Tootfinder

Packers head into bye week seeking to correct costly mistakes from their past two games https://www.foxsports.com/articles/nfl/packers-head-into-bye-week-seeking-to-correct-costly-mistakes-from-their-past-two-games

Efficient Hyperparameter Tuning via Trajectory Invariance Principle
Bingrui Li, Jiaxin Wen, Zhanpeng Zhou, Jun Zhu, Jianfei Chen
https://arxiv.org/abs/2509.25049 https://…

Efficient Hyperparameter Tuning via Trajectory Invariance Principle
As hyperparameter tuning becomes increasingly costly at scale, efficient tuning methods are essential. Yet principles for guiding hyperparameter tuning remain limited. In this work, we seek to establish such principles by considering a broad range of hyperparameters, including batch size, learning rate, and weight decay. We identify a phenomenon we call trajectory invariance, where pre-training loss curves, gradient noise, and gradient norm exhibit invariance--closely overlapping--with respect …

Commitment Gap via Correlation Gap
Shuchi Chawla, Dimitris Christou, Trung Dang
https://arxiv.org/abs/2508.20246 https://arxiv.org/pdf/2508.20246

Commitment Gap via Correlation Gap
Selection problems with costly information, dating back to Weitzman's Pandora's Box problem, have received much attention recently. We study the general model of Costly Information Combinatorial Selection (CICS) that was recently introduced by Chawla et al. [2024] and Bowers et al. [2025]. In this problem, a decision maker needs to select a feasible subset of stochastic variables, and can only learn information about their values through a series of costly steps, modeled by a Markov decision pr…

Personalized Vision via Visual In-Context Learning
Yuxin Jiang, Yuchao Gu, Yiren Song, Ivor Tsang, Mike Zheng Shou
https://arxiv.org/abs/2509.25172 https://

Personalized Vision via Visual In-Context Learning
Modern vision models, trained on large-scale annotated datasets, excel at predefined tasks but struggle with personalized vision -- tasks defined at test time by users with customized objects or novel objectives. Existing personalization approaches rely on costly fine-tuning or synthetic data pipelines, which are inflexible and restricted to fixed task formats. Visual in-context learning (ICL) offers a promising alternative, yet prior methods confine to narrow, in-domain tasks and fail to gener…

After costly personal foul, Schottenheimer calls out Cowboys penalty issues https://cowboyswire.usatoday.com/story/sports/nfl/cowboys/2025/09/30/dallas-cowboys-penalties-vs-packers-brian-schottenhei…

Cardinals committed a costly kickoff blunder in final 30 seconds vs. Seahawks: Breaking down what happened

https://www.cbssports.com/nfl/news/cardina

Paired by the Teacher: Turning Unpaired Data into High-Fidelity Pairs for Low-Resource Text Generation
Yen-Ju Lu, Thomas Thebaud, Laureano Moro-Velazquez, Najim Dehak, Jesus Villalba
https://arxiv.org/abs/2509.25144

Paired by the Teacher: Turning Unpaired Data into High-Fidelity Pairs for Low-Resource Text Generation
We present Paired by the Teacher (PbT), a two-stage teacher-student pipeline that synthesizes accurate input-output pairs without human labels or parallel data. In many low-resource natural language generation (NLG) scenarios, practitioners may have only raw outputs, like highlights, recaps, or questions, or only raw inputs, such as articles, dialogues, or paragraphs, but seldom both. This mismatch forces small models to learn from very few examples or rely on costly, broad-scope synthetic exam…

ActiveCQ: Active Estimation of Causal Quantities
Erdun Gao, Dino Sejdinovic
https://arxiv.org/abs/2509.24293 https://arxiv.org/pdf/2509.24293

ActiveCQ: Active Estimation of Causal Quantities
Estimating causal quantities (CQs) typically requires large datasets, which can be expensive to obtain, especially when measuring individual outcomes is costly. This challenge highlights the importance of sample-efficient active learning strategies. To address the narrow focus of prior work on the conditional average treatment effect, we formalize the broader task of Actively estimating Causal Quantities (ActiveCQ) and propose a unified framework for this general problem. Built upon the insight…

MaskSQL: Safeguarding Privacy for LLM-Based Text-to-SQL via Abstraction
Sepideh Abedini (University of Waterloo, Vector Institute), Shubhankar Mohapatra (University of Waterloo), D. B. Emerson (Vector Institute), Masoumeh Shafieinejad (Vector Institute), Jesse C. Cresswell (Layer 6 AI), Xi He (University of Waterloo, Vector Institute)
https://

MaskSQL: Safeguarding Privacy for LLM-Based Text-to-SQL via Abstraction
Large language models (LLMs) have shown promising performance on tasks that require reasoning, such as text-to-SQL, code generation, and debugging. However, regulatory frameworks with strict privacy requirements constrain their integration into sensitive systems. State-of-the-art LLMs are also proprietary, costly, and resource-intensive, making local deployment impractical. Consequently, utilizing such LLMs often requires sharing data with third-party providers, raising privacy concerns and ris…

SparseServe: Unlocking Parallelism for Dynamic Sparse Attention in Long-Context LLM Serving
Qihui Zhou, Peiqi Yin, Pengfei Zuo, James Cheng
https://arxiv.org/abs/2509.24626 http…

SparseServe: Unlocking Parallelism for Dynamic Sparse Attention in Long-Context LLM Serving
Serving long-context LLMs is costly because attention computation grows linearly with context length. Dynamic sparse attention algorithms (DSAs) mitigate this by attending only to the key-value (KV) cache of critical tokens. However, with DSAs, the main performance bottleneck shifts from HBM bandwidth to HBM capacity: KV caches for unselected tokens must remain in HBM for low-latency decoding, constraining parallel batch size and stalling further throughput gains. Offloading these underutilized…

MTRec: Learning to Align with User Preferences via Mental Reward Models
Mengchen Zhao, Yifan Gao, Yaqing Hou, Xiangyang Li, Pengjie Gu, Zhenhua Dong, Ruiming Tang, Yi Cai
https://arxiv.org/abs/2509.22807

MTRec: Learning to Align with User Preferences via Mental Reward Models
Recommendation models are predominantly trained using implicit user feedback, since explicit feedback is often costly to obtain. However, implicit feedback, such as clicks, does not always reflect users' real preferences. For example, a user might click on a news article because of its attractive headline, but end up feeling uncomfortable after reading the content. In the absence of explicit feedback, such erroneous implicit signals may severely mislead recommender systems. In this paper, we pr…

Scalable Wi-Fi RSS-Based Indoor Localization via Automatic Vision-Assisted Calibration
Abdulkadir Bilge, Erdem Ergen, Burak Soner, Sinem Coleri
https://arxiv.org/abs/2509.22869 …

Scalable Wi-Fi RSS-Based Indoor Localization via Automatic Vision-Assisted Calibration
Wi-Fi-based positioning promises a scalable and privacy-preserving solution for location-based services in indoor environments such as malls, airports, and campuses. RSS-based methods are widely deployable as RSS data is available on all Wi-Fi-capable devices, but RSS is highly sensitive to multipath, channel variations, and receiver characteristics. While supervised learning methods offer improved robustness, they require large amounts of labeled data, which is often costly to obtain. We intro…

Espionage costing Australia $8 billion each year, warns intelligence chief https://therecord.media/espionage-costing-australia-8-billion

