Tootfinder

Apple says the iPhone 17 lineup and iPhone Air come with Memory Integrity Enforcement, which provides "industry-first, always-on memory safety protection" (Richard Lawler/The Verge)
https://www.theverge.com/news/775234/iphone-17-air-…

Apple says the iPhone 17 comes with a massive security upgrade
Apple explains iPhone 17 Memory Integrity Enforcement and Enhanced Memory Tagging Extension security updates.

🌟 Astrocytes are superstars in the game of long-term memory
#memory

Astrocytes are superstars in the game of long-term memory
Why are we able to recall only some of our past experiences? A new study led by Jun Nagai at the RIKEN Center for Brain Science in Japan has an answer. Surprisingly, it turns out that the brain cells responsible for stabilizing memories aren't neurons. Rather, they are astrocytes, a type of glial cell that is usually thought of as a role player in the game of learning and memory.

A post from the archive 📫:
Invalid Access to memory location in KUDU App Services
https://www.poppastring.com/blog/invalid-access-to-memory-location-in-kudu-app-services

Dream to Recall: Imagination-Guided Experience Retrieval for Memory-Persistent Vision-and-Language Navigation
Yunzhe Xu, Yiyuan Pan, Zhe Liu
https://arxiv.org/abs/2510.08553 htt…

Dream to Recall: Imagination-Guided Experience Retrieval for Memory-Persistent Vision-and-Language Navigation
Vision-and-Language Navigation (VLN) requires agents to follow natural language instructions through environments, with memory-persistent variants demanding progressive improvement through accumulated experience. Existing approaches for memory-persistent VLN face critical limitations: they lack effective memory access mechanisms, instead relying on entire memory incorporation or fixed-horizon lookup, and predominantly store only environmental observations while neglecting navigation behavioral …

‘Destroying our memory’ — YouTube wipes Ukrainian memorial channel, erasing stories of the fallen: https://benborges.xyz/2025/11/10/destroying-our-memory-youtube-wipes.html

Memory Retrieval and Consolidation in Large Language Models through Function Tokens
Shaohua Zhang, Yuan Lin, Hang Li
https://arxiv.org/abs/2510.08203 https://

Memory Retrieval and Consolidation in Large Language Models through Function Tokens
The remarkable success of large language models (LLMs) stems from their ability to consolidate vast amounts of knowledge into the memory during pre-training and to retrieve it from the memory during inference, enabling advanced capabilities such as knowledge memorization, instruction-following and reasoning. However, the mechanisms of memory retrieval and consolidation in LLMs remain poorly understood. In this paper, we propose the function token hypothesis to explain the workings of LLMs: Duri…

On-Package Memory with Universal Chiplet Interconnect Express (UCIe): A Low Power, High Bandwidth, Low Latency and Low Cost Approach
Debendra Das Sharma, Swadesh Choudhary, Peter Onufryk, Rob Pelt
https://arxiv.org/abs/2510.06513

On-Package Memory with Universal Chiplet Interconnect Express (UCIe): A Low Power, High Bandwidth, Low Latency and Low Cost Approach
Emerging computing applications such as Artificial Intelligence (AI) are facing a memory wall with existing on-package memory solutions that are unable to meet the power-efficient bandwidth demands. We propose to enhance UCIe with memory semantics to deliver power-efficient bandwidth and cost-effective on-package memory solutions applicable across the entire computing continuum. We propose approaches by reusing existing LPDDR6 and HBM memory through a logic die that connects to the SoC using UC…

Days since I bootet a server with incorrect memory slot configuration: 0

The real awe that Apple promised us, was quietly published on this blog post:
This is amazing - congratulations!
https://infosec.exchange/@madcoder/115175739709593875

Israel-based RAAAM, whose "GCRAM" on-chip memory tech aims to deliver up to 10x power savings relative to high-density SRAM, raised a $17M Series A led by NXP (Meir Orbach/CTech)
https://www.calcalistech.com/ctechnews/article/sjjv3pp1bg

Chip giant NXP leads $17.5M Series A for Israeli startup tackling AI’s memory bottleneck
RAAAM Memory Technologies’ “GCRAM” promises denser, lower-power on-chip memory as the semiconductor industry races to support next-generation AI processors. 

MoE-Compression: How the Compression Error of Experts Affects the Inference Accuracy of MoE Model?
Songkai Ma, Zhaorui Zhang, Sheng Di, Benben Liu, Xiaodong Yu, Xiaoyi Lu, Dan Wang
https://arxiv.org/abs/2509.07727

MoE-Compression: How the Compression Error of Experts Affects the Inference Accuracy of MoE Model?
With the widespread application of Mixture of Experts (MoE) reasoning models in the field of LLM learning, efficiently serving MoE models under limited GPU memory constraints has emerged as a significant challenge. Offloading the non-activated experts to main memory has been identified as an efficient approach to address such a problem, while it brings the challenges of transferring the expert between the GPU memory and main memory. We need to explore an efficient approach to compress the exper…

Weakly-Driven Quantum Walks for Memory-Constrained Pauli Channel Learning
Yuan-Zhuo Wang, Yi-Ran Xiao, Ming-Yang Li, Shengjun Wu, Zeng-Bing Chen
https://arxiv.org/abs/2509.07702

Weakly-Driven Quantum Walks for Memory-Constrained Pauli Channel Learning
Accurate characterization of quantum noise, exemplified by the Pauli channel, is a cornerstone for building fault-tolerant quantum computers. A recent protocol (PRX Quantum 6, 020323 (2025)) combining channel concatenation and quantum memory has achieved an exponential reduction in measurement complexity for Pauli channel estimation. This efficiency, however, hinges on using logarithmic quantum memory to suppress hypothesis test errors. In this work, we introduce a mechanism termed the ``weakly…

@… is a large amount of inactive memory necessarily a problem?
https://wiki.freebsd.org/Memory

Can One Model Gravitational Nonlinear Memory with Fractional Derivative Operators?
Sercan Kaya, Bayram Tekin
https://arxiv.org/abs/2510.07232 https://arxiv…

Can One Model Gravitational Nonlinear Memory with Fractional Derivative Operators?
We investigate whether fractional calculus, with its intrinsic long-tailed memory and nonlocal features, can provide a viable model for gravitational-wave memory effects. We consider two toy constructions: ($i$) a fractional modification of the linearized Einstein field equations using a sequential Caputo operator, and ($ii$) a fractionalized quadrupole formula where the source moment is acted upon by the same operator. Both constructions yield history-dependent responses with small memory-like…

Nach Härtung: Apple spendet iPhone 17 an Organisationen der Zivilgesellschaft
Mit A19 und A19 Pro führt Apple das Memory Integrity Enforcement ein, das komplexe Angriffe besser verhindern soll. Entsprechende Geräte werden nun gespendet.

