Tootfinder

"Rethinking Data Discovery for Libraries and Digital Humanities" @ Library Innovation Lab at Harvard Law School: https://lil.law.harvard.edu/blog/2025/10/24/rethinking-data-discovery-for-libraries-and-digital-humanities/

Rethinking Personal Data: The CJEU’s Contextual Turn in EDPS vs. SRB
https://fpf.org/blog/rethinking-personal-data-the-cjeus-contextual-turn-in-edps-vs-srb/
@…

Rethinking Thinking Tokens: LLMs as Improvement Operators
Lovish Madaan, Aniket Didolkar, Suchin Gururangan, John Quan, Ruan Silva, Ruslan Salakhutdinov, Manzil Zaheer, Sanjeev Arora, Anirudh Goyal
https://arxiv.org/abs/2510.01123

Rethinking Thinking Tokens: LLMs as Improvement Operators
Reasoning training incentivizes LLMs to produce long chains of thought (long CoT), which among other things, allows them to explore solution strategies with self-checking. This results in higher accuracy, but inflates context length, token/compute cost, and answer latency. We ask: Can current models leverage their metacognition to provide other combinations on this Pareto frontier, e.g., better accuracy with lower context length and/or latency? Abstractly, we view the model as an improvement op…

One More Glance with Sharp Eyes: Rethinking Lightweight Captioning as a Practical Visual Specialist
Junha Song, Yongsik Jo, So Yeon Min, Quanting Xie, Taehwan Kim, Yonatan Bisk, Jaegul Choo
https://arxiv.org/abs/2508.21451

One More Glance with Sharp Eyes: Rethinking Lightweight Captioning as a Practical Visual Specialist
Image captioning is fundamental for applications like video instruction systems and exploration robots, yet deploying such models on local devices is challenging due to the high computational demands of multimodal large language models (MLLMs). To address this, we first explore lightweight captioning by implementing a specialist based on a 125M-parameter language model, 56 times smaller than LLaMA-7B, and evaluating its performance on both single-sentence and detailed captioning tasks. Surprisi…

DaVinci said, "As a well-spent day brings happy sleep, so a life well spent brings happy death.” Let your death be as good as your life. | Beyond the Taboo: Rethinking Society's Fear of Death #EndOfLife #Reposted

Rethinking Wine Tasting for Chinese Consumers: A Service Design Approach Enhanced by Multimodal Personalization
Xinyang Shan, Yuanyuan Xu, Tian Xia, Yinshan Lin
https://arxiv.org/abs/2510.00583

Rethinking Wine Tasting for Chinese Consumers: A Service Design Approach Enhanced by Multimodal Personalization
Wine tasting is a multimodal and culturally embedded activity that presents unique challenges when adapted to non-Western contexts. This paper proposes a service design approach rooted in contextual co-creation to reimagine wine tasting experiences for Chinese consumers. Drawing on 26 in-situ interviews and follow-up validation sessions, we identify three distinct user archetypes: Curious Tasters, Experience Seekers, and Knowledge Builders, each exhibiting different needs in vocabulary, interac…

Rethinking Layer-wise Model Merging through Chain of Merges
Pietro Buzzega, Riccardo Salami, Angelo Porrello, Simone Calderara
https://arxiv.org/abs/2508.21421 https://

Rethinking Layer-wise Model Merging through Chain of Merges
Fine-tuning pretrained models has become a standard pathway to achieve state-of-the-art performance across a wide range of domains, leading to a proliferation of task-specific model variants. As the number of such specialized modules in-creases, merging them into a unified model without retraining has become a critical challenge. Existing merging techniques often rely on interference heuristics,importance weighting, or activation matching while treating each layer independently, thereby failing…

Having not written anything about my #tricycle project in months, I've now written two posts in two days. Here's the first:
#BikeTooter
Rethinking the tricycle drive train

Rethinking the tricycle drive train
I've been rereading my posts on design of a tricycle, and especially this one; and I've been looking again at this picture, of Seventy Seven's removable front subframe which carries its front wheel, steering, and transmission systems; and I've been thinking. This will be a short post documenting my thoughts.

Crosslisted article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[4/11]:
- Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs
Hao Ban, Kaiyi Ji

Lorentz, Poincar\'e, and Einstein: Rethinking Doppler, Aberration, and the Fresnel Drag
Galina Weinstein
https://arxiv.org/abs/2509.26389 https://arxiv…

Lorentz, Poincaré, and Einstein: Rethinking Doppler, Aberration, and the Fresnel Drag
This paper examines Lorentz's 1895 derivations of the classical Doppler formula and Fresnel drag, Einstein's 1905 derivation of the relativistic Doppler effect and aberration, and Einstein's 1907 kinematical route to the exact velocity composition law from which Fresnel drag is obtained as a low-velocity limit. Einstein acknowledged that he had read Lorentz's "Versuch" well before 1905. In 1907, Einstein identified Lorentz's "Versuch" as a crucial precursor to relativity. In that work, Lorentz …

UniDex: Rethinking Search Inverted Indexing with Unified Semantic Modeling
Zan Li, Jiahui Chen, Yuan Chai, Xiaoze Jiang, Xiaohua Qi, Zhiheng Qin, Runbin Zhou, Shun Zuo, Guangchao Hao, Kefeng Wang, Jingshan Lv, Yupeng Huang, Xiao Liang, Han Li
https://arxiv.org/abs/2509.24632

