Tootfinder

from my link log —
Dynamic witnesses for static type errors in OCaml, or, ill-typed programs usually go wrong.
https://arxiv.org/abs/1606.07557
saved 2025-05-31

Dynamic Witnesses for Static Type Errors (or, Ill-Typed Programs Usually Go Wrong)
Static type errors are a common stumbling block for newcomers to typed functional languages. We present a dynamic approach to explaining type errors by generating counterexample witness inputs that illustrate how an ill-typed program goes wrong. First, given an ill-typed function, we symbolically execute the body to synthesize witness values that make the program go wrong. We prove that our procedure synthesizes general witnesses in that if a witness is found, then for all inhabited input types…

Taming Uncertainty via Automation: Observing, Analyzing, and Optimizing Agentic AI Systems
Dany Moshkovich, Sergey Zeltyn
https://arxiv.org/abs/2507.11277 …

Taming Uncertainty via Automation: Observing, Analyzing, and Optimizing Agentic AI Systems
Large Language Models (LLMs) are increasingly deployed within agentic systems-collections of interacting, LLM-powered agents that execute complex, adaptive workflows using memory, tools, and dynamic planning. While enabling powerful new capabilities, these systems also introduce unique forms of uncertainty stemming from probabilistic reasoning, evolving memory states, and fluid execution paths. Traditional software observability and operations practices fall short in addressing these challenges…

NemeSys: An Online Underwater Explorer with Goal-Driven Adaptive Autonomy
Adnan Abdullah, Alankrit Gupta, Vaishnav Ramesh, Shivali Patel, Md Jahidul Islam
https://arxiv.org/abs/2507.11889

NemeSys: An Online Underwater Explorer with Goal-Driven Adaptive Autonomy
Adaptive mission control and dynamic parameter reconfiguration are essential for autonomous underwater vehicles (AUVs) operating in GPS-denied, communication-limited marine environments. However, most current AUV platforms execute static, pre-programmed missions or rely on tethered connections and high-latency acoustic channels for mid-mission updates, significantly limiting their adaptability and responsiveness. In this paper, we introduce NemeSys, a novel AUV system designed to support real-t…

Pete Carroll talks Preseason Week 2: 'I want to see us execute' https://www.raiders.com/video/pete-carroll-raiders-training-camp-preseason-week-2-presser-08142025

Envisage: Towards Expressive Visual Graph Querying
Xiaolin Wen, Qishuang Fu, Shuangyue Han, Yichen Guo, Joseph K. Liu, Yong Wang
https://arxiv.org/abs/2507.11999

Envisage: Towards Expressive Visual Graph Querying
Graph querying is the process of retrieving information from graph data using specialized languages (e.g., Cypher), often requiring programming expertise. Visual Graph Querying (VGQ) streamlines this process by enabling users to construct and execute queries via an interactive interface without resorting to complex coding. However, current VGQ tools only allow users to construct simple and specific query graphs, limiting users' ability to interactively express their query intent, especially for…

Consumer Law for AI Agents
Christoph Busch
https://arxiv.org/abs/2507.11567 https://arxiv.org/pdf/2507.11567

Consumer Law for AI Agents
Since the public release of ChatGPT in November 2022, the AI landscape is undergoing a rapid transformation. Currently, the use of AI chatbots by consumers has largely been limited to image generation or question-answering language models. The next generation of AI systems, AI agents that can plan and execute complex tasks with only limited human involvement, will be capable of a much broader range of actions. In particular, consumers could soon be able to delegate purchasing decisions to AI ag…

PuDHammer: Experimental Analysis of Read Disturbance Effects of Processing-using-DRAM in Real DRAM Chips
Ismail Emir Yuksel, Akash Sood, Ataberk Olgun, O\u{g}uzhan Canpolat, Haocong Luo, F. Nisa Bostanc{\i}, Mohammad Sadrosadati, A. Giray Ya\u{g}l{\i}k\c{c}{\i}, Onur Mutlu
https://arxiv.org/abs/2506.12947

PuDHammer: Experimental Analysis of Read Disturbance Effects of Processing-using-DRAM in Real DRAM Chips
Processing-using-DRAM (PuD) is a promising paradigm for alleviating the data movement bottleneck using DRAM's massive internal parallelism and bandwidth to execute very wide operations. Performing a PuD operation involves activating multiple DRAM rows in quick succession or simultaneously, i.e., multiple-row activation. Multiple-row activation is fundamentally different from conventional memory access patterns that activate one DRAM row at a time. However, repeatedly activating even one DRAM ro…

Surfing the SWAVES: Lifecycle-aware Service Placement in MEC
Federico Giarr\`e, Holger Karl
https://arxiv.org/abs/2506.12265 https://…

Surfing the SWAVES: Lifecycle-aware Service Placement in MEC
In Multi-access Edge Computing (MEC) networks, users covered by a mobile network can exploit edge clouds (ECs), computational resources located at the network's edge, to execute virtual network functions (VNFs). ECs are particularly useful when deploying VNFs with strict delay and availability requirements. As users roam in the network and get handed over between cells, deployed VNFs must follow users to retain the benefits of edge computing. Yet, having VNFs ready at the closest EC can be chal…

Learn from previous runs to improve future automation and save plans in a gallery for reuse.
🔀 Parallel execution
Run multiple tasks simultaneously with status indicators for efficient workflow management.
🌐 Web automation
Browse websites, fill forms, navigate deep sites not indexed by search engines, with real-time browser view.
💻 Code execution
Generate and execute code alongside web browsing for comprehensive task automation capabilities.
🔗

Supreme Court to hear Alabama appeal in push to execute intellectually disabled man | The Independent
https://www.independent.co.uk/news/world/americas/supreme-court-execute-intellectually-disabled-joseph-clifton-smith-b2765542.html

@… The public hosted Renovate runs with some extra security measures so you can't execute any code on their systems. Which is fair. So one of the features that I want to use needs https://…