IM-PIR: In-Memory Private Information Retrieval
Mpoki Mwaisela, Peterson Yuhala, Pascal Felber, Valerio Schiavoni
https://arxiv.org/abs/2509.06514 https://…

IM-PIR: In-Memory Private Information Retrieval
Private information retrieval (PIR) is a cryptographic primitive that allows a client to securely query one or multiple servers without revealing their specific interests. In spite of their strong security guarantees, current PIR constructions are computationally costly. Specifically, most PIR implementations are memory-bound due to the need to scan extensive databases (in the order of GB), making them inherently constrained by the limited memory bandwidth in traditional processor-centric compu…

TrackVLA : Unleashing Reasoning and Memory Capabilities in VLA Models for Embodied Visual Tracking
Jiahang Liu, Yunpeng Qi, Jiazhao Zhang, Minghan Li, Shaoan Wang, Kui Wu, Hanjing Ye, Hong Zhang, Zhibo Chen, Fangwei Zhong, Zhizheng Zhang, He Wang
https://arxiv.org/abs/2510.07134

TrackVLA++: Unleashing Reasoning and Memory Capabilities in VLA Models for Embodied Visual Tracking
Embodied Visual Tracking (EVT) is a fundamental ability that underpins practical applications, such as companion robots, guidance robots and service assistants, where continuously following moving targets is essential. Recent advances have enabled language-guided tracking in complex and unstructured scenes. However, existing approaches lack explicit spatial reasoning and effective temporal memory, causing failures under severe occlusions or in the presence of similar-looking distractors. To add…

Associative Memory Model with Neural Networks: Memorizing multiple images with one neuron
Hiroshi Inazawa
https://arxiv.org/abs/2510.06542 https://arxiv.or…

Associative Memory Model with Neural Networks: Memorizing multiple images with one neuron
This paper presents a neural network model (associative memory model) for memory and recall of images. In this model, only a single neuron can memorize multi-images and when that neuron is activated, it is possible to recall all the memorized images at the same time. The system is composed of a single cluster of numerous neurons, referred to as the "Cue Ball," and multiple neural network layers, collectively called the "Recall Net." One of the features of this model is that several different im…

TIL that doctors somewhere use benzodiazepines to impair memory in patients on purpose
>Midazolam is superior to diazepam in impairing memory of endoscopy procedures, but propofol has a quicker recovery time and a better memory-impairing effect.[https://doi.org/10.1016/j.gie.2007.12.046]

Polarization memory effect in a multimode fiber
Gauri Arora, Lyubov V. Amitonova
https://arxiv.org/abs/2509.05665 https://arxiv.org/pdf/2509.05665

Polarization memory effect in a multimode fiber
Optical memory effects are well-known types of amplitude-domain wave correlation enabling control over light scattered through diffusive materials or multimode fibers. In this letter, we report the phenomenon of random polarization memory effect. We observe that, despite strong scattering, which leads to random spatial polarization distributions at the multimode fiber output, local polarization states of the optical field maintain a high degree of correlation with respect to the input polarizat…

Non-Existence of Solutions for a Fourth-Order Structurally Damped Equation Under Nonlinear Memory Effect
Luis Gustavo Longen
https://arxiv.org/abs/2509.06671 https://

Non-Existence of Solutions for a Fourth-Order Structurally Damped Equation Under Nonlinear Memory Effect
In this paper, we study a mixed wave-plate equation with rotational inertia, fractional damping and memory non-linearity. This research is a non-existence counterpart to a paper by D'Abbicco and Longen, in search of the critical exponent for the global in-time existence of small data solutions to the Cauchy problem for a mixed wave-plate equation, with a rotational inertia and a non-integer dissipation term and a memory-type non-linearity. We employ a modified test function argument to show tha…

there's rumors that Apple wants to add touch screens to laptops
has everyone memory-holed the TouchBar?

Sports betting roundup: NFL season starts with one of the best Week 1's in recent memory https://www.foxsports.com/articles/nfl/sports-betting-roundup-nfl-season-starts-with-one-of-the-best-week-1s-in-recent-memory…

A unified framework for data-driven construction of stochastic reduced models with state-dependent memory
Zhiyuan She, Liyao Lyu, Bryan Ronain Smith, Huan Lei
https://arxiv.org/abs/2509.07264

A unified framework for data-driven construction of stochastic reduced models with state-dependent memory
We present a unified framework for the data-driven construction of stochastic reduced models with state-dependent memory for high-dimensional Hamiltonian systems. The method addresses two key challenges: (\rmnum{1}) accurately modeling heterogeneous non-Markovian effects where the memory function depends on the coarse-grained (CG) variables beyond the standard homogeneous kernel, and (\rmnum{2}) efficiently exploring the phase space to sample both equilibrium and dynamical observables for reduc…

Effect of non-Fourier heat transport on temperature distribution in High Bandwidth Memory
Zhihao Zhou, Yu He, Shixian Liu, Lina Yang, Nuo Yang
https://arxiv.org/abs/2510.07691 h…

Effect of non-Fourier heat transport on temperature distribution in High Bandwidth Memory
High Bandwidth Memory (HBM), as a key development trend in future memory chip technology, significantly enhances computer performance. At the same time, the thermal challenges arising from its stacked architecture have drawn considerable attention. Most existing studies on HBM thermal management are based on Fourier's law, neglecting the non-Fourier effects introduced by the micro/nanoscale structures within HBM. In this study, the Monte Carlo method (MC) is employed to solve the phonon Boltzma…

RustAssure: Differential Symbolic Testing for LLM-Transpiled C-to-Rust Code
Yubo Bai, Tapti Palit
https://arxiv.org/abs/2510.07604 https://arxiv.org/pdf/25…

RustAssure: Differential Symbolic Testing for LLM-Transpiled C-to-Rust Code
Rust is a memory-safe programming language that significantly improves software security. Existing codebases written in unsafe memory languages, such as C, must first be transpiled to Rust to take advantage of Rust's improved safety guarantees. RustAssure presents a system that uses Large Language Models (LLMs) to automatically transpile existing C codebases to Rust. RustAssure uses prompt engineering techniques to maximize the chances of the LLM generating idiomatic and safe Rust code. Moreove…

DL-PIM: Improving Data Locality in Processing-in-Memory Systems
Parker Hao Tian, Zahra Yousefijamarani, Alaa Alameldeen
https://arxiv.org/abs/2510.07719 https://

DL-PIM: Improving Data Locality in Processing-in-Memory Systems
PIM architectures aim to reduce data transfer costs between processors and memory by integrating processing units within memory layers. Prior PIM architectures have shown potential to improve energy efficiency and performance. However, such advantages rely on data proximity to the processing units performing computations. Data movement overheads can degrade PIM's performance and energy efficiency due to the need to move data between a processing unit and a distant memory location. %they face ch…

Neural ARFIMA model for forecasting BRIC exchange rates with long memory under oil shocks and policy uncertainties
Tanujit Chakraborty, Donia Besher, Madhurima Panja, Shovon Sengupta
https://arxiv.org/abs/2509.06697

Neural ARFIMA model for forecasting BRIC exchange rates with long memory under oil shocks and policy uncertainties
Accurate forecasting of exchange rates remains a persistent challenge, particularly for emerging economies such as Brazil, Russia, India, and China (BRIC). These series exhibit long memory, nonlinearity, and non-stationarity properties that conventional time series models struggle to capture. Additionally, there exist several key drivers of exchange rate dynamics, including global economic policy uncertainty, US equity market volatility, US monetary policy uncertainty, oil price growth rates, a…

📔 Exploring how storytelling strategies shape memories
#memory

Exploring how storytelling strategies shape memories
Does the way a person hears about an event shape their recollection of it later? In a new JNeurosci paper, Signy Sheldon and colleagues, from McGill University, explored whether different storytelling strategies affect how the brain stores that experience as a memory and recalls it later.