Advancing Quantum Many-Body GW Calculations on Exascale Supercomputing Platforms
Benran Zhang, Daniel Weinberg, Chih-En Hsu, Aaron R. Altman, Yuming Shi, James B. White III, Derek Vigil-Fowler, Steven G. Louie, Jack R. Deslippe, Felipe H. da Jornada, Zhenglu Li, Mauro Del Ben
https://arxiv.org/abs/2509.23018

Advancing Quantum Many-Body GW Calculations on Exascale Supercomputing Platforms
Advanced ab initio materials simulations face growing challenges as increasing systems and phenomena complexity requires higher accuracy, driving up computational demands. Quantum many-body GW methods are state-of-the-art for treating electronic excited states and couplings but often hindered due to the costly numerical complexity. Here, we present innovative implementations of advanced GW methods within the BerkeleyGW package, enabling large-scale simulations on Frontier and Aurora exascale pl…

Anonymous monitoring enables turn-taking and sustainablity in collective resource governance: Multi-player evolutionary dynamical-systems game
Kenji Itao, Kunihiko Kaneko
https://arxiv.org/abs/2507.22555

Anonymous monitoring enables turn-taking and sustainablity in collective resource governance: Multi-player evolutionary dynamical-systems game
Sustainable resource use in large societies requires social institutions that specify acceptable behavior and punish violators. Because mutual monitoring becomes prohibitively costly as populations grow, we examine whether sustainability can be maintained when only anonymized information is available. Using the evolutionary dynamical-systems game framework, we model the common-pool resource management game. In the model, each player's harvesting decisions shape the resource dynamics and depend …

Boosting Ensembles for Statistics of Tails at Conditionally Optimal Advance Split Times
Justin Finkel, Paul A. O'Gorman
https://arxiv.org/abs/2507.22310 https://

Boosting Ensembles for Statistics of Tails at Conditionally Optimal Advance Split Times
Climate science needs more efficient ways to study high-impact, low-probability extreme events, which are rare by definition and costly to simulate in large numbers. Rare event sampling (RES) and ensemble boosting offer a novel strategy to extract more information from those occasional simulated events: small perturbations in advance can turn a moderate event into a severe one, which otherwise might not come for many more simulation-years. But how to choose this ``advance split time'' (AST) rem…

Chat to Chip: Large Language Model Based Design of Arbitrarily Shaped Metasurfaces
Huanshu Zhang, Lei Kang, Sawyer D. Campbell, Douglas H. Werner
https://arxiv.org/abs/2509.24196

Chat to Chip: Large Language Model Based Design of Arbitrarily Shaped Metasurfaces
Traditional metasurface design is limited by the computational cost of full-wave simulations, preventing thorough exploration of complex configurations. Data-driven approaches have emerged as a solution to this bottleneck, replacing costly simulations with rapid neural network evaluations and enabling near-instant design for meta-atoms. Despite advances, implementing a new optical function still requires building and training a task-specific network, along with exhaustive searches for suitable …

Diff-3DCap: Shape Captioning with Diffusion Models
Zhenyu Shu, Jiawei Wen, Shiyang Li, Shiqing Xin, Ligang Liu
https://arxiv.org/abs/2509.23718 https://arx…

Diff-3DCap: Shape Captioning with Diffusion Models
The task of 3D shape captioning occupies a significant place within the domain of computer graphics and has garnered considerable interest in recent years. Traditional approaches to this challenge frequently depend on the utilization of costly voxel representations or object detection techniques, yet often fail to deliver satisfactory outcomes. To address the above challenges, in this paper, we introduce Diff-3DCap, which employs a sequence of projected views to represent a 3D object and a cont…

"Wood burning and gas cooking hugely costly to healthcare systems, New Zealand study finds"
#NewZealand #Energy #Health

Estimating the Empowerment of Language Model Agents
Jinyeop Song, Jeff Gore, Max Kleiman-Weiner
https://arxiv.org/abs/2509.22504 https://arxiv.org/pdf/2509…

Estimating the Empowerment of Language Model Agents
As language model (LM) agents become more capable and gain broader access to real-world tools, there is a growing need for scalable evaluation frameworks of agentic capability. However, conventional benchmark-centric evaluations are costly to design and require human designers to come up with valid tasks that translate into insights about general model capabilities. In this work, we propose information-theoretic evaluation based on empowerment, the mutual information between an agent's actions …

Bayesian Surrogates for Risk-Aware Pre-Assessment of Aging Bridge Portfolios
Sophia V. Kuhn, Rafael Bischof, Marius Weber, Antoine Binggeli, Michael A. Kraus, Walter Kaufmann, Fernando P\'erez-Cruz
https://arxiv.org/abs/2509.25031

Bayesian Surrogates for Risk-Aware Pre-Assessment of Aging Bridge Portfolios
Aging infrastructure portfolios pose a critical resource allocation challenge: deciding which structures require intervention and which can safely remain in service. Structural assessments must balance the trade-off between cheaper, conservative analysis methods and accurate but costly simulations that do not scale portfolio-wide. We propose Bayesian neural network (BNN) surrogates for rapid structural pre-assessment of worldwide common bridge types, such as reinforced concrete frame bridges. T…

Beyond Detection -- Orchestrating Human-Robot-Robot Assistance via an Internet of Robotic Things Paradigm
Joseph Hunt, Koyo Fujii, Aly Magassouba, Praminda Caleb-Solly
https://arxiv.org/abs/2509.22296 …

Beyond Detection -- Orchestrating Human-Robot-Robot Assistance via an Internet of Robotic Things Paradigm
Hospital patient falls remain a critical and costly challenge worldwide. While conventional fall prevention systems typically rely on post-fall detection or reactive alerts, they also often suffer from high false positive rates and fail to address the underlying patient needs that lead to bed-exit attempts. This paper presents a novel system architecture that leverages the Internet of Robotic Things (IoRT) to orchestrate human-robot-robot interaction for proactive and personalized patient assis…

Automated Test Oracles for Flaky Cyber-Physical System Simulators: Approach and Evaluation
Baharin A. Jodat, Khouloud Gaaloul, Mehrdad Sabetzadeh, Shiva Nejati
https://arxiv.org/abs/2508.20902

Automated Test Oracles for Flaky Cyber-Physical System Simulators: Approach and Evaluation
Simulation-based testing of cyber-physical systems (CPS) is costly due to the time-consuming execution of CPS simulators. In addition, CPS simulators may be flaky, leading to inconsistent test outcomes and requiring repeated test re-execution for reliable test verdicts. Automated test oracles that do not require system execution are therefore crucial for reducing testing costs. Ideally, such test oracles should be interpretable to facilitate human understanding of test verdicts, and they must b…

Singleton-Optimized Conformal Prediction
Tao Wang, Yan Sun, Edgar Dobriban
https://arxiv.org/abs/2509.24095 https://arxiv.org/pdf/2509.24095

Singleton-Optimized Conformal Prediction
Conformal prediction can be used to construct prediction sets that cover the true outcome with a desired probability, but can sometimes lead to large prediction sets that are costly in practice. The most useful outcome is a singleton prediction-an unambiguous decision-yet existing efficiency-oriented methods primarily optimize average set size. Motivated by this, we propose a new nonconformity score that aims to minimize the probability of producing non-singleton sets. Starting from a non-conve…