From Leadnow
urgent petition from Leadnow supporter Leslie, who is calling on the federal government to immediately end its contracts with GardaWorld — the Canadian company staffing a new ICE immigration detention facility in the U.S. called Alligator Alcatraz.
GardaWorld — a Canadian-based “private security company” — has million-dollar contracts to execute Trump's racist and inhumane immigration regime, which kidnaps people, tears families apart, and denies people due proc…

A Canonical Bijection Between Finite-Decimal Real Numbers and Natural Numbers with Constant-Time Enumeration Formulas
S. K. Rithvik
https://arxiv.org/abs/2508.10750 https://

A Canonical Bijection Between Finite-Decimal Real Numbers and Natural Numbers with Constant-Time Enumeration Formulas
We present an explicit bijection between finite-decimal real numbers and natural numbers ($\mathbb{N} = \{1, 2, 3, ...\}$) using a systematic 4-tuple parametrization with closed-form mathematical formulas for enumeration. Our enumeration system provides complete indexing of all real numbers with terminating decimal representations through the parametrization $(\text{sign}, N_1, N_2, N_3)$. Both forward and inverse mappings execute in O(1) constant time, achieved through closed-form lexicographi…

Series C, Episode 03 - Volcano
TARRANT: Well, let's go, while we can.
AVON: Execute preprogrammed course.
ZEN: Confirmed.
DAYNA: I didn't believe they'd do it.
TARRANT: Neither did Servalan.
https://blake.torpidity.net/m/303/650 B7B5

Goldman Sachs CTO Marco Argenti says the bank is "going to start augmenting our workforce with Devin", Cognition's AI coding assistant, as Wall Street adopts AI (Hugh Son/CNBC)
https://www.cnbc.com/2025/07/11/goldman-sachs-auto…

Goldman Sachs is piloting its first autonomous coder in major AI milestone for Wall Street
The arrival of agentic AI at Goldman Sachs, in which programs don't just help with tasks but execute complex jobs, signals a shift on Wall Street.

Cybercriminals are using AI to execute highly targeted attacks at scale, causing people to unwittingly send money and sensitive information or simply open themselves up to theft.
Hackers are now able to rent generative AI large language models created in the underground cybercrime community to help formulate text-based scams.
But just as generative AI is enhancing and scaling social engineering attacks, so too is it giving defenders a leg up.

The hacking underworld has removed all of AI's guardrails, but the good guys are closing in
Fake Taylor Swift ads and malicious QR codes are just some of the newest ways cybercriminals are using AI as the cat-and-mouse cybersecurity game heats up.

Finally a useful magic quadrant
Thanks to @… for the discovery.
#cybersecurity #vulnerability

Today I finally remembered the syntax to delete a remote git branch: `git push origin --delete 42_not_needed_branch` (and was brave enought to just execute it without checking, yolo)

How Quantum Agents Can Change Which Strategies Are More Complex
Spiros Kechrimparis, Nix Barnett, Mile Gu, Hyukjoon Kwon
https://arxiv.org/abs/2508.08092 https://

How Quantum Agents Can Change Which Strategies Are More Complex
Whether winning blackjack or navigating busy streets, achieving desired outcomes requires agents to execute adaptive strategies, strategies where actions depend contextually on past events. In complexity science, this motivates memory as an operational quantifier of complexity: given two strategies, the more complex one demands the agent to track more about the past. Here, we show that conclusions about complexity fundamentally depend on whether agents can process and store quantum information.…

from my link log —
Distance-based ISA for efficient register renaming.
https://www.sigarch.org/distance-based-isa-for-efficient-register-management/
saved 2025-06-04

Distance-Based ISA for Efficient Register Management
CPU cores have become significantly wider over the past decade. Ten years ago, the highest-performance CPUs could decode only up to four instructions simultaneously and execute up to eight instruct…

SHIELDA: Structured Handling of Exceptions in LLM-Driven Agentic Workflows
Jingwen Zhou, Jieshan Chen, Qinghua Lu, Dehai Zhao, Liming Zhu
https://arxiv.org/abs/2508.07935 https:…

SHIELDA: Structured Handling of Exceptions in LLM-Driven Agentic Workflows
Large Language Model (LLM) agentic systems are software systems powered by LLMs that autonomously reason, plan, and execute multi-step workflows to achieve human goals, rather than merely executing predefined steps. During execution, these workflows frequently encounter exceptions. Existing exception handling solutions often treat exceptions superficially, failing to trace execution-phase exceptions to their reasoning-phase root causes. Furthermore, their recovery logic is brittle, lacking stru…

TooBadRL: Trigger Optimization to Boost Effectiveness of Backdoor Attacks on Deep Reinforcement Learning
Songze Li, Mingxuan Zhang, Oubo Ma, Kang Wei, Shouling Ji
https://arxiv.org/abs/2506.09562

TooBadRL: Trigger Optimization to Boost Effectiveness of Backdoor Attacks on Deep Reinforcement Learning
Deep reinforcement learning (DRL) has achieved remarkable success in a wide range of sequential decision-making domains, including robotics, healthcare, smart grids, and finance. Recent research demonstrates that attackers can efficiently exploit system vulnerabilities during the training phase to execute backdoor attacks, producing malicious actions when specific trigger patterns are present in the state observations. However, most existing backdoor attacks rely primarily on simplistic and heu…

PyVision: Agentic Vision with Dynamic Tooling
Shitian Zhao, Haoquan Zhang, Shaoheng Lin, Ming Li, Qilong Wu, Kaipeng Zhang, Chen Wei
https://arxiv.org/abs/2507.07998

PyVision: Agentic Vision with Dynamic Tooling
LLMs are increasingly deployed as agents, systems capable of planning, reasoning, and dynamically calling external tools. However, in visual reasoning, prior approaches largely remain limited by predefined workflows and static toolsets. In this report, we present PyVision, an interactive, multi-turn framework that enables MLLMs to autonomously generate, execute, and refine Python-based tools tailored to the task at hand, unlocking flexible and interpretable problem-solving. We develop a taxonom…

