Tootfinder

Wow! Using Valinet ExplorerPatcher to change the Windows 11 File Explorer back to the Windows 10 style UI makes it SO MUCH FASTER! https://github.com/valinet/ExplorerPatcher/

Lewis Perelman hatte es 1992 schon drauf:
„The mission of hyperlearning is not only vision but action. HL's purpose is to enhance the human user's ability to direct the potent technology of the smart environment, lest the human be reduced to technology's object.

🐠 3D-printed helix shelters increase baby coral survival rates
#coral

3D-printed helix shelters increase baby coral survival rates
To dramatically increase coral survival rates, scientists at the University of Hawaiʻi at Mānoa Hawaiʻi Institute of Marine Biology (HIMB) have developed innovative 3D-printed ceramic structures that provide crucial protection for baby corals. These new designs offer a low-cost and scalable solution to enhance reef recovery worldwide.

Can art enhance your life? Here’s what I learned from Ali Smith, Tracey Emin, Claudia Winkleman and more https://www.theguardian.com/artanddesign/2025/nov/10/…

How European, national and local policies enhance each other’s effectiveness. And how cities make EU policy work for business and society.
https://www.linkedin.com/posts/jaapburger_how-european-national-and-local-policies-a…

How European, national, and local policies enhance each other's effectiveness. The share of electric vans and light trucks in new sales in the Netherlands has risen to more than three-quarters this… | Jaap Burger
How European, national, and local policies enhance each other's effectiveness. The share of electric vans and light trucks in new sales in the Netherlands has risen to more than three-quarters this year. A clear result of the introduction of local zero-emission zones for freight in an increasing number of Dutch cities, and updated taxation rules. The graph and table are from an excellent The International Council on Clean Transportation post by Dr. Sandra Wappelhorst and Eamonn Mulholland exp…

Does spatialized audio enhance the creation of mental representations? Spoiler: No (for their SnapStick-based setup) https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2025.1660373/full "seven blind individuals and se…

Frontiers | Does spatialized audio enhance the creation of mental representations?
Navigating unfamiliar environments without vision is a considerable challenge for blind individuals, as it requires constructing accurate cognitive maps. Bin...

Q for my fellow Trek fans:
To my surprise, my husband's been watching - and enjoying TNG. He's never seen Trek before. I'm tempted to show him TOS next, but wondering if I should interrupt TNG to do it so he has background info for upcoming episodes like "Sarek", "Unification", and "Relics". We just started Season 2.
I'm not sure what he'd think of TOS, and it's a long detour, but I think it'd enhance his appreciation of tho…

"Anyone can adapt this model to explore the potential impact of religion, spirituality and health, including devotional practices."
—Benjamin Doolittle '94 M.Div., '97 M.D., Director of the Yale Program for Medicine, Spirituality, and Religion, speaking about a new research model to enhance investigation conducted at the intersection of religion and medicine

Roblox plans to require all users to undergo an age estimation process to access chat features, starting January 2026, in an effort to enhance child safety (Jay Peters/The Verge)
https://www.theverge.com/news/822718/roblox-age-estimation-verification-chat…

Roblox will require age estimation to chat starting next year
After scrutiny over its ability to protect children on the platform, Roblox is making a big change.

*whispers* Lumines Arise might be the best Enhance puzzle game

Twisted Electron Collisions Enhance the Production of Circular Rydberg States
H. S. Parker, S. L. Sims, D. J. Lamphere, A. L. Harris
https://arxiv.org/abs/2511.17785 https://

Introducing Dev Services for #SpringBoot using #Arconia by @…

Roblox plans to require all users to undergo an age estimation process to access chat features, starting January 2026, in an effort to enhance child safety (Jay Peters/The Verge)
https://www.theverge.com/news/822718/roblox-age-estimation-verification-chat…

Roblox will require age estimation to chat starting next year
After scrutiny over its ability to protect children on the platform, Roblox is making a big change.

Balancing family and career is a challenge I wholeheartedly accept. As an Online Business Consultant, I empower seniors to lead enriching lives. Have you helped enhance a loved one's wellness? Let’s share insights and strategies to make aging a rewarding adventure! 🌟 #AgingWell #FamilyFirst

Meaningless Tokens, Meaningful Gains: How Activation Shifts Enhance LLM Reasoning
Zeru Shi, Yingjia Wan, Zhenting Wang, Qifan Wang, Fan Yang, Elisa Kreiss, Ruixiang Tang
https://arxiv.org/abs/2510.01032

Meaningless Tokens, Meaningful Gains: How Activation Shifts Enhance LLM Reasoning
Motivated by the puzzling observation that inserting long sequences of meaningless tokens before the query prompt can consistently enhance LLM reasoning performance, this work analyzes the underlying mechanism driving this phenomenon and based on these insights proposes a more principled method that allows for similar performance gains. First, we find that the improvements arise from a redistribution of activations in the LLM's MLP layers, where near zero activations become less frequent while …

Sleeping on the job used to be frowned upon.
But a Pew Research Center survey found that 34% of Americans take daily naps.
According to experts, 30 minutes or less of catnapping can “restore alertness, enhance performance and reduce mistakes and accidents” in the workplace.
In the 1960s, President John F. Kennedy caught some extra z’s in early afternoon to keep up his stride.
And NASA pilots take in-flight naps as short as 26 minutes to enhance performance and alertn…

Midday Power Naps: 7 Reasons To Sleep On The Job In 2025
Scientific-backed research shows that midday power naps at work can be a game changer in your mental alertness, energy and productivity—even the company's bottom line.

Hey guys! two more #schwarzwald #photos! And I found them a perfect fit for #FootpathFriday as well.
This day's hike was so diverse. narrow trails, ferns and moss, a lake, some heat…

TTRV: Test-Time Reinforcement Learning for Vision Language Models
Akshit Singh, Shyam Marjit, Wei Lin, Paul Gavrikov, Serena Yeung-Levy, Hilde Kuehne, Rogerio Feris, Sivan Doveh, James Glass, M. Jehanzeb Mirza
https://arxiv.org/abs/2510.06783

TTRV: Test-Time Reinforcement Learning for Vision Language Models
Existing methods for extracting reward signals in Reinforcement Learning typically rely on labeled data and dedicated training splits, a setup that contrasts with how humans learn directly from their environment. In this work, we propose TTRV to enhance vision language understanding by adapting the model on the fly at inference time, without the need for any labeled data. Concretely, we enhance the Group Relative Policy Optimization (GRPO) framework by designing rewards based on the frequency o…

Remember back when JavaScript was meant to enhance the browser experience, and we did graceful degration to make sure things worked even with JS disabled? That was pretty crazy, wasn't it...

