Tootfinder

The Affluent Ceo Show: The Select Circle's Codes To Next Level Scaling With Wealth Sovereignty And Ease
This isn't just another business podcast. It's a transformational journey for high-achieving female entrepreneurs who are ready to stop playing small and start leading with unapologetic power...
Great Australian Pods Podcast Directory:

We have become master cartographers of the "given." By scaling computation, we have built maps so vast and detailed that we often mistake the territory for the grid.
https://www.ocrampal.com/the-question-ai-will-never-ask/

The Question AI Will Never Ask
We have become master cartographers of the "given." By scaling computation, we have built maps so vast and detailed that we often mistake the territory for the grid. But as the dialogue between the AI Practitioner and the Philosopher reveals, our current path in Artificial Intelligence is a pursuit of

Q&A with Ramp CEO Eric Glyman on scaling the expense management company to over $1B revenue, the "SaaS apocalypse", using AI agents to review expenses, and more (Cheeky Pint)
https://cheekypint.substack.com/p/ramp-founder-eric-glyman-on-the-many

Ramp founder Eric Glyman on the many ways AI is changing corporate spending
Eric Glyman is the cofounder and CEO of Ramp, the finance automation platform that now powers over 2% of all corporate spend in the US.

RE: #V2G pilot in Sweden with Energy Bank and Vattenfall is now scaling to 200 cars

Working on commercial stuff with an #acting #coaching client and played with scaling the work up and down: still grounding things in what's really happening, but seeing them find the small internal version they welcome us to join them in was very good to see.

"University of Houston’s Carbon Capture Breakthrough Cuts Costs, but Scale Remains Uncertain"
#US #USA #America #CarbonCapture

University of Houston’s Carbon Capture Breakthrough Cuts Costs, but Scale Remains Uncertain | Happy Eco News
The University of Houston’s carbon capture researchers achieved 90% CO2 removal at $70 per ton using membraneless technology; however, scaling faces challenges related to cost, policy, and infrastructure.

"Scaling ORCID Adoption: Technical and Organizational Approaches Within a Research Organization"
#ORCID iD use…

[1/?]
So this happened while I was up a mountain:
https://www.joshtumath.uk/posts/2026-01-27-try-text-scaling-support-in-chrome-canary/
But the post didn’t have a demo. Last night I made one:

An interview with SemiAnalysis CEO Dylan Patel on logic, memory, and power bottlenecks in scaling AI compute, Nvidia securing TSMC N3 allocation early, and more (Dwarkesh Patel/Dwarkesh Podcast)
https://www.dwarkesh.com/p/dylan-patel

McClatchy began rolling out a "content scaling agent" that summarizes and repurposes reporters' work with new headlines in Q1, prompting some employee pushback (Corbin Bolies/The Wrap)
https://www.thewrap.com/media-platforms/jo

McClatchy Journalists Revolt Against AI: ‘It’s a Betrayal’ | Exclusive
Sacramento Bee staffers refuse bylines over a new AI tool as colleagues at the Miami Herald and Charlotte Observer harbor concerns.

Tomb Raider: Greece and Egypt
Having decried the lack of verticality in the Peruvian levels, St Francis's Folly more than made amends. The main part of the level has you scaling up and down a central room, opening doors with levels and solving puzzles in rooms names after Greek mythology1. The permanence of enemy deaths is very noticeable here, where the bats you shoot at the top of the room can sometimes be found lying on the ground at the bottom; when using original…

German bargain grocer Aldi plans to open more than 180 U.S. stores this year.
The chain, which has been rapidly expanding since inflation surged in 2021, has set a goal of 3,200 stores globally by the end of 2028.
Trader Joe’s has been on an expansion spree.
Many Dollar General stores have begun selling fresh produce.
“Discounters are in this really tricky spot, where price is paramount, but they’re up against the likes of Walmart,” Moran said.
Walmart and Amaz…

UrbanFM: Scaling Urban Spatio-Temporal Foundation Models
Wei Chen, Yuqian Wu, Junle Chen, Xiaofang Zhou, Yuxuan Liang
https://arxiv.org/abs/2602.20677 https://arxiv.org/pdf/2602.20677 https://arxiv.org/html/2602.20677
arXiv:2602.20677v1 Announce Type: new
Abstract: Urban systems, as dynamic complex systems, continuously generate spatio-temporal data streams that encode the fundamental laws of human mobility and city evolution. While AI for Science has witnessed the transformative power of foundation models in disciplines like genomics and meteorology, urban computing remains fragmented due to "scenario-specific" models, which are overfitted to specific regions or tasks, hindering their generalizability. To bridge this gap and advance spatio-temporal foundation models for urban systems, we adopt scaling as the central perspective and systematically investigate two key questions: what to scale and how to scale. Grounded in first-principles analysis, we identify three critical dimensions: heterogeneity, correlation, and dynamics, aligning these principles with the fundamental scientific properties of urban spatio-temporal data. Specifically, to address heterogeneity through data scaling, we construct WorldST. This billion-scale corpus standardizes diverse physical signals, such as traffic flow and speed, from over 100 global cities into a unified data format. To enable computation scaling for modeling correlations, we introduce the MiniST unit, a novel split mechanism that discretizes continuous spatio-temporal fields into learnable computational units to unify representations of grid-based and sensor-based observations. Finally, addressing dynamics via architecture scaling, we propose UrbanFM, a minimalist self-attention architecture designed with limited inductive biases to autonomously learn dynamic spatio-temporal dependencies from massive data. Furthermore, we establish EvalST, the largest-scale urban spatio-temporal benchmark to date. Extensive experiments demonstrate that UrbanFM achieves remarkable zero-shot generalization across unseen cities and tasks, marking a pivotal first step toward large-scale urban spatio-temporal foundation models.
toXiv_bot_toot

All the legal battles are about who can exploit users even more. These German processes will not lead to cost reduction through scaling and standardisation, nor will they make EV charging more accessible.

For some reason, my home server was using the "performance" CPU scaling governor. Changing it to "conservative" seems to have lowered power consumption for the whole machine by almost 10%. This saves more than 25€ per year in electricity cost.
You can check your own CPU scaling governor with `cat /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor`.

OpenAI is scaling back shopping directly inside ChatGPT via Instant Checkout by having checkouts instead take place in the specific apps that plug into ChatGPT (The Information)
https://www.theinformation.com/articles/openai-scales-back-shopping-plans-chatgp…

OpenAI Scales Back Shopping Plans for ChatGPT
OpenAI is scaling back its plan to introduce shopping directly inside ChatGPT, marking a change in its high-profile effort to put checkouts inside the chatbot. Instead of allowing users to make purchases directly from product listings that show up in ChatGPT search results, the company is now ...

Modular architecture: customize Directus to match your branding and workflows. Extensions, custom endpoints, hooks — all possible.
☁️ Cloud or Self-Hosted — Your Choice
Self-service cloud starting at $15/month with auto-scaling & global CDN. Or deploy locally/on-prem.
One-click deploy via #Railway included.
📊 The Numbers Speak for Themselves:
⭐ 34.5k GitHub St…

"The Ocean Cleanup removed a record 25 million kilos of plastic in 2025 (and they’re just getting started)"
#Oceans #Environment #Plastic

The Ocean Cleanup removed a record 25 million kilos of plastic in 2025 (and they’re just getting started) | The Optimist Daily
With 25 million kilos of plastic removed in 2025 alone, The Ocean Cleanup is scaling up efforts to tackle plastic pollution from rivers to open ocean.

Firefox is choking on video on my 4k monitor on Kubuntu. Youtube's status for nerds is showing 10 - 20% of frames dropped.
Chromium is fine. I think removing all the monitor scaling helps but does not fully fix it.
#ubuntu #linux

And there we are. Trump is already blackmailing Europe with 'his' LNG. We urgently need to reduce our natural gas consumption by speeding up the energy transition: focus on energy efficiency, electrification, and scaling up EU production of biomethane, developing way too slow to meet its 2030 target.

Trump Threatens to Cut Off EU's American LNG Supplies - Washington Today
US President Donald Trump is threatening to cut off American liquefied natural gas (LNG) supplies to the European Union if Brussels refuses to ratify a trade agreement favorable to Washington. The US Ambassador to the EU, Andrew Puzder, stated that the implementation of the energy part of the agreement would be in question if the EU demanded changes to any points of the document.