"Indoor air pollution from New Zealand’s 523,000 wood burners was estimated to account for 446 hospital admissions for heart and lung problems, and 101 early deaths annually, in a country with a population of just over 5 million people. "
Wood burning and gas cooking hugely costly to healthcare systems, New Zealand study finds | Environment | The Guardian

Efficient Fine-Grained GPU Performance Modeling for Distributed Deep Learning of LLM
Biyao Zhang, Mingkai Zheng, Debargha Ganguly, Xuecen Zhang, Vikash Singh, Vipin Chaudhary, Zhao Zhang
https://arxiv.org/abs/2509.22832

Efficient Fine-Grained GPU Performance Modeling for Distributed Deep Learning of LLM
Training Large Language Models(LLMs) is one of the most compute-intensive tasks in high-performance computing. Predicting end-to-end training time for multi-billion parameter models distributed across hundreds of GPUs remains challenging due to complex interactions between transformer components, parallelism strategies(data, model, pipeline, tensor), and multi-tier communication. Learned models require costly sampling, while analytical models often struggle with real-world network and hardware …

Generative multi-fidelity modeling and downscaling via spatial autoregressive transport maps
Alejandro Calle-Saldarriaga, Paul F. V. Wiemann, Matthias Katzfuss
https://arxiv.org/abs/2509.22474

Generative multi-fidelity modeling and downscaling via spatial autoregressive transport maps
Spatial fields are often available at multiple fidelities or resolutions, where high-fidelity data is typically more costly to obtain than low-fidelity data. Statistical surrogates or emulators can predict high-fidelity fields from cheap low-fidelity output. We propose a highly scalable Bayesian approach that can learn the joint non-Gaussian distribution and nonlinear dependence structure of nonstationary spatial fields at multiple fidelities from a small number of training samples. Our method …

Judge deals Amazon costly defeat ahead of FTC trial | Courthouse News Service
https://www.courthousenews.com/judge-deals-amazon-costly-defeat-ahead-of-ftc-trial/

Incentives in Federated Learning with Heterogeneous Agents
Ariel D. Procaccia, Han Shao, Itai Shapira
https://arxiv.org/abs/2509.21612 https://arxiv.org/pd…

Incentives in Federated Learning with Heterogeneous Agents
Federated learning promises significant sample-efficiency gains by pooling data across multiple agents, yet incentive misalignment is an obstacle: each update is costly to the contributor but boosts every participant. We introduce a game-theoretic framework that captures heterogeneous data: an agent's utility depends on who supplies each sample, not just how many. Agents aim to meet a PAC-style accuracy threshold at minimal personal cost. We show that uncoordinated play yields pathologies: pure…

AUV-Fusion: Cross-Modal Adversarial Fusion of User Interactions and Visual Perturbations Against VARS
Hai Ling, Tianchi Wang, Xiaohao Liu, Zhulin Tao, Lifang Yang, Xianglin Huang
https://arxiv.org/abs/2507.22880

AUV-Fusion: Cross-Modal Adversarial Fusion of User Interactions and Visual Perturbations Against VARS
Modern Visual-Aware Recommender Systems (VARS) exploit the integration of user interaction data and visual features to deliver personalized recommendations with high precision. However, their robustness against adversarial attacks remains largely underexplored, posing significant risks to system reliability and security. Existing attack strategies suffer from notable limitations: shilling attacks are costly and detectable, and visual-only perturbations often fail to align with user preferences.…

Don’t forget these 5: Early penalties were costly https://www.dallascowboys.com/news/don-t-forget-these-5-early-penalties-were-costly

An Adaptive CUR Algorithm and its Application to Reduced-Order Modeling of Random PDEs
Grishma Palkar, Hessam Babaee
https://arxiv.org/abs/2509.21480 https://

An Adaptive CUR Algorithm and its Application to Reduced-Order Modeling of Random PDEs
Certain classes of CUR algorithms, also referred to as cross or pseudoskeleton algorithms, are widely used for low-rank matrix approximation when direct access to all matrix entries is costly. Their key advantage lies in constructing a rank-r approximation by sampling only r columns and r rows of the target matrix. This property makes them particularly attractive for reduced-order modeling of nonlinear matrix differential equations, where nonlinear operations on low-rank matrices can otherwise …

Ravens' Henry baffled by third fumble in 3 games https://www.espn.com/nfl/story/_/id/46352433/derrick-henry-apologetic-costly-fumble-ravens-loss

From David Suzuki
Science Matters - Costly geoengineering schemes could stall real solutions
Because the fossil fuel industry and its supporters have done everything they can to stall needed solutions to the climate crisis, some people say we must now engineer our way out of the mess we created. Many are promoting schemes that block sunlight from reaching Earth, reflect more of it back into space or absorb carbon from the atmosphere.

"Air pollution from wood burning and gas cooking is massively costly to our healthcare systems and the economy. These are the conclusions of a peer-reviewed study from New Zealand that calculated the cost of hospital treatment, days off ill and early deaths from the air pollution produced by fireplaces, stoves, gas cooking and un-flued room heaters."

NFL Announces Punishment for Two Raiders Players https://heavy.com/sports/nfl/las-vegas-raiders/nfl-isaiah-pola-mao-devin-white/?adt_ei=[email]

Endogenous Quality in Social Learning
Georgy Lukyanov, Konstantin Shamruk, Ekaterina Logina
https://arxiv.org/abs/2508.20539 https://arxiv.org/pdf/2508.205…

Endogenous Quality in Social Learning
We study a dynamic reputation model with a fixed posted price where only purchases are public. A long-lived seller chooses costly quality; each buyer observes the purchase history and a private signal. Under a Markov selection, beliefs split into two cascades - where actions are unresponsive and investment is zero - and an interior region where the seller invests. The policy is inverse-U in reputation and produces two patterns: Early Resolution (rapid absorption at the optimistic cascade) and D…

Vision-Language Alignment from Compressed Image Representations using 2D Gaussian Splatting
Yasmine Omri, Connor Ding, Tsachy Weissman, Thierry Tambe
https://arxiv.org/abs/2509.22615

Vision-Language Alignment from Compressed Image Representations using 2D Gaussian Splatting
Modern vision language pipelines are driven by RGB vision encoders trained on massive image text corpora. While these pipelines have enabled impressive zero shot capabilities and strong transfer across tasks, they still inherit two structural inefficiencies from the pixel domain: (i) transmitting dense RGB images from edge devices to the cloud is energy intensive and costly, and (ii) patch based tokenization explodes sequence length, stressing attention budgets and context limits. We explore 2D…

Enabling Equitable Access to Trustworthy Financial Reasoning
William Jurayj, Nils Holzenberger, Benjamin Van Durme
https://arxiv.org/abs/2508.21051 https://

Enabling Equitable Access to Trustworthy Financial Reasoning
According to the United States Internal Revenue Service, ''the average American spends $\$270$ and 13 hours filing their taxes''. Even beyond the U.S., tax filing requires complex reasoning, combining application of overlapping rules with numerical calculations. Because errors can incur costly penalties, any automated system must deliver high accuracy and auditability, making modern large language models (LLMs) poorly suited for this task. We propose an approach that integrates LLMs with a symb…