A multi-modal tactile fingertip design for robotic hands to enhance dexterous manipulation
Zhuowei Xu, Zilin Si, Kevin Zhang, Oliver Kroemer, Zeynep Temel
https://arxiv.org/abs/2510.05382

A multi-modal tactile fingertip design for robotic hands to enhance dexterous manipulation
Tactile sensing holds great promise for enhancing manipulation precision and versatility, but its adoption in robotic hands remains limited due to high sensor costs, manufacturing and integration challenges, and difficulties in extracting expressive and reliable information from signals. In this work, we present a low-cost, easy-to-make, adaptable, and compact fingertip design for robotic hands that integrates multi-modal tactile sensors. We use strain gauge sensors to capture static forces and…

Let's dissect this AI garbage
1. The camera is a "Hitachi MP-EG10", not the "Hitachi MP-Eg1"
2. It's actually not a driver for the camera but for the Hitachi MP-ADI1 ISA interface kit (the camera is from 1997 and predates USB and didn't have an easy way to directly transfer data)
3. It's in a little plastic baggy, not "sealed"
4. It's neither valuable nor for "anyone"
5. It doesn't enhance any experiences

Probing Latent Knowledge Conflict for Faithful Retrieval-Augmented Generation
Linfeng Gao, Baolong Bi, Zheng Yuan, Le Wang, Zerui Chen, Zhimin Wei, Shenghua Liu, Qinggang Zhang, Jinsong Su
https://arxiv.org/abs/2510.12460

Probing Latent Knowledge Conflict for Faithful Retrieval-Augmented Generation
Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm to enhance the factuality of Large Language Models (LLMs). However, existing RAG systems often suffer from an unfaithfulness issue, where the model's response contradicts evidence from the retrieved context. Existing approaches to improving contextual faithfulness largely rely on external interventions, such as prompt engineering, decoding constraints, or reward-based fine-tuning. These works treat the LLM as a black box an…

AiDE-Q: Synthetic Labeled Datasets Can Enhance Learning Models for Quantum Property Estimation
Xinbiao Wang, Yuxuan Du, Zihan Lou, Yang Qian, Kaining Zhang, Yong Luo, Bo Du, Dacheng Tao
https://arxiv.org/abs/2509.26109

AiDE-Q: Synthetic Labeled Datasets Can Enhance Learning Models for Quantum Property Estimation
Quantum many-body problems are central to various scientific disciplines, yet their ground-state properties are intrinsically challenging to estimate. Recent advances in deep learning (DL) offer potential solutions in this field, complementing prior purely classical and quantum approaches. However, existing DL-based models typically assume access to a large-scale and noiseless labeled dataset collected by infinite sampling. This idealization raises fundamental concerns about their practical uti…

Sora 2 is scary, but I don't disapprove of its existence. The technology is coming one way or another. Might as well showcase how it can be used for good, which the TikTok-like format does effectively.
However, I do disapprove of the lack of transparency. This is not a raw text-to-video model. If other companies' services are any guide, it's probably using LLMs to enhance the prompt, generate the script, perhaps much more. But that’s all hidden from the user, who only …

Software Defect Prediction using Autoencoder Transformer Model
Seshu Barma, Mohanakrishnan Hariharan, Satish Arvapalli
https://arxiv.org/abs/2510.10840 https://

Software Defect Prediction using Autoencoder Transformer Model
An AI-ML-powered quality engineering approach uses AI-ML to enhance software quality assessments by predicting defects. Existing ML models struggle with noisy data types, imbalances, pattern recognition, feature extraction, and generalization. To address these challenges, we develop a new model, Adaptive Differential Evolution (ADE) based Quantum Variational Autoencoder-Transformer (QVAET) Model (ADE-QVAET). ADE combines with QVAET to obtain high-dimensional latent features and maintain sequent…

Unified framework for precise background modeling to enhance rare event detection at the Kuo-Sheng nuclear reactor laboratory
Subhasis Parhi, Lakhwinder Singh, Venktesh Singh, Henry Tsz-King Wong
https://arxiv.org/abs/2510.05868

Unified framework for precise background modeling to enhance rare event detection at the Kuo-Sheng nuclear reactor laboratory
A background model has been designed for TEXONO experiment using Geant4 sim- ulation software. The contamination of different radioactive isotopes in the detector background has been considered from both the detector set-up and the environment. 238 U and 232 Th have been confined in the front end electronics of the HPGe detector. These two isotopes are confined by breaking the complete chains into constituent decay chains on the basis of half-life of the isotopes. 235 U isotope is also confined…

Nitrogen-doped carbon quantum dots enhance bacteria growth and biosensing signals
David Rutherford, Marketa \v{S}lapal Ba\v{r}inkov\'a, Jaroslav Kuli\v{c}ek, Jelena Kozic, Jovana Prekodravac Filipovi\'c, Bohuslav Rezek
https://arxiv.org/abs/2510.06454

Nitrogen-doped carbon quantum dots enhance bacteria growth and biosensing signals
Carbon quantum dots (CQDs) are known for their antibacterial properties and ability to inhibit bacteria growth. In the current study, we observed a dopant and concentration-dependency on the antibacterial effect of CQDs. High concentrations of CQDs completely inhibited bacteria growth yet low concentrations enhanced growth. Unlike undoped CQDs, nitrogen-doped CQDs (N-CQDs) enhanced bacteria growth in a concentration-dependant manner and nitrogen/iron co-doped CQDs (Fe/N-CQDs) resulted in growth…

Causal Inspired Multi Modal Recommendation
Jie Yang, Chenyang Gu, Zixuan Liu
https://arxiv.org/abs/2510.12325 https://arxiv.org/pdf/2510.12325

Causal Inspired Multi Modal Recommendation
Multimodal recommender systems enhance personalized recommendations in e-commerce and online advertising by integrating visual, textual, and user-item interaction data. However, existing methods often overlook two critical biases: (i) modal confounding, where latent factors (e.g., brand style or product category) simultaneously drive multiple modalities and influence user preference, leading to spurious feature-preference associations; (ii) interaction bias, where genuine user preferences are m…

India officially notifies its first data protection law to establish a framework for data processing, protection, and governance, including verifiable consent (The Economic Times)
https://economictimes.indiatimes.c…

India notifies its first data protection law to strengthen privacy, security
India has officially notified the Digital Personal Data Protection Rules, 2025, establishing a framework for data processing, protection, and governance. These rules, enforcing the Digital Personal Data Protection Act, 2023, introduce verifiable consent, breach notification mandates, and data retention limits. They aim to enhance individual control and foster safer digital ecosystems.

U-Turn: Enhancing Incorrectness Analysis by Reversing Direction
Flavio Ascari, Roberto Bruni, Roberta Gori, Azalea Raad
https://arxiv.org/abs/2510.09292 https://

U-Turn: Enhancing Incorrectness Analysis by Reversing Direction
O'Hearn's Incorrectness Logic (IL) has sparked renewed interest in static analyses that aim to detect program errors rather than prove their absence, thereby avoiding false alarms -- a critical factor for practical adoption in industrial settings. As new incorrectness logics emerge to capture diverse error-related properties, a key question arises: can the combination of (in)correctness techniques enhance precision, expressiveness, automation, or scalability? Notable frameworks, such as outcome…

The Impact of Sanctions on decentralised Privacy Tools: A Case Study of Tornado Cash
Raffaele Cristodaro, Benjamin Kramer, Claudio J. Tessone
https://arxiv.org/abs/2510.09443 ht…

The Impact of Sanctions on decentralised Privacy Tools: A Case Study of Tornado Cash
This paper investigates the impact of sanctions on Tornado Cash, a smart contract protocol designed to enhance transaction privacy. Following the U.S. Department of the Treasury's sanctions against Tornado Cash in August 2022, platform activity declined sharply. We document a significant and sustained reduction in transaction volume, user diversity, and overall protocol utilization after the sanctions were imposed. Our analysis draws on transaction data from three major blockchains: Ethereum, B…

THEAS: Efficient Power Management in Multi-Core CPUs via Cache-Aware Resource Scheduling
Said Muhammad, Lahlou Laaziz, Nadjia Kara, Phat Tan Nguyen, Timothy Murphy
https://arxiv.org/abs/2510.09847