Convergence Sans Synchronization
Arya Tanmay Gupta
https://arxiv.org/abs/2508.06949 https://arxiv.org/pdf/2508.06949

Convergence Sans Synchronization
We currently see a steady rise in the usage and size of multiprocessor systems, and so the community is evermore interested in developing fast parallel processing algorithms. However, most algorithms require a synchronization mechanism, which is costly in terms of computational resources and time. If an algorithm can be executed in asynchrony, then it can use all the available computation power, and the nodes can execute without being scheduled or locked. However, to show that an algorithm guar…

Reading Command output line by line
Sometimes, you want to execute a system command from within a Go app and process it's output line-by-line in a streaming fashion.
https://www.yellowduck.be/posts/reading-command-output-line-by-line/

A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges
Yunjia Xi, Jianghao Lin, Yongzhao Xiao, Zheli Zhou, Rong Shan, Te Gao, Jiachen Zhu, Weiwen Liu, Yong Yu, Weinan Zhang
https://arxiv.org/abs/2508.05668

A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges
The advent of Large Language Models (LLMs) has significantly revolutionized web search. The emergence of LLM-based Search Agents marks a pivotal shift towards deeper, dynamic, autonomous information seeking. These agents can comprehend user intentions and environmental context and execute multi-turn retrieval with dynamic planning, extending search capabilities far beyond the web. Leading examples like OpenAI's Deep Research highlight their potential for deep information mining and real-world a…

🎯 Why Developers Are Going Crazy For It
1. True Agentic Intelligence 🤝
Unlike traditional chatbots, Kimi K2 can: • Plan and execute multi-step tasks autonomously • Use tools and APIs intelligently • Handle complex workflows without human intervention • Adapt strategies based on real-time feedback

OK so, let's see how far I can get figuring out the VSC8512 SERDES stuff without any nonpublic information.
It looks like everything fun is accessed via register 18G "global command and serdes configuration".
This is a 16-bit register which is basically a mailbox to the internal MCU.
Bit 15 (0x8000) is documented as "execute command". This always has to be set when writing to the PHY, then you wait for it to be cleared before doing anything else. Tha…

#InfoSec

The new Mastodon version seems to shit itself on Safari? The Home/Trending/etc links don't work when clicked. And then after a few minutes they start working again, randomly. I only have this in the console.
Anybody using Safari here? v18.5
#mastodon

Trump calls up nonimmigration officers to help execute ICE deportation operation (Anna Giaritelli/Washington Examiner)
https://www.washingtonexaminer.com/news/3460118/doj-dhs-diverted-assist-ice-deportations-illegal-immigrants-trump/
http://www.memeorandum.com/250702/p61#a250702p61

Data Center Appliance: »A data center appliance is a ready-to-use device that integrates key software and hardware components to execute a specific IT function. It is a functional unit comprised of hardware and software designed for a specific, often narrowly defined, purpose.« 🤡🤯 #buzzworddetective

Grounded Vision-Language Navigation for UAVs with Open-Vocabulary Goal Understanding
Yuhang Zhang, Haosheng Yu, Jiaping Xiao, Mir Feroskhan
https://arxiv.org/abs/2506.10756

Grounded Vision-Language Navigation for UAVs with Open-Vocabulary Goal Understanding
Vision-and-language navigation (VLN) is a long-standing challenge in autonomous robotics, aiming to empower agents with the ability to follow human instructions while navigating complex environments. Two key bottlenecks remain in this field: generalization to out-of-distribution environments and reliance on fixed discrete action spaces. To address these challenges, we propose Vision-Language Fly (VLFly), a framework tailored for Unmanned Aerial Vehicles (UAVs) to execute language-guided flight.…

AI Agents and the Law
Mark O. Riedl, Deven R. Desai
https://arxiv.org/abs/2508.08544 https://arxiv.org/pdf/2508.08544…

AI Agents and the Law
As AI becomes more "agentic," it faces technical and socio-legal issues it must address if it is to fulfill its promise of increased economic productivity and efficiency. This paper uses technical and legal perspectives to explain how things change when AI systems start being able to directly execute tasks on behalf of a user. We show how technical conceptions of agents track some, but not all, socio-legal conceptions of agency. That is, both computer science and the law recognize the problems …

I've just found out that the nano text editor can sort lines by pressing Ctrl-T (execute any command on marked lines) and then entering "| sort" (like in a shell pipe).
https://unix.stackexchange.com/a/717925

Open Source Planning & Control System with Language Agents for Autonomous Scientific Discovery
Licong Xu, Milind Sarkar, Anto I. Lonappan, \'I\~nigo Zubeldia, Pablo Villanueva-Domingo, Santiago Casas, Christian Fidler, Chetana Amancharla, Ujjwal Tiwari, Adrian Bayer, Chadi Ait Ekiou, Miles Cranmer, Adrian Dimitrov, James Fergusson, Kahaan Gandhi, Sven Krippendorf, Andrew Laverick, Julien Lesgourgues, Antony Lewis, Thomas Meier, Blake Sherwin, Kristen Surrao, Francisco Villaescu…

Open Source Planning & Control System with Language Agents for Autonomous Scientific Discovery
We present a multi-agent system for automation of scientific research tasks, cmbagent. The system is formed by about 30 Large Language Model (LLM) agents and implements a Planning & Control strategy to orchestrate the agentic workflow, with no human-in-the-loop at any point. Each agent specializes in a different task (performing retrieval on scientific papers and codebases, writing code, interpreting results, critiquing the output of other agents) and the system is able to execute code locally.…

Reasoning to Edit: Hypothetical Instruction-Based Image Editing with Visual Reasoning
Qingdong He, Xueqin Chen, Chaoyi Wang, Yanjie Pan, Xiaobin Hu, Zhenye Gan, Yabiao Wang, Chengjie Wang, Xiangtai Li, Jiangning Zhang
https://arxiv.org/abs/2507.01908