How the unraveling of two Pentagon projects may result in a costly do-over (Alexandra Alper/Reuters)
https://www.reuters.com/world/us/how-unraveling-two-pentagon-projects-may-result-costly-do-over-2025-08-13/
http://www.memeorandum.com/250813/p71#a250813p71

Developing Vision-Language-Action Model from Egocentric Videos
Tomoya Yoshida, Shuhei Kurita, Taichi Nishimura, Shinsuke Mori
https://arxiv.org/abs/2509.21986 https://

Developing Vision-Language-Action Model from Egocentric Videos
Egocentric videos capture how humans manipulate objects and tools, providing diverse motion cues for learning object manipulation. Unlike the costly, expert-driven manual teleoperation commonly used in training Vision-Language-Action models (VLAs), egocentric videos offer a scalable alternative. However, prior studies that leverage such videos for training robot policies typically rely on auxiliary annotations, such as detailed hand-pose recordings. Consequently, it remains unclear whether VLAs…

Gamification of Immersive Cervical Rehabilitation Exercises in VR: An Exploratory Study on Chin Tuck and Range of Motion Exercises
Haitham Abdelsalam, Chanelle Montpetit, Arash Harirpoush, Maryse Fortin, Yiming Xiao
https://arxiv.org/abs/2508.18580

Gamification of Immersive Cervical Rehabilitation Exercises in VR: An Exploratory Study on Chin Tuck and Range of Motion Exercises
Chronic neck pain is a prevalent condition that affects millions of individuals worldwide, causing significant individual suffering and socioeconomic burdens. Although exercise rehabilitation is a staple in relieving pain and improving muscle function for the condition, traditional one-on-one rehabilitation sessions are costly and suffer from poor adherence and accessibility for the patients. Thanks to the increasing accessibility and recent advancements in sensing and display technology, virtu…

👾 Unsupervised Instance Segmentation with Superpixels
#cs #arxiv

Unsupervised Instance Segmentation with Superpixels
Instance segmentation is essential for numerous computer vision applications, including robotics, human-computer interaction, and autonomous driving. Currently, popular models bring impressive performance in instance segmentation by training with a large number of human annotations, which are costly to collect. For this reason, we present a new framework that efficiently and effectively segments objects without the need for human annotations. Firstly, a MultiCut algorithm is applied to self-sup…

Colts WR Mitchell on blown TD, fumble: 'It stings' https://www.espn.com/nfl/story/_/id/46416799/colts-wr-adonai-mitchell-blown-td-fumble-stings

Automatic Inspection Based on Switch Sounds of Electric Point Machines
Ayano Shibata, Toshiki Gunji, Mitsuaki Tsuda, Takashi Endo, Kota Dohi, Tomoya Nishida, Satoko Nomoto
https://arxiv.org/abs/2508.20870

Automatic Inspection Based on Switch Sounds of Electric Point Machines
Since 2018, East Japan Railway Company and Hitachi, Ltd. have been working to replace human inspections with IoT-based monitoring. The purpose is Labor-saving required for equipment inspections and provide appropriate preventive maintenance. As an alternative to visual inspection, it has been difficult to substitute electrical characteristic monitoring, and the introduction of new high-performance sensors has been costly. In 2019, we implemented cameras and microphones in an ``NS'' electric poi…

Deep learning for interval-censored failure time data from case-cohort studies
Yeyu Xiao, Yonghong Long
https://arxiv.org/abs/2509.22081 https://arxiv.org/…

Deep learning for interval-censored failure time data from case-cohort studies
Interval-censored data are common in fields such as epidemiology and demography. When the failure event of interest is relatively rare and the collection of covariates is costly, researchers often adopt the case-cohort design to reduce study costs. However, existing studies typically rely on the assumption of linearity in modeling covariates, which may not capture the complex and nonlinear relationships present in real data. To address this limitation, we consider a class of transformation mode…

Overclocking Electrostatic Generative Models
Daniil Shlenskii, Alexander Korotin
https://arxiv.org/abs/2509.22454 https://arxiv.org/pdf/2509.22454

Overclocking Electrostatic Generative Models
Electrostatic generative models such as PFGM++ have recently emerged as a powerful framework, achieving state-of-the-art performance in image synthesis. PFGM++ operates in an extended data space with auxiliary dimensionality $D$, recovering the diffusion model framework as $D\to\infty$, while yielding superior empirical results for finite $D$. Like diffusion models, PFGM++ relies on expensive ODE simulations to generate samples, making it computationally costly. To address this, we propose Inve…

Surfacing from replies (see context upthread).
I’ve watched the pendulum swing back and forth multiple times in my career between “code reuse ftw!!” and “no dependencies!!” The one thing I can say with confidence is that both those extremes as dogma are ridiculous and costly. It’s all tradeoffs; you can’t escape the part where you think carefully and contextually.
1/ https://hachyderm.io/@inthehands/115237696859291899

In short: EVERYONE *normally* involved in retiring power plants agreed that this one is a costly and redundant antique that is not needed for #Michigan or #Midwest power resiliency. Keeping it online is adding to Consumers Energy customers' bills, as cheaper sources are left offline to make room for th…

Representing LLMs in Prompt Semantic Task Space
Idan Kashani, Avi Mendelson, Yaniv Nemcovsky
https://arxiv.org/abs/2509.22506 https://arxiv.org/pdf/2509.22…

Representing LLMs in Prompt Semantic Task Space
Large language models (LLMs) achieve impressive results over various tasks, and ever-expanding public repositories contain an abundance of pre-trained models. Therefore, identifying the best-performing LLM for a given task is a significant challenge. Previous works have suggested learning LLM representations to address this. However, these approaches present limited scalability and require costly retraining to encompass additional models and datasets. Moreover, the produced representation utili…

Interpretable Spectral Features Predict Conductivity in Self-Driving Doped Conjugated Polymer Labs
Ankush Kumar Mishra, Jacob P. Mauthe, Nicholas Luke, Aram Amassian, Baskar Ganapathysubramanian
https://arxiv.org/abs/2509.21330

Interpretable Spectral Features Predict Conductivity in Self-Driving Doped Conjugated Polymer Labs
Self-driving labs (SDLs) promise faster materials discovery by coupling automation with machine learning, but a central challenge is predicting costly, slow-to-measure properties from inexpensive, automatable readouts. We address this for doped conjugated polymers by learning interpretable spectral fingerprints from optical spectroscopy to predict electrical conductivity. Optical spectra are fast, non-destructive, and sensitive to aggregation and charge generation; we automate their featurizati…

Multi-Order Monte Carlo IMEX hierarchies for uncertainty quantification in multiscale hyperbolic systems
Giulia Bertaglia, Walter Boscheri, Lorenzo Pareschi
https://arxiv.org/abs/2508.20187

Multi-Order Monte Carlo IMEX hierarchies for uncertainty quantification in multiscale hyperbolic systems
We introduce a novel Multi-Order Monte Carlo approach for uncertainty quantification in the context of multiscale time-dependent partial differential equations. The new framework leverages Implicit-Explicit Runge-Kutta time integrators to satisfy the asymptotic-preserving property across different discretization orders of accuracy. In contrast to traditional Multi-Level Monte Carlo methods, which require costly hierarchical re-meshing, our method constructs a multi-order hierarchy by varying bo…

Sad to see Trump Tariffs kill off a US-based small business that offers a unique product that works perfectly but will no longer be available because it’s now too costly to produce: the Starling Home hub that magically made your Google Nest devices play friendly with Apple Home and HomeKit. Will remain supported but no longer available for purchase because of tariffs. https://…

Starling Hub | Nest HomeKit Bridge | Complete Smart Home Control
Connect Nest to Apple HomeKit and AirPlay. Perfectly integrate Thermostat, Protect, Cameras, Speakers, Secure and Nest x Yale Lock with Home, iOS, Siri and other smart home devices and HomeKit apps.

