Tootfinder

Anthropic's Jack Clark argues that, while he is optimistic about AI's progress, the industry must do a better job of listening to people's concerns about it (Jack Clark/Import AI)
https://importai.substack.com/p/import-ai-431-technological-optimism…

Import AI 431: Technological Optimism and Appropriate Fear
What do we do if AI progress keeps happening?

This thread in progress is incredible.
https://mastodon.green/@IcooIey/115720697777005544

There’s this place we walk by pretty regularly that’s semi-abandoned. The owner replaces parts when they fall off and there are lights at night, but the front and back have been left to return to nature. This chunk of land is worth ~$2.5M Canadian, so an odd situation. Anyhow, I enjoy watching the progress of the informal small-scale rewilding.
#Photography

Europe has to ramp up its military aid again. Ukraine is starting to regain territory and that progress needs to be accelerated.
https://kyivindependent.com/military-aid-to-ukraine-declines-sharply-in-recent-months-report-finds/…

Military aid to Ukraine declines sharply in recent months, report says
In July and August, total military aid to Ukraine fell 43% lower than the amount received in the first half of the year, a report by the Kiel Institute finds.

Here's how Browns QB Shedeur Sanders is making progress https://www.espn.com/nfl/story/_/id/47280047/how-cleveland-browns-quarterback-rookie-shedeur-sanders-making-progress-offense

A silent scenery in four acts...
(Selenium-toned[1] 4x6 salt print (still in final wash) plus previous work-in-progress stages... see alt text for details)
The picture/motif itself is one of my personal favorites and was taken 4 years ago in the Alpstein massif, when clouds were spontaneously forming around us, creating a wonderful light/scene/drama and a dear memory... now also as print which likely will/can outlast myself
[1] The tones will become more neutral once dry...…

On the subject of joys and problems of fieldwork, flight to Antarctica delayed by 24 hours.
At least I'll be able to clear my inbox I suppose ..
#iQ2300 expedition has actually been in the field a couple of weeks already - you can follow our progress and all the complex logistics around working #Antarctica as well as the joys and problems of #Fieldwork on the expedition blog:  
https://www.polar.se/en/expeditions/iq2300-202526/

ProGress: Structured Music Generation via Graph Diffusion and Hierarchical Music Analysis
Stephen Ni-Hahn, Chao P\'eter Yang, Mingchen Ma, Cynthia Rudin, Simon Mak, Yue Jiang
https://arxiv.org/abs/2510.10249

ProGress: Structured Music Generation via Graph Diffusion and Hierarchical Music Analysis
Artificial Intelligence (AI) for music generation is undergoing rapid developments, with recent symbolic models leveraging sophisticated deep learning and diffusion model algorithms. One drawback with existing models is that they lack structural cohesion, particularly on harmonic-melodic structure. Furthermore, such existing models are largely "black-box" in nature and are not musically interpretable. This paper addresses these limitations via a novel generative music framework that incorporate…

"In summary, #AGI, as commonly conceived, will not happen because it ignores the physical constraints of computation, the exponential costs of linear progress, and the fundamental limits we are already encountering. Superintelligence is a fantasy because it assumes that intelligence can recursively self-improve without bound, ignoring the physical and economic realities that constrain all systems. …

Nine lower bound conjectures on streaming approximation algorithms for CSPs
Noah G. Singer
https://arxiv.org/abs/2510.10714 https://arxiv.org/pdf/2510.1071…

Nine lower bound conjectures on streaming approximation algorithms for CSPs
In this column, we overview recent progress by many authors on understanding the approximability of constraint satisfaction problems (CSPs) in low-space streaming models. Inspired by this recent progress, we collate nine conjectural lower bounds against streaming algorithms for CSPs, some of which appear here for the first time.

The last Volkswagen ID.3 has been built at the 'Gläserne Manufaktur' (Transparent Factory) in Dresden.
A symbolic end to a symbolic factory, itself an icon of early 21st-century Germany, when nothing but progress seemed possible?
https://www.instagram.com/vwmanufaktur_de/

Gläserne Manufaktur Dresden on Instagram: "Zu Beginn nächster Woche endet ein Kapitel und öffnet gleichzeitig ein Neues … 🫶🏻 #Volkswagen #HomeOfID #GläserneManufaktur #WayToZero #elektromobilität #vwlove #vwlife #vwid3 #emobility #elektroauto #carsofinstagram #vwid #ID3 #carmanufacturing"
1,543 likes, 363 comments - vwmanufaktur_de on December 12, 2025: "Zu Beginn nächster Woche endet ein Kapitel und öffnet gleichzeitig ein Neues … 🫶🏻 #Volkswagen #HomeOfID #GläserneManufaktur #WayToZero #elektromobilität #vwlove #vwlife #vwid3 #emobility #elektroauto #carsofinstagram #vwid #ID3 #carmanufacturing".

I just saw a fucking IRL bluesky username

Really feeling the slowness of #fsharp compilation process. I am surprised they haven't made more progress in this area but I am sure I am not understanding the full complexities involved - or perhaps it's not a big enough issue to warrant too much attention. Either way. The only thing that's missing for this beautiful ecosystem of f#/.net world in my book.

Tensor Logic: The Language of AI
Pedro Domingos
https://arxiv.org/abs/2510.12269 https://arxiv.org/pdf/2510.12269…

Tensor Logic: The Language of AI
Progress in AI is hindered by the lack of a programming language with all the requisite features. Libraries like PyTorch and TensorFlow provide automatic differentiation and efficient GPU implementation, but are additions to Python, which was never intended for AI. Their lack of support for automated reasoning and knowledge acquisition has led to a long and costly series of hacky attempts to tack them on. On the other hand, AI languages like LISP an Prolog lack scalability and support for learn…

If I were to build a new national party in the US or EU, it would be abundance-based—and begin with a merciless assault on administrative burden and bureaucratic disentitlement. @ezraklein is right that bureaucracy blocks progress, but it also disenfranchises.