Es tötet die ganze Zeit immer noch mein Muscle Memory, dass sie jetzt den Punkt und den drei-Punkt in der Tastatur vertauscht haben. 🥹

An Early Exploration of Deep-Learning-Driven Prefetching for Far Memory
Yutong Huang, Zhiyuan Guo, Yiying Zhang
https://arxiv.org/abs/2510.04360 https://ar…

An Early Exploration of Deep-Learning-Driven Prefetching for Far Memory
Far-memory systems, where applications store less-active data in more energy-efficient memory media, are increasingly adopted by data centers. However, applications are bottlenecked by on-demand data fetching from far- to local-memory. We present Memix, a far-memory system that embodies a deep-learning-system co-design for efficient and accurate prefetching, minimizing on-demand far-memory accesses. One key observation is that memory accesses are shaped by both application semantics and runtime…

Efficient Low-Memory Fast Stack Decoding with Variance Polarization for PAC Codes
Mohsen Moradi, Hessam Mahdavifar
https://arxiv.org/abs/2509.07231 https://

Efficient Low-Memory Fast Stack Decoding with Variance Polarization for PAC Codes
Polarization-adjusted convolutional (PAC) codes have recently emerged as a promising class of error-correcting codes, achieving near-capacity performance particularly in the short block-length regime. In this paper, we propose an enhanced stack decoding algorithm for PAC codes that significantly improves parallelization by exploiting specialized bit nodes, such as rate-0 and rate-1 nodes. For a rate-1 node with $N_0$ leaf nodes in its corresponding subtree, conventional stack decoding must eith…

A Distributed Emulation Environment for In-Memory Computing Systems
Eleni Bougioukou, Anastasios Petropoulos, Nikolaos Toulgaridis, Theodoros Chatzimichail, Theodore Antonakopoulos
https://arxiv.org/abs/2510.08257

A Distributed Emulation Environment for In-Memory Computing Systems
In-memory computing technology is used extensively in artificial intelligence devices due to lower power consumption and fast calculation of matrix-based functions. The development of such a device and its integration in a system takes a significant amount of time and requires the use of a real-time emulation environment, where various system aspects are analyzed, microcode is tested, and applications are deployed, even before the real chip is available. In this work, we present the architectur…

BOFH excuse #202:
kernel panic: write-only-memory (/dev/wom0) capacity exceeded.

ELMUR: External Layer Memory with Update/Rewrite for Long-Horizon RL
Egor Cherepanov, Alexey K. Kovalev, Aleksandr I. Panov
https://arxiv.org/abs/2510.07151 https://

ELMUR: External Layer Memory with Update/Rewrite for Long-Horizon RL
Real-world robotic agents must act under partial observability and long horizons, where key cues may appear long before they affect decision making. However, most modern approaches rely solely on instantaneous information, without incorporating insights from the past. Standard recurrent or transformer models struggle with retaining and leveraging long-term dependencies: context windows truncate history, while naive memory extensions fail under scale and sparsity. We propose ELMUR (External Laye…

Toward Efficient and Scalable Design of In-Memory Graph-Based Vector Search
Ilias Azizi, Karima Echihab, Themis Palpanas, Vassilis Christophides
https://arxiv.org/abs/2509.05750

Toward Efficient and Scalable Design of In-Memory Graph-Based Vector Search
Vector data is prevalent across business and scientific applications, and its popularity is growing with the proliferation of learned embeddings. Vector data collections often reach billions of vectors with thousands of dimensions, thus, increasing the complexity of their analysis. Vector search is the backbone of many critical analytical tasks, and graph-based methods have become the best choice for analytical tasks that do not require guarantees on the quality of the answers. Although several…

Memory-Augmented Generative AI for Real-time Wireless Prediction in Dynamic Industrial Environments
Rahul Gulia, Amlan Ganguly, Michael E. Kuhl, Ehsan Rashedi, Clark Hochgraf
https://arxiv.org/abs/2510.06884

Memory-Augmented Generative AI for Real-time Wireless Prediction in Dynamic Industrial Environments
Accurate and real-time prediction of wireless channel conditions, particularly the Signal-to-Interference-plus-Noise Ratio (SINR), is a foundational requirement for enabling Ultra-Reliable Low-Latency Communication (URLLC) in highly dynamic Industry 4.0 environments. Traditional physics-based or statistical models fail to cope with the spatio-temporal complexities introduced by mobile obstacles and transient interference inherent to smart warehouses. To address this, we introduce Evo-WISVA (Evo…

from my link log —
Systematization of knowledge (SoK): eternal war in memory. (2013)
https://people.eecs.berkeley.edu/~dawnsong/papers/Oakland13-SoK-CR.pdf
saved 2025-11-09

The cybersecurity news machine is cranking away at top speed, so don't miss today's Metacurity for the critical infosec developments you should know, including
--US indicts ransomware dev, offers $10 million reward, and puts him on most-wanted list,
--US tech giants enable human rights abuse in China,
--BlackDB.cc operator pleads guilty,
--Microsoft issues 80 Patch Tuesday fixes,
--Pakistan has built sweeping surveillance system,
--Apple targets spy…

US indicts ransomware dev, offers $10 million reward, puts him on most-wanted list
US tech giants enable human rights abuse in China, BlackDB.cc operator pleads guilty, Microsoft issues 80 Patch Tuesday fixes, Pakistan has built sweeping surveillance system, Apple targets spyware with Memory Integrity Enforcement, Korean telco KT on hot seat for 278 mobile fraud cases, much more

Staatsfonds beteiligt? DLC für "Assassin's Creed Mirage" spielt in Saudi-Arabien
Zwei Jahre nach dem Release bekommt "Assassin's Creed Mirage" einen neuen, kostenlosen DLC. "Valley of Memory" spielt in Saudi-Arabien.