How California reached a deal to let ride-hailing drivers unionize while reducing insurance requirements for Uber and Lyft, ending years of costly legal fights (Tyler Katzenberger/Politico)
https://www.politico.com/news/2025/09/14/california-uber-lyft-union-00562…

Multimodal Speckle-polarization Fiber-optic Sensing for Localized and High-bandwidth Vibration Monitoring
Catarina S. Monteiro, Tom\'as Lopes, Joana Teixeira, Tiago Ferreira, Pedro A. S. Jorge, Nuno A. Silva
https://arxiv.org/abs/2509.22079

Multimodal Speckle-polarization Fiber-optic Sensing for Localized and High-bandwidth Vibration Monitoring
High-bandwidth and multi-point acoustic and vibration sensing is a critical asset for real-time condition monitoring, maintenance, and surveillance applications. In the case of large scales and harsh environments, optical fiber distributed sensing has emerged as a compelling alternative to electronic transducers, featuring lower installation and maintenance costs, along with compact footprints and enhanced robustness. Yet, current distributed fiber-optic sensing solutions are typically costly a…

New preprint: "The Reverse File System: Towards open cost-effective secure WORM storage devices for logging"
https://arxiv.org/abs/2509.17969

Novel Approaches to Artificial Intelligence Development Based on the Nearest Neighbor Method
I. I. Priezzhev, D. A. Danko, A. V. Shubin
https://arxiv.org/abs/2508.18953 https://…

Novel Approaches to Artificial Intelligence Development Based on the Nearest Neighbor Method
Modern neural network technologies, including large language models, have achieved remarkable success in various applied artificial intelligence applications, however, they face a range of fundamental limitations. Among them are hallucination effects, high computational complexity of training and inference, costly fine-tuning, and catastrophic forgetting issues. These limitations significantly hinder the use of neural networks in critical areas such as medicine, industrial process management, a…

‘LMFAO!’: Outrage Over Trump’s Costly Honors for Slain ‘Podcaster’ Flips Into Laughter Once Viewers Notice JD Vance’s Embarrassing Antics
https://atlantablackstar.com/2025/09/13/trumps-costly-honors-for-slain-podcaster-flipped-into-laughter-viewers-notice-jd-vances-embarrassing-antics/

It's mostly posturing . Shale gas won't be economically viable and will meet huge opposition from communities.
Get ready for fracking, Reform UK tells energy firms - BBC News
https://www.bbc.co.uk/news/articles/c74172wlezwo

Get ready for fracking, Reform UK tells energy firms
The party is serious about going after shale gas - but critics argue it's too difficult and costly.

How Hurricane Resilience for Commercial Real Estate is Leveraging Drones and AI
CNBC - August 20, 2025
“As season after season produces more intense storms resulting in increasingly costly damage, facilities managers in commercial real estate are making property resilience a priority.”
https://www.

How hurricane resilience for commercial real estate is leveraging drones and AI
Site Technologies employs drones to help CRE facilities managers see where the vulnerabilities are in their properties and address them before storms hit.

GraphMend: Code Transformations for Fixing Graph Breaks in PyTorch 2
Savini Kashmira, Jayanaka Dantanarayana, Thamirawaran Sathiyalogeswaran, Yichao Yuan, Nishil Talati, Krisztian Flautner, Lingjia Tang, Jason Mars
https://arxiv.org/abs/2509.16248

GraphMend: Code Transformations for Fixing Graph Breaks in PyTorch 2
This paper presents GraphMend, a high-level compiler that eliminates FX graph breaks in PyTorch 2 programs. Although PyTorch 2 introduced TorchDynamo and TorchInductor to enable just-in-time graph compilation, unresolved dynamic control flow and unsupported Python constructs often fragment models into multiple FX graphs. These fragments force frequent fallbacks to eager mode, incur costly CPU-to-GPU synchronizations, and reduce optimization opportunities. GraphMend addresses this limitation by …

LLM as an Execution Estimator: Recovering Missing Dependency for Practical Time-travelling Debugging
Yunrui Pei, Hongshu Wang, Wenjie Zhang, Yun Lin, Weiyu Kong, Jin song Dong
https://arxiv.org/abs/2508.18721

LLM as an Execution Estimator: Recovering Missing Dependency for Practical Time-travelling Debugging
Dynamic data dependency, answering "why a variable has this value?", is critical for debugging. Given a program step `s` reading a variable `v`, finding the dynamic definition of `v` is challenging. Traditional methods require either (1) exhaustive instrumentation of all possible definitions of `v` in one run or (2) replicating the run to re-examine reads/writes - both costly. If `v` is defined in a library, instrumentation becomes expensive; for non-deterministic programs, replication is infea…

"Smoke From Wildfires Caused by Climate Change Will Fuel Many More Premature Deaths in the U.S., a New Study Warns"
#US #USA #America

Smoke From Wildfires Caused by Climate Change Will Fuel Many More Premature Deaths in the U.S., a New Study Warns - Inside Climate News
This would represent some of the country’s most costly consequences of a warming climate by mid-century, researchers say.

The point is the mask: scaling coral reef segmentation with weak supervision
Matteo Contini, Victor Illien, Sylvain Poulain, Serge Bernard, Julien Barde, Sylvain Bonhommeau, Alexis Joly
https://arxiv.org/abs/2508.18958

The point is the mask: scaling coral reef segmentation with weak supervision
Monitoring coral reefs at large spatial scales remains an open challenge, essential for assessing ecosystem health and informing conservation efforts. While drone-based aerial imagery offers broad spatial coverage, its limited resolution makes it difficult to reliably distinguish fine-scale classes, such as coral morphotypes. At the same time, obtaining pixel-level annotations over large spatial extents is costly and labor-intensive, limiting the scalability of deep learning-based segmentation …

VR Fire safety training application
Ujwal M R
https://arxiv.org/abs/2508.15788 https://arxiv.org/pdf/2508.15788

VR Fire safety training application
Fire emergencies can happen without warning and knowing how to respond quickly can save lives Unfortunately traditional fire drills can be disruptive costly and often fail to recreate the pressure of a real emergency This project introduces a Virtual Reality VR Fire Safety Training Application that gives people a safe yet realistic way to practice life saving skills Using a VR headset and motion controllers trainees step into a 3D world where fire hazards smoke and evacuation routes are brought…

Retrieval-Augmented Defense: Adaptive and Controllable Jailbreak Prevention for Large Language Models
Guangyu Yang, Jinghong Chen, Jingbiao Mei, Weizhe Lin, Bill Byrne
https://arxiv.org/abs/2508.16406 …

Retrieval-Augmented Defense: Adaptive and Controllable Jailbreak Prevention for Large Language Models
Large Language Models (LLMs) remain vulnerable to jailbreak attacks, which attempt to elicit harmful responses from LLMs. The evolving nature and diversity of these attacks pose many challenges for defense systems, including (1) adaptation to counter emerging attack strategies without costly retraining, and (2) control of the trade-off between safety and utility. To address these challenges, we propose Retrieval-Augmented Defense (RAD), a novel framework for jailbreak detection that incorporate…

Israel-based Vega, which offers an AI-based security analytics platform, raised $65M in seed and Series A led by Accel at a $400M valuation (Meytal Vaizberg/Globes)
https://en.globes.co.il/en/article-israeli-security-analytics-co-vega-raises-65m-10…

Israeli security analytics co Vega raises $65m
The company has developed AI-native security analytics and investigation across any stack, without forcing costly migrations or pipeline engineering.

