLMs…

Machine Learning · Computer Science 2026-02-03 Ziwei Luo , Ziqi Jin , Lei Wang , Lidong Bing , Thomas B. Schön

The emergence of long-context large language models (LLMs) offers a promising alternative to traditional retrieval-augmented generation (RAG) for processing extensive documents. However, the computational overhead of long-context inference…

Computation and Language · Computer Science 2025-06-24 Guanzheng Chen , Qilong Feng , Jinjie Ni , Xin Li , Michael Qizhe Shieh

As large language models (LLMs) witness increasing deployment in complex, high-stakes decision-making scenarios, it becomes imperative to ground their reasoning in causality rather than spurious correlations. However, strong performance on…

Artificial Intelligence · Computer Science 2026-02-24 Yuzhe Wang , Yaochen Zhu , Jundong Li

Recent progress in aligning image and video generative models with Group Relative Policy Optimization (GRPO) has improved human preference alignment, but existing variants remain inefficient due to sequential rollouts and large numbers of…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Yuming Li , Yikai Wang , Yuying Zhu , Zhongyu Zhao , Ming Lu , Qi She , Shanghang Zhang

Since local LLM inference on resource-constrained edge devices imposes a severe performance bottleneck, this paper proposes distributed prompt caching to enhance inference performance by cooperatively sharing intermediate processing states…

Machine Learning · Computer Science 2026-04-13 Hiroki Matsutani , Naoki Matsuda , Naoto Sugiura

In this paper, we introduce data multiplexing (DataMUX), a technique that enables deep neural networks to process multiple inputs simultaneously using a single compact representation. DataMUX demonstrates that neural networks are capable of…

Machine Learning · Computer Science 2022-11-15 Vishvak Murahari , Carlos E. Jimenez , Runzhe Yang , Karthik Narasimhan

We study allowing large language models (LLMs) to process arbitrarily long prompts through the lens of inference-time scaling. We propose Recursive Language Models (RLMs), a general inference paradigm that treats long prompts as part of an…

Artificial Intelligence · Computer Science 2026-05-12 Alex L. Zhang , Tim Kraska , Omar Khattab

Large language models have been widely adopted but require significant GPU memory for inference. We develop a procedure for Int8 matrix multiplication for feed-forward and attention projection layers in transformers, which cut the memory…

Machine Learning · Computer Science 2022-11-11 Tim Dettmers , Mike Lewis , Younes Belkada , Luke Zettlemoyer

Distributed computing frameworks such as MapReduce are often used to process large computational jobs. They operate by partitioning each job into smaller tasks executed on different servers. The servers also need to exchange intermediate…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-04-20 Konstantinos Konstantinidis , Aditya Ramamoorthy

We present Diffusion Model Patching (DMP), a simple method to boost the performance of pre-trained diffusion models that have already reached convergence, with a negligible increase in parameters. DMP inserts a small, learnable set of…

Computer Vision and Pattern Recognition · Computer Science 2024-12-12 Seokil Ham , Sangmin Woo , Jin-Young Kim , Hyojun Go , Byeongjun Park , Changick Kim

Inference scaling methods for LLMs often rely on decomposing problems into steps (or groups of tokens), followed by sampling and selecting the best next steps. However, these steps and their sizes are often predetermined or manually…

We present DMax, a new paradigm for efficient diffusion language models (dLLMs). It mitigates error accumulation in parallel decoding, enabling aggressive decoding parallelism while preserving generation quality. Unlike conventional masked…

Machine Learning · Computer Science 2026-05-18 Zigeng Chen , Gongfan Fang , Xinyin Ma , Ruonan Yu , Xinchao Wang

Large-scale atomistic simulations are essential to bridge computational materials and chemistry to realistic materials and drug discovery applications. In the past few years, rapid developments of machine learning interatomic potentials…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-02-03 Kevin Han , Bowen Deng , Amir Barati Farimani , Gerbrand Ceder

Large multimodal models (LMMs) typically employ an encoding module to transform multimodal data inputs into embeddings, which are then fed to language models for further processing. However, efficiently serving LMMs remains highly…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-30 Tianyu Guo , Tianming Xu , Xianjie Chen , Junru Chen , Nong Xiao , Xianwei Zhang