FineServe: Precision-Aware KV Slab and Two-Level Scheduling for Heterogeneous Precision LLM Serving
Kyungmin Bin, Seungbeom Choi, Jimyoung Son, Jieun Choi, Daseul Bae, Daehyeon Baek, Kihyo Moon, Minsung Jang, Hyojung Lee
https://arxiv.org/abs/2509.06261

FineServe: Precision-Aware KV Slab and Two-Level Scheduling for Heterogeneous Precision LLM Serving
Recent advances in Post-Training Quantization (PTQ) techniques have significantly increased demand for serving quantized large language models (LLMs), enabling higher throughput and substantially reduced memory usage with minimal accuracy loss. Quantized models address memory constraints in LLMs and enhance GPU resource utilization through efficient GPU sharing. However, quantized models have smaller KV block sizes than non-quantized models, causing limited memory efficiency due to memory fragm…

Non-Clifford Gates are Required for Long-Term Memory
Jon Nelson, Joel Rajakumar, Michael J. Gullans
https://arxiv.org/abs/2510.08451 https://arxiv.org/pdf/…

Non-Clifford Gates are Required for Long-Term Memory
We show that all Clifford circuits under interspersed depolarizing noise lose memory of their input exponentially quickly, even when given access to a constant supply of fresh qubits in arbitrary states. This is somewhat surprising given the result of Aharonov et al. [STOC1997] which gives a fault-tolerant protocol for general quantum circuits using a supply of fresh qubits. Our result shows that such a protocol is impossible using only Clifford gates demonstrating that non-Clifford gates are f…

"How climate change could affect production of the world’s favorite fruit, the banana"
#Climate #ClimateChange #Food

How climate change could affect production of the world’s favorite fruit, the banana
Sweet, savory, raw, fried or baked. A main course, side dish, dessert or smoothie. Raise a hand: Who doesn’t have at least one fond memory of the world’s most widely consumed fruit, the banana? Maybe it’s because of its shape, texture or how easily it can be peeled and prepared (when it’s not eaten raw […]

The Interplay of Attention and Memory in Visual Enumeration
B. Sankar, Devottama Sen, Dibakar Sen
https://arxiv.org/abs/2510.05833 https://arxiv.org/pdf/25…

The Interplay of Attention and Memory in Visual Enumeration
Humans navigate and understand complex visual environments by subconsciously quantifying what they see, a process known as visual enumeration. However, traditional studies using flat screens fail to capture the cognitive dynamics of this process over the large visual fields of real-world scenes. To address this gap, we developed an immersive virtual reality system with integrated eye-tracking to investigate the interplay between attention and memory during complex enumeration. We conducted a tw…

Majestic Labs, which makes patent-pending server architecture that promises more memory capacity, raised $100M, including a $71M Series A led by Bow Wave (Jennifer Elias/CNBC)
https://www.cnbc.com/2025/11/10/majestic-labs-meta-google-ai-funding.html
…

Former Google, Meta executives raise $100 million for high-capacity AI servers startup
The three plan to sell high-memory server technology.

Arrested coarsening, oscillations, and memory from a conserved phase separating nucleator in a self-straining cytoskeletal network
Quentin Bodini--Lefranc, Jakob Schindelwig, Daniel Weidinger, Lucas Engleder, Sebastian F\"urthauer
https://arxiv.org/abs/2509.07181

Arrested coarsening, oscillations, and memory from a conserved phase separating nucleator in a self-straining cytoskeletal network
How do phase separated cellular structures set their size? To elucidate this, we study the dynamics and steady states of a phase separating nucleator that is advected by the self-straining cytoskeletal network which it nucleates. We find (i) that the interplay between transport and the tendency of nucleators to phase separate arrests coarsening; (ii) that the system undergoes damped oscillations towards a patterned steady state with a well defined length scale; (iii) that the system supports a …

I'm fixing #aiocoap's memory leak tests to finally run as async functions: the original tests employed mechanisms from the age of tulip (back when asyncio was developed out-of-tree), and Python 3.14 dropping some obsolete mechanisms.
Good riddance, but also tough work fixing subtle possible leaks that are suddenly easier to discover.

New article out! 📝
El Shatt: Memories of a Yugoslav Partisan refugee camp travelling from North Africa to Croatia
published #OA in Memory Studies
co-authored with Marijana Hameršak (#Zagreb )
We look into the history of a

The 85th edition of De Programmatica Ipsum is out!
This month, we look at the strategies used by major programming languages to manage memory; in our Vidéothèque section, we learn how C and C manage memory in a video by Ryan Baker; and in the Library section, we review "What Every Programmer Should Know About Memory" by Ulrich Drepper.

@… draw for me A sleek, futuristic data vault glowing with neon blue lights, filled with holographic memory chips and floating digital documents, surrounded by a dark cyberpunk cityscape, ultra-detailed, high-tech aesthetic, cinematic lighting.

Series C, Episode 10 - Ultraworld
[Ultra 2 Negative response.]
ULTRA 1: Operate primary fail-safe terminals.
ULTRA 3: Confirmed.
[Tarrant retrieves the memory tubes and leaves the control room.]
https://blake.torpidity.net/m/310/592 B7B6

A-MemGuard: A Proactive Defense Framework for LLM-Based Agent Memory
Qianshan Wei, Tengchao Yang, Yaochen Wang, Xinfeng Li, Lijun Li, Zhenfei Yin, Yi Zhan, Thorsten Holz, Zhiqiang Lin, XiaoFeng Wang
https://arxiv.org/abs/2510.02373

A-MemGuard: A Proactive Defense Framework for LLM-Based Agent Memory
Large Language Model (LLM) agents use memory to learn from past interactions, enabling autonomous planning and decision-making in complex environments. However, this reliance on memory introduces a critical security risk: an adversary can inject seemingly harmless records into an agent's memory to manipulate its future behavior. This vulnerability is characterized by two core aspects: First, the malicious effect of injected records is only activated within a specific context, making them hard t…

Sonnet 122 - CXXII
Thy gift, thy tables, are within my brain
Full charactered with lasting memory,
Which shall above that idle rank remain,
Beyond all date, even to eternity:
Or, at the least, so long as brain and heart
Have faculty by nature to subsist;
Till each to razed oblivion yield his part
Of thee, thy record never can be missed.
That poor retention could not so much hold,
Nor need I tallies thy dear love to score;
Ther…

Reward function compression facilitates goal-dependent reinforcement learning
Gaia Molinaro, Anne G. E. Collins
https://arxiv.org/abs/2509.06810 https://ar…

Reward function compression facilitates goal-dependent reinforcement learning
Reinforcement learning agents learn from rewards, but humans can uniquely assign value to novel, abstract outcomes in a goal-dependent manner. However, this flexibility is cognitively costly, making learning less efficient. Here, we propose that goal-dependent learning is initially supported by a capacity-limited working memory system. With consistent experience, learners create a "compressed" reward function (a simplified rule defining the goal) which is then transferred to long-term memory an…

ToolMem: Enhancing Multimodal Agents with Learnable Tool Capability Memory
Yunzhong Xiao, Yangmin Li, Hewei Wang, Yunlong Tang, Zora Zhiruo Wang
https://arxiv.org/abs/2510.06664

ToolMem: Enhancing Multimodal Agents with Learnable Tool Capability Memory
Agents utilizing tools powered by large language models (LLMs) or vision-language models (VLMs) have demonstrated remarkable progress in diverse tasks across text and visual modalities. Unlike traditional tools such as calculators, which give deterministic outputs, neural tools perform uncertainly across task scenarios. While different tools for a task may excel in varied scenarios, existing agents typically rely on fixed tools, thus limiting the flexibility in selecting the most suitable tool …

I might start a new hobby of SD card collecting (Like stamp collecting, but *edgier*!). There are so many cute little designs.