When Support Hides Progress: Insights from a Physics Tutorial on Solving Laplace's Equation Using Separation of Variables in Cartesian Coordinates
Jaya Shivangani Kashyap, Robert Devaty, Chandralekha Singh
https://arxiv.org/abs/2510.11968

When Support Hides Progress: Insights from a Physics Tutorial on Solving Laplace's Equation Using Separation of Variables in Cartesian Coordinates
The electrostatic potential in certain types of boundary value problems can be found by solving Laplace's Equation (LE). To develop students' ability for solving problems that can be solved effectively using Laplace's equation in an upper-level electricity and magnetism course, we developed and validated a tutorial focused on finding electrostatic potential in a Cartesian coordinate system. The tutorial was implemented across three instructors' classes, accompanied by scaffolded pretest and pos…

SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models
Weiyang Jin, Yuwei Niu, Jiaqi Liao, Chengqi Duan, Aoxue Li, Shenghua Gao, Xihui Liu
https://arxiv.org/abs/2510.12784

SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models
Recently, remarkable progress has been made in Unified Multimodal Models (UMMs), which integrate vision-language generation and understanding capabilities within a single framework. However, a significant gap exists where a model's strong visual understanding often fails to transfer to its visual generation. A model might correctly understand an image based on user instructions, yet be unable to generate a faithful image from text prompts. This phenomenon directly raises a compelling question: …

Structured Sparsity and Weight-adaptive Pruning for Memory and Compute efficient Whisper models
Prasenjit K Mudi, Anshi Sachan, Dahlia Devapriya, Sheetal Kalyani
https://arxiv.org/abs/2510.12666

Structured Sparsity and Weight-adaptive Pruning for Memory and Compute efficient Whisper models
Whisper models have achieved remarkable progress in speech recognition; yet their large size remains a bottleneck for deployment on resource-constrained edge devices. This paper proposes a framework to design fine-tuned variants of Whisper which address the above problem. Structured sparsity is enforced via the Sparse Group LASSO penalty as a loss regularizer, to reduce the number of FLOating Point operations (FLOPs). Further, a weight statistics aware pruning algorithm is proposed. We also des…

Omni-Captioner: Data Pipeline, Models, and Benchmark for Omni Detailed Perception
Ziyang Ma, Ruiyang Xu, Zhenghao Xing, Yunfei Chu, Yuxuan Wang, Jinzheng He, Jin Xu, Pheng-Ann Heng, Kai Yu, Junyang Lin, Eng Siong Chng, Xie Chen
https://arxiv.org/abs/2510.12720

Omni-Captioner: Data Pipeline, Models, and Benchmark for Omni Detailed Perception
Fine-grained perception of multimodal information is critical for advancing human-AI interaction. With recent progress in audio-visual technologies, Omni Language Models (OLMs), capable of processing audio and video signals in parallel, have emerged as a promising paradigm for achieving richer understanding and reasoning. However, their capacity to capture and describe fine-grained details remains limited explored. In this work, we present a systematic and comprehensive investigation of omni de…

Squirrels at War: Trojan Horse
“Don’t worry, you did fine,” Mac said as I followed him down a tunnel. “That faction always laughs at things that make them uncomfortable.” He stopped at a doorway that dilated open. “This room is for waiting,” he said. “Soon we will meet with the military command and some diplomats. In the meantime, we can check on the progress of Lion’s Tooth.” He went to a screen mounted in the wall and began waving his paws.

Hybrid Vision Transformer and Quantum Convolutional Neural Network for Image Classification
Mingzhu Wang, Yun Shang
https://arxiv.org/abs/2510.12291 https://

Hybrid Vision Transformer and Quantum Convolutional Neural Network for Image Classification
Quantum machine learning (QML) holds promise for computational advantage, yet progress on real-world tasks is hindered by classical preprocessing and noisy devices. We introduce ViT-QCNN-FT, a hybrid framework that integrates a fine-tuned Vision Transformer with a quantum convolutional neural network (QCNN) to compress high-dimensional images into features suited for noisy intermediate-scale quantum (NISQ) devices. By systematically probing entanglement, we show that ansatzes with uniformly dis…

A Systematic Study on Generating Web Vulnerability Proof-of-Concepts Using Large Language Models
Mengyao Zhao, Kaixuan Li, Lyuye Zhang, Wenjing Dang, Chenggong Ding, Sen Chen, Zheli Liu
https://arxiv.org/abs/2510.10148

A Systematic Study on Generating Web Vulnerability Proof-of-Concepts Using Large Language Models
Recent advances in Large Language Models (LLMs) have brought remarkable progress in code understanding and reasoning, creating new opportunities and raising new concerns for software security. Among many downstream tasks, generating Proof-of-Concept (PoC) exploits plays a central role in vulnerability reproduction, comprehension, and mitigation. While previous research has focused primarily on zero-day exploitation, the growing availability of rich public information accompanying disclosed CVEs…

Climate action is finally moving from promises to practice. The Global Implementation Accelerator is bridging the gap between national climate plans and real-world results.
Here's what's working: Private capital restoring Brazilian forests. Unilever switching to renewables. H&M and IKEA modernizing Vietnam's grid. Companies in Taiwan pooling demand for clean energy.
The breakthrough? Aligning business needs with national climate goals creates wins on both sides.

From Plans to Progress: A Blueprint for Delivering 1.5°C Through the ‘Global Mutirão’
The Global Mutirão sent a clear message: delivering 1.5°C is only possible through shared effort.

Progress on the peace plan: will there be a quick ceasefire? #shorts: https://benborges.xyz/2025/12/08/progress-on-the-peace-plan.html

Stop DDoS Attacking the Research Community with AI-Generated Survey Papers
Jianghao Lin, Rong Shan, Jiachen Zhu, Yunjia Xi, Yong Yu, Weinan Zhang
https://arxiv.org/abs/2510.09686

Stop DDoS Attacking the Research Community with AI-Generated Survey Papers
Survey papers are foundational to the scholarly progress of research communities, offering structured overviews that guide both novices and experts across disciplines. However, the recent surge of AI-generated surveys, especially enabled by large language models (LLMs), has transformed this traditionally labor-intensive genre into a low-effort, high-volume output. While such automation lowers entry barriers, it also introduces a critical threat: the phenomenon we term the "survey paper DDoS att…

Translating Milli/Microrobots with A Value-Centered Readiness Framework
Hakan Ceylan, Edoardo Sinibaldi, Sanjay Misra, Pankaj J. Pasricha, Dietmar W. Hutmacher
https://arxiv.org/abs/2510.12090