Active Query Selection for Crowd-Based Reinforcement Learning
Jonathan Erskine, Taku Yamagata, Ra\'ul Santos-Rodr\'iguez
https://arxiv.org/abs/2508.19132 https://…

Active Query Selection for Crowd-Based Reinforcement Learning
Preference-based reinforcement learning has gained prominence as a strategy for training agents in environments where the reward signal is difficult to specify or misaligned with human intent. However, its effectiveness is often limited by the high cost and low availability of reliable human input, especially in domains where expert feedback is scarce or errors are costly. To address this, we propose a novel framework that combines two complementary strategies: probabilistic crowd modelling to …

Scensory: Automated Real-Time Fungal Identification and Spatial Mapping
Yanbaihui Liu, Erica Babusci, Claudia K. Gunsch, Boyuan Chen
https://arxiv.org/abs/2509.19318 https://

Scensory: Automated Real-Time Fungal Identification and Spatial Mapping
Indoor fungal contamination poses significant risks to public health, yet existing detection methods are slow, costly, and lack spatial resolution. Conventional approaches rely on laboratory analysis or high-concentration sampling, making them unsuitable for real-time monitoring and scalable deployment. We introduce \textbf{\textit{Scensory}}, a robot-enabled olfactory system that simultaneously identifies fungal species and localizes their spatial origin using affordable volatile organic compo…

Ransomware Negotiation: Dynamics and Privacy-Preserving Mechanism Design
Haohui Zhang, Sirui Shen, Xinyu Hu, Chenglu Jin
https://arxiv.org/abs/2508.15844 https://

Ransomware Negotiation: Dynamics and Privacy-Preserving Mechanism Design
Ransomware attacks have become a pervasive and costly form of cybercrime, causing tens of millions of dollars in losses as organizations increasingly pay ransoms to mitigate operational disruptions and financial risks. While prior research has largely focused on proactive defenses, the post-infection negotiation dynamics between attackers and victims remains underexplored. This paper presents a formal analysis of attacker-victim interactions in modern ransomware incidents using a finite-horizon…

KeyWorld: Key Frame Reasoning Enables Effective and Efficient World Models
Sibo Li, Qianyue Hao, Yu Shang, Yong Li
https://arxiv.org/abs/2509.21027 https://

KeyWorld: Key Frame Reasoning Enables Effective and Efficient World Models
Robotic world models are a promising paradigm for forecasting future environment states, yet their inference speed and the physical plausibility of generated trajectories remain critical bottlenecks, limiting their real-world applications. This stems from the redundancy of the prevailing frame-to-frame generation approach, where the model conducts costly computation on similar frames, as well as neglecting the semantic importance of key transitions. To address this inefficiency, we propose KeyW…

Israel's Qatar attack was a costly failure (Barak Ravid/Axios)
https://www.axios.com/2025/09/16/israel-qatar-strike-failed-hamas-survive
http://www.memeorandum.com/250916/p41#a250916p41

Breaking Barriers in Software Testing: The Power of AI-Driven Automation
Saba Naqvi, Mohammad Baqar
https://arxiv.org/abs/2508.16025 https://arxiv.org/pdf/…

Breaking Barriers in Software Testing: The Power of AI-Driven Automation
Software testing remains critical for ensuring reliability, yet traditional approaches are slow, costly, and prone to gaps in coverage. This paper presents an AI-driven framework that automates test case generation and validation using natural language processing (NLP), reinforcement learning (RL), and predictive models, embedded within a policy-driven trust and fairness model. The approach translates natural language requirements into executable tests, continuously optimizes them through learn…

EventTracer: Fast Path Tracing-based Event Stream Rendering
Zhenyang Li, Xiaoyang Bai, Jinfan Lu, Pengfei Shen, Edmund Y. Lam, Yifan Peng
https://arxiv.org/abs/2508.18071 https:…

EventTracer: Fast Path Tracing-based Event Stream Rendering
Simulating event streams from 3D scenes has become a common practice in event-based vision research, as it meets the demand for large-scale, high temporal frequency data without setting up expensive hardware devices or undertaking extensive data collections. Yet existing methods in this direction typically work with noiseless RGB frames that are costly to render, and therefore they can only achieve a temporal resolution equivalent to 100-300 FPS, far lower than that of real-world event data. In…

Stochastic Path Planning in Correlated Obstacle Fields
Li Zhou, Elvan Ceyhan
https://arxiv.org/abs/2509.19559 https://arxiv.org/pdf/2509.19559

Stochastic Path Planning in Correlated Obstacle Fields
We introduce the Stochastic Correlated Obstacle Scene (SCOS) problem, a navigation setting with spatially correlated obstacles of uncertain blockage status, realistically constrained sensors that provide noisy readings and costly disambiguation. Modeling the spatial correlation with Gaussian Random Field (GRF), we develop Bayesian belief updates that refine blockage probabilities, and use the posteriors to reduce search space for efficiency. To find the optimal traversal policy, we propose a no…

Knock-Knock: Black-Box, Platform-Agnostic DRAM Address-Mapping Reverse Engineering
Antoine Plin, Lorenzo Casalino, Thomas Rokicki, Ruben Salvador
https://arxiv.org/abs/2509.19568

Knock-Knock: Black-Box, Platform-Agnostic DRAM Address-Mapping Reverse Engineering
Modern Systems-on-Chip (SoCs) employ undocumented linear address-scrambling functions to obfuscate DRAM addressing, which complicates DRAM-aware performance optimizations and hinders proactive security analysis of DRAM-based attacks; most notably, Rowhammer. Although previous work tackled the issue of reversing physical-to-DRAM mapping, existing heuristic-based reverse-engineering approaches are partial, costly, and impractical for comprehensive recovery. This paper establishes a rigorous theor…

FORGE: Forming Semantic Identifiers for Generative Retrieval in Industrial Datasets
Kairui Fu, Tao Zhang, Shuwen Xiao, Ziyang Wang, Xinming Zhang, Chenchi Zhang, Yuliang Yan, Junjun Zheng, Yu Li, Zhihong Chen, Jian Wu, Xiangheng Kong, Shengyu Zhang, Kun Kuang, Yuning Jiang, Bo Zheng
https://arxiv.org/abs/2509.20904

FORGE: Forming Semantic Identifiers for Generative Retrieval in Industrial Datasets
Semantic identifiers (SIDs) have gained increasing attention in generative retrieval (GR) due to their meaningful semantic discriminability. However, current research on SIDs faces three main challenges: (1) the absence of large-scale public datasets with multimodal features, (2) limited investigation into optimization strategies for SID generation, which typically rely on costly GR training for evaluation, and (3) slow online convergence in industrial deployment. To address these challenges, w…