THEAS: Efficient Power Management in Multi-Core CPUs via Cache-Aware Resource Scheduling
The dynamic adaptation of resource levels enables the system to enhance energy efficiency while maintaining the necessary computational resources, particularly in scenarios where workloads fluctuate significantly over time. The proposed approach can play a crucial role in heterogeneous systems where workload characteristics are not uniformly distributed, such as non-pinning tasks. The deployed THEAS algorithm in this research work ensures a balance between performance and power consumption, mak…

Personalized Motion Guidance Framework for Athlete-Centric Coaching
Ryota Takamidoa, Chiharu Suzukia, Hiroki Nakamoto
https://arxiv.org/abs/2510.10496 https://

Personalized Motion Guidance Framework for Athlete-Centric Coaching
A critical challenge in contemporary sports science lies in filling the gap between group-level insights derived from controlled hypothesis-driven experiments and the real-world need for personalized coaching tailored to individual athletes' unique movement patterns. This study developed a Personalized Motion Guidance Framework (PMGF) to enhance athletic performance by generating individualized motion-refinement guides using generative artificial intelligence techniques. PMGF leverages a vertic…

FedLoDrop: Federated LoRA with Dropout for Generalized LLM Fine-tuning
Sijing Xie, Dingzhu Wen, Changsheng You, Qimei Chen, Mehdi Bennis, Kaibin Huang
https://arxiv.org/abs/2510.12078

FedLoDrop: Federated LoRA with Dropout for Generalized LLM Fine-tuning
Fine-tuning (FT) large language models (LLMs) is crucial for adapting general-purpose models to specific tasks, enhancing accuracy and relevance with minimal resources. To further enhance generalization ability while reducing training costs, this paper proposes Federated LoRA with Dropout (FedLoDrop), a new framework that applies dropout to the rows and columns of the trainable matrix in Federated LoRA. A generalization error bound and convergence analysis under sparsity regularization are obta…

MixReasoning: Switching Modes to Think
Haiquan Lu, Gongfan Fang, Xinyin Ma, Qi Li, Xinchao Wang
https://arxiv.org/abs/2510.06052 https://arxiv.org/pdf/2510…

MixReasoning: Switching Modes to Think
Reasoning models enhance performance by tackling problems in a step-by-step manner, decomposing them into sub-problems and exploring long chains of thought before producing an answer. However, applying extended reasoning to every step introduces substantial redundancy, as sub-problems vary widely in difficulty and complexity: a small number of pivotal steps are genuinely challenging and decisive for the final answer, while many others only involve straightforward revisions or simple computation…

"Q&A: How ‘vehicle-to-grid’ technology could boost China’s electricity system"
#China #Energy

Q&A: How ‘vehicle-to-grid’ technology could boost China’s electricity system - Carbon Brief
China’s surging electric vehicles ownership is opening the door to a new technology that can help to enhance the flexibility of electricity supply

Homogenization-based optimization of wall thickness distribution for TPMS two-fluid heat exchangers
Kaito Ohtani, Hiroki Kawabe, Kentaro Yaji, Kikuo Fujita, Vikrant Aute
https://arxiv.org/abs/2510.10622

Homogenization-based optimization of wall thickness distribution for TPMS two-fluid heat exchangers
Triply Periodic Minimal Surface (TPMS) structures are attracting growing attention as promising geometries for next-generation high-performance heat exchangers (HXs), due to their continuous flow paths and high surface-area-to-volume ratio that enhance heat transfer performance. Among these, graded TPMS structures with spatially varying thickness have emerged as a potential means to further improve performance. This study proposes an optimization method of wall thickness distribution for TPMS H…

Knowledge-Decoupled Functionally Invariant Path with Synthetic Personal Data for Personalized ASR
Yue Gu, Zhihao Du, Ying Shi, Jiqing Han, Yongjun He
https://arxiv.org/abs/2510.10401

Knowledge-Decoupled Functionally Invariant Path with Synthetic Personal Data for Personalized ASR
Fine-tuning generic ASR models with large-scale synthetic personal data can enhance the personalization of ASR models, but it introduces challenges in adapting to synthetic personal data without forgetting real knowledge, and in adapting to personal data without forgetting generic knowledge. Considering that the functionally invariant path (FIP) framework enables model adaptation while preserving prior knowledge, in this letter, we introduce FIP into synthetic-data-augmented personalized ASR mo…

Glad to share the publication of our #newpaper :
A Predictive Approach to Enhance Time-Series Forecasting
By Skye Gunasekaran, Assel Kembay, Hugo Ladret, Rui-Jie Zhu, myself, Omid Kavehei and Jason Eshraghian
The lead author, Jason Eshragian, speaks most clearly about it:
For the amount of compute they burn, transformers are pretty bad at tim…

Bit Allocation Transfer for Perceptual Quality Enhancement of VVC Intra Coding
Runyu Yang, Ivan V. Baji\'c
https://arxiv.org/abs/2510.10970 https://arx…

Bit Allocation Transfer for Perceptual Quality Enhancement of VVC Intra Coding
Mainstream image and video coding standards -- including state-of-the-art codecs like H.266/VVC, AVS3, and AV1 -- adopt a block-based hybrid coding framework. While this framework facilitates straightforward optimization for Peak Signal-to-Noise Ratio (PSNR), it struggles to effectively optimize perceptually-aligned metrics such as Multi-Scale Structural Similarity (MS-SSIM). To address this challenge, this paper proposes a low-complexity method to enhance perceptual quality in VVC intra coding…

Large Language Model-Empowered Channel Prediction and Predictive Beamforming for LEO Satellite Communications
Zhixiong Chen, Hyundong Shin, Arumugam Nallanathan, Jonathon Chambers
https://arxiv.org/abs/2510.10561

Large Language Model-Empowered Channel Prediction and Predictive Beamforming for LEO Satellite Communications
Accurate channel prediction and effective beamforming are essential for low Earth orbit (LEO) satellite communications to enhance system capacity and enable high-speed connectivity. Most existing channel prediction and predictive beamforming methods are limited by model generalization capabilities and struggle to adapt to time-varying wireless propagation environments. Inspired by the remarkable generalization and reasoning capabilities of large language models (LLMs), this work proposes an LLM…

Federated Data Analytics for Cancer Immunotherapy: A Privacy-Preserving Collaborative Platform for Patient Management
Mira Raheem, Michael Papazoglou, Bernd Kr\"amer, Neamat El-Tazi, Amal Elgammal
https://arxiv.org/abs/2510.09155

Federated Data Analytics for Cancer Immunotherapy: A Privacy-Preserving Collaborative Platform for Patient Management
Connected health is a multidisciplinary approach focused on health management, prioritizing pa-tient needs in the creation of tools, services, and treatments. This paradigm ensures proactive and efficient care by facilitating the timely exchange of accurate patient information among all stake-holders in the care continuum. The rise of digital technologies and process innovations promises to enhance connected health by integrating various healthcare data sources. This integration aims to persona…

Punctuation matters, yo.
https://www.instagram.com/reel/DR032CTDDv1/?utm_source=ig_web_copy_link&igsh=NTc4MTIwNjQ2YQ==

Chrissi Dennis and Monkey Buddies Activities on Instagram: "They just need a refresher in punctuation. Find Punctuation Rap Battle on Amazon for another genre of music to clear up the confusion! Or, see the comments below. #monkeybuddies #chrissidennis #punctuation #godrestyemerrygentlemen"
Understanding the punctuation of God Rest Ye Merry Gentlemen is crucial to correctly singing this classic Christmas carol. The video explores the placement of commas and the history behind this festive song. By learning the correct punctuation, you can enhance your singing and holiday experience. Learn the right comma placement, the story behind the song, and the tips to improve your caroling. Improve your punctuation skills and make the holiday season even more enjoyable.