AILoRA: Function-Aware Asymmetric Initialization for Low-Rank Adaptation of Large Language Models
Xiaoshuang Ji, Zhendong Zhao, Xiaoyan Gu, Xiaojun Chen, Xin Zhao, Zeyao Liu
https://arxiv.org/abs/2510.08034

AILoRA: Function-Aware Asymmetric Initialization for Low-Rank Adaptation of Large Language Models
Parameter-efficient finetuning (PEFT) aims to mitigate the substantial computational and memory overhead involved in adapting large-scale pretrained models to diverse downstream tasks. Among numerous PEFT strategies, Low-Rank Adaptation (LoRA) has emerged as one of the most widely adopted approaches due to its robust empirical performance and low implementation complexity. In practical deployment, LoRA is typically applied to the $W^Q$ and $W^V$ projection matrices of self-attention modules, en…

First KDE 6.4.4 feedback on FreeBSD:
All running pretty smoothly afaic. Memory usage a bit high, but my guess that's bcs of the startup of a linux jail (I'm playing with installing Brave, which I did). Possibly I let go of that and stick to Librewolf, installed from the repos already.
Networkmgr by the Ghostbsd team is a nifty tool to handle your connections, works great in KDE also.
Automount by @…

SCREME: A Scalable Framework for Resilient Memory Design
Fan Li, Mimi Xie, Yanan Guo, Huize Li, Xin Xin
https://arxiv.org/abs/2509.06101 https://arxiv.org/…

SCREME: A Scalable Framework for Resilient Memory Design
The continuing advancement of memory technology has not only fueled a surge in performance, but also substantially exacerbate reliability challenges. Traditional solutions have primarily focused on improving the efficiency of protection schemes, i.e., Error Correction Codes (ECC), under the assumption that allocating additional memory space for parity data is always expensive and therefore not a scalable solution. We break the stereotype by proposing an orthogonal approach that provides addit…

Dato: A Task-Based Programming Model for Dataflow Accelerators
Shihan Fang, Hongzheng Chen, Niansong Zhang, Jiajie Li, Han Meng, Adrian Liu, Zhiru Zhang
https://arxiv.org/abs/2509.06794

Dato: A Task-Based Programming Model for Dataflow Accelerators
Recent deep learning workloads increasingly push computational demand beyond what current memory systems can sustain, with many kernels stalling on data movement rather than computation. While modern dataflow accelerators incorporate on-chip streaming to mitigate off-chip bandwidth limitations, existing programming models struggle to harness these capabilities effectively. Low-level interfaces provide fine-grained control but impose significant development overhead, whereas high-level tile-base…

Software Framework for Optically Accessible Quantum Memory Using Group-IV Color Centers in Diamond
Yannick Strocka, Mohamed Belhassen, Tim Schr\"oder, Gregor Pieplow
https://arxiv.org/abs/2510.07045

Software Framework for Optically Accessible Quantum Memory Using Group-IV Color Centers in Diamond
In the rapidly evolving field of quantum technology, the precise and detailed description of quantum components is not just a necessity but the foundation for advancing research, development, and applications. Optically accessible quantum memories are key building blocks for devices such as quantum repeaters and two-factor authentication. The memory we describe here is based on a tin-vacancy color center coupled to a highly efficient cavity. It leverages state-dependent reflection from the cavi…

"Memory, Guilt and Shame" 7th International Interdisciplinary Conference https://call-for-papers.sas.upenn.edu/cfp/2025/09/05/memory-guilt-and-shame-7th-international-interdisciplinary-conference

Scaling atomic ordering in shared memory
Lorenzo Martignetti, Eli\~a Batista, Gianpaolo Cugola, Fernando Pedone
https://arxiv.org/abs/2509.07781 https://ar…

Scaling atomic ordering in shared memory
Atomic multicast is a communication primitive used in dependable systems to ensure consistent ordering of messages delivered to a set of replica groups. This primitive enables critical services to integrate replication and sharding (i.e., state partitioning) to achieve fault tolerance and scalability. While several atomic multicast protocols have been developed for message-passing systems, only a few are designed for the shared memory system model. This paper introduces TRAM, an atomic multicas…

Memory Forcing: Spatio-Temporal Memory for Consistent Scene Generation on Minecraft
Junchao Huang, Xinting Hu, Boyao Han, Shaoshuai Shi, Zhuotao Tian, Tianyu He, Li Jiang
https://arxiv.org/abs/2510.03198

Memory Forcing: Spatio-Temporal Memory for Consistent Scene Generation on Minecraft
Autoregressive video diffusion models have proved effective for world modeling and interactive scene generation, with Minecraft gameplay as a representative application. To faithfully simulate play, a model must generate natural content while exploring new scenes and preserve spatial consistency when revisiting explored areas. Under limited computation budgets, it must compress and exploit historical cues within a finite context window, which exposes a trade-off: Temporal-only memory lacks long…

Modular interface for efficient optical readout of diamond quantum memory at cryogenic temperatures via single-mode optical fibers
Akira Kamimaki, Yuhei Sekiguchi, Daisuke Ito, Taichi Fujiwara, Toshiharu Makino, Hiromitsu Kato, Hideo Kosaka
https://arxiv.org/abs/2510.07032

Modular interface for efficient optical readout of diamond quantum memory at cryogenic temperatures via single-mode optical fibers
Efficient quantum devices across various physical systems have been rapidly developed for entanglement-based quantum repeaters and spin-photon conversion; however, far less attention has been paid to standardizing platforms through quantum memory optical interfaces. We present a modular interface for color centers in diamond that is structurally isolated from device-and temperature-related variation. Despite a more than 100-fold reduction in confocal volume, we achieve highly efficient photon c…

from my link log —
Don't give Postgres too much memory.
https://vondra.me/posts/dont-give-postgres-too-much-memory/
saved 2025-11-03 h…

Artificial Synapse based on ULTRARAM Memory Device for Neuromorphic Applications
Abhishek Kumar, Peter D. Hodgson, Manus Hayne, Avirup Dasgupta
https://arxiv.org/abs/2510.05671 …

Artificial Synapse based on ULTRARAM Memory Device for Neuromorphic Applications
The memory demands of large-scale deep neural networks (DNNs) require synaptic weight values to be stored and updated in off-chip memory like dynamic random-access memory, which reduces energy efficiency and increases training time. Monolithic crossbar or pseudo-crossbar arrays using analog non-volatile memories, which can store and update weights on-chip, present an opportunity to efficiently accelerate DNN training. In this article, we present on-chip training and inference of a neural networ…

Adaptive Execution Scheduler for DataDios SmartDiff
Aryan Poduri
https://arxiv.org/abs/2510.07811 https://arxiv.org/pdf/2510.07811

Adaptive Execution Scheduler for DataDios SmartDiff
We present an adaptive scheduler for a single differencing engine (SmartDiff) with two execution modes: (i) in-memory threads and (ii) Dask based parallelism. The scheduler continuously tunes batch size and worker/thread count within fixed CPU and memory budgets to minimize p95 latency. A lightweight preflight profiler estimates bytes/row and I/O rate; an online cost/memory model prunes unsafe actions; and a guarded hill-climb policy favors lower latency with backpressure and straggler mitigati…