UniDex: Rethinking Search Inverted Indexing with Unified Semantic Modeling
Inverted indexing has traditionally been a cornerstone of modern search systems, leveraging exact term matches to determine relevance between queries and documents. However, this term-based approach often emphasizes surface-level token overlap, limiting the system's generalization capabilities and retrieval effectiveness. To address these challenges, we propose UniDex, a novel model-based method that employs unified semantic modeling to revolutionize inverted indexing. UniDex replaces complex m…

Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification
Lukas Rauch, Ren\'e Heinrich, Houtan Ghaffari, Lukas Miklautz, Ilyass Moummad, Bernhard Sick, Christoph Scholz
https://arxiv.org/abs/2509.24901

Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification
Although probing frozen models has become a standard evaluation paradigm, self-supervised learning in audio defaults to fine-tuning. A key reason is that global pooling creates an information bottleneck causing linear probes to misrepresent the embedding quality: The $\texttt{cls}$-token discards crucial token information about dispersed, localized events in multi-label audio. This weakness is rooted in the mismatch between the pretraining objective (operating globally) and the downstream task …

Joyride: Rethinking Linux's network stack design for better performance, security, and reliability
Yanlin Du, Ruslan Nikolaev
https://arxiv.org/abs/2509.25015 https://

Joyride: Rethinking Linux's network stack design for better performance, security, and reliability
Contemporary distributed computing workloads, including scientific computation, data mining, and machine learning, increasingly demand OS networking with minimal latency as well as high throughput, security, and reliability. However, Linux's conventional TCP/IP stack becomes increasingly problematic for high-end NICs, particularly those operating at 100 Gbps and beyond. These limitations come mainly from overheads associated with kernel space processing, mode switching, and data copying in th…

ACLA 26 - Law and Literature: Rethinking the Interdiscipline
https://ift.tt/rmUodCW
updated: Monday, September 1, 2025 - 3:12pmfull name / name of organization: Nimisha Sinha…
via Input 4 RELCFP

A Graph Talks, But Who's Listening? Rethinking Evaluations for Graph-Language Models
Soham Petkar, Hari Aakash K, Anirudh Vempati, Akshit Sinha, Ponnurangam Kumarauguru, Chirag Agarwal
https://arxiv.org/abs/2508.20583

A Graph Talks, But Who's Listening? Rethinking Evaluations for Graph-Language Models
Developments in Graph-Language Models (GLMs) aim to integrate the structural reasoning capabilities of Graph Neural Networks (GNNs) with the semantic understanding of Large Language Models (LLMs). However, we demonstrate that current evaluation benchmarks for GLMs, which are primarily repurposed node-level classification datasets, are insufficient to assess multimodal reasoning. Our analysis reveals that strong performance on these benchmarks is achievable using unimodal information alone, sugg…

Rethinking Portfolio Risk: Forecasting Volatility Through Cointegrated Asset Dynamics
Gabriele Casto
https://arxiv.org/abs/2509.23533 https://arxiv.org/pdf…

Rethinking Portfolio Risk: Forecasting Volatility Through Cointegrated Asset Dynamics
We introduce the Historical and Dynamic Volatility Ratios (HVR/DVR) and show that equity and index volatilities are cointegrated at intraday and daily horizons. This allows us to construct a VECM to forecast portfolio volatility by exploiting volatility cointegration. On S&P 500 data, HVR is generally stationary and cointegration with the index is frequent; the VECM implementation yields substantially lower mean absolute percentage error (MAPE) than covariance-based forecasts at short- to mediu…

Rethinking Testing for LLM Applications: Characteristics, Challenges, and a Lightweight Interaction Protocol
Wei Ma, Yixiao Yang, Qiang Hu, Shi Ying, Zhi Jin, Bo Du, Zhenchang Xing, Tianlin Li, Junjie Shi, Yang Liu, Linxiao Jiang
https://arxiv.org/abs/2508.20737

Rethinking Testing for LLM Applications: Characteristics, Challenges, and a Lightweight Interaction Protocol
Applications of Large Language Models~(LLMs) have evolved from simple text generators into complex software systems that integrate retrieval augmentation, tool invocation, and multi-turn interactions. Their inherent non-determinism, dynamism, and context dependence pose fundamental challenges for quality assurance. This paper decomposes LLM applications into a three-layer architecture: \textbf{\textit{System Shell Layer}}, \textbf{\textit{Prompt Orchestration Layer}}, and \textbf{\textit{LLM In…

Piketty with a refreshingly-different take on tariffs: https://www.lemonde.fr/blog/piketty/2025/10/07/rethinking-world-trade/

"Live and Let Die: Rethinking Personal Digital Archiving, Memory, and Forgetting Through a Library Lens" https://lil.law.harvard.edu/blog/2025/08/20/live-and-let-die-rethinking-personal-digit…

Rethinking Denial-of-Service: A Conditional Taxonomy Unifying Availability and Sustainability Threats
Mark Dorsett, Scott Man, Tim Koussas
https://arxiv.org/abs/2508.19283 https…

Rethinking Denial-of-Service: A Conditional Taxonomy Unifying Availability and Sustainability Threats
This paper proposes a unified, condition-based framework for classifying both legacy and cloud-era denial-of-service (DoS) attacks. The framework comprises three interrelated models: a formal conditional tree taxonomy, a hierarchical lattice structure based on order theory, and a conceptual Venn diagram. At its core, the taxonomy introduces six observable conditions (C0-C5) grounded in real-world attack behaviours, including source distribution, traffic volume, infrastructure targeting, and fin…

Rethinking Entropy Regularization in Large Reasoning Models
Yuxian Jiang, Yafu Li, Guanxu Chen, Dongrui Liu, Yu Cheng, Jing Shao
https://arxiv.org/abs/2509.25133 https://…