Translating Milli/Microrobots with A Value-Centered Readiness Framework
Untethered mobile milli/microrobots hold transformative potential for interventional medicine by enabling more precise and entirely non-invasive diagnosis and therapy. Realizing this promise requires bridging the gap between groundbreaking laboratory demonstrations and successful clinical integration. Despite remarkable technical progress over the past two decades, most millirobots and microrobots remain confined to laboratory proof-of-concept demonstrations, with limited real-world feasibility…

Impressive video, as always the question is how much of this is "staged", in perfect conditions, what are the actual capabilities? But regardlessly, the progress in robotics is real and there are probably a lot of applications in warehouse and factory settings already.
https://youtu.be/Eu5mYMavctM?si=goMOny

Raiders’ Win Over Titans: Step Forward or Fool’s Gold? https://raiderramble.com/2025/10/14/raiders-win-over-titans-step-forward-or-fools-gold/

https://truthout.org/articles/progressive-launches-primary-challenge-to-democrat-who-once-got-2m-from-aipac/

Progressive Launches Primary Challenge to Democrat Who Once Got $2M From AIPAC
AIPAC spent $2 million to oppose progressive Nida Allam from being elected in North Carolina in 2022.

A Hierarchical Quantized Tokenization Framework for Task-Adaptive Graph Representation Learning
Yang Xiang, Li Fan, Chenke Yin, Chengtao Ji
https://arxiv.org/abs/2510.12369 http…

A Hierarchical Quantized Tokenization Framework for Task-Adaptive Graph Representation Learning
Recent progress in language and vision foundation models demonstrates the importance of discrete token interfaces that transform complex inputs into compact sequences for large-scale modeling. Extending this paradigm to graphs requires a tokenization scheme that handles non-Euclidean structures and multi-scale dependencies efficiently. Existing approaches to graph tokenization, linearized, continuous, and quantized, remain limited in adaptability and efficiency. In particular, most current quan…

Cowboys Update CeeDee Lamb Concussion Progress Ahead of Week 15 https://heavy.com/sports/nfl/dallas-cowboys/ceedee-lamb-concussion-progress-ahead-of-week-15/?adt_ei=[email]

World breaks renewable records - adding 582 GW of capacity in 2024 - but must move faster to hit the agreed 2030 tripling goal.
From @irena-official.bsky.social:
https://www.irena.org/News/pressreleases/2

World Breaks Renewable Records but Must Move Faster to Hit 2030 Tripling Goal
The world is falling behind on its renewable energy and efficiency goals despite record progress last year, confirms a new report released today by the International Renewable Energy Agency (IRENA), the COP30 Brazilian Presidency, and the Global Renewables Alliance (GRA) during a pre-COP30 high-level event in Brasília.

RE: https://techhub.social/@year_progress/115527647378420904
this is fine :mortysmile:

SeFEF: A Seizure Forecasting Evaluation Framework
Ana Sofia Carmo, Louren\c{c}o Abrunhosa Rodrigues, Ana Rita Peralta, Ana Fred, Carla Bentes, Hugo Pl\'acido da Silva
https://arxiv.org/abs/2510.11275

SeFEF: A Seizure Forecasting Evaluation Framework
The lack of standardization in seizure forecasting slows progress in the field and limits the clinical translation of forecasting models. In this work, we introduce a Python-based framework aimed at streamlining the development, assessment, and documentation of individualized seizure forecasting algorithms. The framework automates data labeling, cross-validation splitting, forecast post-processing, performance evaluation, and reporting. It supports various forecasting horizons and includes a …

Beyond-Diagonal RIS Architecture Design and Optimization under Physics-Consistent Models
Zheyu Wu, Matteo Nerini, Bruno Clerckx
https://arxiv.org/abs/2510.12366 https://

Beyond-Diagonal RIS Architecture Design and Optimization under Physics-Consistent Models
Reconfigurable intelligent surface (RIS) is a promising technology for future wireless communication systems. Conventional RIS is constrained to a diagonal scattering matrix, which limits its flexibility. Recently, beyond-diagonal RIS (BD-RIS) has been proposed as a more general RIS architecture class that allows inter-element connections and shows great potential for performance improvement. Despite extensive progress on BD-RIS, most existing studies rely on simplified channel models that igno…

"Labor’s environmental law overhaul: a little progress and a lot of compromise|"
#Australia #Environment

Labor’s environmental law overhaul: a little progress and a lot of compromise
Labor’s long-awaited environmental reforms do represent progress. But ambition levels have been dialled back and much depends on the detail.

Hybridization of second-order gravitational self-force and numerical relativity waveforms for quasi-circular and non-spinning black hole binaries
Hector Iglesias, Leanne Durkan, Deirdre Shoemaker
https://arxiv.org/abs/2510.11685

Hybridization of second-order gravitational self-force and numerical relativity waveforms for quasi-circular and non-spinning black hole binaries
In the past few decades, the waveform community has made advances in producing waveforms that span the inspiral-merger-ringdown of comparable-mass-ratio black hole binaries using advances in post-Newtonian and numerical relativity (NR) theory along with state-of-the-art gravitational wave models. Current methods in NR have shown progress towards producing stable simulations reaching mass ratios of 1:100; however, the computational cost becomes prohibitively expensive as the mass ratio and the l…

Inpainting the Neural Picture: Inferring Unrecorded Brain Area Dynamics from Multi-Animal Datasets
Ji Xia, Yizi Zhang, Shuqi Wang, Genevera I. Allen, Liam Paninski, Cole Lincoln Hurwitz, Kenneth D. Miller
https://arxiv.org/abs/2510.11924

Inpainting the Neural Picture: Inferring Unrecorded Brain Area Dynamics from Multi-Animal Datasets
Characterizing interactions between brain areas is a fundamental goal of systems neuroscience. While such analyses are possible when areas are recorded simultaneously, it is rare to observe all combinations of areas of interest within a single animal or recording session. How can we leverage multi-animal datasets to better understand multi-area interactions? Building on recent progress in large-scale, multi-animal models, we introduce NeuroPaint, a masked autoencoding approach for inferring the…

Strong convergence: a short survey
Ramon van Handel
https://arxiv.org/abs/2510.12520 https://arxiv.org/pdf/2510.12520…

Strong convergence: a short survey
A family of random matrices is said to converge strongly to a limiting family of operators if the operator norm of every noncommutative polynomial of the matrices converges to that of the limiting operators. Recent developments surrounding the strong convergence phenomenon have led to new progress on important problems in random graphs, geometry, operator algebras, and applied mathematics. We review classical and recent results in this area, and their applications to various areas of mathematic…

Scientists at NeurIPS, which drew a record 26,000 attendees this year, say key questions about how AI models work and how to measure them remain unresolved (Jared Perlo/NBC News)
https://www.nbcnews.com/tech/tech-news/ai-progress-surges-resea…

AI progress surges while researchers struggle to explain It
Academics, start-up founders and researchers representing industrial titans from around the globe descended on San Diego for the top gathering in AI.