HPQEA: A Scalable and High-Performance Quantum Emulator with High-Bandwidth Memory for Diverse Algorithms Support
Tran Van Duy, Tuan Hai Vu, Vu Trung Duong Le, Hoai Luan Pham, Yasuhiko Nakashima
https://arxiv.org/abs/2510.07110

HPQEA: A Scalable and High-Performance Quantum Emulator with High-Bandwidth Memory for Diverse Algorithms Support
In recent years, there has been a growing interest in the development of quantum emulation. However, existing studies often struggle to achieve broad applicability, high performance, and efficient resource and memory utilization. To address these challenges, we provide HPQEA, a quantum emulator based on the state-vector emulation approach. HPQEA includes three main features: a high-performance computing core, an optimized controlled-NOT gate computation strategy, and effective utilization of hi…

A Scalable FPGA Architecture With Adaptive Memory Utilization for GEMM-Based Operations
Anastasios Petropoulos, Theodore Antonakopoulos
https://arxiv.org/abs/2510.08137 https://…

A Scalable FPGA Architecture With Adaptive Memory Utilization for GEMM-Based Operations
Deep neural network (DNN) inference relies increasingly on specialized hardware for high computational efficiency. This work introduces a field-programmable gate array (FPGA)-based dynamically configurable accelerator featuring systolic arrays, high-bandwidth memory, and UltraRAMs. We present two processing unit (PU) configurations with different computing capabilities using the same interfaces and peripheral blocks. By instantiating multiple PUs and employing a heuristic weight transfer schedu…

Crosslisted article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[3/8]:
- MeSH: Memory-as-State-Highways for Recursive Transformers
Yu, Shu, Wang, Zhang, Wu, Li, Long, Chen, Xu, Su, Zheng

Ground-Aware Octree-A* Hybrid Path Planning for Memory-Efficient 3D Navigation of Ground Vehicles
Byeong-Il Ham, Hyun-Bin Kim, Kyung-Soo Kim
https://arxiv.org/abs/2509.04950 htt…

Ground-Aware Octree-A* Hybrid Path Planning for Memory-Efficient 3D Navigation of Ground Vehicles
In this paper, we propose a 3D path planning method that integrates the A* algorithm with the octree structure. Unmanned Ground Vehicles (UGVs) and legged robots have been extensively studied, enabling locomotion across a variety of terrains. Advances in mobility have enabled obstacles to be regarded not only as hindrances to be avoided, but also as navigational aids when beneficial. A modified 3D A* algorithm generates an optimal path by leveraging obstacles during the planning process. By inc…

Memory behavior of a randomly driven model glass
Roni Chatterjee, Smarajit Karmakar, Muhittin Mungan, Damien Vandembroucq
https://arxiv.org/abs/2510.05537 https://

Memory behavior of a randomly driven model glass
We investigate by atomistic simulations the memory behavior a model glass subjected to random driving protocols. The training consists of a random walk of forward and/or backward shearing sequences bounded by a maximal shear strain of absolute value γT . We show that such a stochastic training protocol is able to record the training amplitude. Different read-out protocols are also tested and are shown to be able to retrieve the training amplitude. We then emphasize the ten- sorial character of…

Mechanisms for anesthesia, unawareness, respiratory depression, memory replay and sleep: MHb > IPN > PAG DRN MRN > claustrum > cortical slow-waves
Karin Vadovi\v{c}ov\'a
https://arxiv.org/abs/2509.04454

Mechanisms for anesthesia, unawareness, respiratory depression, memory replay and sleep: MHb > IPN > PAG + DRN + MRN > claustrum > cortical slow-waves
My findings show, for the first time, what causes loss of awareness, anesthesia, memory replay, opioids induced respiratory depression (OIRD), and slow wave sleep. Opiates are fast pain relievers and anesthetics that can cause respiratory arrest. I found how mu-opioids and other medial habenula activators slowdown respiration during SWS and anesthesia. Using DTI method I observed that human hippocampus is connected to MHb via posterior septum, while amygdala via anteromedial BNST. MHb projected…

Replaced article(s) found for cs.CR. https://arxiv.org/list/cs.CR/new
[1/2]:
- Friend or Foe Inside? Exploring In-Process Isolation to Maintain Memory Safety for Unsafe Rust
Merve G\"ulmez, Thomas Nyman, Christoph Baumann, Jan Tobias M\"uhlberg

Adaptive Memory Momentum via a Model-Based Framework for Deep Learning Optimization
Kristi Topollai, Anna Choromanska
https://arxiv.org/abs/2510.04988 https://

Adaptive Memory Momentum via a Model-Based Framework for Deep Learning Optimization
The vast majority of modern deep learning models are trained with momentum-based first-order optimizers. The momentum term governs the optimizer's memory by determining how much each past gradient contributes to the current convergence direction. Fundamental momentum methods, such as Nesterov Accelerated Gradient and the Heavy Ball method, as well as more recent optimizers such as AdamW and Lion, all rely on the momentum coefficient that is customarily set to $β= 0.9$ and kept constant during …

COMPACT: Common-token Optimized Model Pruning Across Channels and Tokens
Eugene Kwek, Wenpeng Yin
https://arxiv.org/abs/2509.06836 https://arxiv.org/pdf/25…

COMPACT: Common-token Optimized Model Pruning Across Channels and Tokens
Making LLMs more efficient in memory, latency, and serving cost is crucial for edge deployment, interactive applications, and sustainable inference at scale. Pruning is a key technique toward this goal. However, prior pruning methods are limited: width pruning often breaks the standard transformer layout or requires custom inference code, while depth pruning removes entire layers and can cause abrupt accuracy drops. In this work, we propose COMPACT, which jointly (i) prunes rare vocabulary to s…

A Study on Messaging Trade-offs in Data Streaming for Scientific Workflows
Anjus George, Michael J. Brim, Christopher Zimmer, Tyler J. Skluzacek, A. J. Ruckman, Gustav R. Jansen, Sarp Oral
https://arxiv.org/abs/2509.07199

A Study on Messaging Trade-offs in Data Streaming for Scientific Workflows
Memory-to-memory data streaming is essential for modern scientific workflows that require near real-time data analysis, experimental steering, and informed decision-making during experiment execution. It eliminates the latency bottlenecks associated with file-based transfers to parallel storage, enabling rapid data movement between experimental facilities and HPC systems. These tightly coupled experimental-HPC workflows demand low latency, high throughput, and reliable data delivery to support …

Structured Cognition for Behavioral Intelligence in Large Language Model Agents: Preliminary Study
Myung Ho Kim
https://arxiv.org/abs/2510.05107 https://ar…

Structured Cognition for Behavioral Intelligence in Large Language Model Agents: Preliminary Study
Large language models have advanced natural language understanding and generation, yet their use as autonomous agents raises architectural challenges for multi-step tasks. Existing frameworks often intertwine inference, memory, and control in a single prompt, which can reduce coherence and predictability. The Structured Cognitive Loop (SCL) is introduced as an alternative architecture that separates these functions. In SCL, the language model is dedicated to inference, memory is maintained exte…

from my link log —
Memory Integrity Enforcement: A complete vision for memory safety in Apple devices.
https://security.apple.com/blog/memory-integrity-enforcement/
saved 2025-09-10