Did you know veterinary medicine students experience burn-out? Art can help with that!
This September, we partnered with the #UniversityOfGeorgia College of Veterinary Medicine on a program to enhance their students' clinical skills AND their well-being.

Efficient LLM Inference over Heterogeneous Edge Networks with Speculative Decoding
Bingjie Zhu, Zhixiong Chen, Liqiang Zhao, Hyundong Shin, Arumugam Nallanathan
https://arxiv.org/abs/2510.11331

Efficient LLM Inference over Heterogeneous Edge Networks with Speculative Decoding
Large language model (LLM) inference at the network edge is a promising serving paradigm that leverages distributed edge resources to run inference near users and enhance privacy. Existing edge-based LLM inference systems typically adopt autoregressive decoding (AD), which only generates one token per forward pass. This iterative process, compounded by the limited computational resources of edge nodes, results in high serving latency and constrains the system's ability to support multiple users…

The Influence of Magnetic Complexity of Active Regions on Solar Wind Properties During Solar Cycles 23 and 24
Xinzheng Shi, Hui Fu, Zhenghua Huang, Limei Yan, Qi Liu, Lidong Xia
https://arxiv.org/abs/2510.08975

The Influence of Magnetic Complexity of Active Regions on Solar Wind Properties During Solar Cycles 23 and 24
Linking solar wind properties to the activities and characteristics of its source regions can enhance our understanding of its origin and generation mechanisms. Using the Mount Wilson magnetic classification (MWMC), we categorize all active regions (ARs) between 1999 and 2020 into three groups: alpha, beta, and complex ARs. Subsequently, we classify the near-Earth AR solar wind into the corresponding three types based on the magnetic type of ARs. Our results show that alpha, beta, and complex A…

ADiP: Adaptive Precision Systolic Array for Matrix Multiplication Acceleration
Ahmed J. Abdelmaksoud, Cristian Sestito, Shiwei Wang, Themis Prodromakis
https://arxiv.org/abs/2510.10623

ADiP: Adaptive Precision Systolic Array for Matrix Multiplication Acceleration
Transformers are at the core of modern AI nowadays. They rely heavily on matrix multiplication and require efficient acceleration due to their substantial memory and computational requirements. Quantization plays a vital role in reducing memory usage, and can be exploited for computations by designing reconfigurable architectures that enhance matrix multiplication by dynamically adjusting the precision. This paper proposes ADiP, a novel adaptive-precision systolic array architecture designed fo…

Retrofitting Control Flow Graphs in LLVM IR for Auto Vectorization
Shihan Fang, Wenxin Zheng
https://arxiv.org/abs/2510.04890 https://arxiv.org/pdf/2510.04…

Retrofitting Control Flow Graphs in LLVM IR for Auto Vectorization
Modern processors increasingly rely on SIMD instruction sets, such as AVX and RVV, to significantly enhance parallelism and computational performance. However, production-ready compilers like LLVM and GCC often fail to fully exploit available vectorization opportunities due to disjoint vectorization passes and limited extensibility. Although recent attempts in heuristics and intermediate representation (IR) designs have attempted to address these problems, efficiently simplifying control flow a…

Monte Carlo quasi-interpolation of spherical data
Zhengjie Sun, Mengyuan Lv, Xingping Sun
https://arxiv.org/abs/2510.12027 https://arxiv.org/pdf/2510.12027…

Monte Carlo quasi-interpolation of spherical data
We establish a deterministic and stochastic spherical quasi-interpolation framework featuring scaled zonal kernels derived from radial basis functions on the ambient Euclidean space. The method incorporates both quasi-Monte Carlo and Monte Carlo quadrature rules to construct easily computable quasi-interpolants, which provide efficient approximation to Sobolev-space functions for both clean and noisy data. To enhance the approximation power and robustness of our quasi-interpolants, we develop a…

✨ Smartcard passthrough support, comprehensive resource monitoring dashboard, and many more features being added regularly to enhance functionality
🔧 Technical approach: #Electron application running Windows as virtual machine inside #Docker container, uses

Reasoning in the Dark: Interleaved Vision-Text Reasoning in Latent Space
Chao Chen, Zhixin Ma, Yongqi Li, Yupeng Hu, Yinwei Wei, Wenjie Li, Liqiang Nie
https://arxiv.org/abs/2510.12603

Reasoning in the Dark: Interleaved Vision-Text Reasoning in Latent Space
Multimodal reasoning aims to enhance the capabilities of MLLMs by incorporating intermediate reasoning steps before reaching the final answer. It has evolved from text-only reasoning to the integration of visual information, enabling the thought process to be conveyed through both images and text. Despite its effectiveness, current multimodal reasoning methods depend on explicit reasoning steps that require labor-intensive vision-text annotations and inherently introduce significant inference l…

🏈 How name, image, and likeness policies boost college football's competitive balance
#sports

How name, image, and likeness policies boost college football's competitive balance
A study published in Management Science challenges conventional wisdom about name, image, and likeness (NIL) policies in college football, demonstrating they actively enhance competitive balance and broaden opportunities for athletes.

Laminar: A Scalable Asynchronous RL Post-Training Framework
Guangming Sheng, Yuxuan Tong, Borui Wan, Wang Zhang, Chaobo Jia, Xibin Wu, Yuqi Wu, Xiang Li, Chi Zhang, Yanghua Peng, Haibin Lin, Xin Liu, Chuan Wu
https://arxiv.org/abs/2510.12633

Laminar: A Scalable Asynchronous RL Post-Training Framework
Reinforcement learning (RL) post-training for Large Language Models (LLMs) is now scaling to large clusters and running for extended durations to enhance model reasoning performance. However, the scalability of existing RL frameworks is limited, as extreme long-tail skewness in RL trajectory generation causes severe GPU underutilization. Current asynchronous RL systems attempt to mitigate this, but they rely on global weight synchronization between the actor and all rollouts, which creates a ri…

A look at Apple's plans to enhance satellite connectivity in its products, Siri's Gemini upgrade, new 2026 Macs, a Health service, and the future of Fitness (Mark Gurman/Bloomberg)
https://www.bloomberg.com/news/newslette…

"Coch and Daniel do not call for more neuroscience in classrooms, but for better scientific literacy among teachers, school leaders, and teacher educators. They demonstrate that anyone seeking to apply brain research to enhance teaching must first comprehend what that research can – and cannot – reveal."

