Tootfinder

This https://arxiv.org/abs/2505.14759 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSE_…

LEANCODE: Understanding Models Better for Code Simplification of Pre-trained Large Language Models
Large Language Models for code often entail significant computational complexity, which grows significantly with the length of the input code sequence. We propose LeanCode for code simplification to reduce training and prediction time, leveraging code contexts in utilizing attention scores to represent the tokens' importance. We advocate for the selective removal of tokens based on the average context-aware attention scores rather than average scores across all inputs. LeanCode uses the attenti…

This https://arxiv.org/abs/2506.06266 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Cartridges: Lightweight and general-purpose long context representations via self-study
Large language models are often used to answer queries grounded in large text corpora (e.g. codebases, legal documents, or chat histories) by placing the entire corpus in the context window and leveraging in-context learning (ICL). Although current models support contexts of 100K-1M tokens, this setup is costly to serve because the memory consumption of the KV cache scales with input length. We explore an alternative: training a smaller KV cache offline on each corpus. At inference time, we loa…

Label-Context-Dependent Internal Language Model Estimation for CTC
Zijian Yang, Minh-Nghia Phan, Ralf Schl\"uter, Hermann Ney
https://arxiv.org/abs/2506.06096

Label-Context-Dependent Internal Language Model Estimation for CTC
Although connectionist temporal classification (CTC) has the label context independence assumption, it can still implicitly learn a context-dependent internal language model (ILM) due to modern powerful encoders. In this work, we investigate the implicit context dependency modeled in the ILM of CTC. To this end, we propose novel context-dependent ILM estimation methods for CTC based on knowledge distillation (KD) with theoretical justifications. Furthermore, we introduce two regularization meth…

Compression of executable QR codes or sQRy for Industry: an example for Wi-Fi access points
Stefano Scanzio, Gabriele Formis, Pietro Chiavassa, Lukasz Wisniewski, Gianluca Cena
https://arxiv.org/abs/2506.06100

Compression of executable QR codes or sQRy for Industry: an example for Wi-Fi access points
Executable QR codes, or sQRy, is a technology dated 2022 that permits to include a runnable program inside a QR code, enabling interaction with the user even in the absence of an Internet connection. sQRy are enablers for different practical applications, including network equipment configuration, diagnostics, and enhanced smart manuals in industrial contexts. Many other non-industry-related fields can also benefit from this technology. Regardless of where sQRy are used, text strings are among …

This https://arxiv.org/abs/2502.12096 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIT_…

Token Communications: A Unified Framework for Cross-modal Context-aware Semantic Communications
In this paper, we introduce token communications (TokCom), a large model-driven framework to leverage cross-modal context information in generative semantic communications (GenSC). TokCom is a new paradigm, motivated by the recent success of generative foundation models and multimodal large language models (GFM/MLLMs), where the communication units are tokens, enabling efficient transformer-based token processing at the transmitter and receiver. In this paper, we introduce the potential opportu…

Microgrids Coalitions for Energy Market Balancing
Viorica Chifu, Cristina Bianca Pop, Tudor Cioara, Ionut Anghel
https://arxiv.org/abs/2506.06058 https://

Microgrids Coalitions for Energy Market Balancing
With the integration of renewable sources in electricity distribution networks, the need to develop intelligent mechanisms for balancing the energy market has arisen. In the absence of such mechanisms, the energy market may face imbalances that can lead to power outages, financial losses or instability at the grid level. In this context, the grouping of microgrids into optimal coalitions that can absorb energy from the market during periods of surplus or supply energy to the market during perio…

This https://arxiv.org/abs/2411.02829 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csDC_…

CE-CoLLM: Efficient and Adaptive Large Language Models Through Cloud-Edge Collaboration
Large Language Models (LLMs) exhibit remarkable human-like predictive capabilities. However, it is challenging to deploy LLMs to provide efficient and adaptive inference services at the edge. This paper proposes a novel Cloud-Edge Collaboration framework for LLMs (CE-CoLLM) to tackle these challenges. First, we identify the transmission of LLM contextual data between the cloud and edge as a key performance bottleneck, which introduces substantial communication overhead that dominates overall in…

This https://arxiv.org/abs/2506.06091 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

MIRIAD: Augmenting LLMs with millions of medical query-response pairs
LLMs are bound to transform healthcare with advanced decision support and flexible chat assistants. However, LLMs are prone to generate inaccurate medical content. To ground LLMs in high-quality medical knowledge, LLMs have been equipped with external knowledge via RAG, where unstructured medical knowledge is split into small text chunks that can be selectively retrieved and integrated into the LLMs context. Yet, existing RAG pipelines rely on raw, unstructured medical text, which can be noisy,…

On the Fixed-Length-Burst Levenshtein Ball with Unit Radius
Yuanxiao Xi, Yubo Sun, Gennian Ge
https://arxiv.org/abs/2506.07817 https://

On the Fixed-Length-Burst Levenshtein Ball with Unit Radius
Consider a length-$n$ sequence $\bm{x}$ over a $q$-ary alphabet. The \emph{fixed-length Levenshtein ball} $\mathcal{L}_t(\bm{x})$ of radius $t$ encompasses all length-$n$ $q$-ary sequences that can be derived from $\bm{x}$ by performing $t$ deletions followed by $t$ insertions. Analyzing the size and structure of these balls presents significant challenges in combinatorial coding theory. Recent studies have successfully characterized fixed-length Levenshtein balls in the context of a single del…

Improving Neural Diarization through Speaker Attribute Attractors and Local Dependency Modeling
David Palzer, Matthew Maciejewski, Eric Fosler-Lussier
https://arxiv.org/abs/2506.05593

Improving Neural Diarization through Speaker Attribute Attractors and Local Dependency Modeling
In recent years, end-to-end approaches have made notable progress in addressing the challenge of speaker diarization, which involves segmenting and identifying speakers in multi-talker recordings. One such approach, Encoder-Decoder Attractors (EDA), has been proposed to handle variable speaker counts as well as better guide the network during training. In this study, we extend the attractor paradigm by moving beyond direct speaker modeling and instead focus on representing more detailed `speake…