George Pickens, Donovan Wilson among 4 Cowboys fined $63K for Week 7 non-penalties https://cowboyswire.usatoday.com/story/sports/nfl/cowboys/2025/10/25/cowboys-fines-63k-week-7-washington…

CYCLE-INSTRUCT: Fully Seed-Free Instruction Tuning via Dual Self-Training and Cycle Consistency
Zhanming Shen, Hao Chen, Yulei Tang, Shaolin Zhu, Wentao Ye, Xiaomeng Hu, Haobo Wang, Gang Chen, Junbo Zhao
https://arxiv.org/abs/2508.16100

CYCLE-INSTRUCT: Fully Seed-Free Instruction Tuning via Dual Self-Training and Cycle Consistency
Instruction tuning is vital for aligning large language models (LLMs) with human intent, but current methods typically rely on costly human-annotated seed data or powerful external teacher models. While instruction back-translation techniques reduce this dependency, they remain fundamentally tethered to an initial seed set, which limits full automation, introduces biases, and can lead to inefficient use of unlabeled corpora. In this paper, we propose Cycle-Instruct, a novel framework that achie…

Israel-based Terra Security, which offers an AI-driven penetration testing platform, raised a $30M Series A led by Felicis, bringing its total funding to $38M (Meir Orbach/CTech)
https://www.calcalistech.com/ctechnews/article/awdq1yv5k

AI startup Terra Security raises $30M Series A for continuous penetration testing
Israeli startup aims to scale offensive security testing beyond manual and costly methods.

Fulcrum: Optimizing Concurrent DNN Training and Inferencing on Edge Accelerators
Prashanthi S. K., Saisamarth Taluri, Pranav Gupta, Amartya Ranjan Saikia, Kunal Kumar Sahoo, Atharva Vinay Joshi, Lakshya Karwa, Kedar Dhule, Yogesh Simmhan
https://arxiv.org/abs/2509.20205

Fulcrum: Optimizing Concurrent DNN Training and Inferencing on Edge Accelerators
The proliferation of GPU accelerated edge devices like Nvidia Jetsons and the rise in privacy concerns are placing an emphasis on concurrent DNN training and inferencing on edge devices. Inference and training have different computing and QoS goals. But edge accelerators like Jetson do not support native GPU sharing and expose 1000s of power modes. This requires careful time-sharing of concurrent workloads to meet power--performance goals, while limiting costly profiling. In this paper, we desi…

Mixture of Thoughts: Learning to Aggregate What Experts Think, Not Just What They Say
Jacob Fein-Ashley, Dhruv Parikh, Rajgopal Kannan, Viktor Prasanna
https://arxiv.org/abs/2509.21164

Mixture of Thoughts: Learning to Aggregate What Experts Think, Not Just What They Say
Open-source Large Language Models (LLMs) increasingly specialize by domain (e.g., math, code, general reasoning), motivating systems that leverage complementary strengths across models. Prior multi-LLM approaches either (i) route a query to one or a few experts and generate independently, (ii) aggregate outputs from each model via costly multi-turn exchanges, or (iii) fuse weights into a single model-typically requiring architectural homogeneity. We introduce Mixture of Thoughts (MoT), a simple…

Coarse-to-Fine Grounded Memory for LLM Agent Planning
Wei Yang, Jinwei Xiao, Hongming Zhang, Qingyang Zhang, Yanna Wang, Bo Xu
https://arxiv.org/abs/2508.15305 https://

Coarse-to-Fine Grounded Memory for LLM Agent Planning
Recent advancements in Large Language Models (LLMs) have driven growing interest in LLM-based agents for complex planning tasks. To avoid costly agent training, many studies adopted memory mechanism that enhances LLM with offline experiences or online trajectory analysis. However, existing works focus on single-granularity memory derived from dynamic environmental interactions, which are inherently constrained by the quality of the collected experiences. This limitation, in turn, constrain the …

Self-evolved Imitation Learning in Simulated World
Yifan Ye, Jun Cen, Jing Chen, Zhihe Lu
https://arxiv.org/abs/2509.19460 https://arxiv.org/pdf/2509.19460…

Self-evolved Imitation Learning in Simulated World
Imitation learning has been a trend recently, yet training a generalist agent across multiple tasks still requires large-scale expert demonstrations, which are costly and labor-intensive to collect. To address the challenge of limited supervision, we propose Self-Evolved Imitation Learning (SEIL), a framework that progressively improves a few-shot model through simulator interactions. The model first attempts tasksin the simulator, from which successful trajectories are collected as new demonst…

FAST: Foreground-aware Diffusion with Accelerated Sampling Trajectory for Segmentation-oriented Anomaly Synthesis
Xichen Xu, Yanshu Wang, Jinbao Wang, Xiaoning Lei, Guoyang Xie, Guannan Jiang, Zhichao Lu
https://arxiv.org/abs/2509.20295

FAST: Foreground-aware Diffusion with Accelerated Sampling Trajectory for Segmentation-oriented Anomaly Synthesis
Industrial anomaly segmentation relies heavily on pixel-level annotations, yet real-world anomalies are often scarce, diverse, and costly to label. Segmentation-oriented industrial anomaly synthesis (SIAS) has emerged as a promising alternative; however, existing methods struggle to balance sampling efficiency and generation quality. Moreover, most approaches treat all spatial regions uniformly, overlooking the distinct statistical differences between anomaly and background areas. This uniform …

Why are the Broncos off to a 1-2 start? Three trends to explain their early struggles https://www.espn.com/nfl/story/_/id/46348870/denver-broncos-2025-nfl-penalties-missing-big-plays-defense-fourth-quarter-struggles

Recovering Wasserstein Distance Matrices from Few Measurements
Muhammad Rana, Abiy Tasissa, HanQin Cai, Yakov Gavriyelov, Keaton Hamm
https://arxiv.org/abs/2509.19250 https://…

Recovering Wasserstein Distance Matrices from Few Measurements
This paper proposes two algorithms for estimating square Wasserstein distance matrices from a small number of entries. These matrices are used to compute manifold learning embeddings like multidimensional scaling (MDS) or Isomap, but contrary to Euclidean distance matrices, are extremely costly to compute. We analyze matrix completion from upper triangular samples and Nyström completion in which $\mathcal{O}(d\log(d))$ columns of the distance matrices are computed where $d$ is the desired embe…

UnPose: Uncertainty-Guided Diffusion Priors for Zero-Shot Pose Estimation
Zhaodong Jiang, Ashish Sinha, Tongtong Cao, Yuan Ren, Bingbing Liu, Binbin Xu
https://arxiv.org/abs/2508.15972

UnPose: Uncertainty-Guided Diffusion Priors for Zero-Shot Pose Estimation
Estimating the 6D pose of novel objects is a fundamental yet challenging problem in robotics, often relying on access to object CAD models. However, acquiring such models can be costly and impractical. Recent approaches aim to bypass this requirement by leveraging strong priors from foundation models to reconstruct objects from single or multi-view images, but typically require additional training or produce hallucinated geometry. To this end, we propose UnPose, a novel framework for zero-shot,…