LLMAtKGE: Large Language Models as Explainable Attackers against Knowledge Graph Embeddings
Ting Li, Yang Yang, Yipeng Yu, Liang Yao, Guoqing Chao, Ruifeng Xu
https://arxiv.org/abs/2510.11584

LLMAtKGE: Large Language Models as Explainable Attackers against Knowledge Graph Embeddings
Adversarial attacks on knowledge graph embeddings (KGE) aim to disrupt the model's ability of link prediction by removing or inserting triples. A recent black-box method has attempted to incorporate textual and structural information to enhance attack performance. However, it is unable to generate human-readable explanations, and exhibits poor generalizability. In the past few years, large language models (LLMs) have demonstrated powerful capabilities in text comprehension, generation, and reas…

Worry slyly steals our peace today. Let's combat this by harnessing mindfulness to enhance seniors' well-being. By focusing on current strengths and letting go of future anxieties, we can achieve true serenity. Deep breaths in – peace welcomed. Cheers to a harmonious future now! 💪✨ #MindfulMoments #PeacefulLiving✨

TraceAegis: Securing LLM-Based Agents via Hierarchical and Behavioral Anomaly Detection
Jiahao Liu, Bonan Ruan, Xianglin Yang, Zhiwei Lin, Yan Liu, Yang Wang, Tao Wei, Zhenkai Liang
https://arxiv.org/abs/2510.11203

TraceAegis: Securing LLM-Based Agents via Hierarchical and Behavioral Anomaly Detection
LLM-based agents have demonstrated promising adaptability in real-world applications. However, these agents remain vulnerable to a wide range of attacks, such as tool poisoning and malicious instructions, that compromise their execution flow and can lead to serious consequences like data breaches and financial loss. Existing studies typically attempt to mitigate such anomalies by predefining specific rules and enforcing them at runtime to enhance safety. Yet, designing comprehensive rules is di…

LLMs are All You Need? Improving Fuzz Testing for MOJO with Large Language Models
Linghan Huang, Peizhou Zhao, Huaming Chen
https://arxiv.org/abs/2510.10179 https://

LLMs are All You Need? Improving Fuzz Testing for MOJO with Large Language Models
The rapid development of large language models (LLMs) has revolutionized software testing, particularly fuzz testing, by automating the generation of diverse and effective test inputs. This advancement holds great promise for improving software reliability. Meanwhile, the introduction of MOJO, a high-performance AI programming language blending Python's usability with the efficiency of C and C++, presents new opportunities to enhance AI model scalability and programmability. However, as a new l…

Autonomous Soft Robotic Guidewire Navigation via Imitation Learning
Noah Barnes, Ji Woong Kim, Lingyun Di, Hannah Qu, Anuruddha Bhattacharjee, Miroslaw Janowski, Dheeraj Gandhi, Bailey Felix, Shaopeng Jiang, Olivia Young, Mark Fuge, Ryan D. Sochol, Jeremy D. Brown, Axel Krieger
https://arxiv.org/abs/2510.09497

Autonomous Soft Robotic Guidewire Navigation via Imitation Learning
In endovascular surgery, endovascular interventionists push a thin tube called a catheter, guided by a thin wire to a treatment site inside the patient's blood vessels to treat various conditions such as blood clots, aneurysms, and malformations. Guidewires with robotic tips can enhance maneuverability, but they present challenges in modeling and control. Automation of soft robotic guidewire navigation has the potential to overcome these challenges, increasing the precision and safety of endova…

DODO: Causal Structure Learning with Budgeted Interventions
Matteo Gregorini, Chiara Boldrini, Lorenzo Valerio
https://arxiv.org/abs/2510.08207 https://arx…

DODO: Causal Structure Learning with Budgeted Interventions
Artificial Intelligence has achieved remarkable advancements in recent years, yet much of its progress relies on identifying increasingly complex correlations. Enabling causality awareness in AI has the potential to enhance its performance by enabling a deeper understanding of the underlying mechanisms of the environment. In this paper, we introduce DODO, an algorithm defining how an Agent can autonomously learn the causal structure of its environment through repeated interventions. We assume a…

Serial-Parallel Dual-Path Architecture for Speaking Style Recognition
Guojian Li, Qijie Shao, Zhixian Zhao, Shuiyuan Wang, Zhonghua Fu, Lei Xie
https://arxiv.org/abs/2510.11732 …

Serial-Parallel Dual-Path Architecture for Speaking Style Recognition
Speaking Style Recognition (SSR) identifies a speaker's speaking style characteristics from speech. Existing style recognition approaches primarily rely on linguistic information, with limited integration of acoustic information, which restricts recognition accuracy improvements. The fusion of acoustic and linguistic modalities offers significant potential to enhance recognition performance. In this paper, we propose a novel serial-parallel dual-path architecture for SSR that leverages acoustic…

Query-Specific GNN: A Comprehensive Graph Representation Learning Method for Retrieval Augmented Generation
Yuchen Yan, Zhihua Liu, Hao Wang, Weiming Li, Xiaoshuai Hao
https://arxiv.org/abs/2510.11541 …

Query-Specific GNN: A Comprehensive Graph Representation Learning Method for Retrieval Augmented Generation
Retrieval-augmented generation (RAG) has demonstrated its ability to enhance Large Language Models (LLMs) by integrating external knowledge sources. However, multi-hop questions, which require the identification of multiple knowledge targets to form a synthesized answer, raise new challenges for RAG systems. Under the multi-hop settings, existing methods often struggle to fully understand the questions with complex semantic structures and are susceptible to irrelevant noise during the retrieval…

Self-Supervised Representation Learning with ID-Content Modality Alignment for Sequential Recommendation
Donglin Zhou, Weike Pan, Zhong Ming
https://arxiv.org/abs/2510.10556 htt…

Self-Supervised Representation Learning with ID-Content Modality Alignment for Sequential Recommendation
Sequential recommendation (SR) models often capture user preferences based on the historically interacted item IDs, which usually obtain sub-optimal performance when the interaction history is limited. Content-based sequential recommendation has recently emerged as a promising direction that exploits items' textual and visual features to enhance preference learning. However, there are still three key challenges: (i) how to reduce the semantic gap between different content modality representatio…

MMOT: The First Challenging Benchmark for Drone-based Multispectral Multi-Object Tracking
Tianhao Li, Tingfa Xu, Ying Wang, Haolin Qin, Xu Lin, Jianan Li
https://arxiv.org/abs/2510.12565

MMOT: The First Challenging Benchmark for Drone-based Multispectral Multi-Object Tracking
Drone-based multi-object tracking is essential yet highly challenging due to small targets, severe occlusions, and cluttered backgrounds. Existing RGB-based tracking algorithms heavily depend on spatial appearance cues such as color and texture, which often degrade in aerial views, compromising reliability. Multispectral imagery, capturing pixel-level spectral reflectance, provides crucial cues that enhance object discriminability under degraded spatial conditions. However, the lack of dedicate…

Rewiring Development in Brain Segmentation: Leveraging Adult Brain Priors for Enhancing Infant MRI Segmentation
Alemu Sisay Nigru, Michele Svanera, Austin Dibble, Connor Dalby, Mattia Savardi, Sergio Benini
https://arxiv.org/abs/2510.09306

Rewiring Development in Brain Segmentation: Leveraging Adult Brain Priors for Enhancing Infant MRI Segmentation
Accurate segmentation of infant brain MRI is critical for studying early neurodevelopment and diagnosing neurological disorders. Yet, it remains a fundamental challenge due to continuously evolving anatomy of the subjects, motion artifacts, and the scarcity of high-quality labeled data. In this work, we present LODi, a novel framework that utilizes prior knowledge from an adult brain MRI segmentation model to enhance the segmentation performance of infant scans. Given the abundance of publicly …

Interactive semantic segmentation for phosphene vision neuroprosthetics https://arxiv.org/abs/2509.19957 "findings demonstrate the value of user feedback and the potential of gaze-guided semantic segmentation to enhance neuroprosthetic vision";

A GPU-Accelerated Matrix-Free FAS Multigrid Solver for Navier-Stokes Equations with Memory-Efficient Implementations
Jiale Meng, Shuqi Tang, Steven M. Wise, Zhenlin Guo
https://arxiv.org/abs/2510.11152