Time is Not Compute: Scaling Laws for Wall-Clock Constrained Training on Consumer GPUs
Yi Liu
https://arxiv.org/abs/2603.28823 https://arxiv.org/pdf/2603.28823 https://arxiv.org/html/2603.28823
arXiv:2603.28823v1 Announce Type: new
Abstract: Scaling laws relate model quality to compute budget (FLOPs), but practitioners face wall-clock time constraints, not compute budgets. We study optimal model sizing under fixed time budgets from 5 minutes to 24 hours on consumer GPUs (RTX 4090). Across 70 runs spanning 50M--1031M parameters, we find: (1)~at each time budget a U-shaped curve emerges where too-small models overfit and too-large models undertrain; (2)~optimal model size follows $N^* \propto t^{0.60}$, growing \emph{faster} than Chinchilla's $N^* \propto C^{0.50}$, with $\alpha = 0.60 \pm 0.07$ robustly exceeding compute-optimal across all sensitivity analyses; (3)~a \emph{dual U-shape mechanism}: short-budget U-curves arise from compute bottlenecks, while long-budget U-curves emerge from data bottlenecks (overfitting), with an intermediate regime where the U-curve temporarily disappears. These findings have immediate implications for researchers training on consumer hardware, where wall-clock time -- not FLOPs -- is the binding constraint. We release all code, logs, and 70 experimental configurations.
toXiv_bot_toot

Cursor's recent experiment involved running hundreds of AI agents for nearly a week to build a web browser, writing 1M lines of code across 1,000 files (Simon Willison/Simon Willison's Weblog)
https://simonwillison.net/2026/Jan/19/scaling-long-running-a…

Scaling long-running autonomous coding
Wilson Lin at Cursor has been doing some experiments to see how far you can push a large fleet of "autonomous" coding agents: This post describes what we've learned from …

Practically just waiting for #Gnome 50 to release to give it another shot. Stabilization of VRR and fractional scaling, plus so many improvements to the Gnome Mutter compositor make me curious.
Weirdly this is a controversial opinion, but I absolutely love the #Adwaita design language and …

@… wrt recent github tickets (on my phone and can't comment on the thread yet): the point of making it an env var is that *you do not need to use the UI to set it*.
If you're stuck in an edge case with broken scaling auto detection and the UI is tiny or enormous you probably won't be able to effectively interact with the preferenc…

Replaced article(s) found for cs.OS. https://arxiv.org/list/cs.OS/new
[1/1]:
- Flare: Anomaly Diagnostics for Divergent LLM Training in GPU Clusters of Thousand-Plus Scale
Weihao Cui, Ji Zhang, Han Zhao, Chao Liu, Jian Sha, Bingsheng He, Minyi Guo, Quan Chen
https://arxiv.org/abs/2502.05413 https://mastoxiv.page/@arXiv_csOS_bot/113983966659919298
- Towards High-Goodput LLM Serving with Prefill-decode Multiplexing
Chen, Cui, Zhao, Xu, Fan, Chen, Zhou, Sun, He, Chen
https://arxiv.org/abs/2504.14489 https://mastoxiv.page/@arXiv_csOS_bot/114380402335312857
- Scaling Data Center TCP to Terabits with Laminar
Rajath Shashidhara, Antoine Kaufmann, Simon Peter
https://arxiv.org/abs/2504.19058 https://mastoxiv.page/@arXiv_csNI_bot/114420037697903281
toXiv_bot_toot

Q&A with Elizabeth Hansen Shapiro on her new report, to be published next week, which argues local news funders should pick winners, scale up, and force mergers (Richard Tofel/Nieman Lab)
https://www.niemanlab.org/2026/03/its-time…

It’s time for local news funders to pick winners, scale up, and force mergers, a new report argues
"I don’t think we’re in a stage, any longer, of innovation. It really is a challenge of what are the scaling solutions."

reading a prelim paper on scaling up gpu-accelerated database query engines and feeling kinda gobsmacked at where that world is at
i remember when we built a “massive” memory machine at princeton with … i think it was 256 MB of RAM. (it sat idle except when ken thompson was logged in and building hash tables for chess endgames which was most of the time)

Marco DeepResearch: Unlocking Efficient Deep Research Agents via Verification-Centric Design
Bin Zhu, Qianghuai Jia, Tian Lan, Junyang Ren, Feng Gu, Feihu Jiang, Longyue Wang, Zhao Xu, Weihua Luo
https://arxiv.org/abs/2603.28376 https://arxiv.org/pdf/2603.28376 https://arxiv.org/html/2603.28376
arXiv:2603.28376v1 Announce Type: new
Abstract: Deep research agents autonomously conduct open-ended investigations, integrating complex information retrieval with multi-step reasoning across diverse sources to solve real-world problems. To sustain this capability on long-horizon tasks, reliable verification is critical during both training and inference. A major bottleneck in existing paradigms stems from the lack of explicit verification mechanisms in QA data synthesis, trajectory construction, and test-time scaling. Errors introduced at each stage propagate downstream and degrade the overall agent performance. To address this, we present Marco DeepResearch, a deep research agent optimized with a verification-centric framework design at three levels: \textbf{(1)~QA Data Synthesis:} We introduce verification mechanisms to graph-based and agent-based QA synthesis to control question difficulty while ensuring answers are unique and correct; \textbf{(2)~Trajectory Construction:} We design a verification-driven trajectory synthesis method that injects explicit verification patterns into training trajectories; and \textbf{(3)~Test-time scaling:} We use Marco DeepResearch itself as a verifier at inference time and effectively improve performance on challenging questions. Extensive experimental results demonstrate that our proposed Marco DeepResearch agent significantly outperforms 8B-scale deep research agents on most challenging benchmarks, such as BrowseComp and BrowseComp-ZH. Crucially, under a maximum budget of 600 tool calls, Marco DeepResearch even surpasses or approaches several 30B-scale agents, like Tongyi DeepResearch-30B.
toXiv_bot_toot

@… how many you have? Got 160 pods on my cluster with the 4 nodes running, it more than doubles when things start scaling