Rethinking Entropy Regularization in Large Reasoning Models
Reinforcement learning with verifiable rewards (RLVR) has shown great promise in enhancing the reasoning abilities of large reasoning models (LRMs). However, it suffers from a critical issue: entropy collapse and premature convergence. Naive entropy regularization, a common approach for encouraging exploration in the traditional RL literature, fails to address this problem in the context of LRM. Our analysis reveals that this failure stems from the vast action space and long trajectories in LRM…

Thirteen newsroom leaders and ethicists discuss elements of journalistic ethics, including dealing with AI, anonymous leaks, bias, lies, and audience needs (Columbia Journalism Review)
https://www.cjr.org/feature/thirteen-journ

Thirteen Journalists on How They Are Rethinking Ethics 
We asked newsroom leaders and ethicists what they’re keeping or changing in an era of Trump, “fake news,” AI, and industry decline.

Prediction-Powered Communication with Distortion Guarantees
Matteo Zecchin, Unnikrishnan Kunnath Ganesan, Giuseppe Durisi, Petar Popovski, Osvaldo Simeone
https://arxiv.org/abs/2509.24373

Prediction-Powered Communication with Distortion Guarantees
The development of 6G wireless systems is taking place alongside the development of increasingly intelligent wireless devices and network nodes. The changing technological landscape is motivating a rethinking of classical Shannon information theory that emphasizes semantic and task-oriented paradigms. In this paper, we study a prediction-powered communication setting, in which devices, equipped with artificial intelligence (AI)-based predictors, communicate under zero-delay constraints with str…

from my link log —
CHERI with a Linux on top.
https://lwn.net/SubscriberLink/1037974/903c6f9a42f7782a/
saved 2025-09-26 https://

ACLA 26 - Law and Literature: Rethinking the Interdiscipline
https://ift.tt/rmUodCW
updated: Monday, September 1, 2025 - 3:12pmfull name / name of organization: Nimisha Sinha…
via Input 4 RELCFP

Rethinking Caching for LLM Serving Systems: Beyond Traditional Heuristics
Jungwoo Kim, Minsang Kim, Jaeheon Lee, Chanwoo Moon, Heejin Kim, Taeho Hwang, Woosuk Chung, Yeseong Kim, Sungjin Lee
https://arxiv.org/abs/2508.18736

Rethinking Caching for LLM Serving Systems: Beyond Traditional Heuristics
Serving Large Language Models (LLMs) at scale requires meeting strict Service Level Objectives (SLOs) under severe computational and memory constraints. Nevertheless, traditional caching strategies fall short: exact-matching and prefix caches neglect query semantics, while state-of-the-art semantic caches remain confined to traditional intuitions, offering little conceptual departure. Building on this, we present SISO, a semantic caching system that redefines efficiency for LLM serving. SISO in…

“…across social media, extraordinary scenes keep surfacing - unarmed men & women staring down heavily armed masked men. People getting out of their cars or running out of restaurants to confront ICE agents.
…not lone individuals who suddenly snap. This is grassroots non-violent resistance. When the rule of law has failed in the courts and in democracy, ordinary people have stepped up to defend their neighbours.”

Rethinking the Role of the Bystander
Trump's storm troopers couldn't be more menacing, even if they adopted the Death's Head symbol of the SS.

Rethinking Quantum Repeaters: Balancing Scalability, Feasibility, and Interoperability
Javier Rey-Dom\'inguez, Mohsen Razavi
https://arxiv.org/abs/2508.16310 https://…

Rethinking Quantum Repeaters: Balancing Scalability, Feasibility, and Interoperability
Quantum repeaters are enabling technologies for long-distance quantum communications. Despite the significant progress in the field, we still not only face implementation challenges but also need theoretical solutions that better meet all the desired design criteria. Preliminary solutions for quantum repeaters often do not scale well, while the most advanced solutions are so demanding that their implementation may take a long time and require substantial changes to current telecom infrastructur…

Blogged: “Rethinking my backups”
https://strugglers.net/posts/2025/rethinking-my-backups/

“AI has brought the cost of disinformation down to nothing. It has automated bullshit.”
#ArtificialStupidity https://www.desmog.com/2025/08/27/ai-slop-…

AI ‘Slop’ Websites Are Publishing Climate Science Denial
At the start of June, MSN, the world’s fourth-largest news aggregator, posted an article from a new climate-focused publication, Climate Cosmos, entitled: “Why Top Experts Are Rethinking Climate Alarmism”. The article – by “Kathleen Westbrook M.Sc Climate Science” – cited a finding from the “Global Climate Research Institute” that “65 percent of surveyed climate professionals […]

Rethinking Purity and Diversity in Multi-Behavior Sequential Recommendation from the Frequency Perspective
Yongqiang Han, Kai Cheng, Kefan Wang, Enhong Chen
https://arxiv.org/abs/2508.20427

Rethinking Purity and Diversity in Multi-Behavior Sequential Recommendation from the Frequency Perspective
In recommendation systems, users often exhibit multiple behaviors, such as browsing, clicking, and purchasing. Multi-behavior sequential recommendation (MBSR) aims to consider these different behaviors in an integrated manner to improve the recommendation performance of the target behavior. However, some behavior data will also bring inevitable noise to the modeling of user interests. Some research efforts focus on data denoising from the frequency domain perspective to improve the accuracy of …

