Big Data and Digital Economy

Últimos artículos

• Kalypso: Relational LLM Serving

  Hojae Son, Md Ashraful Islam, Huy Gia Cao, Hui Guan, Marco Serafini · 17 de agosto de 2026

  Large language models are increasingly used as semantic operators for filtering, extracting, ranking, joining, and transforming unstructured data. Existing semantic query processing systems invoke request-centric LLM serving systems that are unaware of the query plan, leaving substantial performance…

• Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization

  Muhammad Junaid Ali, Smail Niar, El-Ghazali Talbi · 4 de agosto de 2026

  Large Language Models (LLMs) have achieved widespread adoption because of their strong reasoning and query-response capabilities. However, deploying them in embedded and edge computing environments remains challenging because of strict latency, memory, and energy constraints. Their large parameter c…

• How Many Bits Can an Adapter Write? Measuring the Capacity and Memorization of Parameter-Efficient Fine-Tuning

  Kaizhen Tan, Heqing Du, Yang Feng · 24 de julio de 2026

  A LoRA adapter is a few megabytes that almost everyone treats as a skill rather than a record of the data behind it. We put that assumption on a scale. Extending compression-based memorization analysis to the frozen-base setting, we measure directly, in bits, how much a low-rank adapter writes into …

• Agora: Collective and Permissionless Internet-Scale Pretraining of Large Language Models

  Gil Avraham, Violetta Shevchenko, Hadi Mohaghegh Dolatabadi, Karol Pajak, James Snewin, Harry Xi, Rodney O'Donnell, Thalaiyasingam Ajanthan, Sameera Ramasinghe, Chamin Hewa Koneputugodage, Shamane Siriwardhana, Alexander Long · 16 de julio de 2026

  Training large language models at the multi-billion to trillion parameter scale is confined to datacenters, where data-parallel (DP) and model-parallel (MP) techniques presume homogeneous accelerators, high-speed interconnects, and a single orchestrating entity. Frontier model development is thereby…

• Efficient and Privacy Aware Edge Cloud Collaborative Inference for Large Language Models

  Yi Li, Chen Li, Jiexiong Liu · 16 de julio de 2026

  On-device LLM inference faces a trilemma of response latency, limited hardware resources and user privacy. Full cloud inference delivers strong computing power but exposes user prompts and dialogue data, while standalone on-device inference is unfeasible for most consumer and embedded edge devices. …

• MemDecay: Region-Aware KV Cache Eviction for Efficient LLM Agent Inference

  Venkatesha Matam, Keon Kim · 14 de julio de 2026

  Large language model (LLM) agents accumulate heterogeneous context, including system instructions, plans, user turns, retrieved documents, tool outputs, and intermediate reasoning, whose key-value (KV) cache can become a major memory bottleneck. Existing eviction policies generally apply the same at…

• Boltzmann MapReduce: A Partition-Function Reduce for Forkable Sandboxes

  Yossi Eliaz · 14 de julio de 2026

  To leading order under local asymptotic normality (LAN), the confidence density a worker emits over a chunk of size $n$ is a Gibbs--Boltzmann measure $\exp\{-\beta E(\theta)\}$ whose inverse temperature is the sample size, $\beta=n$. Three consequences are exact in the Gaussian/linear case and first…

• What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents

  Ashwin Gerard Colaco, Nada Lahjouji · 10 de julio de 2026

  Large language models, and the agents built on them, spend an ever-growing share of their compute and memory on remembering: caching attention keys and values, carrying long prompts, maintaining recurrent state, and storing what happened in previous turns and sessions. Because none of this memory is…

• Memory Scarcity, Open Models, and the Restructuring of the AI Industry, 2026-2030 -- A quantitative scenario analysis of inference economics, training-cost divergence, and infrastructure solvency

  Satoshi Matsuoka · 9 de julio de 2026

  We analyze how four forces restructure the AI industry over 2026-2030: the DRAM/HBM price surge, frontier-capable open-weight models (GLM-5.2), rapid inference-efficiency gains (near-Shannon-limit KV-cache compression, lightweight local runtimes), and the entry of Meta and xAI into compute resale on…