Reasoning to Edit: Hypothetical Instruction-Based Image Editing with Visual Reasoning
Instruction-based image editing (IIE) has advanced rapidly with the success of diffusion models. However, existing efforts primarily focus on simple and explicit instructions to execute editing operations such as adding, deleting, moving, or swapping objects. They struggle to handle more complex implicit hypothetical instructions that require deeper reasoning to infer plausible visual changes and user intent. Additionally, current datasets provide limited support for training and evaluating rea…

Your Agent Can Defend Itself against Backdoor Attacks
Li Changjiang, Liang Jiacheng, Cao Bochuan, Chen Jinghui, Wang Ting
https://arxiv.org/abs/2506.08336 …

Your Agent Can Defend Itself against Backdoor Attacks
Despite their growing adoption across domains, large language model (LLM)-powered agents face significant security risks from backdoor attacks during training and fine-tuning. These compromised agents can subsequently be manipulated to execute malicious operations when presented with specific triggers in their inputs or environments. To address this pressing risk, we present ReAgent, a novel defense against a range of backdoor attacks on LLM-based agents. Intuitively, backdoor attacks often res…

from my link log —
Tracking source locations for profiling GPU programs in Futhark.
https://futhark-lang.org/blog/2025-07-29-tracking-source-locations.html
saved 2025-08-01

Execution-Feedback Driven Test Generation from SWE Issues
Toufique Ahmed, Jatin Ganhotra, Avraham Shinnar, Martin Hirzel
https://arxiv.org/abs/2508.06365 https://

Execution-Feedback Driven Test Generation from SWE Issues
A software engineering issue (SWE issue) is easier to resolve when accompanied by a reproduction test. Unfortunately, most issues do not come with functioning reproduction tests, so this paper explores how to generate them automatically. The primary challenge in this setting is that the code to be tested is either missing or wrong, as evidenced by the existence of the issue in the first place. This has held back test generation for this setting: without the correct code to execute, it is diffic…

This https://arxiv.org/abs/2505.16764 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csPL_…

Can a domain-specific language improve program structure comprehension of data pipelines? A mixed-methods study
In many application domains, domain-specific languages can allow domain experts to contribute to collaborative projects more correctly and efficiently. To do so, they must be able to understand program structure from reading existing source code. With high-quality data becoming an increasingly important resource, the creation of data pipelines is an important application domain for domain-specific languages. We execute a mixed-method study consisting of a controlled experiment and a follow-up…

Wait-Only Broadcast Protocols are Easier to Verify
Lucie Guillou, Arnaud Sangnier, Nathalie Sznajder
https://arxiv.org/abs/2506.22144 https://

Wait-Only Broadcast Protocols are Easier to Verify
We study networks of processes that all execute the same finite-state protocol and communicate via broadcasts. We are interested in two problems with a parameterized number of processes: the synchronization problem which asks whether there is an execution which puts all processes on a given state; and the repeated coverability problem which asks if there is an infinite execution where a given transition is taken infinitely often. Since both problems are undecidable in the general case, we inves…

@… Under hospitals in Israel are refuges to protect the patients and staffs from bombing. Under hospitals in Gaza are military facilities used to plan & execute bombings of civilian targets in Israel.

This https://arxiv.org/abs/2502.10090 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Manual2Skill: Learning to Read Manuals and Acquire Robotic Skills for Furniture Assembly Using Vision-Language Models
Humans possess an extraordinary ability to understand and execute complex manipulation tasks by interpreting abstract instruction manuals. For robots, however, this capability remains a substantial challenge, as they cannot interpret abstract instructions and translate them into executable actions. In this paper, we present Manual2Skill, a novel framework that enables robots to perform complex assembly tasks guided by high-level manual instructions. Our approach leverages a Vision-Language Mode…

De-AntiFake: Rethinking the Protective Perturbations Against Voice Cloning Attacks
Wei Fan, Kejiang Chen, Chang Liu, Weiming Zhang, Nenghai Yu
https://arxiv.org/abs/2507.02606

De-AntiFake: Rethinking the Protective Perturbations Against Voice Cloning Attacks
The rapid advancement of speech generation models has heightened privacy and security concerns related to voice cloning (VC). Recent studies have investigated disrupting unauthorized voice cloning by introducing adversarial perturbations. However, determined attackers can mitigate these protective perturbations and successfully execute VC. In this study, we conduct the first systematic evaluation of these protective perturbations against VC under realistic threat models that include perturbatio…

W przypadku #PyPy, przyczyną jest zawsze jakiś wyciek zasobów…
https://github.com/vutran1710/PyrateLimiter/pull/205

Petri Net Modeling and Deadlock-Free Scheduling of Attachable Heterogeneous AGV Systems
Boyu Li, Zhengchen Li, Weimin Wu, Mengchu Zhou
https://arxiv.org/abs/2508.00724 https://

Petri Net Modeling and Deadlock-Free Scheduling of Attachable Heterogeneous AGV Systems
The increasing demand for automation and flexibility drives the widespread adoption of heterogeneous automated guided vehicles (AGVs). This work intends to investigate a new scheduling problem in a material transportation system consisting of attachable heterogeneous AGVs, namely carriers and shuttles. They can flexibly attach to and detach from each other to cooperatively execute complex transportation tasks. While such collaboration enhances operational efficiency, the attachment-induced sync…

20-GHz bandwidth optical activation function based on a semiconductor laser
Hai-Fei Guo, Zheng-Can Sun, Yi-Wei Shen, Rui-Qian Li, Xing Li, Cheng Wang
https://arxiv.org/abs/2507.00468

20-GHz bandwidth optical activation function based on a semiconductor laser
Optical neural networks usually execute the linear multiply-accumulate operation in the optical domain, whereas the nonlinear activation function is mostly implemented in the digital or electrical domain. Here we demonstrate a broadband activation function operated in the optical domain. The optical activation function (OAF) is achieved by a semiconductor laser with optical injection, which is operated in the unstable-locked regime above the Hopf bifurcation. The operation bandwidth of the OAF …

Hijacking JARVIS: Benchmarking Mobile GUI Agents against Unprivileged Third Parties
Guohong Liu, Jialei Ye, Jiacheng Liu, Yuanchun Li, Wei Liu, Pengzhi Gao, Jian Luan, Yunxin Liu
https://arxiv.org/abs/2507.04227