Efficient Cell Painting Image Representation Learning via Cross-Well Aligned Masked Siamese Network
Pin-Jui Huang, Yu-Hsuan Liao, SooHeon Kim, NoSeong Park, JongBae Park, DongMyung Shin
https://arxiv.org/abs/2509.19896

Efficient Cell Painting Image Representation Learning via Cross-Well Aligned Masked Siamese Network
Computational models that predict cellular phenotypic responses to chemical and genetic perturbations can accelerate drug discovery by prioritizing therapeutic hypotheses and reducing costly wet-lab iteration. However, extracting biologically meaningful and batch-robust cell painting representations remains challenging. Conventional self-supervised and contrastive learning approaches often require a large-scale model and/or a huge amount of carefully curated data, still struggling with batch ef…

JD.com reports Q2 revenue up 22% YoY to $49.7B, above $46.8B est., and net income down 50% YoY to ~$846M, benefiting from government-directed consumer subsidies (Bloomberg)
https://www.bloomberg.com/news/articles/2025-08-14/jd-…

Clotho: Measuring Task-Specific Pre-Generation Test Adequacy for LLM Inputs
Juyeon Yoon, Somin Kim, Robert Feldt, Shin Yoo
https://arxiv.org/abs/2509.17314 https://

Clotho: Measuring Task-Specific Pre-Generation Test Adequacy for LLM Inputs
Software increasingly relies on the emergent capabilities of Large Language Models (LLMs), from natural language understanding to program analysis and generation. Yet testing them on specific tasks remains difficult and costly: many prompts lack ground truth, forcing reliance on human judgment, while existing uncertainty and adequacy measures typically require full inference. A key challenge is to assess input adequacy in a way that reflects the demands of the task, ideally before even generati…

ROPA: Synthetic Robot Pose Generation for RGB-D Bimanual Data Augmentation
Jason Chen, I-Chun Arthur Liu, Gaurav Sukhatme, Daniel Seita
https://arxiv.org/abs/2509.19454 https://…

ROPA: Synthetic Robot Pose Generation for RGB-D Bimanual Data Augmentation
Training robust bimanual manipulation policies via imitation learning requires demonstration data with broad coverage over robot poses, contacts, and scene contexts. However, collecting diverse and precise real-world demonstrations is costly and time-consuming, which hinders scalability. Prior works have addressed this with data augmentation, typically for either eye-in-hand (wrist camera) setups with RGB inputs or for generating novel images without paired actions, leaving augmentation for eye…

A Comprehensive Evaluation of YOLO-based Deer Detection Performance on Edge Devices
Bishal Adhikari, Jiajia Li, Eric S. Michel, Jacob Dykes, Te-Ming Paul Tseng, Mary Love Tagert, Dong Chen
https://arxiv.org/abs/2509.20318

A Comprehensive Evaluation of YOLO-based Deer Detection Performance on Edge Devices
The escalating economic losses in agriculture due to deer intrusion, estimated to be in the hundreds of millions of dollars annually in the U.S., highlight the inadequacy of traditional mitigation strategies since these methods are often labor-intensive, costly, and ineffective for modern farming systems. To overcome this, there is a critical need for intelligent, autonomous solutions which require accurate and efficient deer detection. But the progress in this field is impeded by a significant…

Distribution-Aligned Decoding for Efficient LLM Task Adaptation
Senkang Hu, Xudong Han, Jinqi Jiang, Yihang Tao, Zihan Fang, Sam Tak Wu Kwong, Yuguang Fang
https://arxiv.org/abs/2509.15888

Distribution-Aligned Decoding for Efficient LLM Task Adaptation
Adapting billion-parameter language models to a downstream task is still costly, even with parameter-efficient fine-tuning (PEFT). We re-cast task adaptation as output-distribution alignment: the objective is to steer the output distribution toward the task distribution directly during decoding rather than indirectly through weight updates. Building on this view, we introduce Steering Vector Decoding (SVD), a lightweight, PEFT-compatible, and theoretically grounded method. We start with a short…

Source: Jets cutting Gipson after costly fumble https://www.espn.com/nfl/story/_/id/46214547/source-jets-cutting-xavier-gipson-kickoff-fumble

Lidar-based Tracking of Traffic Participants with Sensor Nodes in Existing Urban Infrastructure
Simon Sch\"afer, Bassam Alrifaee, Ehsan Hashemi
https://arxiv.org/abs/2509.20009

Lidar-based Tracking of Traffic Participants with Sensor Nodes in Existing Urban Infrastructure
This paper presents a lidar-only state estimation and tracking framework, along with a roadside sensing unit for integration with existing urban infrastructure. Urban deployments demand scalable, real-time tracking solutions, yet traditional remote sensing remains costly and computationally intensive, especially under perceptually degraded conditions. Our sensor node couples a single lidar with an edge computing unit and runs a computationally efficient, GPU-free observer that simultaneously es…

FlexMUSE: Multimodal Unification and Semantics Enhancement Framework with Flexible interaction for Creative Writing
Jiahao Chen, Zhiyong Ma, Wenbiao Du, Qingyuan Chuai
https://arxiv.org/abs/2508.16230 …

FlexMUSE: Multimodal Unification and Semantics Enhancement Framework with Flexible interaction for Creative Writing
Multi-modal creative writing (MMCW) aims to produce illustrated articles. Unlike common multi-modal generative (MMG) tasks such as storytelling or caption generation, MMCW is an entirely new and more abstract challenge where textual and visual contexts are not strictly related to each other. Existing methods for related tasks can be forcibly migrated to this track, but they require specific modality inputs or costly training, and often suffer from semantic inconsistencies between modalities. Th…

A Guide for Manual Annotation of Scientific Imagery: How to Prepare for Large Projects
Azim Ahmadzadeh, Rohan Adhyapak, Armin Iraji, Kartik Chaurasiya, V Aparna, Petrus C. Martens
https://arxiv.org/abs/2508.14801

A Guide for Manual Annotation of Scientific Imagery: How to Prepare for Large Projects
Despite the high demand for manually annotated image data, managing complex and costly annotation projects remains under-discussed. This is partly due to the fact that leading such projects requires dealing with a set of diverse and interconnected challenges which often fall outside the expertise of specific domain experts, leaving practical guidelines scarce. These challenges range widely from data collection to resource allocation and recruitment, from mitigation of biases to effective traini…

World4RL: Diffusion World Models for Policy Refinement with Reinforcement Learning for Robotic Manipulation
Zhennan Jiang, Kai Liu, Yuxin Qin, Shuai Tian, Yupeng Zheng, Mingcai Zhou, Chao Yu, Haoran Li, Dongbin Zhao
https://arxiv.org/abs/2509.19080

Robust Vision-Language Models via Tensor Decomposition: A Defense Against Adversarial Attacks
Het Patel, Muzammil Allie, Qian Zhang, Jia Chen, Evangelos E. Papalexakis
https://arxiv.org/abs/2509.16163 …

Robust Vision-Language Models via Tensor Decomposition: A Defense Against Adversarial Attacks
Vision language models (VLMs) excel in multimodal understanding but are prone to adversarial attacks. Existing defenses often demand costly retraining or significant architecture changes. We introduce a lightweight defense using tensor decomposition suitable for any pre-trained VLM, requiring no retraining. By decomposing and reconstructing vision encoder representations, it filters adversarial noise while preserving meaning. Experiments with CLIP on COCO and Flickr30K show improved robustness.…