• Is Your NPU Ready for LLMs? Dissecting the Hidden Efficiency Bottlenecks in Mobile LLM Inference

  Guanyu Cai, Ruiming Tian, Lang Yang, Zhouhong Ren, Jinliang Yuan, Lingkun Li, Jiliang Wang · 8 de julio de 2026

  Deploying Large Language Models (LLMs) on mobile devices enhances privacy and reduces latency, but is severely bottlenecked by hardware inefficiency. We present the first comprehensive, cross-layer measurement study of mobile LLM inference, uniquely spanning five mainstream frameworks (e.g., llama.c…

• Towards Mitigation of Hallucination for LLM-empowered Agents: Progressive Generalization Bound Exploration and Watchdog Monitor

  Siyuan Liu, Wenjing Liu, Zhiwei Xu, Xin Wang, Bo Chen, Tao Li · 7 de julio de 2026

  Empowered by large language models (LLMs), intelligent agents have become a popular paradigm for interacting with open environments to facilitate AI deployment. However, hallucinations generated by LLMs-where outputs are inconsistent with facts-pose a significant challenge, undermining the credibili…

• From Tokens to States: LLMs as a Special Case of World Models and the Continuous Path Beyond

  Paul Dubois · 29 de junio de 2026

  The AI community has framed the relationship between large language models (LLMs) and world models as a dichotomy: LLMs predict tokens; world models simulate reality. Yann LeCun argues in 2022 that reaching general intelligence requires abandoning autoregressive token prediction in favour of latent-…

• End-to-End Dynamic Sparsity for Resource-Adaptive LLM Inference

  Yuhang Chen, Jinhao Duan, Ruichen Zhang, Mingfu Liang, Xiaohan Wei, Yunchen Pu, Fei Tian, Chonglin Sun, Parish Aggarwal, Frank Shyu, Luke Simon, Sandeep Pandey, Tianlong Chen, Xi Liu · 29 de junio de 2026

  Large Language Models (LLMs) inference is typically deployed under a static resource assumption, where models execute a fixed computational graph regardless of the runtime environment. However, real-world cloud infrastructure is inherently dynamic, characterized by fluctuating availability (e.g., sp…

• Stabilizing black-box algorithms through task-oriented randomization

  Yali Wang, Zhaojun Wang · 25 de junio de 2026

  As black-box models become foundational to modern research, ensuring their stability is paramount for the realization of trustworthy artificial intelligence. The inherent diversity of inputs - ranging from structured Gaussian distributions to complex data with unknown structures - poses a significan…

• TRUSTMEM: Learning Trustworthy Memory Consolidation for LLM Agents with Long-Term Memory

  Tianyu Yang, Sudipta Paul, Vijay Srinivasan, Vivek Kulkarni, Srinivas Chappidi · 25 de junio de 2026

  Large language model (LLM) agents rely on long-term memory to support extended interactions and personalized assistance beyond finite context windows. Existing memory agents actively update external memory through generated write, revise, and delete operations, but these updates may omit important i…

• Agent Skill Framework: Perspectives on the Potential of Small to Medium Language Models in Industrial Environments

  Yangjie Xu, Lujun Li, Lama Sleem, Niccolo Gentile, Yewei Song, Yiqun Wang, Siming Ji, Wenbo Wu, Radu State · 23 de junio de 2026

  Agent skills are widely supported by major agentic frameworks and perform well with proprietary models, yet their effectiveness for small and medium-sized open source language models (270 M-80B) remains underexplored. We systematically study the Skill paradigm in resource-constrained industrial sett…

• A Verifiable Search Is Not a Learnable Chain-of-Thought

  Harsh Patel · 23 de junio de 2026

  It is tempting to assume any task solvable by a short program can be taught to a model as its chain-of-thought: write the steps out, fine-tune, and the model follows. This paper shows the assumption fails for an identifiable class of procedures. The testbed is nine reasoning tasks, each from a deter…

• Agent-as-a-Router: Agentic Model Routing for Coding Tasks

  Pengfei Zhou, Zhiwei Tang, Yixing Ma, Jiasheng Tang, Yizeng Han, Zhenglin Wan, Fanqing Meng, Wei Wang, Bohan Zhuang, Wangbo Zhao, Yang You · 23 de junio de 2026