What's Not on the Plate? Rethinking Food Computing through Indigenous Indian Datasets
Pamir Gogoi, Neha Joshi, Ayushi Pandey, Deepthi Sudharsan, Saransh Kumar Gupta, Lipika Dey, Partha Pratim Das, Kalika Bali, Vivek Seshadri
https://arxiv.org/abs/2509.16286

What's Not on the Plate? Rethinking Food Computing through Indigenous Indian Datasets
This paper presents a multimodal dataset of 1,000 indigenous recipes from remote regions of India, collected through a participatory model involving first-time digital workers from rural areas. The project covers ten endangered language communities in six states. Documented using a dedicated mobile app, the data set includes text, images, and audio, capturing traditional food practices along with their ecological and cultural contexts. This initiative addresses gaps in food computing, such as t…

Rethinking scale in network neuroscience: Contributions and opportunities at the nanoscale
Richard Betzel, Caio Seguin, Maria Grazia Puxeddu
https://arxiv.org/abs/2508.16760 htt…

Rethinking scale in network neuroscience: Contributions and opportunities at the nanoscale
Network science has been applied widely to study brain network organization, especially at the meso-scale, where nodes represent brain areas and edges reflect interareal connectivity inferred from imaging or tract-tracing data. While this approach has yielded important insights into large-scale brain network architecture, its foundational assumptions often misalign with the biological realities of neural systems. In this review, we argue that network science finds its most direct and mechanisti…

Stratify or Die: Rethinking Data Splits in Image Segmentation
Naga Venkata Sai Jitin Jami, Thomas Altstidl, Jonas Mueller, Jindong Li, Dario Zanca, Bjoern Eskofier, Heike Leutheuser
https://arxiv.org/abs/2509.21056

Stratify or Die: Rethinking Data Splits in Image Segmentation
Random splitting of datasets in image segmentation often leads to unrepresentative test sets, resulting in biased evaluations and poor model generalization. While stratified sampling has proven effective for addressing label distribution imbalance in classification tasks, extending these ideas to segmentation remains challenging due to the multi-label structure and class imbalance typically present in such data. Building on existing stratification concepts, we introduce Iterative Pixel Stratifi…

Engineering the Future of R&D: The Case for AI-Driven, Integrated Biotechnology Ecosystems
Alex Zhavoronkov, Chuen Yan Leung
https://arxiv.org/abs/2509.21390 https://…

Engineering the Future of R&D: The Case for AI-Driven, Integrated Biotechnology Ecosystems
The escalating cost, extended timelines, and low success rates in pharmaceutical research demand a fundamental rethinking of biotechnology R&D infrastructure. This chapter introduces the concept of the AI-Integrated Biotechnology Hub, a purpose-built research ecosystem uniting residential, commercial, clinical, and research facilities under a central, AI-driven operating system. Designed as a multi-sided platform, the hub leverages continuous, multi-modal health data collection, advanced smart …

Lessons from Biophilic Design: Rethinking Affective Interaction Design in Built Environments
Shruti Rao, Judith Good, Hamed Alavi
https://arxiv.org/abs/2508.19867 https://

Lessons from Biophilic Design: Rethinking Affective Interaction Design in Built Environments
The perspectives of affective interaction in built environments are largely overlooked and instead dominated by affective computing approaches that view emotions as "static", computable states to be detected and regulated. To address this limitation, we interviewed architects to explore how biophilic design -- our deep-rooted emotional connection with nature -- could shape affective interaction design in smart buildings. Our findings reveal that natural environments facilitate self-directed emo…

Replaced article(s) found for cs.FL. https://arxiv.org/list/cs.FL/new
[1/1]:
- Rethinking meaning and ontologies from the perspective of ontological units
Paul Fabry, Adrien Barton, Jean-Fran\c{c}ois \'Ethier

Rethinking Reference Trajectories in Agile Drone Racing: A Unified Reference-Free Model-Based Controller via MPPI
Fangguo Zhao, Xin Guan, Shuo Li
https://arxiv.org/abs/2509.14726

Rethinking Reference Trajectories in Agile Drone Racing: A Unified Reference-Free Model-Based Controller via MPPI
While model-based controllers have demonstrated remarkable performance in autonomous drone racing, their performance is often constrained by the reliance on pre-computed reference trajectories. Conventional approaches, such as trajectory tracking, demand a dynamically feasible, full-state reference, whereas contouring control relaxes this requirement to a geometric path but still necessitates a reference. Recent advancements in reinforcement learning (RL) have revealed that many model-based con…

Rethinking Transformer Connectivity: TLinFormer, A Path to Exact, Full Context-Aware Linear Attention
Zhongpan Tang
https://arxiv.org/abs/2508.20407 https://

Rethinking Transformer Connectivity: TLinFormer, A Path to Exact, Full Context-Aware Linear Attention
The Transformer architecture has become a cornerstone of modern artificial intelligence, but its core self-attention mechanism suffers from a complexity bottleneck that scales quadratically with sequence length, severely limiting its application in long-sequence tasks. To address this challenge, existing linear attention methods typically sacrifice model performance by relying on data-agnostic kernel approximations or restrictive context selection. This paper returns to the first principles of …

HTML is Dead, Long Live HTML
Rethinking DOM from first principles
Cover Image: Browsers are in a very weird place. While WebAssembly has succeeded, even on the server, the client still feels largely the same as it did 10 years ago.
🌐 https://acko.net/blog/html-is-dead-long-live…

HTML is Dead, Long Live HTML
Rethinking DOM from first principles

Rethinking the joint estimation of magnitude and phase for time-frequency domain neural vocoders
Lingling Dai, Andong Li, Tong Lei, Meng Yu, Xiaodong Li, Chengshi Zheng
https://arxiv.org/abs/2509.18806