Replaced article(s) found for cs.DS. https://arxiv.org/list/cs.DS/new
[1/1]:
- Fully Dynamic Adversarially Robust Correlation Clustering in Polylogarithmic Update Time
Vladimir Braverman, Prathamesh Dharangutte, Shreyas Pai, Vihan Shah, Chen Wang
https://arxiv.org/abs/2411.09979 https://mastoxiv.page/@arXiv_csDS_bot/113502653187863544
- A Simple and Combinatorial Approach to Proving Chernoff Bounds and Their Generalizations
William Kuszmaul
https://arxiv.org/abs/2501.03488 https://mastoxiv.page/@arXiv_csDS_bot/113791396712128907
- The Structural Complexity of Matrix-Vector Multiplication
Emile Anand, Jan van den Brand, Rose McCarty
https://arxiv.org/abs/2502.21240 https://mastoxiv.page/@arXiv_csDS_bot/114097340825270885
- Clustering under Constraints: Efficient Parameterized Approximation Schemes
Sujoy Bhore, Ameet Gadekar, Tanmay Inamdar
https://arxiv.org/abs/2504.06980 https://mastoxiv.page/@arXiv_csDS_bot/114312444050875805
- Minimizing Envy and Maximizing Happiness in Graphical House Allocation
Anubhav Dhar, Ashlesha Hota, Palash Dey, Sudeshna Kolay
https://arxiv.org/abs/2505.00296 https://mastoxiv.page/@arXiv_csDS_bot/114437013364446063
- Fast and Simple Densest Subgraph with Predictions
Thai Bui, Luan Nguyen, Hoa T. Vu
https://arxiv.org/abs/2505.12600 https://mastoxiv.page/@arXiv_csDS_bot/114538936921930134
- Compressing Suffix Trees by Path Decompositions
Becker, Cenzato, Gagie, Kim, Koerkamp, Manzini, Prezza
https://arxiv.org/abs/2506.14734 https://mastoxiv.page/@arXiv_csDS_bot/114703384646892523
- Improved sampling algorithms and functional inequalities for non-log-concave distributions
Yuchen He, Zhehan Lei, Jianan Shao, Chihao Zhang
https://arxiv.org/abs/2507.11236 https://mastoxiv.page/@arXiv_csDS_bot/114862112197588124
- Deterministic Lower Bounds for $k$-Edge Connectivity in the Distributed Sketching Model
Peter Robinson, Ming Ming Tan
https://arxiv.org/abs/2507.11257 https://mastoxiv.page/@arXiv_csDS_bot/114862223634372292
- Optimally detecting uniformly-distributed $\ell_2$ heavy hitters in data streams
Santhoshini Velusamy, Huacheng Yu
https://arxiv.org/abs/2509.07286 https://mastoxiv.page/@arXiv_csDS_bot/115178875220889588
- Uncrossed Multiflows and Applications to Disjoint Paths
Chandra Chekuri, Guyslain Naves, Joseph Poremba, F. Bruce Shepherd
https://arxiv.org/abs/2511.00254 https://mastoxiv.page/@arXiv_csDS_bot/115490402963680492
- Dynamic Matroids: Base Packing and Covering
Tijn de Vos, Mara Grilnberger
https://arxiv.org/abs/2511.15460 https://mastoxiv.page/@arXiv_csDS_bot/115580946319285096
- Branch-width of connectivity functions is fixed-parameter tractable
Tuukka Korhonen, Sang-il Oum
https://arxiv.org/abs/2601.04756 https://mastoxiv.page/@arXiv_csDS_bot/115864074799755995
- CoinPress: Practical Private Mean and Covariance Estimation
Sourav Biswas, Yihe Dong, Gautam Kamath, Jonathan Ullman
https://arxiv.org/abs/2006.06618
- The Ideal Membership Problem and Abelian Groups
Andrei A. Bulatov, Akbar Rafiey
https://arxiv.org/abs/2201.05218
- Bridging Classical and Quantum: Group-Theoretic Approach to Quantum Circuit Simulation
Daksh Shami
https://arxiv.org/abs/2407.19575 https://mastoxiv.page/@arXiv_quantph_bot/112874282709517475
- Young domination on Hamming rectangles
Janko Gravner, Matja\v{z} Krnc, Martin Milani\v{c}, Jean-Florent Raymond
https://arxiv.org/abs/2501.03788 https://mastoxiv.page/@arXiv_mathCO_bot/113791421814248215
- On the Space Complexity of Online Convolution
Joel Daniel Andersson, Amir Yehudayoff
https://arxiv.org/abs/2505.00181 https://mastoxiv.page/@arXiv_csCC_bot/114437005955255553
- Universal Solvability for Robot Motion Planning on Graphs
Anubhav Dhar, Pranav Nyati, Tanishq Prasad, Ashlesha Hota, Sudeshna Kolay
https://arxiv.org/abs/2506.18755 https://mastoxiv.page/@arXiv_csCC_bot/114737342714568702
- Colorful Minors
Evangelos Protopapas, Dimitrios M. Thilikos, Sebastian Wiederrecht
https://arxiv.org/abs/2507.10467
- Learning fermionic linear optics with Heisenberg scaling and physical operations
Aria Christensen, Andrew Zhao
https://arxiv.org/abs/2602.05058
toXiv_bot_toot

“AI Prototyping Fallacy”: Because I’m used to code doing the same thing over and over again and reasonably scaling, I’m quite sure same approach can be used for evaluating LLMs!

Jay Graber is stepping down as Bluesky CEO, saying a "seasoned operator focused on scaling and execution" is needed; VC Toni Schneider is named interim CEO (Kate Knibbs/Wired)
https://www.wired.com/story/bluesky-ceo-jay-graber-is-stepping-down/
…

Bluesky CEO Jay Graber Is Stepping Down
Venture capitalist Toni Schneider will take over as interim CEO as Bluesky’s board of directors hunts for a permanent replacement.

Contrasting success in neurotechnology: Sensory substitution, brain–computer interfaces, and the limits of dimensional reduction https://www.researchgate.net/publication/3

I've been a GNOME user primarily for... probably over a decade at this point, occasionally trying #KDEPlasma. Nothing particularly bad about GNOME but recently been having some issues with scaling and theming so decided to try Plasma 6 and I think it might stick this time!

Crosslisted article(s) found for astro-ph.GA. https://arxiv.org/list/astro-ph.GA/new
[1/1]:
- Analytical Scaling of Relativistic Drag in the Interstellar Medium
Lucky Gangwar

Australian Business Podcast
Australia's top business podcast for growing and scaling your business from idea to a 7-figure exit...
Great Australian Pods Podcast Directory: https://www.greataustralianpods.com/australian-business/

OpenAI says ChatGPT has 900M weekly active users, 50M consumer subscribers, and weekly Codex users have more than tripled since the start of the year to 1.6M (OpenAI)
https://openai.com/index/scaling-ai-for-everyone

National Grid DSO's contracted flexibility numbers are impressive. The domestic segment is showing particularly strong growth, with EV charging accounting for the majority of this. Many small units are coming together to make a big contribution.
https://dso.nationalg…

Scaling Vision Transformers: Evaluating DeepSpeed for Image-Centric Workloads
Huy Trinh, Rebecca Ma, Zeqi Yu, Tahsin Reza
https://arxiv.org/abs/2602.21081 https://arxiv.org/pdf/2602.21081 https://arxiv.org/html/2602.21081
arXiv:2602.21081v1 Announce Type: new
Abstract: Vision Transformers (ViTs) have demonstrated remarkable potential in image processing tasks by utilizing self-attention mechanisms to capture global relationships within data. However, their scalability is hindered by significant computational and memory demands, especially for large-scale models with many parameters. This study aims to leverage DeepSpeed, a highly efficient distributed training framework that is commonly used for language models, to enhance the scalability and performance of ViTs. We evaluate intra- and inter-node training efficiency across multiple GPU configurations on various datasets like CIFAR-10 and CIFAR-100, exploring the impact of distributed data parallelism on training speed, communication overhead, and overall scalability (strong and weak scaling). By systematically varying software parameters, such as batch size and gradient accumulation, we identify key factors influencing performance of distributed training. The experiments in this study provide a foundational basis for applying DeepSpeed to image-related tasks. Future work will extend these investigations to deepen our understanding of DeepSpeed's limitations and explore strategies for optimizing distributed training pipelines for Vision Transformers.
toXiv_bot_toot

Proton Energy Dependence of Radiation Induced Low Gain Avalanche Detector Degradation
Veronika Kraus, Marcos Fernandez Garcia, Luca Menzio, Michael Moll
https://arxiv.org/abs/2602.01800 https://arxiv.org/pdf/2602.01800 https://arxiv.org/html/2602.01800
arXiv:2602.01800v1 Announce Type: new
Abstract: Low Gain Avalanche Detectors (LGADs) are key components for precise timing measurements in high-energy physics experiments, including the High Luminosity upgrades of the current LHC detectors. Their performance is, however, limited by radiation induced degradation of the gain layer, primarily driven by acceptor removal. This study presents a systematic comparison of how the degradation evolves with different incident proton energies, using LGADs from Hamamatsu Photonics (HPK) and The Institute of Microelectronics of Barcelona (IMB-CNM) irradiated with 18 MeV, 24 MeV, 400 MeV and 23 GeV protons and fluences up to 2.5x10^15 p/cm2. Electrical characterization is used to extract the acceptor removal coefficients for different proton energies, whereas IR TCT measurements offer complementary insight into the gain evolution in LGADs after irradiation. Across all devices, lower energy protons induce stronger gain layer degradation, confirming expectations. However, 400 MeV protons consistently appear less damaging than both lower and higher energy protons, an unexpected deviation from a monotonic energy trend. Conversion of proton fluences to 1 MeV neutron-equivalent fluences reduces but does not eliminate these differences, indicating that the standard Non-Ionizing Energy Loss (NIEL) scaling does not fully account for the underlying defect formation mechanisms at different energies and requires revision when considering irradiation fields that contain a broader spectrum of particle types and energies.
toXiv_bot_toot