Hijacking JARVIS: Benchmarking Mobile GUI Agents against Unprivileged Third Parties
Mobile GUI agents are designed to autonomously execute diverse device-control tasks by interpreting and interacting with mobile screens. Despite notable advancements, their resilience in real-world scenarios where screen content may be partially manipulated by untrustworthy third parties remains largely unexplored. Owing to their black-box and autonomous nature, these agents are vulnerable to manipulations that could compromise user devices. In this work, we present the first systematic investi…

Knowledge-Guided Attention-Inspired Learning for Task Offloading in Vehicle Edge Computing
Ke Ma, Junfei Xie
https://arxiv.org/abs/2506.04456 https://

Knowledge-Guided Attention-Inspired Learning for Task Offloading in Vehicle Edge Computing
Vehicle edge computing (VEC) brings abundant computing resources close to vehicles by deploying them at roadside units (RSUs) or base stations, thereby enabling diverse computation-intensive and delay sensitive applications. Existing task offloading strategies are often computationally expensive to execute or generate suboptimal solutions. In this paper, we propose a novel learning-based approach, Knowledge-guided Attention-inspired Task Offloading (KATO), designed to efficiently offload tasks …

Intercepting 3I/ATLAS at Closest Approach to Jupiter with the Juno spacecraft
Abraham Loeb, Adam Hibberd, Adam Crowl
https://arxiv.org/abs/2507.21402 https://

Intercepting 3I/ATLAS at Closest Approach to Jupiter with the Juno spacecraft
The interstellar object 3I/ATLAS is expected to arrive at a distance of $53.56(\pm 0.45)$ million ${\rm km}$ ($0.358\pm 0.003$~au) from Jupiter on March 16, 2026. We show that applying a total thrust $Δ$V of $2.6755{\rm km~s^{-1}}$ to lower perijove on September 9, 2025 and then execute a Jupiter Oberth Maneuver, can bring the Juno spacecraft from its orbit around Jupiter to intercept the path of 3I/ATLAS on March 14, 2026. A close fly-by might be able to probe the nature of 3I/ATLAS far bette…

Phi-Ground Tech Report: Advancing Perception in GUI Grounding
Miaosen Zhang, Ziqiang Xu, Jialiang Zhu, Qi Dai, Kai Qiu, Yifan Yang, Chong Luo, Tianyi Chen, Justin Wagle, Tim Franklin, Baining Guo
https://arxiv.org/abs/2507.23779

Phi-Ground Tech Report: Advancing Perception in GUI Grounding
With the development of multimodal reasoning models, Computer Use Agents (CUAs), akin to Jarvis from \textit{"Iron Man"}, are becoming a reality. GUI grounding is a core component for CUAs to execute actual actions, similar to mechanical control in robotics, and it directly leads to the success or failure of the system. It determines actions such as clicking and typing, as well as related parameters like the coordinates for clicks. Current end-to-end grounding models still achieve less than 65\…

from my link log —
Implement your programming language twice.
https://futhark-lang.org/blog/2025-05-07-implement-your-language-twice.html
saved 2025-05-08

This https://arxiv.org/abs/2505.23073 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAR_…

DX100: A Programmable Data Access Accelerator for Indirection
Indirect memory accesses frequently appear in applications where memory bandwidth is a critical bottleneck. Prior indirect memory access proposals, such as indirect prefetchers, runahead execution, fetchers, and decoupled access/execute architectures, primarily focus on improving memory access latency by loading data ahead of computation but still rely on the DRAM controllers to reorder memory requests and enhance memory bandwidth utilization. DRAM controllers have limited visibility to future …

Real-Time Iteration Scheme for Diffusion Policy
Yufei Duan, Hang Yin, Danica Kragic
https://arxiv.org/abs/2508.05396 https://arxiv.org/pdf/2508.05396

Real-Time Iteration Scheme for Diffusion Policy
Diffusion Policies have demonstrated impressive performance in robotic manipulation tasks. However, their long inference time, resulting from an extensive iterative denoising process, and the need to execute an action chunk before the next prediction to maintain consistent actions limit their applicability to latency-critical tasks or simple tasks with a short cycle time. While recent methods explored distillation or alternative policy structures to accelerate inference, these often demand addi…

Agent-based Liquidity Risk Modelling for Financial Markets
Perukrishnen Vytelingum, Rory Baggott, Namid Stillman, Jianfei Zhang, Dingqiu Zhu, Tao Chen, Justin Lyon
https://arxiv.org/abs/2505.15296

Agent-based Liquidity Risk Modelling for Financial Markets
In this paper, we describe a novel agent-based approach for modelling the transaction cost of buying or selling an asset in financial markets, e.g., to liquidate a large position as a result of a margin call to meet financial obligations. The simple act of buying or selling in the market causes a price impact and there is a cost described as liquidity risk. For example, when selling a large order, there is market slippage -- each successive trade will execute at the same or worse price. When th…

Simpler, Better, Faster, Stronger: Revisiting a Successful Reduction Rule for Dominating Set
Lukas Geis, Alexander Leonhardt, Johannes Meintrup, Ulrich Meyer, Manuel Penschuck
https://arxiv.org/abs/2506.14564

Simpler, Better, Faster, Stronger: Revisiting a Successful Reduction Rule for Dominating Set
DominatingSet is a classical NP-complete problem and also known to be W[2]-hard. Thus, there is little hope for small kernels on general graphs. However, in practice, reduction rules to heuristically shrink instances are used. In this context, Rule1 by Alber et. al. is quite successful, yet at times somewhat expensive to execute. We propose a linear time algorithm implementing and surpassing the original Rule1 formulation. Our discussions and proofs yield interesting structural insights into th…

Quantum Circuit Caches and Compressors for Low Latency, High Throughput Computing
Ioana Moflic, Alan Robertson, Simon J. Devitt, Alexandru Paler
https://arxiv.org/abs/2507.20677