Confusion is the Final Barrier: Rethinking Jailbreak Evaluation and Investigating the Real Misuse Threat of LLMs
Yu Yan, Sheng Sun, Zhe Wang, Yijun Lin, Zenghao Duan, zhifei zheng, Min Liu, Zhiyi yin, Jianping Zhang
https://arxiv.org/abs/2508.16347

Confusion is the Final Barrier: Rethinking Jailbreak Evaluation and Investigating the Real Misuse Threat of LLMs
With the development of Large Language Models (LLMs), numerous efforts have revealed their vulnerabilities to jailbreak attacks. Although these studies have driven the progress in LLMs' safety alignment, it remains unclear whether LLMs have internalized authentic knowledge to deal with real-world crimes, or are merely forced to simulate toxic language patterns. This ambiguity raises concerns that jailbreak success is often attributable to a hallucination loop between jailbroken LLM and judger L…

Is Measurement Enough? Rethinking Output Validation in Quantum Program Testing
Jiaming Ye, Xiongfei Wu, Shangzhou Xia, Fuyuan Zhang, Jianjun Zhao
https://arxiv.org/abs/2509.16595

Is Measurement Enough? Rethinking Output Validation in Quantum Program Testing
As quantum computing continues to emerge, ensuring the quality of quantum programs has become increasingly critical. Quantum program testing has emerged as a prominent research area within the scope of quantum software engineering. While numerous approaches have been proposed to address quantum program quality assurance, our analysis reveals that most existing methods rely on measurement-based validation in practice. However, due to the inherently probabilistic nature of quantum programs, measu…

PFD or PDF: Rethinking the Probability of Failure in Mitigation Safety Functions
Hamid Jahanian
https://arxiv.org/abs/2508.12814 https://arxiv.org/pdf/2508…

PFD or PDF: Rethinking the Probability of Failure in Mitigation Safety Functions
SIL (Safety Integrity Level) allocation plays a crucial role in defining the design requirements for Safety Functions (SFs) within high-risk industries. SIL is typically determined based on the estimated Probability of Failure on Demand (PFD), which must remain within permissible limits to manage risk effectively. Extensive research has been conducted on determining target PFD and SIL, with a stronger emphasis on preventive SFs than on mitigation SFs. In this paper, we address a rather conceptu…

Vision-Free Retrieval: Rethinking Multimodal Search with Textual Scene Descriptions
Ioanna Ntinou, Alexandros Xenos, Yassine Ouali, Adrian Bulat, Georgios Tzimiropoulos
https://arxiv.org/abs/2509.19203

Vision-Free Retrieval: Rethinking Multimodal Search with Textual Scene Descriptions
Contrastively-trained Vision-Language Models (VLMs), such as CLIP, have become the standard approach for learning discriminative vision-language representations. However, these models often exhibit shallow language understanding, manifesting bag-of-words behaviour. These limitations are reinforced by their dual-encoder design, which induces a modality gap. Additionally, the reliance on vast web-collected data corpora for training makes the process computationally expensive and introduces signif…

CIRSense: Rethinking WiFi Sensing with Channel Impulse Response
Ruiqi Kong, He Chen
https://arxiv.org/abs/2510.11374 https://arxiv.org/pdf/2510.11374

CIRSense: Rethinking WiFi Sensing with Channel Impulse Response
WiFi sensing based on channel state information (CSI) collected from commodity WiFi devices has shown great potential across a wide range of applications, including vital sign monitoring and indoor localization. Existing WiFi sensing approaches typically estimate motion information directly from CSI. However, they often overlook the inherent advantages of channel impulse response (CIR), a delay-domain representation that enables more intuitive and principled motion sensing by naturally concentr…

Help or Hurdle? Rethinking Model Context Protocol-Augmented Large Language Models
Wei Song, Haonan Zhong, Ziqi Ding, Jingling Xue, Yuekang Li
https://arxiv.org/abs/2508.12566 ht…

Help or Hurdle? Rethinking Model Context Protocol-Augmented Large Language Models
The Model Context Protocol (MCP) enables large language models (LLMs) to access external resources on demand. While commonly assumed to enhance performance, how LLMs actually leverage this capability remains poorly understood. We introduce MCPGAUGE, the first comprehensive evaluation framework for probing LLM-MCP interactions along four key dimensions: proactivity (self-initiated tool use), compliance (adherence to tool-use instructions), effectiveness (task performance post-integration), and o…

Allen: Rethinking MAS Design through Step-Level Policy Autonomy
Qiangong Zhou, Zhiting Wang, Mingyou Yao, Zongyang Liu
https://arxiv.org/abs/2508.11294 https://

Allen: Rethinking MAS Design through Step-Level Policy Autonomy
We introduce a new Multi-Agent System (MAS) - Allen, designed to address two core challenges in current MAS design: (1) improve system's policy autonomy, empowering agents to dynamically adapt their behavioral strategies, and (2) achieving the trade-off between collaborative efficiency, task supervision, and human oversight in complex network topologies. Our core insight is to redefine the basic execution unit in the MAS, allowing agents to autonomously form different patterns by combining th…

Rethinking Reliability Using Network Coding: a Practical 5G Evaluation
Laura Landon, Vipindev Adat Vasudevan, Junmo Sung, Muriel M\'edard
https://arxiv.org/abs/2508.10247 ht…