Prandtl number dependence of rotating internally heated convection
Rodolfo Ostilla-M\'onico, Ali Arslan
https://arxiv.org/abs/2602.21860 https://arxiv.org/pdf/2602.21860 https://arxiv.org/html/2602.21860
arXiv:2602.21860v1 Announce Type: new
Abstract: We investigate the influence of the Prandtl number ($Pr$) on penetrative internally heated convection (IHC) in both non-rotating and rotating regimes using three-dimensional direct numerical simulations. By varying $Pr$ between 0.1 and 100, we show that the global mean temperature $\langle \overline{T} \rangle$ is not very sensitive to $Pr$, and is primarily controlled by the dynamics of the unstably stratified top boundary layer. In contrast, the Prandtl number dictates the behavior of the lower, stably stratified region and affects the vertical convective heat flux $\langle \overline{wT} \rangle$. In the non-rotating case, low $Pr$ fluids exhibit a ``symmetry recovery'' where turbulent stirring agitates the stable layer, whereas high $Pr$ fluids transition toward a ``dead zone'' of suppressed fluctuations. Under rotation, we find that $\langle \overline{wT} \rangle$ is enhanced across all Prandtl numbers, though global cooling efficiency, measured by the reduction in $\langle \overline{T} \rangle$, is only improved for $Pr\ge1$ due to the emergence of Ekman pumping. These results demonstrate that while IHC shares some scaling similarities with Rayleigh-B\'enard convection at the top boundary, the internal stratification creates a unique sensitivity to $Pr$ that is critical for understanding heat transport in planetary and stellar interiors.
toXiv_bot_toot

Sources: Apple wound down plans for an AI-based virtual health coach in recent weeks; Eddy Cue has told colleagues that Apple needs to move faster in health (Mark Gurman/Bloomberg)
https://www.bloomberg.com/news/articles/20…

Taking a step closer to scaling up residential #V2G, a nationwide network of Swedish electricians will start offering installations of the Ambibox DC bidirectional charger (compatible with cars from the VW Group) in February.

Replaced article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[1/5]:
- Beyond In-Distribution Success: Scaling Curves of CoT Granularity for Language Model Generalization
Ru Wang, Wei Huang, Selena Song, Haoyu Zhang, Qian Niu, Yusuke Iwasawa, Yutaka Matsuo, Jiaxian Guo
https://arxiv.org/abs/2502.18273 https://mastoxiv.page/@arXiv_csCL_bot/114069031700102129
- Benchmarking NLP-supported Language Sample Analysis for Swiss Children's Speech
Anja Ryser, Yingqiang Gao, Sarah Ebling
https://arxiv.org/abs/2504.00780 https://mastoxiv.page/@arXiv_csCL_bot/114267149909002069
- Cultural Biases of Large Language Models and Humans in Historical Interpretation
Fabio Celli, Georgios Spathulas
https://arxiv.org/abs/2504.02572 https://mastoxiv.page/@arXiv_csCL_bot/114278467094094490
- BRIDGE: Benchmarking Large Language Models for Understanding Real-world Clinical Practice Text
Jiageng Wu, et al.
https://arxiv.org/abs/2504.19467 https://mastoxiv.page/@arXiv_csCL_bot/114420036189999973
- Understanding the Anchoring Effect of LLM with Synthetic Data: Existence, Mechanism, and Potentia...
Yiming Huang, Biquan Bie, Zuqiu Na, Weilin Ruan, Songxin Lei, Yutao Yue, Xinlei He
https://arxiv.org/abs/2505.15392 https://mastoxiv.page/@arXiv_csCL_bot/114550277171100272
- Just as Humans Need Vaccines, So Do Models: Model Immunization to Combat Falsehoods
Raza, Qureshi, Farooq, Lotif, Chadha, Pandya, Emmanouilidis
https://arxiv.org/abs/2505.17870 https://mastoxiv.page/@arXiv_csCL_bot/114572956853819813
- LingoLoop Attack: Trapping MLLMs via Linguistic Context and State Entrapment into Endless Loops
Fu, Jiang, Hong, Li, Guo, Yang, Chen, Zhang
https://arxiv.org/abs/2506.14493 https://mastoxiv.page/@arXiv_csCL_bot/114703502552989170
- GHTM: A Graph-based Hybrid Topic Modeling Approach with a Benchmark Dataset for the Low-Resource ...
Farhana Haque, Md. Abdur Rahman, Sumon Ahmed
https://arxiv.org/abs/2508.00605 https://mastoxiv.page/@arXiv_csCL_bot/114969875643478303
- Link Prediction for Event Logs in the Process Industry
Anastasia Zhukova, Thomas Walton, Christian E. Lobm\"uller, Bela Gipp
https://arxiv.org/abs/2508.09096 https://mastoxiv.page/@arXiv_csCL_bot/115020938764936882
- AirQA: A Comprehensive QA Dataset for AI Research with Instance-Level Evaluation
Huang, Cao, Zhang, Kang, Wang, Wang, Luo, Zheng, Qian, Chen, Yu
https://arxiv.org/abs/2509.16952 https://mastoxiv.page/@arXiv_csCL_bot/115253526588472475
- Multi-View Attention Multiple-Instance Learning Enhanced by LLM Reasoning for Cognitive Distortio...
Jun Seo Kim, Hyemi Kim, Woo Joo Oh, Hongjin Cho, Hochul Lee, Hye Hyeon Kim
https://arxiv.org/abs/2509.17292 https://mastoxiv.page/@arXiv_csCL_bot/115253586227941157
- Dual-Space Smoothness for Robust and Balanced LLM Unlearning
Han Yan, Zheyuan Liu, Meng Jiang
https://arxiv.org/abs/2509.23362 https://mastoxiv.page/@arXiv_csCL_bot/115293308293558024
- The Rise of AfricaNLP: Contributions, Contributors, Community Impact, and Bibliometric Analysis
Tadesse Destaw Belay, et al.
https://arxiv.org/abs/2509.25477 https://mastoxiv.page/@arXiv_csCL_bot/115298213432594791
- Open ASR Leaderboard: Towards Reproducible and Transparent Multilingual and Long-Form Speech Reco...
Srivastav, Zheng, Bezzam, Le Bihan, Koluguri, \.Zelasko, Majumdar, Moumen, Gandhi
https://arxiv.org/abs/2510.06961 https://mastoxiv.page/@arXiv_csCL_bot/115343748052193267
- Neuron-Level Analysis of Cultural Understanding in Large Language Models
Taisei Yamamoto, Ryoma Kumon, Danushka Bollegala, Hitomi Yanaka
https://arxiv.org/abs/2510.08284 https://mastoxiv.page/@arXiv_csCL_bot/115349533441895984
- CLMN: Concept based Language Models via Neural Symbolic Reasoning
Yibo Yang
https://arxiv.org/abs/2510.10063 https://mastoxiv.page/@arXiv_csCL_bot/115372392366793754
- Schema for In-Context Learning
Chen, Chen, Wang, Leong, Fung, Bernales, Aspuru-Guzik
https://arxiv.org/abs/2510.13905 https://mastoxiv.page/@arXiv_csCL_bot/115389057899856601
- Evaluating Latent Knowledge of Public Tabular Datasets in Large Language Models
Matteo Silvestri, Fabiano Veglianti, Flavio Giorgi, Fabrizio Silvestri, Gabriele Tolomei
https://arxiv.org/abs/2510.20351 https://mastoxiv.page/@arXiv_csCL_bot/115428615784704418
- LuxIT: A Luxembourgish Instruction Tuning Dataset from Monolingual Seed Data
Julian Valline, Cedric Lothritz, Siwen Guo, Jordi Cabot
https://arxiv.org/abs/2510.24434 https://mastoxiv.page/@arXiv_csCL_bot/115457025096322944
- Surfacing Subtle Stereotypes: A Multilingual, Debate-Oriented Evaluation of Modern LLMs
Muhammed Saeed, Muhammad Abdul-mageed, Shady Shehata
https://arxiv.org/abs/2511.01187 https://mastoxiv.page/@arXiv_csCL_bot/115491321130591723
toXiv_bot_toot

Extending $\mu$P: Spectral Conditions for Feature Learning Across Optimizers
Akshita Gupta, Marieme Ngom, Sam Foreman, Venkatram Vishwanath
https://arxiv.org/abs/2602.20937 https://arxiv.org/pdf/2602.20937 https://arxiv.org/html/2602.20937
arXiv:2602.20937v1 Announce Type: new
Abstract: Several variations of adaptive first-order and second-order optimization methods have been proposed to accelerate and scale the training of large language models. The performance of these optimization routines is highly sensitive to the choice of hyperparameters (HPs), which are computationally expensive to tune for large-scale models. Maximal update parameterization $(\mu$P$)$ is a set of scaling rules which aims to make the optimal HPs independent of the model size, thereby allowing the HPs tuned on a smaller (computationally cheaper) model to be transferred to train a larger, target model. Despite promising results for SGD and Adam, deriving $\mu$P for other optimizers is challenging because the underlying tensor programming approach is difficult to grasp. Building on recent work that introduced spectral conditions as an alternative to tensor programs, we propose a novel framework to derive $\mu$P for a broader class of optimizers, including AdamW, ADOPT, LAMB, Sophia, Shampoo and Muon. We implement our $\mu$P derivations on multiple benchmark models and demonstrate zero-shot learning rate transfer across increasing model width for the above optimizers. Further, we provide empirical insights into depth-scaling parameterization for these optimizers.
toXiv_bot_toot