Quantum Circuit Caches and Compressors for Low Latency, High Throughput Computing
Utility-scale quantum programs contain operations on the order of $>10^{15}$ which must be prepared and piped from a classical co-processor to the control unit of the quantum device. The latency of this process significantly increases with the size of the program: existing high-level classical representations of quantum programs are typically memory intensive and do not naïvely efficiently scale to the degree required to execute utility-scale programs in real-time. To combat this limitation, w…

Budget Allocation Policies for Real-Time Multi-Agent Path Finding
Raz Beck, Roni Stern
https://arxiv.org/abs/2507.16874 https://arxiv.org/pdf/2507.16874

Budget Allocation Policies for Real-Time Multi-Agent Path Finding
Multi-Agent Pathfinding (MAPF) is the problem of finding paths for a set of agents such that each agent reaches its desired destination while avoiding collisions with the other agents. Many MAPF solvers are designed to run offline, that is, first generate paths for all agents and then execute them. Real-Time MAPF (RT-MAPF) embodies a realistic MAPF setup in which one cannot wait until a complete path for each agent has been found before they start to move. Instead, planning and execution are in…

A System Level Compiler for Massively-Parallel, Spatial, Dataflow Architectures
Dirk Van Essendelft, Patrick Wingo, Terry Jordan, Ryan Smith, Wissam Saidi
https://arxiv.org/abs/2506.15875

A System Level Compiler for Massively-Parallel, Spatial, Dataflow Architectures
We have developed a novel compiler called the Multiple-Architecture Compiler for Advanced Computing Hardware (MACH) designed specifically for massively-parallel, spatial, dataflow architectures like the Wafer Scale Engine. Additionally, MACH can execute code on traditional unified-memory devices. MACH addresses the complexities in compiling for spatial architectures through a conceptual Virtual Machine, a flexible domain-specific language, and a compiler that can lower high-level languages to m…

from my link log —
Decomposing transactional systems.
https://transactional.blog/blog/2025-decomposing-transactional-systems
saved 2025-04-18

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges
Lajos Muzsai, David Imolai, Andr\'as Luk\'acs
https://arxiv.org/abs/2506.02048

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges
Large Language Models (LLMs) still struggle with the structured reasoning and tool-assisted computation needed for problem solving in cybersecurity applications. In this work, we introduce "random-crypto", a cryptographic Capture-the-Flag (CTF) challenge generator framework that we use to fine-tune a tool-augmented Llama-3.1-8B with Guided Reinforcement Prompt Optimisation (GRPO), allowing the agent to iteratively write and execute Python inside an isolated REPL. GRPO yields a +53% absolute jum…

DeepGo: Predictive Directed Greybox Fuzzing
Peihong Lin, Pengfei Wang, Xu Zhou, Wei Xie, Gen Zhang, Kai Lu
https://arxiv.org/abs/2507.21952 https://arxiv.o…

DeepGo: Predictive Directed Greybox Fuzzing
The state-of-the-art DGF techniques redefine and optimize the fitness metric to reach the target sites precisely and quickly. However, optimizations for fitness metrics are mainly based on heuristic algorithms, which usually rely on historical execution information and lack foresight on paths that have not been exercised yet. Thus, those hard-to-execute paths with complex constraints would hinder DGF from reaching the targets, making DGF less efficient. In this paper, we propose DeepGo, a predi…

Optimization and Synthesis of Quantum Circuits with Global Gates
Alejandro Villoria, Henning Basold, Alfons Laarman
https://arxiv.org/abs/2507.20694 https://

Optimization and Synthesis of Quantum Circuits with Global Gates
Compiling quantum circuits to account for hardware restrictions is an essential part of the quantum computing stack. Circuit compilation allows us to adapt algorithm descriptions into a sequence of operations supported by real quantum hardware, and has the potential to significantly improve their performance when optimization techniques are added to the process. One such optimization technique is reducing the number of quantum gates that are needed to execute a circuit. For instance, methods fo…

This https://arxiv.org/abs/2505.14314 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAR_…

Low-Cost FlashAttention with Fused Exponential and Multiplication Hardware Operators
Attention mechanisms, particularly within Transformer architectures and large language models (LLMs), have revolutionized sequence modeling in machine learning and artificial intelligence applications. To compute attention for increasingly long sequences, specialized accelerators have been proposed to execute key attention steps directly in hardware. Among the various recently proposed architectures, those based on variants of the FlashAttention algorithm, originally designed for GPUs, stand ou…

Enhancing Speech Instruction Understanding and Disambiguation in Robotics via Speech Prosody
David Sasu, Kweku Andoh Yamoah, Benedict Quartey, Natalie Schluter
https://arxiv.org/abs/2506.02057

Enhancing Speech Instruction Understanding and Disambiguation in Robotics via Speech Prosody
Enabling robots to accurately interpret and execute spoken language instructions is essential for effective human-robot collaboration. Traditional methods rely on speech recognition to transcribe speech into text, often discarding crucial prosodic cues needed for disambiguating intent. We propose a novel approach that directly leverages speech prosody to infer and resolve instruction intent. Predicted intents are integrated into large language models via in-context learning to disambiguate and …

Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunities
Yuanchen Bei, Weizhi Zhang, Siwen Wang, Weizhi Chen, Sheng Zhou, Hao Chen, Yong Li, Jiajun Bu, Shirui Pan, Yizhou Yu, Irwin King, Fakhri Karray, Philip S. Yu
https://arxiv.org/abs/2506.18019

Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunities
AI agents have experienced a paradigm shift, from early dominance by reinforcement learning (RL) to the rise of agents powered by large language models (LLMs), and now further advancing towards a synergistic fusion of RL and LLM capabilities. This progression has endowed AI agents with increasingly strong abilities. Despite these advances, to accomplish complex real-world tasks, agents are required to plan and execute effectively, maintain reliable memory, and coordinate smoothly with other age…

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[5/5]:
Imagine, Verify, Execute: Memory-Guided Agentic Exploration with Vision-Language Models