Rethinking Reliability Using Network Coding: a Practical 5G Evaluation
This work presents the design and implementation of a real-time network coding system integrated into the IP layer of a 5G testbed, offering an alternative to conventional retransmission-based reliability mechanisms such as ARQ and HARQ. Using a netfilter-based packet interception framework, we inject forward erasure correction using Random Linear Network Coding (RLNC) into live traffic between a gNB and UE over a 3GPP RF link. We evaluate a block coding scheme, analyzing its impact on throughp…

Replaced article(s) found for q-fin.ST. https://arxiv.org/list/q-fin.ST/new
[1/1]:
- Rethinking Beta: A Causal Take on CAPM
Naftali Cohen
https://

Consumer Autonomy or Illusion? Rethinking Consumer Agency in the Age of Algorithms
Pegah Nokhiz, Aravinda Kanchana Ruwanpathirana
https://arxiv.org/abs/2508.13440 https://

Consumer Autonomy or Illusion? Rethinking Consumer Agency in the Age of Algorithms
Consumer agency in the digital age is increasingly constrained by systemic barriers and algorithmic manipulation, raising concerns about the authenticity of consumption choices. Nowadays, financial decisions are shaped by external pressures like obligatory consumption, algorithmic persuasion, and unstable work schedules that erode financial autonomy. Obligatory consumption (like hidden fees) is intensified by digital ecosystems. Algorithmic tactics like personalized recommendations lead to impu…

From Restoration to Reconstruction: Rethinking 3D Gaussian Splatting for Underwater Scenes
Guoxi Huang, Haoran Wang, Zipeng Qi, Wenjun Lu, David Bull, Nantheera Anantrasirichai
https://arxiv.org/abs/2509.17789

From Restoration to Reconstruction: Rethinking 3D Gaussian Splatting for Underwater Scenes
Underwater image degradation poses significant challenges for 3D reconstruction, where simplified physical models often fail in complex scenes. We propose \textbf{R-Splatting}, a unified framework that bridges underwater image restoration (UIR) with 3D Gaussian Splatting (3DGS) to improve both rendering quality and geometric fidelity. Our method integrates multiple enhanced views produced by diverse UIR models into a single reconstruction pipeline. During inference, a lightweight illumination g…

SMEC: Rethinking Matryoshka Representation Learning for Retrieval Embedding Compression
Biao Zhang, Lixin Chen, Tong Liu, Bo Zheng
https://arxiv.org/abs/2510.12474 https://

SMEC: Rethinking Matryoshka Representation Learning for Retrieval Embedding Compression
Large language models (LLMs) generate high-dimensional embeddings that capture rich semantic and syntactic information. However, high-dimensional embeddings exacerbate computational complexity and storage requirements, thereby hindering practical deployment. To address these challenges, we propose a novel training framework named Sequential Matryoshka Embedding Compression (SMEC). This framework introduces the Sequential Matryoshka Representation Learning(SMRL) method to mitigate gradient varia…

From Hype to Insight: Rethinking Large Language Model Integration in Visual Speech Recognition
Rishabh Jain, Naomi Harte
https://arxiv.org/abs/2509.14880 https://

From Hype to Insight: Rethinking Large Language Model Integration in Visual Speech Recognition
Advances in self-supervised encoders have improved Visual Speech Recognition (VSR). Recent approaches integrating these encoders with LLM decoders improves transcription accuracy; however, it remains unclear whether these gains stem from visual understanding or stronger language modeling. In this work, we systematically evaluate LLM decoders by freezing or selectively updating the visual encoder, scaling decoder size, comparing adaptation strategies and architectures, and varying training data …

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[2/5]:
- Rethinking Distribution Shifts: Empirical Analysis and Inductive Modeling for Tabular Data
Tianyu Wang, Jiashuo Liu, Peng Cui, Hongseok Namkoong

CFP ACLA 2025: The Future is Past: Rethinking Dystopia in Contemporary Film and Literature
https://ift.tt/1Gw5mNU
updated: Thursday, August 28, 2025 - 8:06amfull name / name of organization: Elif Sendur Allison…
via Input 4 RELCFP

Rethinking Autonomy: Preventing Failures in AI-Driven Software Engineering
Satyam Kumar Navneet, Joydeep Chandra
https://arxiv.org/abs/2508.11824 https://a…

Rethinking Autonomy: Preventing Failures in AI-Driven Software Engineering
The integration of Large Language Models (LLMs) into software engineering has revolutionized code generation, enabling unprecedented productivity through promptware and autonomous AI agents. However, this transformation introduces significant risks, including insecure code generation, hallucinated outputs, irreversible actions, and a lack of transparency and accountability. Incidents like the Replit database deletion underscore the urgent need for robust safety and governance mechanisms. This p…

Rethinking Molecule Synthesizability with Chain-of-Reaction
Seul Lee, Karsten Kreis, Srimukh Prasad Veccham, Meng Liu, Danny Reidenbach, Saee Paliwal, Weili Nie, Arash Vahdat
https://arxiv.org/abs/2509.16084

Rethinking Molecule Synthesizability with Chain-of-Reaction
A well-known pitfall of molecular generative models is that they are not guaranteed to generate synthesizable molecules. There have been considerable attempts to address this problem, but given the exponentially large combinatorial space of synthesizable molecules, existing methods have shown limited coverage of the space and poor molecular optimization performance. To tackle these problems, we introduce ReaSyn, a generative framework for synthesizable projection where the model explores the ne…

The Hidden Cost of Correlation: Rethinking Privacy Leakage in Local Differential Privacy
Sandaru Jayawardana, Sennur Ulukus, Ming Ding, Kanchana Thilakarathna
https://arxiv.org/abs/2508.12539