Time-Dilation Methods for Extreme Multiscale Timestepping Problems
Philip F. Hopkins, Elias R. Most
https://arxiv.org/abs/2510.09756 https://arxiv.org/pdf/…

Time-Dilation Methods for Extreme Multiscale Timestepping Problems
Many astrophysical simulations involve extreme dynamic range of timescales around 'special points' in the domain (e.g. black holes, stars, planets, disks, galaxies, shocks, mixing interfaces), where processes on small scales couple strongly to those on large scales. Adaptive resolution, multi-physics, and hybrid numerical methods have enabled tremendous progress on the spatial, physics, and numerical challenges involved. But often the limiter for following the long timescales of global evolutio…

Ideal Optical Antimatter using Passive Lossy Materials under Complex Frequency Excitation
Olivia Y. Long, Peter B. Catrysse, Seunghoon Han, Shanhui Fan
https://arxiv.org/abs/2510.11796

Ideal Optical Antimatter using Passive Lossy Materials under Complex Frequency Excitation
The original concept of left-handed material has inspired the possibility of optical antimatter, where the effect of light propagation through a medium can be completely cancelled by its complementary medium. Despite recent progress in the development of negative-index metamaterials, losses continue to be a significant barrier to realizing optical antimatter. In this work, we show that passive, lossy materials can be used to realize optical antimatter when illuminated by light at a complex freq…

CodePlot-CoT: Mathematical Visual Reasoning by Thinking with Code-Driven Images
Chengqi Duan, Kaiyue Sun, Rongyao Fang, Manyuan Zhang, Yan Feng, Ying Luo, Yufang Liu, Ke Wang, Peng Pei, Xunliang Cai, Hongsheng Li, Yi Ma, Xihui Liu
https://arxiv.org/abs/2510.11718

CodePlot-CoT: Mathematical Visual Reasoning by Thinking with Code-Driven Images
Recent advances in Large Language Models (LLMs) and Vision Language Models (VLMs) have shown significant progress in mathematical reasoning, yet they still face a critical bottleneck with problems requiring visual assistance, such as drawing auxiliary lines or plotting functions to solve the problems. Most LLMs and VLMs are constrained to text-only reasoning chains, while multimodal unified models that can generate interleaved text and images lack the necessary precision and controllability for…

Visualizing the Impact of Quenched Disorder on 2D Electron Wigner Solids
Zhehao Ge, Conor Smith, Zehao He, Yubo Yang, Qize Li, Ziyu Xiang, Jianghan Xiao, Wenjie Zhou, Salman Kahn, Melike Erdi, Rounak Banerjee, Takashi Taniguchi, Kenji Watanabe, Seth Ariel Tongay, Miguel A. Morales, Shiwei Zhang, Feng Wang, Michael F. Crommie
https://arxiv.…

Visualizing the Impact of Quenched Disorder on 2D Electron Wigner Solids
Electron Wigner solids (WSs)1-12 provide an ideal system for understanding the competing effects of electron-electron and electron-disorder interactions, a central unsolved problem in condensed matter physics. Progress in this topic has been limited by a lack of single-defect-resolved experimental measurements as well as accurate theoretical tools to enable realistic experiment-theory comparison. Here we overcome these limitations by combining atomically-resolved scanning tunneling microscopy (…

A Hybrid Agent-Based and System Dynamics Framework for Modelling Project Execution and Technology Maturity in Early-Stage R&D
R. W. S. Pessoa, M. H. N{\ae}ss, J. C. Bijos, C. M. Rebello, D. Colombo, L. Schnitman, I. B. R. Nogueira
https://arxiv.org/abs/2510.09688

A Hybrid Agent-Based and System Dynamics Framework for Modelling Project Execution and Technology Maturity in Early-Stage R&D
This paper presents a hybrid approach to predict the evolution of technological maturity in R and D projects, using the oil and gas sector as an example. Integrating System Dynamics (SD) and Agent Based Modelling (ABM) allows the proposed multi level framework to capture uncertainties in work effort, team size, and project duration, which influence technological progress. While AB SD hybrid models are established in other fields, their use in R and D remains limited. The model combines system l…

Deep Associations, High Creativity: A Simple yet Effective Metric for Evaluating Large Language Models
Ziliang Qiu, Renfen Hu
https://arxiv.org/abs/2510.12110 https://

Deep Associations, High Creativity: A Simple yet Effective Metric for Evaluating Large Language Models
The evaluation of LLMs' creativity represents a crucial research domain, though challenges such as data contamination and costly human assessments often impede progress. Drawing inspiration from human creativity assessment, we propose PACE, asking LLMs to generate Parallel Association Chains to Evaluate their creativity. PACE minimizes the risk of data contamination and offers a straightforward, highly efficient evaluation, as evidenced by its strong correlation with Chatbot Arena Creative Writ…

#HoldTheLine

Shutdown progress in doubt as Democrats grow emboldened from election wins
Elections this week that energized Democrats and angered President Donald Trump have cast a chill over efforts to end the record-breaking government shutdown, raising fresh doubts about the possibility of a breakthrough despite the punishing toll of federal closures on the country. Trump has increased pressure on Senate Republicans to end the shutdown — now at 37 days, the longest in U.S. history — calling it a “big factor, negative” in the poor GOP showings across the country. Democrat…

From Press Progress
A Year of Government Interference in Collective Bargaining
More often than not, governments across Canada sided with corporations instead of workers.
#canpoli #cdnpoli

A Year of Government Interference in Collective Bargaining
More often than not, governments across Canada sided with corporations instead of workers.