Fast $k$-means Seeding Under The Manifold Hypothesis
Poojan Shah, Shashwat Agrawal, Ragesh Jaiswal
https://arxiv.org/abs/2602.01104 https://arxiv.org/pdf/2602.01104 https://arxiv.org/html/2602.01104
arXiv:2602.01104v1 Announce Type: new
Abstract: We study beyond worst case analysis for the $k$-means problem where the goal is to model typical instances of $k$-means arising in practice. Existing theoretical approaches provide guarantees under certain assumptions on the optimal solutions to $k$-means, making them difficult to validate in practice. We propose the manifold hypothesis, where data obtained in ambient dimension $D$ concentrates around a low dimensional manifold of intrinsic dimension $d$, as a reasonable assumption to model real world clustering instances. We identify key geometric properties of datasets which have theoretically predictable scaling laws depending on the quantization exponent $\varepsilon = 2/d$ using techniques from optimum quantization theory. We show how to exploit these regularities to design a fast seeding method called $\operatorname{Qkmeans}$ which provides $O(\rho^{-2} \log k)$ approximate solutions to the $k$-means problem in time $O(nD) \widetilde{O}(\varepsilon^{1 \rho}\rho^{-1}k^{1 \gamma})$; where the exponent $\gamma = \varepsilon \rho$ for an input parameter $\rho < 1$. This allows us to obtain new runtime - quality tradeoffs. We perform a large scale empirical study across various domains to validate our theoretical predictions and algorithm performance to bridge theory and practice for beyond worst case data clustering.
toXiv_bot_toot

Monzo is shuttering its US operations to focus on scaling in the UK and Europe; source: it will lay off ~50 employees and close clients' accounts in June (Aisha S Gani/Bloomberg)
https://www.bloomberg.com/news/articles/20…

"Pod is now scaling its smart charging capabilities across its existing customer base and extending access to rewards beyond early trials and subscribers to its all-inclusive Pod Drive charging service. Available to thousands more #EV drivers across the UK, Pod could pay out well over £1m in rewards by the end of the year."

Frequency-Dependent Magnetic modulation of deposition morphology
S. K. Saroj, P. K. Panigrahi
https://arxiv.org/abs/2602.21789 https://arxiv.org/pdf/2602.21789 https://arxiv.org/html/2602.21789
arXiv:2602.21789v1 Announce Type: new
Abstract: This paper presents a novel approach for magnetic modulation of deposition morphology in an evaporating ferrofluid droplet. The magnetic field strength and ferrofluid concentration are kept unchanged, while the actuation frequencies are varied from 0.016 Hz to 5 Hz. In the absence of a magnetic field, a coffee-ring formation is observed and consistent with previous studies\cite{deegan1997capillary,deegan2000contact,saroj2019drying}. The application of a time-dependent magnetic field significantly modifies the deposition morphology. The periodic magnetic field induces the formation of multiple concentric rings during evaporation. The number of rings initially increases with increasing actuation frequency of the electromagnet. However, beyond a critical actuation frequency ($f_c = 0.2\,\text{Hz}$), the number of rings decreases. At higher actuation frequencies, magnetic particles preferentially deposit in the central region of the droplet, resulting in suppression of the coffee-ring effect. Additionally, the thickness of the inner rings and the ring spacing decrease with increasing actuation frequency up to critical actuation frequency. The transition from multi-ring formation to coffee-ring suppression is governed by the competition among magnetic forcing, capillary flow, and particle diffusion. The underlying physical mechanisms responsible for droplet dynamics and deposition morphology under periodic magnetic fields are evaluated using scaling arguments. The results demonstrate that diffusive particle transport plays a dominant role in determining the deposition pattern. A non-dimensional magnetic switching number, based on the magnetic perturbation timescale, is introduced as a control parameter to characterize the frequency-dependent deposition behavior.
toXiv_bot_toot

Anthropic adjusts Claude session limits and says users will use up their limits faster during peak hours, amid compute strain due to Claude's new popularity (Brent D. Griffiths/Business Insider)
https://www.businessinsider.com/claude-usage-caps-chang…

Claude's popularity is forcing it to hit the brakes on users
"I know this was frustrating," an Anthropic official wrote in an announcement of the changes. "We're continuing to invest in scaling efficiently.

Compressing Transformer Language Models via Matrix Product Operator Decomposition: A Case Study on PicoGPT
Younes Javanmard, Tanmoy Pandit, Masoud Mardani
https://arxiv.org/abs/2603.28534 https://arxiv.org/pdf/2603.28534 https://arxiv.org/html/2603.28534
arXiv:2603.28534v1 Announce Type: new
Abstract: Transformer-based language models achieve strong performance across NLP tasks, but their quadratic parameter scaling with hidden dimension makes deployment on resource-constrained hardware expensive. We study Matrix Product Operator (MPO) decomposition as a principled compression method for transformers. MPO factorises weight matrices into chains of low-rank cores, with approximation quality controlled by the bond dimension chi. We replace every nn.Linear layer in PicoGPT, a GPT-2-style character-level language model with about 1M parameters, with an MPOLinear module parameterised as an MPO chain. Cores are initialised either by TT-SVD from pretrained dense weights or from random initialisation, and trained using standard PyTorch autograd without a custom backward pass. We derive balanced factorisation schemes for the five distinct weight shapes in PicoGPT and evaluate bond dimensions chi in {4, 8, 16, 32} on Tiny Shakespeare. MPO compression achieves up to 13x compression per transformer block at chi = 4. At chi = 16, the model uses 191,872 parameters instead of 1,020,224 while retaining 97.7% of baseline token accuracy (51.6% vs 52.8%). Reconstruction error follows the expected trend and is lower for three-site than two-site factorisations at the same bond dimension. The chi = 8 model gives the best accuracy per parameter, exceeding the dense baseline by 2.7x on this metric. These results show that MPO parameterisation is a practical and theoretically grounded alternative to low-rank methods and unstructured pruning for transformer compression.
toXiv_bot_toot

Memo: Sam Altman says OpenAI's next model finished pretraining, and moves Safety to Research and Security to Scaling; Fidji Simo becomes CEO of "AGI Deployment" (Alex Heath/Sources)
https://sources.news/p/why-openai-killed-sora

Why OpenAI killed Sora
It's about GPUs. Also: CPUs are back, Meta's big stock awards, a CEO actually not blaming AI for layoffs, and more.

Q&A with Jensen Huang, who says "we've achieved AGI", on running Nvidia, AI scaling laws, OpenClaw, future of coding, data centers in space, China, and more (Lex Fridman)
https://lexfridman.com/jensen-huang-transcript

Untied Ulysses: Memory-Efficient Context Parallelism via Headwise Chunking
Ravi Ghadia, Maksim Abraham, Sergei Vorobyov, Max Ryabinin
https://arxiv.org/abs/2602.21196 https://arxiv.org/pdf/2602.21196 https://arxiv.org/html/2602.21196
arXiv:2602.21196v1 Announce Type: new
Abstract: Efficiently processing long sequences with Transformer models usually requires splitting the computations across accelerators via context parallelism. The dominant approaches in this family of methods, such as Ring Attention or DeepSpeed Ulysses, enable scaling over the context dimension but do not focus on memory efficiency, which limits the sequence lengths they can support. More advanced techniques, such as Fully Pipelined Distributed Transformer or activation offloading, can further extend the possible context length at the cost of training throughput. In this paper, we present UPipe, a simple yet effective context parallelism technique that performs fine-grained chunking at the attention head level. This technique significantly reduces the activation memory usage of self-attention, breaking the activation memory barrier and unlocking much longer context lengths. Our approach reduces intermediate tensor memory usage in the attention layer by as much as 87.5$\%$ for 32B Transformers, while matching previous context parallelism techniques in terms of training speed. UPipe can support the context length of 5M tokens when training Llama3-8B on a single 8$\times$H100 node, improving upon prior methods by over 25$\%$.
toXiv_bot_toot