The Hidden Cost of Correlation: Rethinking Privacy Leakage in Local Differential Privacy
Local differential privacy (LDP) has emerged as a promising paradigm for privacy-preserving data collection in distributed systems, where users contribute multi-dimensional records with potentially correlated attributes. Recent work has highlighted that correlation-induced privacy leakage (CPL) plays a critical role in shaping the privacy-utility trade-off under LDP, especially when correlations exist among attributes. Nevertheless, it remains unclear to what extent the prevailing assumptions a…

Rethinking Cross-Corpus Speech Emotion Recognition Benchmarking: Are Paralinguistic Pre-Trained Representations Sufficient?
Orchid Chetia Phukan, Mohd Mujtaba Akhtar, Girish, Swarup Ranjan Behera, Parabattina Bhagath, Pailla Balakrishna Reddy, Arun Balaji Buduru
https://arxiv.org/abs/2509.16182

Rethinking Cross-Corpus Speech Emotion Recognition Benchmarking: Are Paralinguistic Pre-Trained Representations Sufficient?
Recent benchmarks evaluating pre-trained models (PTMs) for cross-corpus speech emotion recognition (SER) have overlooked PTM pre-trained for paralinguistic speech processing (PSP), raising concerns about their reliability, since SER is inherently a paralinguistic task. We hypothesize that PSP-focused PTM will perform better in cross-corpus SER settings. To test this, we analyze state-of-the-art PTMs representations including paralinguistic, monolingual, multilingual, and speaker recognition. Ou…

Established Psychometric vs. Ecologically Valid Questionnaires: Rethinking Psychological Assessments in Large Language Models
Dongmin Choi, Woojung Song, Jongwook Han, Eun-Ju Lee, Yohan Jo
https://arxiv.org/abs/2509.10078

Established Psychometric vs. Ecologically Valid Questionnaires: Rethinking Psychological Assessments in Large Language Models
Researchers have applied established psychometric questionnaires (e.g., BFI, PVQ) to measure the personality traits and values reflected in the responses of Large Language Models (LLMs). However, concerns have been raised about applying these human-designed questionnaires to LLMs. One such concern is their lack of ecological validity--the extent to which survey questions adequately reflect and resemble real-world contexts in which LLMs generate texts in response to user queries. However, it rem…

Rethinking User Empowerment in AI Recommender Systems: Designing through Transparency and Control
Mengke Wu, Weizi Liu, Yanyun Wang, Weiyu Ding, Mike Yao
https://arxiv.org/abs/2509.11098

Rethinking User Empowerment in AI Recommender Systems: Designing through Transparency and Control
Smart recommendation algorithms have revolutionized content delivery and improved efficiency across various domains. However, concerns about user agency persist due to their inherent opacity (information asymmetry) and one-way influence (power asymmetry). This study introduces a provotype designed to enhance user agency by providing actionable transparency and control over data management and content delivery. We conducted qualitative interviews with 19 participants to explore their preferences…

Rethinking Human Preference Evaluation of LLM Rationales
Ziang Li, Manasi Ganti, Zixian Ma, Helena Vasconcelos, Qijia He, Ranjay Krishna
https://arxiv.org/abs/2509.11026 https:/…

Rethinking Human Preference Evaluation of LLM Rationales
Large language models (LLMs) often generate natural language rationales -- free-form explanations that help improve performance on complex reasoning tasks and enhance interpretability for human users. However, evaluating these rationales remains challenging. While recent work has relied on binary preference judgments from humans or LLM judges, such evaluations are often opaque and coarse-grained, offering limited insight into what makes one rationale better than another. In this work, we rethin…

HERO: Rethinking Visual Token Early Dropping in High-Resolution Large Vision-Language Models
Xu Li, Yuxuan Liang, Xiaolei Chen, Yi Zheng, Haotian Chen, Bin Li, Xiangyang Xue
https://arxiv.org/abs/2509.13067

HERO: Rethinking Visual Token Early Dropping in High-Resolution Large Vision-Language Models
By cropping high-resolution images into local tiles and encoding them independently, High-Resolution Large Vision-Language Models (HR-LVLMs) have demonstrated remarkable fine-grained visual understanding capabilities. However, this divide-and-conquer paradigm significantly increases the number of visual tokens, resulting in substantial computational and memory overhead. To better understand and address this challenge, we empirically investigate visual token utilization in HR-LVLMs and uncover t…

Rethinking Technology Stack Selection with AI Coding Proficiency
Xiaoyu Zhang, Weipeng Jiang, Juan Zhai, Shiqing Ma, Qingshuang Bao, Chenhao Lin, Chao Shen, Tianlin Li, Yang Liu
https://arxiv.org/abs/2509.11132

Rethinking Technology Stack Selection with AI Coding Proficiency
Large language models (LLMs) are now an integral part of software development workflows and are reshaping the whole process. Traditional technology stack selection has not caught up. Most of the existing selection methods focus solely on the inherent attributes of the technology, overlooking whether the LLM can effectively leverage the chosen technology. For example, when generating code snippets using popular libraries like Selenium (one of the most widely used test automation tools with over …

Rethinking How We Discuss the Guidance of Student Researchers in Computing
Shomir Wilson
https://arxiv.org/abs/2510.08885 https://arxiv.org/pdf/2510.08885