The #iQ2300 expedition has actually been in the field a couple of weeks already - you can follow our progress and all the complex logistics around working #Antarctica as well as the joys and problems of #Fieldwork on the expedition blog:
https://www.polar.se/en/expeditions/iq2300-202526/

Defects4C: Benchmarking Large Language Model Repair Capability with C/C Bugs
Jian Wang, Xiaofei Xie, Qiang Hu, Shangqing Liu, Jiongchi Yu, Jiaolong Klong, Yi Li
https://arxiv.org/abs/2510.11059

Defects4C: Benchmarking Large Language Model Repair Capability with C/C++ Bugs
Automated Program Repair (APR) plays a critical role in enhancing the quality and reliability of software systems. While substantial progress has been made in Java-based APR, largely facilitated by benchmarks like Defects4J, there remains a significant gap in research on C/C++ program repair, despite the widespread use of C/C++ and the prevalence of associated vulnerabilities. This gap is primarily due to the lack of high-quality, open-source benchmarks tailored for C/C++. To address this iss…

Americans Much More Positive About Progress on Drugs (Justin McCarthy/Gallup)
https://news.gallup.com/poll/697445/americans-positive-progress-drugs.aspx
http://www.memeorandum.com/251105/p94#a251105p94

The Lego (building) table is finished. My son already has plans to move his in progress build to finish it.
#woodworking
#finished

Ok, I’m procrastinating downloading a bunch of vids with yt-dlp and at this point I’m already reaching the tabs limit on this Safari profile
What’d be the best way of downloading a bunch of videos with yt-dlp while still keeping a good control of what failed and what succeeded? (this is basically impossible from its output if you feed it a bunch of links in a single go)
I was wanting a webui I could selfhost and it’d show progress and status for each video it’s downloading (and let me pass custom options to the yt-dlp command, such as filename), but should I just make a script with a for loop for each URL instead?

The p-adic distance of special points to subvarieties
Jos\'e Felipe Voloch
https://arxiv.org/abs/2510.08786 https://arxiv.org/pdf/2510.08786

The p-adic distance of special points to subvarieties
In a paper of Tate and the author, we conjectured a uniform bound for the p-adic distance of torsion points on a semiabelian variety, not lying in a subvariety, to that subvariety. We survey the progress made on that conjecture and on similar statements in analogous situations.

An Empirical Study for Representations of Videos in Video Question Answering via MLLMs
Zhi Li, Yanan Wang, Hao Niu, Julio Vizcarra, Masato Taya
https://arxiv.org/abs/2510.12299 …

An Empirical Study for Representations of Videos in Video Question Answering via MLLMs
Multimodal large language models have recently achieved remarkable progress in video question answering (VideoQA) by jointly processing visual, textual, and audio information. However, it remains unclear which video representations are most effective for MLLMs, and how different modalities balance task accuracy against computational efficiency. In this work, we present a comprehensive empirical study of video representation methods for VideoQA with MLLMs. We systematically evaluate single modal…

CeeDee Lamb injury update: Dallas Cowboys star makes progress at Wednesday practice https://www.sportingnews.com/us/nfl/dallas-cowboys/news/ceedee-lamb-injury-update-dallas-cowboys-progress-wednes…

50 years ago tonight, the jerry garcia band in #berkeley, the 1st of 2 fun shows featuring muscle shoals session player tim henson on 2nd keyboards, perhaps in town to contribute to garcia’s in-progress “reflections” sessions. also the 1st full soundboard of the new garcia band:

Progress towards generalized Nash-Williams' conjecture on $K_4$-decompositions
Menglong Zhang, Gennian Ge
https://arxiv.org/abs/2510.07783 https://arxi…

Progress towards generalized Nash-Williams' conjecture on $K_4$-decompositions
A $K_4$-decomposition of a graph is a partition of its edges into $K_4$s. A fractional $K_4$-decomposition is an assignment of a nonnegative weight to each $K_4$ in a graph such that the sum of the weights of the $K_4$s containing any given edge is one. Formulating a nonlinear programming and reducing the number of variables slowly, we prove that every graph on $n$ vertices with minimum degree at least $\frac{31}{33}n$ has a fractional $K_4$-decomposition. This improves a result of Montgomery t…

@… yeah, I think it’s time. It’s the #1 template syntax that folks use in Eleventy so it makes sense
Made a lot of progress yesterday: https://github.com/11ty/nunjucks/

BridgeCode: A Dual Speech Representation Paradigm for Autoregressive Zero-Shot Text-to-Speech Synthesis
Jingyuan Xing, Mingru Yang, Zhipeng Li, Xiaofen Xing, Xiangmin Xu
https://arxiv.org/abs/2510.11646

BridgeCode: A Dual Speech Representation Paradigm for Autoregressive Zero-Shot Text-to-Speech Synthesis
Autoregressive (AR) frameworks have recently achieved remarkable progress in zero-shot text-to-speech (TTS) by leveraging discrete speech tokens and large language model techniques. Despite their success, existing AR-based zero-shot TTS systems face two critical limitations: (i) an inherent speed-quality trade-off, as sequential token generation either reduces frame rates at the cost of expressiveness or enriches tokens at the cost of efficiency, and (ii) a text-oriented supervision mismatch, a…

Efficient Perceptual Image Super Resolution: AIM 2025 Study and Benchmark
Bruno Longarela, Marcos V. Conde, Alvaro Garcia, Radu Timofte
https://arxiv.org/abs/2510.12765 https://…

Efficient Perceptual Image Super Resolution: AIM 2025 Study and Benchmark
This paper presents a comprehensive study and benchmark on Efficient Perceptual Super-Resolution (EPSR). While significant progress has been made in efficient PSNR-oriented super resolution, approaches focusing on perceptual quality metrics remain relatively inefficient. Motivated by this gap, we aim to replicate or improve the perceptual results of Real-ESRGAN while meeting strict efficiency constraints: a maximum of 5M parameters and 2000 GFLOPs, calculated for an input size of 960x540 pixels…

From the article: "In this century, the émigré fraction of U.S. Nobels in physics, chemistry and medicine now stands at 40 percent." https://mastodon.social/@ScienceScholar/115701386822807521

Joel Mokyr, Philippe Aghion, and Peter Howitt win the Nobel Prize in Economics for their work on how innovation and technological progress helps economic growth (Eshe Nelson/New York Times)
https://www.nytimes.com/2025/10/13/business/nobel-prize-economics.html…

Joel Mokyr, Philippe Aghion and Peter Howitt Share Nobel in Economics
Joel Mokyr, Philippe Aghion and Peter Howitt won the prize for showing how “society must keep an eye on the factors that generate and sustain economic growth,” an award committee member said.