  Real-world users typically have access to multiple Large Language Models (LLMs) from different providers, and these LLMs often excel at distinct domains, yet none dominate all. Consequently, routing each task to the most suitable model becomes critical for both performance and cost. Existing routers…

• Token-Operations-Oriented Inference Optimization Techniques for Large Models

  Shiguo Lian, Kai Wang, Zhaoxiang Liu, Wen Liu, Minjie Hua, Yutong Liu, Jiangze Yan, Xin Wang, Cong Wang, Yilin Zhang, Yi Shen, Jieyun Huang, Fang Zhao, Huanlin Gao, Ping Chen, Xinyu Yang, Kaikai Zhao, Yantao Li, Yao Zhao, Xinggang Wang, Huishuai Zhang, Dongyan Zhao, Junping Du, Tao Chen, Xiang Gao, Qinghuai Ma · 19 de junio de 2026

  Large model inference optimization serves as a key foundation for supporting the scalable, low-cost, and highly stable operation of large model services. Centered on token-oriented inference optimization technology, this paper proposes for the first time a four-layer technical architecture consistin…

• Closing the Social-Semantic Gap: SPSD for Edge-Based Prompt Compression in Cloud LLM Inference

  Abhinit Sen, Ajeet Kumar, Manaranjan Pradhan · 19 de junio de 2026

  The prefill stage of Large Language Model (LLM) inference is a growing contributor to cloud-scale energy cost. Many consumer-support and conversational prompts contain social scaffolding: politeness markers, apologetic preamble, repetition, and rapport-building language that is important for human c…

• Techniques for Peak Memory Reduction for LoRA Fine-tuning of LLMs on Edge Devices

  Hassan Dbouk, Matthias Reisser, Prathamesh Mandke, Likhita Arun Navali, Christos Louizos · 19 de junio de 2026

  Fine-tuning of Large Language Models (LLMs) using Low-Rank Adaptation (LoRA) on an end-user's data offers personalized experiences while keeping data private, but faces severe memory constraints on consumer hardware. Peak memory during fine-tuning often exceeds device limits, especially for models w…

• A Spatio-Temporal Expert Prefetching Framework for Efficient MoE-based LLM Inference

  Yingnan Zhao, Razvan Bunescu, Ahmed Louri, Avinash Karanth, Ke Wang · 16 de junio de 2026

  Mixture-of-Experts (MoE) based large language models (LLMs), such as Qwen and DeepSeek, have recently emerged as an effective approach to improving model capacity without proportionally increasing computational cost. By replacing the conventional feed-forward network in dense LLMs with a set of expe…

• Mixtures of Subspaces for Bandwidth Efficient Context Parallel Training

  Sameera Ramasinghe, Ajanthan Thalaiyasingam, Hadi Mohaghegh Dolatabadi, Gil Avraham, Violetta Shevchenko, Yan Zuo, Chamin Hewa Koneputugodage, Alexander Long · 16 de junio de 2026

  Pretraining language models with extended context windows enhances their ability to leverage rich information during generation. Existing methods split input sequences into chunks, broadcast them across multiple devices, and compute attention block by block which incurs significant communication ove…

• LLMs Contain Multitudes: How Deployment Context Reshapes Model-Level Preferences and Values

  Filip Trhlik, Aoife O'Flynn, Angela Yu, Arduin Findeis, Paula Buttery · 15 de junio de 2026

  Large language models (LLMs) are increasingly characterised in recent evaluation work as having stable, model-level preference and value systems. However, accompanying robustness checks are limited to incidental prompt perturbations such as syntax variation and option reordering. This leaves open wh…

• STREAM: Multi-Tier LLM Inference Middleware with Dual-Channel HPC Token Streaming

  Anas Nassar, Steve Mohr, Leonard Apanasevich, Himanshu Sharma · 15 de junio de 2026

  Researchers and practitioners working with large language models face a fragmented landscape: local models are free and private but hardware limits the model size and context windows a researcher can use; institutional HPC centers offer powerful GPU resources at no marginal cost and keep data within…