Replaced article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[4/5]:
- Retrieving Climate Change Disinformation by Narrative
Upravitelev, Solopova, Jakob, Sahitaj, M\"oller, Schmitt
https://arxiv.org/abs/2603.22015 https://mastoxiv.page/@arXiv_csCL_bot/116283633674519408
- PaperVoyager : Building Interactive Web with Visual Language Models
Dasen Dai, Biao Wu, Meng Fang, Wenhao Wang
https://arxiv.org/abs/2603.22999 https://mastoxiv.page/@arXiv_csCL_bot/116289015432093128
- Continual Robot Skill and Task Learning via Dialogue
Weiwei Gu, Suresh Kondepudi, Anmol Gupta, Lixiao Huang, Nakul Gopalan
https://arxiv.org/abs/2409.03166 https://mastoxiv.page/@arXiv_csRO_bot/113089412115632702
- Shifting Perspectives: Steering Vectors for Robust Bias Mitigation in LLMs
Zara Siddique, Irtaza Khalid, Liam D. Turner, Luis Espinosa-Anke
https://arxiv.org/abs/2503.05371 https://mastoxiv.page/@arXiv_csLG_bot/114136994263573386
- SkillFlow: Scalable and Efficient Agent Skill Retrieval System
Fangzhou Li, Pagkratios Tagkopoulos, Ilias Tagkopoulos
https://arxiv.org/abs/2504.06188 https://mastoxiv.page/@arXiv_csAI_bot/114306773220502860
- Large Language Models for Computer-Aided Design: A Survey
Licheng Zhang, Bach Le, Naveed Akhtar, Siew-Kei Lam, Tuan Ngo
https://arxiv.org/abs/2505.08137 https://mastoxiv.page/@arXiv_csLG_bot/114504972217393639
- Structured Agent Distillation for Large Language Model
Liu, Kong, Dong, Yang, Li, Tang, Yuan, Niu, Zhang, Zhao, Lin, Huang, Wang
https://arxiv.org/abs/2505.13820 https://mastoxiv.page/@arXiv_csLG_bot/114544636506163783
- VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction
Fan, Zhang, Li, Zhang, Chen, Hu, Wang, Qu, Zhou, Wang, Yan, Xu, Theiss, Chen, Li, Tu, Wang, Ranjan
https://arxiv.org/abs/2505.20279 https://mastoxiv.page/@arXiv_csCV_bot/114578817567171199
- Learning to Diagnose Privately: DP-Powered LLMs for Radiology Report Classification
Bhattacharjee, Tian, Rubin, Lo, Merchant, Hanson, Gounley, Tandon
https://arxiv.org/abs/2506.04450 https://mastoxiv.page/@arXiv_csCR_bot/114635189706505648
- L-MARS: Legal Multi-Agent Workflow with Orchestrated Reasoning and Agentic Search
Ziqi Wang, Boqin Yuan
https://arxiv.org/abs/2509.00761 https://mastoxiv.page/@arXiv_csAI_bot/115140304787881576
- Your Models Have Thought Enough: Training Large Reasoning Models to Stop Overthinking
Han, Huang, Liao, Jiang, Lu, Zhao, Wang, Zhou, Jiang, Liang, Zhou, Sun, Yu, Xiao
https://arxiv.org/abs/2509.23392 https://mastoxiv.page/@arXiv_csAI_bot/115293169353788311
- Person-Centric Annotations of LAION-400M: Auditing Bias and Its Transfer to Models
Leander Girrbach, Stephan Alaniz, Genevieve Smith, Trevor Darrell, Zeynep Akata
https://arxiv.org/abs/2510.03721 https://mastoxiv.page/@arXiv_csCV_bot/115332690912652473
- Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
Zhang, Hu, Upasani, Ma, Hong, Kamanuru, Rainton, Wu, Ji, Li, Thakker, Zou, Olukotun
https://arxiv.org/abs/2510.04618 https://mastoxiv.page/@arXiv_csLG_bot/115332999596603375
- Mitigating Premature Exploitation in Particle-based Monte Carlo for Inference-Time Scaling
Giannone, Xu, Nayak, Awhad, Sudalairaj, Xu, Srivastava
https://arxiv.org/abs/2510.05825 https://mastoxiv.page/@arXiv_csLG_bot/115338159696513898
- Complete asymptotic type-token relationship for growing complex systems with inverse power-law co...
Pablo Rosillo-Rodes, Laurent H\'ebert-Dufresne, Peter Sheridan Dodds
https://arxiv.org/abs/2511.02069 https://mastoxiv.page/@arXiv_physicssocph_bot/115496283627867809
- ViPRA: Video Prediction for Robot Actions
Sandeep Routray, Hengkai Pan, Unnat Jain, Shikhar Bahl, Deepak Pathak
https://arxiv.org/abs/2511.07732 https://mastoxiv.page/@arXiv_csRO_bot/115535941444003568
- AISAC: An Integrated multi-agent System for Transparent, Retrieval-Grounded Scientific Assistance
Chandrachur Bhattacharya, Sibendu Som
https://arxiv.org/abs/2511.14043
- VideoARM: Agentic Reasoning over Hierarchical Memory for Long-Form Video Understanding
Yufei Yin, Qianke Meng, Minghao Chen, Jiajun Ding, Zhenwei Shao, Zhou Yu
https://arxiv.org/abs/2512.12360 https://mastoxiv.page/@arXiv_csCV_bot/115729238732682644
- RadImageNet-VQA: A Large-Scale CT and MRI Dataset for Radiologic Visual Question Answering
L\'eo Butsanets, Charles Corbi\`ere, Julien Khlaut, Pierre Manceron, Corentin Dancette
https://arxiv.org/abs/2512.17396 https://mastoxiv.page/@arXiv_csCV_bot/115762705911757243
- Measuring all the noises of LLM Evals
Sida Wang
https://arxiv.org/abs/2512.21326 https://mastoxiv.page/@arXiv_csLG_bot/115779597137785637
toXiv_bot_toot

Learning from Trials and Errors: Reflective Test-Time Planning for Embodied LLMs
Yining Hong, Huang Huang, Manling Li, Li Fei-Fei, Jiajun Wu, Yejin Choi
https://arxiv.org/abs/2602.21198 https://arxiv.org/pdf/2602.21198 https://arxiv.org/html/2602.21198
arXiv:2602.21198v1 Announce Type: new
Abstract: Embodied LLMs endow robots with high-level task reasoning, but they cannot reflect on what went wrong or why, turning deployment into a sequence of independent trials where mistakes repeat rather than accumulate into experience. Drawing upon human reflective practitioners, we introduce Reflective Test-Time Planning, which integrates two modes of reflection: \textit{reflection-in-action}, where the agent uses test-time scaling to generate and score multiple candidate actions using internal reflections before execution; and \textit{reflection-on-action}, which uses test-time training to update both its internal reflection model and its action policy based on external reflections after execution. We also include retrospective reflection, allowing the agent to re-evaluate earlier decisions and perform model updates with hindsight for proper long-horizon credit assignment. Experiments on our newly-designed Long-Horizon Household benchmark and MuJoCo Cupboard Fitting benchmark show significant gains over baseline models, with ablative studies validating the complementary roles of reflection-in-action and reflection-on-action. Qualitative analyses, including real-robot trials, highlight behavioral correction through reflection.
toXiv_bot_toot

Does Order Matter : Connecting The Law of Robustness to Robust Generalization
Himadri Mandal, Vishnu Varadarajan, Jaee Ponde, Aritra Das, Mihir More, Debayan Gupta
https://arxiv.org/abs/2602.20971 https://arxiv.org/pdf/2602.20971 https://arxiv.org/html/2602.20971
arXiv:2602.20971v1 Announce Type: new
Abstract: Bubeck and Sellke (2021) pose as an open problem the connection between the law of robustness and robust generalization. The law of robustness states that overparameterization is necessary for models to interpolate robustly; in particular, robust interpolation requires the learned function to be Lipschitz. Robust generalization asks whether small robust training loss implies small robust test loss. We resolve this problem by explicitly connecting the two for arbitrary data distributions. Specifically, we introduce a nontrivial notion of robust generalization error and convert it into a lower bound on the expected Rademacher complexity of the induced robust loss class. Our bounds recover the $\Omega(n^{1/d})$ regime of Wu et al.\ (2023) and show that, up to constants, robust generalization does not change the order of the Lipschitz constant required for smooth interpolation. We conduct experiments to probe the predicted scaling with dataset size and model capacity, testing whether empirical behavior aligns more closely with the predictions of Bubeck and Sellke (2021) or Wu et al.\ (2023). For MNIST, we find that the lower-bound Lipschitz constant scales on the order predicted by Wu et al.\ (2023). Informally, to obtain low robust generalization error, the Lipschitz constant must lie in a range that we bound, and the allowable perturbation radius is linked to the Lipschitz scale.
toXiv_bot_toot