AI is the Strategy: From Agentic AI to Autonomous Business Models onto Strategy in the Age of AI
Ren\'e Bohnsack, Mickie de Wet
https://arxiv.org/abs/2506.17339

AI is the Strategy: From Agentic AI to Autonomous Business Models onto Strategy in the Age of AI
This article develops the concept of Autonomous Business Models (ABMs) as a distinct managerial and strategic logic in the age of agentic AI. While most firms still operate within human-driven or AI-augmented models, we argue that we are now entering a phase where agentic AI (systems capable of initiating, coordinating, and adapting actions autonomously) can increasingly execute the core mechanisms of value creation, delivery, and capture. This shift reframes AI not as a tool to support strateg…

Prompt Optimization and Evaluation for LLM Automated Red Teaming
Michael Freenor, Lauren Alvarez, Milton Leal, Lily Smith, Joel Garrett, Yelyzaveta Husieva, Madeline Woodruff, Ryan Miller, Erich Kummerfeld, Rafael Medeiros, Sander Schulhoff
https://arxiv.org/abs/2507.22133

Prompt Optimization and Evaluation for LLM Automated Red Teaming
Applications that use Large Language Models (LLMs) are becoming widespread, making the identification of system vulnerabilities increasingly important. Automated Red Teaming accelerates this effort by using an LLM to generate and execute attacks against target systems. Attack generators are evaluated using the Attack Success Rate (ASR) the sample mean calculated over the judgment of success for each attack. In this paper, we introduce a method for optimizing attack generator prompts that applie…

TypeTele: Releasing Dexterity in Teleoperation by Dexterous Manipulation Types
Yuhao Lin, Yi-Lin Wei, Haoran Liao, Mu Lin, Chengyi Xing, Hao Li, Dandan Zhang, Mark Cutkosky, Wei-Shi Zheng
https://arxiv.org/abs/2507.01857

TypeTele: Releasing Dexterity in Teleoperation by Dexterous Manipulation Types
Dexterous teleoperation plays a crucial role in robotic manipulation for real-world data collection and remote robot control. Previous dexterous teleoperation mostly relies on hand retargeting to closely mimic human hand postures. However, these approaches may fail to fully leverage the inherent dexterity of dexterous hands, which can execute unique actions through their structural advantages compared to human hands. To address this limitation, we propose TypeTele, a type-guided dexterous teleo…

DX100: A Programmable Data Access Accelerator for Indirection
Alireza Khadem, Kamalavasan Kamalakkannan, Zhenyan Zhu, Akash Poptani, Yufeng Gu, Jered Benjamin Dominguez-Trujillo, Nishil Talati, Daichi Fujiki, Scott Mahlke, Galen Shipman, Reetuparna Das
https://arxiv.org/abs/2505.23073

DX100: A Programmable Data Access Accelerator for Indirection
Indirect memory accesses frequently appear in applications where memory bandwidth is a critical bottleneck. Prior indirect memory access proposals, such as indirect prefetchers, runahead execution, fetchers, and decoupled access/execute architectures, primarily focus on improving memory access latency by loading data ahead of computation but still rely on the DRAM controllers to reorder memory requests and enhance memory bandwidth utilization. DRAM controllers have limited visibility to future …

Scheduzz: Constraint-based Fuzz Driver Generation with Dual Scheduling
Yan Li, Wenzhang Yang, Yuekun Wang, Jian Gao, Shaohua Wang, Yinxing Xue, Lijun Zhang
https://arxiv.org/abs/2507.18289

Scheduzz: Constraint-based Fuzz Driver Generation with Dual Scheduling
Fuzzing a library requires experts to understand the library usage well and craft high-quality fuzz drivers, which is tricky and tedious. Therefore, many techniques have been proposed to automatically generate fuzz drivers. However, they fail to generate rational fuzz drivers due to the lack of adherence to proper library usage conventions, such as ensuring a resource is closed after being opened. To make things worse, existing library fuzzing techniques unconditionally execute each driver, res…

Reconfigurable qubit states and quantum trajectories in a synthetic artificial neuron network with a process to direct information generation from co-integrated burst-mode spiking under non-Markovianity
Osama M. Nayfeh, Chris S. Horne
https://arxiv.org/abs/2507.16669

Reconfigurable qubit states and quantum trajectories in a synthetic artificial neuron network with a process to direct information generation from co-integrated burst-mode spiking under non-Markovianity
A synthetic artificial neuron network functional in a regime where quantum information processes are co-integrated with spiking computation provides significant improvement in the capabilities of neuromorphic systems in performing artificial intelligence and autonomy tasks. This provides the ability to execute with the qubit coherence states and entanglement as well as in tandem to perform functions such as read out and basic arithmetic with conventional spike-encoding. Ultimately, this enables…

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding
Chetan Pathade
https://arxiv.org/abs/2507.22304 https://arx…

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding
Vision-language models (VLMs) have revolutionized multimodal AI applications but introduce novel security vulnerabilities that remain largely unexplored. We present the first comprehensive study of steganographic prompt injection attacks against VLMs, where malicious instructions are invisibly embedded within images using advanced steganographic techniques. Our approach demonstrates that current VLM architectures can inadvertently extract and execute hidden prompts during normal image processin…

MCP4EDA: LLM-Powered Model Context Protocol RTL-to-GDSII Automation with Backend Aware Synthesis Optimization
Yiting Wang, Wanghao Ye, Yexiao He, Yiran Chen, Gang Qu, Ang Li
https://arxiv.org/abs/2507.19570

MCP4EDA: LLM-Powered Model Context Protocol RTL-to-GDSII Automation with Backend Aware Synthesis Optimization
This paper presents MCP4EDA, the first Model Context Protocol server that enables Large Language Models (LLMs) to control and optimize the complete open-source RTL-to-GDSII design flow through natural language interaction. The system integrates Yosys synthesis, Icarus Verilog simulation, OpenLane place-and-route, GTKWave analysis, and KLayout visualization into a unified LLM-accessible interface, enabling designers to execute complex multi-tool EDA workflows conversationally via AI assistants s…