How Raiders' Chip Kelly Is Conducting Brock Bowers' Impact https://www.si.com/nfl/raiders/onsi/las-vegas-chip-kelly-conducting-brock-bowers-impact

Blue Genie Art Bazaar in progress
https://nakatsubyjna.com/2025/12/02/blue-genie-art-bazaar-in-progress/

Blue Genie Art Bazaar in progress
Nakatsu by JNA is participating in the Blue Genie Art Bazaar November 14th every day (10am-10pm) through December 25 (10-6pm) a free event with 200+ artists at 6100 Airport Blvd

Magnetic Materials for Quantum Magnonics
Rostyslav O. Serha, Carsten Dubs, Andrii V. Chumak
https://arxiv.org/abs/2510.09331 https://arxiv.org/pdf/2510.093…

Magnetic Materials for Quantum Magnonics
Quantum magnonics studies the quantum properties of magnons, the quanta of spin waves, and their application in quantum information processing. Progress in this field depends on identifying magnetic materials with characteristics tailored to the diverse requirements of magnonics and quantum magnonics. For single-magnon excitation, its control, hybrid coupling, and entanglement, the most critical property is the ability to support long magnon lifetimes. This perspective reviews established and e…

A Survey on Parallel Reasoning
Ziqi Wang, Boye Niu, Zipeng Gao, Zhi Zheng, Tong Xu, Linghui Meng, Zhongli Li, Jing Liu, Yilong Chen, Chen Zhu, Hua Wu, Haifeng Wang, Enhong Chen
https://arxiv.org/abs/2510.12164

A Survey on Parallel Reasoning
With the increasing capabilities of Large Language Models (LLMs), parallel reasoning has emerged as a new inference paradigm that enhances reasoning robustness by concurrently exploring multiple lines of thought before converging on a final answer. It has become a significant trend to explore parallel reasoning to overcome the fragility of standard sequential methods and improve practical performance. In this paper, we aim to survey and summarize the progress and challenges of parallel reasonin…

Joe Mixon injury: Texans RB making progress but no timetable for return, according to Houston GM

https://www.cbssports.com/nfl/news/joe-mix

Dr. Bias: Social Disparities in AI-Powered Medical Guidance
Emma Kondrup, Anne Imouza
https://arxiv.org/abs/2510.09162 https://arxiv.org/pdf/2510.09162

Dr. Bias: Social Disparities in AI-Powered Medical Guidance
With the rapid progress of Large Language Models (LLMs), the general public now has easy and affordable access to applications capable of answering most health-related questions in a personalized manner. These LLMs are increasingly proving to be competitive, and now even surpass professionals in some medical capabilities. They hold particular promise in low-resource settings, considering they provide the possibility of widely accessible, quasi-free healthcare support. However, evaluations that …

A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System
Jiale Guo, Suizhi Huang, Mei Li, Dong Huang, Xingsheng Chen, Regina Zhang, Zhijiang Guo, Han Yu, Siu-Ming Yiu, Christian Jensen, Pietro Lio, Kwok-Yan Lam
https://arxiv.org/abs/2510.09721

A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System
The integration of LLMs into software engineering has catalyzed a paradigm shift from traditional rule-based systems to sophisticated agentic systems capable of autonomous problem-solving. Despite this transformation, the field lacks a comprehensive understanding of how benchmarks and solutions interconnect, hindering systematic progress and evaluation. This survey presents the first holistic analysis of LLM-empowered software engineering, bridging the critical gap between evaluation and soluti…

Sparse graphs and their Benjamini-Schramm limits: a spectral tour
Charles Bordenave
https://arxiv.org/abs/2510.10299 https://arxiv.org/pdf/2510.10299

Sparse graphs and their Benjamini-Schramm limits: a spectral tour
Sparse graphs with bounded average degree form a rich class of discrete structures where local geometry strongly influences global behavior. The Benjamini-Schramm (BS) convergence offers a natural framework to describe their asymptotic local structure. In this note, we survey spectral aspects of BS convergence and their applications, with a focus on random Schreier graphs and covering graphs. We review some recent progress on the spectral decomposition of the local operators on graphs. We discu…

ZeroGR: A Generalizable and Scalable Framework for Zero-Shot Generative Retrieval
Weiwei Sun, Keyi Kong, Xinyu Ma, Shuaiqiang Wang, Dawei Yin, Maarten de Rijke, Zhaochun Ren, Yiming Yang
https://arxiv.org/abs/2510.10419

ZeroGR: A Generalizable and Scalable Framework for Zero-Shot Generative Retrieval
Generative retrieval (GR) reformulates information retrieval (IR) by framing it as the generation of document identifiers (docids), thereby enabling an end-to-end optimization and seamless integration with generative language models (LMs). Despite notable progress under supervised training, GR still struggles to generalize to zero-shot IR scenarios, which are prevalent in real-world applications. To tackle this challenge, we propose \textsc{ZeroGR}, a zero-shot generative retrieval framework th…

Thoughts on AI progress and why AI labs' actions hint at a worldview in which AI models will continue to fare poorly at generalization and on-the-job learning (Dwarkesh Patel/Dwarkesh Podcast)
https://www.dwarkesh.com/p/thoughts-on-ai-progress-dec-2025

Thoughts on AI progress (Dec 2025)
Why I'm moderately bearish in the short term, and explosively bullish in the long term

:skull:
https://techhub.social/@year_progress/115300211297418056

Trump 'extremely frustrated' with Russia, Ukraine amid slow peace progress, White House says: https://benborges.xyz/2025/12/12/trump-extremely-frustrated-with-russia.html

iMoWM: Taming Interactive Multi-Modal World Model for Robotic Manipulation
Chuanrui Zhang, Zhengxian Wu, Guanxing Lu, Yansong Tang, Ziwei Wang
https://arxiv.org/abs/2510.09036 h…

iMoWM: Taming Interactive Multi-Modal World Model for Robotic Manipulation
Learned world models hold significant potential for robotic manipulation, as they can serve as simulator for real-world interactions. While extensive progress has been made in 2D video-based world models, these approaches often lack geometric and spatial reasoning, which is essential for capturing the physical structure of the 3D world. To address this limitation, we introduce iMoWM, a novel interactive world model designed to generate color images, depth maps, and robot arm masks in an autoreg…

iCodeReviewer: Improving Secure Code Review with Mixture of Prompts
Yun Peng, Kisub Kim, Linghan Meng, Kui Liu
https://arxiv.org/abs/2510.12186 https://arx…

iCodeReviewer: Improving Secure Code Review with Mixture of Prompts
Code review is an essential process to ensure the quality of software that identifies potential software issues at an early stage of software development. Among all software issues, security issues are the most important to identify, as they can easily lead to severe software crashes and service disruptions. Recent research efforts have been devoted to automated approaches to reduce the manual efforts required in the secure code review process. Despite the progress, current automated approaches…

Climate change isn't gender-neutral. The 2023/2024 El Niño drought in Southern Africa didn't just destroy crops—it fueled gender-based violence and put women environmental defenders at risk.
COP30's new Belém Gender Action Plan tackles this head-on with gender-responsive budgeting and support for climate action that protects women.