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[1/6]:
- Towards Attributions of Input Variables in a Coalition
Xinhao Zheng, Huiqi Deng, Quanshi Zhang
https://arxiv.org/abs/2309.13411
- Knee or ROC
Veronica Wendt, Jacob Steiner, Byunggu Yu, Caleb Kelly, Justin Kim
https://arxiv.org/abs/2401.07390
- Rethinking Disentanglement under Dependent Factors of Variation
Antonio Almud\'evar, Alfonso Ortega
https://arxiv.org/abs/2408.07016 https://mastoxiv.page/@arXiv_csLG_bot/112959235461894530
- Minibatch Optimal Transport and Perplexity Bound Estimation in Discrete Flow Matching
Etrit Haxholli, Yeti Z. Gurbuz, Ogul Can, Eli Waxman
https://arxiv.org/abs/2411.00759 https://mastoxiv.page/@arXiv_csLG_bot/113423933393275133
- Predicting Subway Passenger Flows under Incident Situation with Causality
Xiannan Huang, Shuhan Qiu, Quan Yuan, Chao Yang
https://arxiv.org/abs/2412.06871 https://mastoxiv.page/@arXiv_csLG_bot/113632934357523592
- Characterizing LLM Inference Energy-Performance Tradeoffs across Workloads and GPU Scaling
Paul Joe Maliakel, Shashikant Ilager, Ivona Brandic
https://arxiv.org/abs/2501.08219 https://mastoxiv.page/@arXiv_csLG_bot/113831081884570770
- Universality of Benign Overfitting in Binary Linear Classification
Ichiro Hashimoto, Stanislav Volgushev, Piotr Zwiernik
https://arxiv.org/abs/2501.10538 https://mastoxiv.page/@arXiv_csLG_bot/113872351652969955
- Safe Reinforcement Learning for Real-World Engine Control
Julian Bedei, Lucas Koch, Kevin Badalian, Alexander Winkler, Patrick Schaber, Jakob Andert
https://arxiv.org/abs/2501.16613 https://mastoxiv.page/@arXiv_csLG_bot/113910356206562660
- A Statistical Learning Perspective on Semi-dual Adversarial Neural Optimal Transport Solvers
Roman Tarasov, Petr Mokrov, Milena Gazdieva, Evgeny Burnaev, Alexander Korotin
https://arxiv.org/abs/2502.01310
- Improving the Convergence of Private Shuffled Gradient Methods with Public Data
Shuli Jiang, Pranay Sharma, Zhiwei Steven Wu, Gauri Joshi
https://arxiv.org/abs/2502.03652 https://mastoxiv.page/@arXiv_csLG_bot/113961314098841096
- Using the Path of Least Resistance to Explain Deep Networks
Sina Salek, Joseph Enguehard
https://arxiv.org/abs/2502.12108 https://mastoxiv.page/@arXiv_csLG_bot/114023706252106865
- Distributional Vision-Language Alignment by Cauchy-Schwarz Divergence
Wenzhe Yin, Zehao Xiao, Pan Zhou, Shujian Yu, Jiayi Shen, Jan-Jakob Sonke, Efstratios Gavves
https://arxiv.org/abs/2502.17028 https://mastoxiv.page/@arXiv_csLG_bot/114063477202397951
- Armijo Line-search Can Make (Stochastic) Gradient Descent Provably Faster
Sharan Vaswani, Reza Babanezhad
https://arxiv.org/abs/2503.00229 https://mastoxiv.page/@arXiv_csLG_bot/114103018985567633
- Semantic Parallelism: Redefining Efficient MoE Inference via Model-Data Co-Scheduling
Yan Li, Zhenyu Zhang, Zhengang Wang, Pengfei Chen, Pengfei Zheng
https://arxiv.org/abs/2503.04398 https://mastoxiv.page/@arXiv_csLG_bot/114120014622063602
- A Survey on Federated Fine-tuning of Large Language Models
Wu, Tian, Li, Sun, Tam, Zhou, Liao, Xiong, Guo, Li, Xu
https://arxiv.org/abs/2503.12016 https://mastoxiv.page/@arXiv_csLG_bot/114182234054681647
- Towards Trustworthy GUI Agents: A Survey
Yucheng Shi, Wenhao Yu, Jingyuan Huang, Wenlin Yao, Wenhu Chen, Ninghao Liu
https://arxiv.org/abs/2503.23434 https://mastoxiv.page/@arXiv_csLG_bot/114263024618476521
- CONTINA: Confidence Interval for Traffic Demand Prediction with Coverage Guarantee
Chao Yang, Xiannan Huang, Shuhan Qiu, Yan Cheng
https://arxiv.org/abs/2504.13961 https://mastoxiv.page/@arXiv_csLG_bot/114380404041503229
- Regularity and Stability Properties of Selective SSMs with Discontinuous Gating
Nikola Zubi\'c, Davide Scaramuzza
https://arxiv.org/abs/2505.11602 https://mastoxiv.page/@arXiv_csLG_bot/114538965060456498
- RECON: Robust symmetry discovery via Explicit Canonical Orientation Normalization
Alonso Urbano, David W. Romero, Max Zimmer, Sebastian Pokutta
https://arxiv.org/abs/2505.13289 https://mastoxiv.page/@arXiv_csLG_bot/114539124884913788
- RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models
Yilang Zhang, Bingcong Li, Georgios B. Giannakis
https://arxiv.org/abs/2505.18877 https://mastoxiv.page/@arXiv_csLG_bot/114578778213033886
- SuperMAN: Interpretable and Expressive Networks over Temporally Sparse Heterogeneous Data
Bechler-Speicher, Zerio, Huri, Vestergaard, Gilad-Bachrach, Jess, Bhatt, Sazonovs
https://arxiv.org/abs/2505.19193 https://mastoxiv.page/@arXiv_csLG_bot/114578790124778172
toXiv_bot_toot