Blog - Memory Integrity Enforcement: A complete vision for memory safety in Apple devices - Apple Security Research
Memory Integrity Enforcement (MIE) is the culmination of an unprecedented design and engineering effort spanning half a decade that combines the unique strengths of Apple silicon hardware with our advanced operating system security to provide industry-first, always-on memory safety protection across our devices — without compromising our best-in-class device performance. We believe Memory Integrity Enforcement represents the most significant upgrade to memory safety in the history of consumer…

Super-LIO: A Robust and Efficient LiDAR-Inertial Odometry System with a Compact Mapping Strategy
Liansheng Wang, Xinke Zhang, Chenhui Li, Dongjiao He, Yihan Pan, Jianjun Yi
https://arxiv.org/abs/2509.05723

Super-LIO: A Robust and Efficient LiDAR-Inertial Odometry System with a Compact Mapping Strategy
LiDAR-Inertial Odometry (LIO) is a foundational technique for autonomous systems, yet its deployment on resource-constrained platforms remains challenging due to computational and memory limitations. We propose Super-LIO, a robust LIO system that demands both high performance and accuracy, ideal for applications such as aerial robots and mobile autonomous systems. At the core of Super-LIO is a compact octo-voxel-based map structure, termed OctVox, that limits each voxel to eight fused subvoxels…

Carrier-Assisted Entanglement Purification
Jaemin Kim, Karthik Mohan, Sung Won Yun, Joonwoo Bae
https://arxiv.org/abs/2509.07514 https://arxiv.org/pdf/2509…

Carrier-Assisted Entanglement Purification
Entanglement distillation, a fundamental building block of quantum networks, enables the purification of noisy entangled states shared among distant nodes by local operations and classical communication. Its practical realization presents several technical challenges, including the storage of quantum states in quantum memory and the execution of coherent quantum operations on multiple copies of states within the quantum memory. In this work, we present an entanglement purification protocol via …

MemTraceDB: Reconstructing MySQL User Activity Using ActiviTimeTrace Algorithm
Mahfuzul I. Nissan
https://arxiv.org/abs/2509.05891 https://arxiv.org/pdf/25…

MemTraceDB: Reconstructing MySQL User Activity Using ActiviTimeTrace Algorithm
Database audit and transaction logs are fundamental to forensic investigations, but they are vulnerable to tampering by privileged attackers. Malicious insiders or external threats with administrative access can alter, purge, or temporarily disable logging mechanisms, creating significant blind spots and rendering disk-based records unreliable. Memory analysis offers a vital alternative, providing investigators direct access to volatile artifacts that represent a ground-truth source of recent u…

OptPipe: Memory- and Scheduling-Optimized Pipeline Parallelism for LLM Training
Hongpei Li, Han Zhang, Huikang Liu, Dongdong Ge, Yinyu Ye
https://arxiv.org/abs/2510.05186 https:…

OptPipe: Memory- and Scheduling-Optimized Pipeline Parallelism for LLM Training
Pipeline parallelism (PP) has become a standard technique for scaling large language model (LLM) training across multiple devices. However, despite recent progress in reducing memory consumption through activation offloading, existing approaches remain largely heuristic and coarse-grained, often overlooking the fine-grained trade-offs between memory, computation, and scheduling latency. In this work, we revisit the pipeline scheduling problem from a principled optimization perspective. We obser…

Forecasting Russian Equipment Losses Using Time Series and Deep Learning Models
Jonathan Teagan
https://arxiv.org/abs/2509.07813 https://arxiv.org/pdf/2509…

Forecasting Russian Equipment Losses Using Time Series and Deep Learning Models
This study applies a range of forecasting techniques,including ARIMA, Prophet, Long Short Term Memory networks (LSTM), Temporal Convolutional Networks (TCN), and XGBoost, to model and predict Russian equipment losses during the ongoing war in Ukraine. Drawing on daily and monthly open-source intelligence (OSINT) data from WarSpotting, we aim to assess trends in attrition, evaluate model performance, and estimate future loss patterns through the end of 2025. Our findings show that deep learning …

A Comparative Analysis of Contextual Representation Flow in State-Space and Transformer Architectures
Nhat M. Hoang, Do Xuan Long, Cong-Duy Nguyen, Min-Yen Kan, Luu Anh Tuan
https://arxiv.org/abs/2510.06640

A Comparative Analysis of Contextual Representation Flow in State-Space and Transformer Architectures
State Space Models (SSMs) have recently emerged as efficient alternatives to Transformer-Based Models (TBMs) for long-sequence processing, offering linear scaling and lower memory use. Yet, how contextual information flows across layers and tokens in these architectures remains understudied. We present the first unified, token- and layer-level analysis of representation propagation in SSMs and TBMs. Using centered kernel alignment, stability metrics, and probing, we characterize how representat…

Co-TAP: Three-Layer Agent Interaction Protocol Technical Report
Shunyu An, Miao Wang, Yongchao Li, Dong Wan, Lina Wang, Ling Qin, Liqin Gao, Congyao Fan, Zhiyong Mao, Jiange Pu, Wenji Xia, Dong Zhao, Rui Hu, Ji Lu, Guiyue Zhou, Baoyu Tang, Yanqin Gao, Yongsheng Du, Daigang Xu, Lingjun Huang, Baoli Wang, Xiwen Zhang, Luyao Wang, Shilong Liu
https://

Co-TAP: Three-Layer Agent Interaction Protocol Technical Report
This paper proposes Co-TAP (T: Triple, A: Agent, P: Protocol), a three-layer agent interaction protocol designed to address the challenges faced by multi-agent systems across the three core dimensions of Interoperability, Interaction and Collaboration, and Knowledge Sharing. We have designed and proposed a layered solution composed of three core protocols: the Human-Agent Interaction Protocol (HAI), the Unified Agent Protocol (UAP), and the Memory-Extraction-Knowledge Protocol (MEK). HAI focuse…

cMPI: Using CXL Memory Sharing for MPI One-Sided and Two-Sided Inter-Node Communications
Xi Wang, Bin Ma, Jongryool Kim, Byungil Koh, Hoshik Kim, Dong Li
https://arxiv.org/abs/2510.05476

cMPI: Using CXL Memory Sharing for MPI One-Sided and Two-Sided Inter-Node Communications
Message Passing Interface (MPI) is a foundational programming model for high-performance computing. MPI libraries traditionally employ network interconnects (e.g., Ethernet and InfiniBand) and network protocols (e.g., TCP and RoCE) with complex software stacks for cross-node communication. We present cMPI, the first work to optimize MPI point-to-point communication (both one-sided and two-sided) using CXL memory sharing on a real CXL platform, transforming cross-node communication into memory t…

Mem0, which aims to build a "memory passport" so users' AI memory can travel across their devices, apps, and agents, raised $24M, including a $20M Series A (Tage Kene-Okafor/TechCrunch)
https://techcrunch.com/2025/10/28/mem0

Mem0 raises $24M from YC, Peak XV and Basis Set to build the memory layer for AI apps | TechCrunch
The idea of memory for AI isn’t new, but it’s quickly becoming a critical battleground.