A GPU-Accelerated Matrix-Free FAS Multigrid Solver for Navier-Stokes Equations with Memory-Efficient Implementations
We develop a matrix-free Full Approximation Storage (FAS) multigrid solver based on staggered finite differences and implemented on GPU in MATLAB. To enhance performance, intermediate variables are reused, and an X-shape Multi-Color Gauss-Seidel (X-MCGS) smoother is introduced, which eliminates conditional branching by partitioning the grid into four submatrices. Restriction and prolongation operators are also GPU-accelerated. Convergence tests verify robustness and accuracy, while benchmarks s…

HERO: Hardware-Efficient RL-based Optimization Framework for NeRF Quantization
Yipu Zhang, Chaofang Ma, Jinming Ge, Lin Jiang, Jiang Xu, Wei Zhang
https://arxiv.org/abs/2510.09010

HERO: Hardware-Efficient RL-based Optimization Framework for NeRF Quantization
Neural Radiance Field (NeRF) has emerged as a promising 3D reconstruction method, delivering high-quality results for AR/VR applications. While quantization methods and hardware accelerators have been proposed to enhance NeRF's computational efficiency, existing approaches face crucial limitations. Current quantization methods operate without considering hardware architecture, resulting in sub-optimal solutions within the vast design space encompassing accuracy, latency, and model size. Additio…

QuantumBoost: A lazy, yet fast, quantum algorithm for learning with weak hypotheses
Amira Abbas, Yanlin Chen, Tuyen Nguyen, Ronald de Wolf
https://arxiv.org/abs/2510.05089 https…

QuantumBoost: A lazy, yet fast, quantum algorithm for learning with weak hypotheses
The technique of combining multiple votes to enhance the quality of a decision is the core of boosting algorithms in machine learning. In particular, boosting provably increases decision quality by combining multiple weak learners-hypotheses that are only slightly better than random guessing-into a single strong learner that classifies data well. There exist various versions of boosting algorithms, which we improve upon through the introduction of QuantumBoost. Inspired by classical work by Bar…

Police in Edmonton, Canada partner with Axon to test body cameras with AI facial recognition, and say the results will be verified by human officers (Associated Press)
https://apnews.com/article/ai-facial-recognition-axon-edmonton-21f319ce806a0…

AI-equipped police body cameras in Canada's Edmonton spark ethical concerns
Police in Edmonton, Canada, have started a pilot project using AI-equipped body cameras to detect faces on a "high risk" watch list. The move by Axon Enterprise, Inc. has raised ethical concerns, especially since the company previously paused facial recognition due to privacy issues. The pilot aims to enhance officer and public safety by identifying individuals flagged for a history of serious offenses. However, critics worry about societal risks and the lack of public debate. Axon CEO Rick Smi…

An Encoder-Integrated PhoBERT with Graph Attention for Vietnamese Token-Level Classification
Ba-Quang Nguyen
https://arxiv.org/abs/2510.11537 https://arxiv…

An Encoder-Integrated PhoBERT with Graph Attention for Vietnamese Token-Level Classification
We propose a novel neural architecture named TextGraphFuseGAT, which integrates a pretrained transformer encoder (PhoBERT) with Graph Attention Networks for token-level classification tasks. The proposed model constructs a fully connected graph over the token embeddings produced by PhoBERT, enabling the GAT layer to capture rich inter-token dependencies beyond those modeled by sequential context alone. To further enhance contextualization, a Transformer-style self-attention layer is applied on …

CoSPED: Consistent Soft Prompt Targeted Data Extraction and Defense
Yang Zhuochen, Fok Kar Wai, Thing Vrizlynn
https://arxiv.org/abs/2510.11137 https://arx…

CoSPED: Consistent Soft Prompt Targeted Data Extraction and Defense
Large language models have gained widespread attention recently, but their potential security vulnerabilities, especially privacy leakage, are also becoming apparent. To test and evaluate for data extraction risks in LLM, we proposed CoSPED, short for Consistent Soft Prompt targeted data Extraction and Defense. We introduce several innovative components, including Dynamic Loss, Additive Loss, Common Loss, and Self Consistency Decoding Strategy, and tested to enhance the consistency of the soft …

CoRA: Covariate-Aware Adaptation of Time Series Foundation Models
Guo Qin, Zhi Chen, Yong Liu, Zhiyuan Shi, Haixuan Liu, Xiangdong Huang, Jianmin Wang, Mingsheng Long
https://arxiv.org/abs/2510.12681

CoRA: Covariate-Aware Adaptation of Time Series Foundation Models
Time Series Foundation Models (TSFMs) have shown significant impact through their model capacity, scalability, and zero-shot generalization. However, due to the heterogeneity of inter-variate dependencies and the backbone scalability on large-scale multivariate datasets, most TSFMs are typically pre-trained on univariate time series. This limitation renders them oblivious to crucial information from diverse covariates in real-world forecasting tasks. To further enhance the performance of TSFMs,…

Prepared mind, fast response: A temporal decoupling framework for adaptive knowledge orchestration in open-domain dialogue
Jinling Gan, Churong Liang, Runnan Li
https://arxiv.org/abs/2510.08175

Prepared mind, fast response: A temporal decoupling framework for adaptive knowledge orchestration in open-domain dialogue
The latency-quality tradeoff is a fundamental constraint in open-domain dialogue AI systems, since comprehensive knowledge access necessitates prohibitive response delays. Contemporary approaches offer two inadequate solutions: lightweight instruct models achieve sub-second latency but lack reasoning depth, while tool-augmented ReAct agents enhance factuality through external knowledge at the cost of synchronous execution that blocks interaction during re- trieval processes. PMFR is thus propos…

Bee Maps, a decentralized mapping project powered by Hivemapper on the Solana blockchain, raised $32M to expand its network by distributing AI-enabled dashcams (CoinDesk)
https://www.coindesk.com/tech/2025/10/06/bee-maps-r…

Bee Maps Raises $32M to Scale Solana-Powered Decentralized Mapping Network
The fresh capital will be used to distribute more devices, enhance AI models that process and update map features, and boost contributor incentives.

Aging well is a journey rich with opportunities for growth and vitality. My passion is guiding seniors toward resources that enhance financial stability and physical health. 📚💪 Thriving in our golden years begins with informed decision-making. How do you stay active and engaged as you age? Share your insights! #HealthyAging #SeniorLiving

PairSem: LLM-Guided Pairwise Semantic Matching for Scientific Document Retrieval
Wonbin Kweon, Runchu Tian, SeongKu Kang, Pengcheng Jiang, Zhiyong Lu, Jiawei Han, Hwanjo Yu
https://arxiv.org/abs/2510.09897

PairSem: LLM-Guided Pairwise Semantic Matching for Scientific Document Retrieval
Scientific document retrieval is a critical task for enabling knowledge discovery and supporting research across diverse domains. However, existing dense retrieval methods often struggle to capture fine-grained scientific concepts in texts due to their reliance on holistic embeddings and limited domain understanding. Recent approaches leverage large language models (LLMs) to extract fine-grained semantic entities and enhance semantic matching, but they typically treat entities as independent fr…

🎉 Social identification with a team boosts fans' social well-being
#sports…

Social identification with a team boosts fans' social well-being
Sports fans all know that rosy feeling of happiness when we hang out with others who support our favorite team. A new study conducted with sport consumers in the U.S. and the United Kingdom suggests that organizations that want to enhance their supporters' health and well-being can achieve that by bolstering their social identification with the group.