AgentAlign: Navigating Safety Alignment in the Shift from Informative to Agentic Large Language Models
Jinchuan Zhang, Lu Yin, Yan Zhou, Songlin Hu
https://arxiv.org/abs/2505.23020

AgentAlign: Navigating Safety Alignment in the Shift from Informative to Agentic Large Language Models
The acquisition of agentic capabilities has transformed LLMs from "knowledge providers" to "action executors", a trend that while expanding LLMs' capability boundaries, significantly increases their susceptibility to malicious use. Previous work has shown that current LLM-based agents execute numerous malicious tasks even without being attacked, indicating a deficiency in agentic use safety alignment during the post-training phase. To address this gap, we propose AgentAlign, a novel framework t…

GraspMAS: Zero-Shot Language-driven Grasp Detection with Multi-Agent System
Quang Nguyen, Tri Le, Huy Nguyen, Thieu Vo, Tung D. Ta, Baoru Huang, Minh N. Vu, Anh Nguyen
https://arxiv.org/abs/2506.18448

GraspMAS: Zero-Shot Language-driven Grasp Detection with Multi-Agent System
Language-driven grasp detection has the potential to revolutionize human-robot interaction by allowing robots to understand and execute grasping tasks based on natural language commands. However, existing approaches face two key challenges. First, they often struggle to interpret complex text instructions or operate ineffectively in densely cluttered environments. Second, most methods require a training or finetuning step to adapt to new domains, limiting their generation in real-world applicat…

PhishingHook: Catching Phishing Ethereum Smart Contracts leveraging EVM Opcodes
Pasquale De Rosa, Simon Queyrut, Y\'erom-David Bromberg, Pascal Felber, Valerio Schiavoni
https://arxiv.org/abs/2506.19480

PhishingHook: Catching Phishing Ethereum Smart Contracts leveraging EVM Opcodes
The Ethereum Virtual Machine (EVM) is a decentralized computing engine. It enables the Ethereum blockchain to execute smart contracts and decentralized applications (dApps). The increasing adoption of Ethereum sparked the rise of phishing activities. Phishing attacks often target users through deceptive means, e.g., fake websites, wallet scams, or malicious smart contracts, aiming to steal sensitive information or funds. A timely detection of phishing activities in the EVM is therefore crucial …

HetGPU: The pursuit of making binary compatibility towards GPUs
Yiwei Yang, Yusheng Zheng, Tong Yu, Andi Quinn
https://arxiv.org/abs/2506.15993 https://

HetGPU: The pursuit of making binary compatibility towards GPUs
Heterogeneous GPU infrastructures present a binary compatibility challenge: code compiled for one vendor's GPU will not run on another due to divergent instruction sets, execution models, and driver stacks . We propose hetGPU, a new system comprising a compiler, runtime, and abstraction layer that together enable a single GPU binary to execute on NVIDIA, AMD, Intel, and Tenstorrent hardware. The hetGPU compiler emits an architecture-agnostic GPU intermediate representation (IR) and inserts meta…

Enhancing Object Search in Indoor Spaces via Personalized Object-factored Ontologies
Akash Chikhalikar, Ankit A. Ravankar, Jose Victorio Salazar Luces, Yasuhisa Hirata
https://arxiv.org/abs/2506.14422

Enhancing Object Search in Indoor Spaces via Personalized Object-factored Ontologies
Personalization is critical for the advancement of service robots. Robots need to develop tailored understandings of the environments they are put in. Moreover, they need to be aware of changes in the environment to facilitate long-term deployment. Long-term understanding as well as personalization is necessary to execute complex tasks like prepare dinner table or tidy my room. A precursor to such tasks is that of Object Search. Consequently, this paper focuses on locating and searching multipl…

Detecting Hardware Trojans in Microprocessors via Hardware Error Correction Code-based Modules
Alessandro Palumbo, Ruben Salvador
https://arxiv.org/abs/2506.15417

Detecting Hardware Trojans in Microprocessors via Hardware Error Correction Code-based Modules
Software-exploitable Hardware Trojans (HTs) enable attackers to execute unauthorized software or gain illicit access to privileged operations. This manuscript introduces a hardware-based methodology for detecting runtime HT activations using Error Correction Codes (ECCs) on a RISC-V microprocessor. Specifically, it focuses on HTs that inject malicious instructions, disrupting the normal execution flow by triggering unauthorized programs. To counter this threat, the manuscript introduces a Hardw…

Tensor Manipulation Unit (TMU): Reconfigurable, Near-Memory Tensor Manipulation for High-Throughput AI SoC
Weiyu Zhou, Zheng Wang, Chao Chen, Yike Li, Yongkui Yang, Zhuoyu Wu, Anupam Chattopadhyay
https://arxiv.org/abs/2506.14364

Tensor Manipulation Unit (TMU): Reconfigurable, Near-Memory Tensor Manipulation for High-Throughput AI SoC
While recent advances in AI SoC design have focused heavily on accelerating tensor computation, the equally critical task of tensor manipulation, centered on high,volume data movement with minimal computation, remains underexplored. This work addresses that gap by introducing the Tensor Manipulation Unit (TMU), a reconfigurable, near-memory hardware block designed to efficiently execute data-movement-intensive operators. TMU manipulates long datastreams in a memory-to-memory fashion using a RIS…

TopicAttack: An Indirect Prompt Injection Attack via Topic Transition
Yulin Chen, Haoran Li, Yuexin Li, Yue Liu, Yangqiu Song, Bryan Hooi
https://arxiv.org/abs/2507.13686

TopicAttack: An Indirect Prompt Injection Attack via Topic Transition
Large language models (LLMs) have shown remarkable performance across a range of NLP tasks. However, their strong instruction-following capabilities and inability to distinguish instructions from data content make them vulnerable to indirect prompt injection attacks. In such attacks, instructions with malicious purposes are injected into external data sources, such as web documents. When LLMs retrieve this injected data through tools, such as a search engine and execute the injected instruction…