COP30’s Gender Action Plan Needed to Address Climate-Induced Violence - African Climate Wire
Talks underpinning COP30’s Gender Action Plan reveal the fragility of progress in recognising the systems of oppression that affect women, girls, and gender diverse people.

GTAlign: Game-Theoretic Alignment of LLM Assistants for Mutual Welfare
Siqi Zhu, David Zhang, Pedro Cisneros-Velarde, Jiaxuan You
https://arxiv.org/abs/2510.08872 https://

GTAlign: Game-Theoretic Alignment of LLM Assistants for Mutual Welfare
Large Language Models (LLMs) have achieved remarkable progress in reasoning, yet sometimes produce responses that are suboptimal for users in tasks such as writing, information seeking, or providing practical guidance. Conventional alignment practices typically assume that maximizing model reward also maximizes user welfare, but this assumption frequently fails in practice: models may over-clarify or generate overly verbose reasoning when users prefer concise answers. Such behaviors resemble th…

NFL Week 6 roundtable: Joe Flacco's Bengals, Dak Prescott's MVP case, second-year QBs' progress https://www.nytimes.com/athletic/6706476/2025/10/11/nfl-week-6-quarterbacks-joe-flaccos-dak-prescotts-drake-maye/…

Cowboys' defense still a work in progress under new DC Matt Eberflus, what needs to change?

https://www.cbssports.com/nfl/news/cowboys-de…

Guiding Energy-Efficient Locomotion through Impact Mitigation Rewards
Chenghao Wang, Arjun Viswanathan, Eric Sihite, Alireza Ramezani
https://arxiv.org/abs/2510.09543 https://…

Guiding Energy-Efficient Locomotion through Impact Mitigation Rewards
Animals achieve energy-efficient locomotion by their implicit passive dynamics, a marvel that has captivated roboticists for decades.Recently, methods incorporated Adversarial Motion Prior (AMP) and Reinforcement learning (RL) shows promising progress to replicate Animals' naturalistic motion. However, such imitation learning approaches predominantly capture explicit kinematic patterns, so-called gaits, while overlooking the implicit passive dynamics. This work bridges this gap by incorporating…

PAC Reasoning: Controlling the Performance Loss for Efficient Reasoning
Hao Zeng, Jianguo Huang, Bingyi Jing, Hongxin Wei, Bo An
https://arxiv.org/abs/2510.09133 https://…

PAC Reasoning: Controlling the Performance Loss for Efficient Reasoning
Large reasoning models (LRMs) have achieved remarkable progress in complex problem-solving tasks. Despite this success, LRMs typically suffer from high computational costs during deployment, highlighting a need for efficient inference. A popular direction of efficiency improvement is to switch the LRM between thinking and nonthinking modes dynamically. However, such approaches often introduce additional reasoning errors and lack statistical guarantees for the performance loss, which are critica…

BLINK-Twice: You see, but do you observe? A Reasoning Benchmark on Visual Perception
Junyan Ye, Dongzhi Jiang, Jun He, Baichuan Zhou, Zilong Huang, Zhiyuan Yan, Hongsheng Li, Conghui He, Weijia Li
https://arxiv.org/abs/2510.09361

BLINK-Twice: You see, but do you observe? A Reasoning Benchmark on Visual Perception
Recently, Multimodal Large Language Models (MLLMs) have made rapid progress, particularly in enhancing their reasoning capabilities. However, existing reasoning benchmarks still primarily assess language-based reasoning, often treating visual input as replaceable context. To address this gap, we introduce BLINK-Twice, a vision-centric reasoning benchmark grounded in challenging perceptual tasks. Instead of relying on external knowledge, our tasks require models to reason from visual content alo…

Hybrid Models for Natural Language Reasoning: The Case of Syllogistic Logic
Manuel Vargas Guzm\'an, Jakub Szymanik, Maciej Malicki
https://arxiv.org/abs/2510.09472 https://

Hybrid Models for Natural Language Reasoning: The Case of Syllogistic Logic
Despite the remarkable progress in neural models, their ability to generalize, a cornerstone for applications like logical reasoning, remains a critical challenge. We delineate two fundamental aspects of this ability: compositionality, the capacity to abstract atomic logical rules underlying complex inferences, and recursiveness, the aptitude to build intricate representations through iterative application of inference rules. In the literature, these two aspects are often confounded together un…

DiTSinger: Scaling Singing Voice Synthesis with Diffusion Transformer and Implicit Alignment
Zongcai Du, Guilin Deng, Xiaofeng Guo, Xin Gao, Linke Li, Kaichang Cheng, Fubo Han, Siyu Yang, Peng Liu, Pan Zhong, Qiang Fu
https://arxiv.org/abs/2510.09016

DiTSinger: Scaling Singing Voice Synthesis with Diffusion Transformer and Implicit Alignment
Recent progress in diffusion-based Singing Voice Synthesis (SVS) demonstrates strong expressiveness but remains limited by data scarcity and model scalability. We introduce a two-stage pipeline: a compact seed set of human-sung recordings is constructed by pairing fixed melodies with diverse LLM-generated lyrics, and melody-specific models are trained to synthesize over 500 hours of high-quality Chinese singing data. Building on this corpus, we propose DiTSinger, a Diffusion Transformer with Ro…

Gutierrez: Raiders find progress in painful loss to Jaguars https://www.raiders.com/news/gutierrez-raiders-find-progress-in-painful-loss-to-jacksonville-jaguars-nfl-week-9

Leading the Follower: Learning Persuasive Agents in Social Deduction Games
Zhang Zheng, Deheng Ye, Peilin Zhao, Hao Wang
https://arxiv.org/abs/2510.09087 https://