EGSTalker: Real-Time Audio-Driven Talking Head Generation with Efficient Gaussian Deformation
Tianheng Zhu, Yinfeng Yu, Liejun Wang, Fuchun Sun, Wendong Zheng
https://arxiv.org/abs/2510.08587

EGSTalker: Real-Time Audio-Driven Talking Head Generation with Efficient Gaussian Deformation
This paper presents EGSTalker, a real-time audio-driven talking head generation framework based on 3D Gaussian Splatting (3DGS). Designed to enhance both speed and visual fidelity, EGSTalker requires only 3-5 minutes of training video to synthesize high-quality facial animations. The framework comprises two key stages: static Gaussian initialization and audio-driven deformation. In the first stage, a multi-resolution hash triplane and a Kolmogorov-Arnold Network (KAN) are used to extract spatia…

SPICE: Simple and Practical Image Clarification and Enhancement
Alexander Belyaev, Pierre-Alain Fayolle, Michael Cohen
https://arxiv.org/abs/2510.08358 https://

SPICE: Simple and Practical Image Clarification and Enhancement
We introduce a simple and efficient method to enhance and clarify images. More specifically, we deal with low light image enhancement and clarification of hazy imagery (hazy/foggy images, images containing sand dust, and underwater images). Our method involves constructing an image filter to simulate low-light or hazy conditions and deriving approximate reverse filters to minimize distortions in the enhanced images. Experimental results show that our approach is highly competitive and often sur…

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

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

Cross-attention Secretly Performs Orthogonal Alignment in Recommendation Models
Hyunin Lee, Yong Zhang, Hoang Vu Nguyen, Xiaoyi Liu, Namyong Park, Christopher Jung, Rong Jin, Yang Wang, Zhigang Wang, Somayeh Sojoudi, Xue Feng
https://arxiv.org/abs/2510.09435

Cross-attention Secretly Performs Orthogonal Alignment in Recommendation Models
Cross-domain sequential recommendation (CDSR) aims to align heterogeneous user behavior sequences collected from different domains. While cross-attention is widely used to enhance alignment and improve recommendation performance, its underlying mechanism is not fully understood. Most researchers interpret cross-attention as residual alignment, where the output is generated by removing redundant and preserving non-redundant information from the query input by referencing another domain data whic…

Fine-Grained Emotion Recognition via In-Context Learning
Zhaochun Ren, Zhou Yang, Chenglong Ye, Haizhou Sun, Chao Chen, Xiaofei Zhu, Xiangwen Liao
https://arxiv.org/abs/2510.06600

Fine-Grained Emotion Recognition via In-Context Learning
Fine-grained emotion recognition aims to identify the emotional type in queries through reasoning and decision-making processes, playing a crucial role in various systems. Recent methods use In-Context Learning (ICL), enhancing the representation of queries in the reasoning process through semantically similar examples, while further improving emotion recognition by explaining the reasoning mechanisms. However, these methods enhance the reasoning process but overlook the decision-making process…

Does LLM Focus on the Right Words? Diagnosing Language Bias in LLM-based Recommenders
Bohao Wang, Jiawei Chen, Feng Liu, Changwang Zhang, Jun Wang, Canghong Jin, Chun Chen, Can Wang
https://arxiv.org/abs/2510.10978

Does LLM Focus on the Right Words? Diagnosing Language Bias in LLM-based Recommenders
Large language models (LLMs), owing to their extensive open-domain knowledge and semantic reasoning capabilities, have been increasingly integrated into recommender systems (RS). However, a substantial gap remains between the pre-training objectives of LLMs and the specific requirements of recommendation tasks. To address this gap, supervised fine-tuning (SFT) is commonly performed on specially curated recommendation datasets to further enhance their predictive ability. Despite its success, SFT…

DeepPrune: Parallel Scaling without Inter-trace Redundancy
Shangqing Tu, Yaxuan Li, Yushi Bai, Lei Hou, Juanzi Li
https://arxiv.org/abs/2510.08483 https://…

DeepPrune: Parallel Scaling without Inter-trace Redundancy
Parallel scaling has emerged as a powerful paradigm to enhance reasoning capabilities in large language models (LLMs) by generating multiple Chain-of-Thought (CoT) traces simultaneously. However, this approach introduces significant computational inefficiency due to inter-trace redundancy -- our analysis reveals that over 80% of parallel reasoning traces yield identical final answers, representing substantial wasted computation. To address this critical efficiency bottleneck, we propose DeepPru…

Emotion-Disentangled Embedding Alignment for Noise-Robust and Cross-Corpus Speech Emotion Recognition
Upasana Tiwari, Rupayan Chakraborty, Sunil Kumar Kopparapu
https://arxiv.org/abs/2510.09072

Emotion-Disentangled Embedding Alignment for Noise-Robust and Cross-Corpus Speech Emotion Recognition
Effectiveness of speech emotion recognition in real-world scenarios is often hindered by noisy environments and variability across datasets. This paper introduces a two-step approach to enhance the robustness and generalization of speech emotion recognition models through improved representation learning. First, our model employs EDRL (Emotion-Disentangled Representation Learning) to extract class-specific discriminative features while preserving shared similarities across emotion categories. N…

WristWorld: Generating Wrist-Views via 4D World Models for Robotic Manipulation
Zezhong Qian, Xiaowei Chi, Yuming Li, Shizun Wang, Zhiyuan Qin, Xiaozhu Ju, Sirui Han, Shanghang Zhang
https://arxiv.org/abs/2510.07313

WristWorld: Generating Wrist-Views via 4D World Models for Robotic Manipulation
Wrist-view observations are crucial for VLA models as they capture fine-grained hand-object interactions that directly enhance manipulation performance. Yet large-scale datasets rarely include such recordings, resulting in a substantial gap between abundant anchor views and scarce wrist views. Existing world models cannot bridge this gap, as they require a wrist-view first frame and thus fail to generate wrist-view videos from anchor views alone. Amid this gap, recent visual geometry models suc…

Constraint-Aware Route Recommendation from Natural Language via Hierarchical LLM Agents
Tao Zhe, Rui Liu, Fateme Memar, Xiao Luo, Wei Fan, Xinyue Ye, Zhongren Peng, Dongjie Wang
https://arxiv.org/abs/2510.06078

Constraint-Aware Route Recommendation from Natural Language via Hierarchical LLM Agents
Route recommendation aims to provide users with optimal travel plans that satisfy diverse and complex requirements. Classical routing algorithms (e.g., shortest-path and constraint-aware search) are efficient but assume structured inputs and fixed objectives, limiting adaptability to natural-language queries. Recent LLM-based approaches enhance flexibility but struggle with spatial reasoning and the joint modeling of route-level and POI-level preferences. To address these limitations, we propos…

Efficient Prompt Optimisation for Legal Text Classification with Proxy Prompt Evaluator
Hyunji Lee, Kevin Chenhao Li, Matthias Grabmair, Shanshan Xu
https://arxiv.org/abs/2510.08524

Efficient Prompt Optimisation for Legal Text Classification with Proxy Prompt Evaluator
Prompt optimization aims to systematically refine prompts to enhance a language model's performance on specific tasks. Fairness detection in Terms of Service (ToS) clauses is a challenging legal NLP task that demands carefully crafted prompts to ensure reliable results. However, existing prompt optimization methods are often computationally expensive due to inefficient search strategies and costly prompt candidate scoring. In this paper, we propose a framework that combines Monte Carlo Tree Sea…