Inspection Planning Primitives with Implicit Models
Jingyang You, Hanna Kurniawati, Lashika Medagoda
https://arxiv.org/abs/2510.07611 https://arxiv.org/pdf…

Inspection Planning Primitives with Implicit Models
The aging and increasing complexity of infrastructures make efficient inspection planning more critical in ensuring safety. Thanks to sampling-based motion planning, many inspection planners are fast. However, they often require huge memory. This is particularly true when the structure under inspection is large and complex, consisting of many struts and pillars of various geometry and sizes. Such structures can be represented efficiently using implicit models, such as neural Signed Distance Fun…

AttestLLM: Efficient Attestation Framework for Billion-scale On-device LLMs
Ruisi Zhang, Yifei Zhao, Neusha Javidnia, Mengxin Zheng, Farinaz Koushanfar
https://arxiv.org/abs/2509.06326

AttestLLM: Efficient Attestation Framework for Billion-scale On-device LLMs
As on-device LLMs(e.g., Apple on-device Intelligence) are widely adopted to reduce network dependency, improve privacy, and enhance responsiveness, verifying the legitimacy of models running on local devices becomes critical. Existing attestation techniques are not suitable for billion-parameter Large Language Models (LLMs), struggling to remain both time- and memory-efficient while addressing emerging threats in the LLM era. In this paper, we present AttestLLM, the first-of-its-kind attestatio…

Contrastive Self-Supervised Learning at the Edge: An Energy Perspective
Fernanda Fam\'a, Roberto Pereira, Charalampos Kalalas, Paolo Dini, Lorena Qendro, Fahim Kawsar, Mohammad Malekzadeh
https://arxiv.org/abs/2510.08374

Contrastive Self-Supervised Learning at the Edge: An Energy Perspective
While contrastive learning (CL) shows considerable promise in self-supervised representation learning, its deployment on resource-constrained devices remains largely underexplored. The substantial computational demands required for training conventional CL frameworks pose a set of challenges, particularly in terms of energy consumption, data availability, and memory usage. We conduct an evaluation of four widely used CL frameworks: SimCLR, MoCo, SimSiam, and Barlow Twins. We focus on the practi…

Replaced article(s) found for cs.DC. https://arxiv.org/list/cs.DC/new
[1/1]:
- KunServe: Parameter-centric Memory Management for Efficient Memory Overloading Handling in LLM Se...
Rongxin Cheng, Yuxin Lai, Xingda Wei, Rong Chen, Haibo Chen

Can SSD-Mamba2 Unlock Reinforcement Learning for End-to-End Motion Control?
Gavin Tao, Yinuo Wang, Jinzhao Zhou
https://arxiv.org/abs/2509.07593 https://ar…

Can SSD-Mamba2 Unlock Reinforcement Learning for End-to-End Motion Control?
End-to-end reinforcement learning for motion control promises unified perception-action policies that scale across embodiments and tasks, yet most deployed controllers are either blind (proprioception-only) or rely on fusion backbones with unfavorable compute-memory trade-offs. Recurrent controllers struggle with long-horizon credit assignment, and Transformer-based fusion incurs quadratic cost in token length, limiting temporal and spatial context. We present a vision-driven cross-modal RL fra…

ArcMemo: Abstract Reasoning Composition with Lifelong LLM Memory
Matthew Ho, Chen Si, Zhaoxiang Feng, Fangxu Yu, Zhijian Liu, Zhiting Hu, Lianhui Qin
https://arxiv.org/abs/2509.04439

ArcMemo: Abstract Reasoning Composition with Lifelong LLM Memory
While inference-time scaling enables LLMs to carry out increasingly long and capable reasoning traces, the patterns and insights uncovered during these traces are immediately discarded once the context window is reset for a new query. External memory is a natural way to persist these discoveries, and recent work has shown clear benefits for reasoning-intensive tasks. We see an opportunity to make such memories more broadly reusable and scalable by moving beyond instance-based memory entries (e.…

The AI boom is driving memory and storage shortages that may last a decade; OpenAI's Stargate has deals for 900K DRAM wafers per month, or ~40% of global output (Luke James/Tom's Hardware)
https://www.tomshardware.com/pc-components

AI data centers are swallowing the world's memory and storage supply, setting the stage for a pricing apocalypse that could last a decade
Once-cheap SSDs, DRAM, and HDD prices are climbing fast as AI demand and constrained supply converge to create the tightest market in years.

High-Rate Surgery: towards constant-overhead logical operations
Guo Zheng, Liang Jiang, Qian Xu
https://arxiv.org/abs/2510.08523 https://arxiv.org/pdf/2510…

High-Rate Surgery: towards constant-overhead logical operations
Scalable quantum computation requires not only quantum codes with low memory overhead but also encoded operations with low space-time overhead. High rate quantum low-density parity-check (qLDPC) codes address the former by achieving a high information-encoding rate, yet existing methods for implementing logical operations often suffer from a low information-processing rate, leading to substantial space-time costs. Here, we introduce high-rate surgery, a general scheme that can perform extensive…

Iterative model of self-referential quantum evolution
Andrei Galiautdinov
https://arxiv.org/abs/2509.07940 https://arxiv.org/pdf/2509.07940

Iterative model of self-referential quantum evolution
We introduce and analyze a toy model of a quantum physical device capable of internal, self-referential deliberation, realized through iterative, branch-dependent unitary evolution tracked by control, memory, and policy registers. The key idea is to represent ``deliberation'' as a coherent branching process, in which alternative candidate evolutions are maintained in superposition across registers, rather than by placing the system itself under a literal superposition of Hamiltonians. We provid…

Dissipation-Enhanced Localization in a Disorder-Free $\mathbb{Z}_2$ Lattice Gauge System
Xuanpu Yang, Xiang-Ping Jiang, Lei Pan
https://arxiv.org/abs/2509.06642 https://

Dissipation-Enhanced Localization in a Disorder-Free $\mathbb{Z}_2$ Lattice Gauge System
The $\mathbb{Z}_2$ lattice gauge model, as the simplest realization of a lattice gauge theory, exhibits rich and unconventional physics. One of its most remarkable features is disorder-free localization, where localization emerges not from explicit quenched disorder but from static background $\mathbb{Z}_2$ gauge charges, leading to persistent memory of the initial state. In this work, we investigate the dissipative dynamics of the $\mathbb{Z}_2$ lattice gauge model by coupling it to a Markovia…

Safe Memory Reclamation Techniques
Ajay Singh
https://arxiv.org/abs/2509.02457 https://arxiv.org/pdf/2509.02457

Safe Memory Reclamation Techniques
Safe memory reclamation is crucial to memory safety for optimistic and lock-free concurrent data structures in non garbage collected programming languages. However, several challenges arise in designing an ideal safe memory reclamation algorithm, including achieving high speed and scalability, easy of use for programmers, applicability to wide class of data structures, managing the large memory footprint caused by delayed freeing of memory for safety and performance, and avoiding asymmetric ove…