Leading the Follower: Learning Persuasive Agents in Social Deduction Games
Large language model (LLM) agents have shown remarkable progress in social deduction games (SDGs). However, existing approaches primarily focus on information processing and strategy selection, overlooking the significance of persuasive communication in influencing other players' beliefs and responses. In SDGs, success depends not only on making correct deductions but on convincing others to response in alignment with one's intent. To address this limitation, we formalize turn-based dialogue in…

SpaceVista: All-Scale Visual Spatial Reasoning from mm to km
Peiwen Sun, Shiqiang Lang, Dongming Wu, Yi Ding, Kaituo Feng, Huadai Liu, Zhen Ye, Rui Liu, Yun-Hui Liu, Jianan Wang, Xiangyu Yue
https://arxiv.org/abs/2510.09606

SpaceVista: All-Scale Visual Spatial Reasoning from mm to km
With the current surge in spatial reasoning explorations, researchers have made significant progress in understanding indoor scenes, but still struggle with diverse applications such as robotics and autonomous driving. This paper aims to advance all-scale spatial reasoning across diverse scenarios by tackling two key challenges: 1) the heavy reliance on indoor 3D scans and labor-intensive manual annotations for dataset curation; 2) the absence of effective all-scale scene modeling, which often …

MaP: A Unified Framework for Reliable Evaluation of Pre-training Dynamics
Jiapeng Wang, Changxin Tian, Kunlong Chen, Ziqi Liu, Jiaxin Mao, Wayne Xin Zhao, Zhiqiang Zhang, Jun Zhou
https://arxiv.org/abs/2510.09295

MaP: A Unified Framework for Reliable Evaluation of Pre-training Dynamics
Reliable evaluation is fundamental to the progress of Large Language Models (LLMs), yet the evaluation process during pre-training is plagued by significant instability that obscures true learning dynamics. In this work, we systematically diagnose this instability, attributing it to two distinct sources: \textit{Parameter Instability} from training stochasticity and \textit{Evaluation Instability} from noisy measurement protocols. To counteract both sources of noise, we introduce \textbf{MaP}, …

Thoughts on The Curve conference, where prominent figures debated about AI progress, and why automating research engineers is plausible within years (Nathan Lambert/Interconnects)
https://www.interconnects.ai/p/thoughts-on-the-curve

Thoughts on The Curve
The conference and the trajectory.

Already :pika:
https://techhub.social/@year_progress/115258923640814610

Gutierrez: Raiders find progress in painful loss to Jaguars https://www.raiders.com/news/gutierrez-raiders-find-progress-in-painful-loss-to-jacksonville-jaguars-nfl-week-9

Dyna-Mind: Learning to Simulate from Experience for Better AI Agents
Xiao Yu, Baolin Peng, Michel Galley, Hao Cheng, Qianhui Wu, Janardhan Kulkarni, Suman Nath, Zhou Yu, Jianfeng Gao
https://arxiv.org/abs/2510.09577

Dyna-Mind: Learning to Simulate from Experience for Better AI Agents
Reasoning models have recently shown remarkable progress in domains such as math and coding. However, their expert-level abilities in math and coding contrast sharply with their performance in long-horizon, interactive tasks such as web navigation and computer/phone-use. Inspired by literature on human cognition, we argue that current AI agents need ''vicarious trial and error'' - the capacity to mentally simulate alternative futures before acting - in order to enhance their understanding and p…

RefGrader: Automated Grading of Mathematical Competition Proofs using Agentic Workflows
Hamed Mahdavi (Pennsylvania State University), Pouria Mahdavinia (Pennsylvania State University), Samira Malek (Pennsylvania State University), Pegah Mohammadipour (Pennsylvania State University), Alireza Hashemi (City University of New York), Majid Daliri (New York University), Alireza Farhadi (Amirkabir University of Technology), Amir Khasahmadi (Autodesk), Niloofar Mireshghallah (Carnegie Mellon …

RefGrader: Automated Grading of Mathematical Competition Proofs using Agentic Workflows
State-of-the-art (SOTA) LLMs have progressed from struggling on proof-based Olympiad problems to solving most of the IMO 2025 problems, with leading systems reportedly handling 5 of 6 problems. Given this progress, we assess how well these models can grade proofs: detecting errors, judging their severity, and assigning fair scores beyond binary correctness. We study proof-analysis capabilities using a corpus of 90 Gemini 2.5 Pro-generated solutions that we grade on a 1-4 scale with detailed err…

French lawmakers vote to raise France's digital services tax on US tech giants to 6%, up from 3%; the French government opposes the move, fearing US retaliation (Politico)
https://www.politico.eu/article/french-lawmakers-progress-tax…

French lawmakers progress tax on American Big Tech amid huge pushback
PARIS — French lawmakers are moving ahead with plans to double a tax on big tech firms — backing away from a more aggressive push amid fears of provoking U.S. trade retaliation. France’s National A…

One Sentence, Two Embeddings: Contrastive Learning of Explicit and Implicit Semantic Representations
Kohei Oda, Po-Min Chuang, Kiyoaki Shirai, Natthawut Kertkeidkachorn
https://arxiv.org/abs/2510.09293

One Sentence, Two Embeddings: Contrastive Learning of Explicit and Implicit Semantic Representations
Sentence embedding methods have made remarkable progress, yet they still struggle to capture the implicit semantics within sentences. This can be attributed to the inherent limitations of conventional sentence embedding methods that assign only a single vector per sentence. To overcome this limitation, we propose DualCSE, a sentence embedding method that assigns two embeddings to each sentence: one representing the explicit semantics and the other representing the implicit semantics. These embe…

Beyond Single-Granularity Prompts: A Multi-Scale Chain-of-Thought Prompt Learning for Graph
Ziyu Zheng, Yaming Yang, Ziyu Guan, Wei Zhao, Xinyan Huang, Weigang Lu
https://arxiv.org/abs/2510.09394

Beyond Single-Granularity Prompts: A Multi-Scale Chain-of-Thought Prompt Learning for Graph
The "pre-train, prompt'' paradigm, designed to bridge the gap between pre-training tasks and downstream objectives, has been extended from the NLP domain to the graph domain and has achieved remarkable progress. Current mainstream graph prompt-tuning methods modify input or output features using learnable prompt vectors. However, existing approaches are confined to single-granularity (e.g., node-level or subgraph-level) during prompt generation, overlooking the inherently multi-scale structural…