Better Together: Leveraging Unpaired Multimodal Data for Stronger Unimodal Models
Sharut Gupta, Shobhita Sundaram, Chenyu Wang, Stefanie Jegelka, Phillip Isola
https://arxiv.org/abs/2510.08492

Better Together: Leveraging Unpaired Multimodal Data for Stronger Unimodal Models
Traditional multimodal learners find unified representations for tasks like visual question answering, but rely heavily on paired datasets. However, an overlooked yet potentially powerful question is: can one leverage auxiliary unpaired multimodal data to directly enhance representation learning in a target modality? We introduce UML: Unpaired Multimodal Learner, a modality-agnostic training paradigm in which a single model alternately processes inputs from different modalities while sharing pa…

PocketSR: The Super-Resolution Expert in Your Pocket Mobiles
Haoze Sun, Linfeng Jiang, Fan Li, Renjing Pei, Zhixin Wang, Yong Guo, Jiaqi Xu, Haoyu Chen, Jin Han, Fenglong Song, Yujiu Yang, Wenbo Li
https://arxiv.org/abs/2510.03012

PocketSR: The Super-Resolution Expert in Your Pocket Mobiles
Real-world image super-resolution (RealSR) aims to enhance the visual quality of in-the-wild images, such as those captured by mobile phones. While existing methods leveraging large generative models demonstrate impressive results, the high computational cost and latency make them impractical for edge deployment. In this paper, we introduce PocketSR, an ultra-lightweight, single-step model that brings generative modeling capabilities to RealSR while maintaining high fidelity. To achieve this, w…

Multimodal Large Language Model Framework for Safe and Interpretable Grid-Integrated EVs
Jean Douglas Carvalho, Hugo Kenji, Ahmad Mohammad Saber, Glaucia Melo, Max Mauro Dias Santos, Deepa Kundur
https://arxiv.org/abs/2510.02592

Multimodal Large Language Model Framework for Safe and Interpretable Grid-Integrated EVs
The integration of electric vehicles (EVs) into smart grids presents unique opportunities to enhance both transportation systems and energy networks. However, ensuring safe and interpretable interactions between drivers, vehicles, and the surrounding environment remains a critical challenge. This paper presents a multi-modal large language model (LLM)-based framework to process multimodal sensor data - such as object detection, semantic segmentation, and vehicular telemetry - and generate natur…

SID: Multi-LLM Debate Driven by Self Signals
Xuhang Chen, Zhifan Song, Deyi Ji, Shuo Gao, Lanyun Zhu
https://arxiv.org/abs/2510.06843 https://arxiv.org/pdf…

SID: Multi-LLM Debate Driven by Self Signals
Large Language Models (LLMs) have exhibited impressive capabilities across diverse application domains. Recent work has explored Multi-LLM Agent Debate (MAD) as a way to enhance performance by enabling multiple LLMs to discuss and refine responses iteratively. Nevertheless, existing MAD methods predominantly focus on utilizing external structures, such as debate graphs, using LLM-as-a-Judge, while neglecting the application of self signals, such as token logits and attention, that arise during …

MICROTRIPS: MICRO-geography TRavel Intelligence and Pattern Synthesis
Yangyang Wang, Tayo Fabusuyi
https://arxiv.org/abs/2510.05080 https://arxiv.org/pdf/2…

MICROTRIPS: MICRO-geography TRavel Intelligence and Pattern Synthesis
This study presents a novel small-area estimation framework to enhance urban transportation planning through detailed characterization of travel behavior. Our approach improves on the four-step travel model by employing publicly available microdata files and machine learning methods to predict travel behavior for a representative, synthetic population at small geographic areas. This approach enables high-resolution estimation of trip generation, trip distribution, mode choice, and route assignm…

Staircase Streaming for Low-Latency Multi-Agent Inference
Junlin Wang (Zach), Jue Wang (Zach), Zhen (Zach), Xu, Ben Athiwaratkun, Bhuwan Dhingra, Ce Zhang, James Zou
https://arxiv.org/abs/2510.05059 …

Staircase Streaming for Low-Latency Multi-Agent Inference
Recent advances in large language models (LLMs) opened up new directions for leveraging the collective expertise of multiple LLMs. These methods, such as Mixture-of-Agents, typically employ additional inference steps to generate intermediate outputs, which are then used to produce the final response. While multi-agent inference can enhance response quality, it can significantly increase the time to first token (TTFT), posing a challenge for latency-sensitive applications and hurting user experi…

Zero-Shot Robustness of Vision Language Models Via Confidence-Aware Weighting
Nikoo Naghavian, Mostafa Tavassolipour
https://arxiv.org/abs/2510.02913 https://

Zero-Shot Robustness of Vision Language Models Via Confidence-Aware Weighting
Vision-language models like CLIP demonstrate impressive zero-shot generalization but remain highly vulnerable to adversarial attacks. In this work, we propose Confidence-Aware Weighting (CAW) to enhance zero-shot robustness in vision-language models. CAW consists of two components: (1) a Confidence-Aware loss that prioritizes uncertain adversarial examples by scaling the KL divergence between clean and adversarial predictions, and (2) a feature alignment regularization that preserves semantic c…

Estimation of Resistance Training RPE using Inertial Sensors and Electromyography
James Thomas, Johan Walhstr\"om
https://arxiv.org/abs/2510.03197 https://

Estimation of Resistance Training RPE using Inertial Sensors and Electromyography
Accurate estimation of rating of perceived exertion (RPE) can enhance resistance training through personalized feedback and injury prevention. This study investigates the application of machine learning models to estimate RPE during single-arm dumbbell bicep curls, using data from wearable inertial and electromyography (EMG) sensors. A custom dataset of 69 sets and over 1000 repetitions was collected, with statistical features extracted for model training. Among the models evaluated, a random f…

Resource-Efficient Fine-Tuning of LLaMA-3.2-3B for Medical Chain-of-Thought Reasoning
Imran Mansha
https://arxiv.org/abs/2510.05003 https://arxiv.org/pdf/2…

Resource-Efficient Fine-Tuning of LLaMA-3.2-3B for Medical Chain-of-Thought Reasoning
Large Language Models (LLMs) such as GPT-4 and LLaMA have demonstrated remarkable reasoning abilities but require significant computational resources for fine-tuning. This paper presents a resource-efficient fine-tuning approach for LLaMA-3.2-3B to enhance medical chain-of-thought reasoning while operating under constrained GPU and memory settings. Using parameter-efficient tuning techniques such as LoRA and QLoRA, we adapt the base model on publicly available medical reasoning datasets. The mo…

Improving Cooperation in Collaborative Embodied AI
Hima Jacob Leven Suprabha, Laxmi Nag Laxminarayan Nagesh, Ajith Nair, Alvin Reuben Amal Selvaster, Ayan Khan, Raghuram Damarla, Sanju Hannah Samuel, Sreenithi Saravana Perumal, Titouan Puech, Venkataramireddy Marella, Vishal Sonar, Alessandro Suglia, Oliver Lemon
https://arxiv.org/abs/2510…

Improving Cooperation in Collaborative Embodied AI
The integration of Large Language Models (LLMs) into multiagent systems has opened new possibilities for collaborative reasoning and cooperation with AI agents. This paper explores different prompting methods and evaluates their effectiveness in enhancing agent collaborative behaviour and decision-making. We enhance CoELA, a framework designed for building Collaborative Embodied Agents that leverage LLMs for multi-agent communication, reasoning, and task coordination in shared virtual spaces. T…