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[3/6]:
- Towards Scalable Oversight via Partitioned Human Supervision
Ren Yin, Takashi Ishida, Masashi Sugiyama
https://arxiv.org/abs/2510.22500 https://mastoxiv.page/@arXiv_csLG_bot/115451787490434401
- ContextPilot: Fast Long-Context Inference via Context Reuse
Yinsicheng Jiang, Yeqi Huang, Liang Cheng, Cheng Deng, Xuan Sun, Luo Mai
https://arxiv.org/abs/2511.03475 https://mastoxiv.page/@arXiv_csLG_bot/115502245581974540
- Metabolomic Biomarker Discovery for ADHD Diagnosis Using Interpretable Machine Learning
Nabil Belacel, Mohamed Rachid Boulassel
https://arxiv.org/abs/2601.11283 https://mastoxiv.page/@arXiv_csLG_bot/115921183182326799
- PhysE-Inv: A Physics-Encoded Inverse Modeling approach for Arctic Snow Depth Prediction
Akila Sampath, Vandana Janeja, Jianwu Wang
https://arxiv.org/abs/2601.17074
- SAGE-5GC: Security-Aware Guidelines for Evaluating Anomaly Detection in the 5G Core Network
Cristian Manca, Christian Scano, Giorgio Piras, Fabio Brau, Maura Pintor, Battista Biggio
https://arxiv.org/abs/2602.03596
- LORE: Jointly Learning the Intrinsic Dimensionality and Relative Similarity Structure From Ordina...
Anand, Helbling, Davenport, Berman, Alagapan, Rozell
https://arxiv.org/abs/2602.04192
- Towards Robust Scaling Laws for Optimizers
Alexandra Volkova, Mher Safaryan, Christoph H. Lampert, Dan Alistarh
https://arxiv.org/abs/2602.07712 https://mastoxiv.page/@arXiv_csLG_bot/116046369672796465
- Do We Need Adam? Surprisingly Strong and Sparse Reinforcement Learning with SGD in LLMs
Sagnik Mukherjee, Lifan Yuan, Pavan Jayasinha, Dilek Hakkani-T\"ur, Hao Peng
https://arxiv.org/abs/2602.07729 https://mastoxiv.page/@arXiv_csLG_bot/116046377539155485
- AceGRPO: Adaptive Curriculum Enhanced Group Relative Policy Optimization for Autonomous Machine L...
Yuzhu Cai, Zexi Liu, Xinyu Zhu, Cheng Wang, Siheng Chen
https://arxiv.org/abs/2602.07906 https://mastoxiv.page/@arXiv_csLG_bot/116046423413650658
- VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training
Guobin Shen, Chenxiao Zhao, Xiang Cheng, Lei Huang, Xing Yu
https://arxiv.org/abs/2602.10693 https://mastoxiv.page/@arXiv_csLG_bot/116057229834947730
- KBVQ-MoE: KLT-guided SVD with Bias-Corrected Vector Quantization for MoE Large Language Models
Zukang Xu, Zhixiong Zhao, Xing Hu, Zhixuan Chen, Dawei Yang
https://arxiv.org/abs/2602.11184 https://mastoxiv.page/@arXiv_csLG_bot/116062537528208461
- MUSE: Multi-Tenant Model Serving With Seamless Model Updates
Correia, Ferreira, Martins, Bento, Guerreiro, Pereira, Gomes, Bono, Ferreira, Bizarro
https://arxiv.org/abs/2602.11776 https://mastoxiv.page/@arXiv_csLG_bot/116062952355379801
- Pawsterior: Variational Flow Matching for Structured Simulation-Based Inference
Jorge Carrasco-Pollo, Floor Eijkelboom, Jan-Willem van de Meent
https://arxiv.org/abs/2602.13813 https://mastoxiv.page/@arXiv_csLG_bot/116085828112928218
- Silent Inconsistency in Data-Parallel Full Fine-Tuning: Diagnosing Worker-Level Optimization Misa...
Hong Li, Zhen Zhou, Honggang Zhang, Yuping Luo, Xinyue Wang, Han Gong, Zhiyuan Liu
https://arxiv.org/abs/2602.14462 https://mastoxiv.page/@arXiv_csLG_bot/116085997857526328
- Divine Benevolence is an $x^2$: GLUs scale asymptotically faster than MLPs
Alejandro Francisco Queiruga
https://arxiv.org/abs/2602.14495 https://mastoxiv.page/@arXiv_csLG_bot/116086011618741857
- \"UberWeb: Insights from Multilingual Curation for a 20-Trillion-Token Dataset
DatologyAI, et al.
https://arxiv.org/abs/2602.15210 https://mastoxiv.page/@arXiv_csLG_bot/116090912256712568
- GLM-5: from Vibe Coding to Agentic Engineering
GLM-5-Team, et al.
https://arxiv.org/abs/2602.15763 https://mastoxiv.page/@arXiv_csLG_bot/116091080686771018
- Anatomy of Capability Emergence: Scale-Invariant Representation Collapse and Top-Down Reorganizat...
Jayadev Billa
https://arxiv.org/abs/2602.15997 https://mastoxiv.page/@arXiv_csLG_bot/116096541546306333
- AI-CARE: Carbon-Aware Reporting Evaluation Metric for AI Models
KC Santosh, Srikanth Baride, Rodrigue Rizk
https://arxiv.org/abs/2602.16042 https://mastoxiv.page/@arXiv_csLG_bot/116096581524696028
- Beyond Message Passing: A Symbolic Alternative for Expressive and Interpretable Graph Learning
Chuqin Geng, Li Zhang, Haolin Ye, Ziyu Zhao, Yuhe Jiang, Tara Saba, Xinyu Wang, Xujie Si
https://arxiv.org/abs/2602.16947 https://mastoxiv.page/@arXiv_csLG_bot/116102426238903124
toXiv_bot_toot

Crosslisted article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[3/3]:
- Functional Continuous Decomposition
Teymur Aghayev
https://arxiv.org/abs/2602.20857 https://mastoxiv.page/@arXiv_eessSP_bot/116130499236089653
- SpatiaLQA: A Benchmark for Evaluating Spatial Logical Reasoning in Vision-Language Models
Xie, Zhang, Shan, Zhu, Tang, Wei, Song, Wan, Song
https://arxiv.org/abs/2602.20901 https://mastoxiv.page/@arXiv_csCV_bot/116130845273808954
- Some Simple Economics of AGI
Christian Catalini, Xiang Hui, Jane Wu
https://arxiv.org/abs/2602.20946 https://mastoxiv.page/@arXiv_econGN_bot/116130470423837005
- Multimodal MRI Report Findings Supervised Brain Lesion Segmentation with Substructures
Yubin Ge, Yongsong Huang, Xiaofeng Liu
https://arxiv.org/abs/2602.20994 https://mastoxiv.page/@arXiv_eessIV_bot/116130212832138624
- MIP Candy: A Modular PyTorch Framework for Medical Image Processing
Tianhao Fu, Yucheng Chen
https://arxiv.org/abs/2602.21033 https://mastoxiv.page/@arXiv_csCV_bot/116130864279556063
- Empirically Calibrated Conditional Independence Tests
Milleno Pan, Antoine de Mathelin, Wesley Tansey
https://arxiv.org/abs/2602.21036 https://mastoxiv.page/@arXiv_statME_bot/116130690605113562
- Is Multi-Distribution Learning as Easy as PAC Learning: Sharp Rates with Bounded Label Noise
Rafael Hanashiro, Abhishek Shetty, Patrick Jaillet
https://arxiv.org/abs/2602.21039 https://mastoxiv.page/@arXiv_statML_bot/116130572661848449
- Position-Aware Sequential Attention for Accurate Next Item Recommendations
Timur Nabiev, Evgeny Frolov
https://arxiv.org/abs/2602.21052 https://mastoxiv.page/@arXiv_csIR_bot/116130263323086316
- Motivation is Something You Need
Mehdi Acheli, Walid Gaaloul
https://arxiv.org/abs/2602.21064 https://mastoxiv.page/@arXiv_csAI_bot/116130680774678580
- An Enhanced Projection Pursuit Tree Classifier with Visual Methods for Assessing Algorithmic Impr...
Natalia da Silva, Dianne Cook, Eun-Kyung Lee
https://arxiv.org/abs/2602.21130 https://mastoxiv.page/@arXiv_statML_bot/116130610674573081
- Complexity of Classical Acceleration for $\ell_1$-Regularized PageRank
Kimon Fountoulakis, David Mart\'inez-Rubio
https://arxiv.org/abs/2602.21138 https://mastoxiv.page/@arXiv_mathOC_bot/116130547076073836
- LUMEN: Longitudinal Multi-Modal Radiology Model for Prognosis and Diagnosis
Jiang, Yang, Nath, Parida, Kulkarni, Xu, Xu, Anwar, Roth, Linguraru
https://arxiv.org/abs/2602.21142 https://mastoxiv.page/@arXiv_csCV_bot/116130871488694585
- A Benchmark for Deep Information Synthesis
Debjit Paul, et al.
https://arxiv.org/abs/2602.21143 https://mastoxiv.page/@arXiv_csAI_bot/116130692571594706
- Scaling State-Space Models on Multiple GPUs with Tensor Parallelism
Anurag Dutt, Nimit Shah, Hazem Masarani, Anshul Gandhi
https://arxiv.org/abs/2602.21144 https://mastoxiv.page/@arXiv_csDC_bot/116130520888343997
- Not Just How Much, But Where: Decomposing Epistemic Uncertainty into Per-Class Contributions
Mame Diarra Toure, David A. Stephens
https://arxiv.org/abs/2602.21160 https://mastoxiv.page/@arXiv_statML_bot/116130618512594211
- Aletheia tackles FirstProof autonomously
Tony Feng, et al.
https://arxiv.org/abs/2602.21201 https://mastoxiv.page/@arXiv_csAI_bot/116130705679345625
- Squint: Fast Visual Reinforcement Learning for Sim-to-Real Robotics
Abdulaziz Almuzairee, Henrik I. Christensen
https://arxiv.org/abs/2602.21203 https://mastoxiv.page/@arXiv_csRO_bot/116130765974498223
toXiv_bot_toot