Rethinking How We Discuss the Guidance of Student Researchers in Computing
Computing faculty at research universities are often expected to guide the work of undergraduate and graduate student researchers. This guidance is typically called advising or mentoring, but these terms belie the complexity of the relationship, which includes several related but distinct roles. I examine the guidance of student researchers in computing (abbreviated to research guidance or guidance throughout) within a facet framework, creating an inventory of roles that faculty members can hol…

One Shot vs. Iterative: Rethinking Pruning Strategies for Model Compression
Miko{\l}aj Janusz, Tomasz Wojnar, Yawei Li, Luca Benini, Kamil Adamczewski
https://arxiv.org/abs/2508.13836

One Shot vs. Iterative: Rethinking Pruning Strategies for Model Compression
Pruning is a core technique for compressing neural networks to improve computational efficiency. This process is typically approached in two ways: one-shot pruning, which involves a single pass of training and pruning, and iterative pruning, where pruning is performed over multiple cycles for potentially finer network refinement. Although iterative pruning has historically seen broader adoption, this preference is often assumed rather than rigorously tested. Our study presents one of the first …

Co-Alignment: Rethinking Alignment as Bidirectional Human-AI Cognitive Adaptation
Yubo Li, Weiyi Song
https://arxiv.org/abs/2509.12179 https://arxiv.org/pd…

Co-Alignment: Rethinking Alignment as Bidirectional Human-AI Cognitive Adaptation
Current AI alignment through RLHF follows a single directional paradigm that AI conforms to human preferences while treating human cognition as fixed. We propose a shift to co-alignment through Bidirectional Cognitive Alignment (BiCA), where humans and AI mutually adapt. BiCA uses learnable protocols, representation mapping, and KL-budget constraints for controlled co-evolution. In collaborative navigation, BiCA achieved 85.5% success versus 70.3% baseline, with 230% better mutual adaptation an…

Rethinking Reasoning in Document Ranking: Why Chain-of-Thought Falls Short
Xuan Lu, Haohang Huang, Rui Meng, Yaohui Jin, Wenjun Zeng, Xiaoyu Shen
https://arxiv.org/abs/2510.08985

Rethinking Reasoning in Document Ranking: Why Chain-of-Thought Falls Short
Document reranking is a key component in information retrieval (IR), aimed at refining initial retrieval results to improve ranking quality for downstream tasks. Recent studies--motivated by large reasoning models (LRMs)--have begun incorporating explicit chain-of-thought (CoT) reasoning into LLM-based rerankers. However, the effectiveness of such reasoning for ranking tasks remains underexplored. In this work, we present the first systematic study of reasoning in reranking across both pointwis…

Inflated Excellence or True Performance? Rethinking Medical Diagnostic Benchmarks with Dynamic Evaluation
Xiangxu Zhang, Lei Li, Yanyun Zhou, Xiao Zhou, Yingying Zhang, Xian Wu
https://arxiv.org/abs/2510.09275

Inflated Excellence or True Performance? Rethinking Medical Diagnostic Benchmarks with Dynamic Evaluation
Medical diagnostics is a high-stakes and complex domain that is critical to patient care. However, current evaluations of large language models (LLMs) are fundamentally misaligned with real-world clinical practice. Most of them rely on static benchmarks derived from public medical exam items, which tend to overestimate model performance and ignore the difference between textbook cases and the ambiguous, varying conditions in the real world. Recent efforts toward dynamic evaluation offer a promi…

DeCodec: Rethinking Audio Codecs as Universal Disentangled Representation Learners
Xiaoxue Luo, Jinwei Huang, Runyan Yang, Yingying Gao, Junlan Feng, Chao Deng, Shilei Zhang
https://arxiv.org/abs/2509.09201

DeCodec: Rethinking Audio Codecs as Universal Disentangled Representation Learners
Universal audio codecs learn entangled representations across audio types, whereas some specific codecs offer decoupled representations but are limited to speech. Real-world audio, however, often contains mixed speech and background sounds, and downstream tasks require selective access to these components. Therefore, we rethink the audio codec as a universal disentangled representation learner to enable controllable feature selection across different audio tasks. To this end, we introduce DeCod…

More performant and scalable: Rethinking contrastive vision-language pre-training of radiology in the LLM era
Yingtai Li, Haoran Lai, Xiaoqian Zhou, Shuai Ming, Wenxin Ma, Wei Wei, Shaohua Kevin Zhou
https://arxiv.org/abs/2509.13175

More performant and scalable: Rethinking contrastive vision-language pre-training of radiology in the LLM era
The emergence of Large Language Models (LLMs) presents unprecedented opportunities to revolutionize medical contrastive vision-language pre-training. In this paper, we show how LLMs can facilitate large-scale supervised pre-training, thereby advancing vision-language alignment. We begin by demonstrate that modern LLMs can automatically extract diagnostic labels from radiology reports with remarkable precision (>96\% AUC in our experiments) without complex prompt engineering, enabling the creati…

Hallucination vs interpretation: rethinking accuracy and precision in AI-assisted data extraction for knowledge synthesis
Xi Long, Christy Boscardin, Lauren A. Maggio, Joseph A. Costello, Ralph Gonzales, Rasmyah Hammoudeh, Ki Lai, Yoon Soo Park, Brian C. Gin
https://arxiv.org/abs/2508.09458

Hallucination vs interpretation: rethinking accuracy and precision in AI-assisted data extraction for knowledge synthesis
Knowledge syntheses (literature reviews) are essential to health professions education (HPE), consolidating findings to advance theory and practice. However, they are labor-intensive, especially during data extraction. Artificial Intelligence (AI)-assisted extraction promises efficiency but raises concerns about accuracy, making it critical to distinguish AI 'hallucinations' (fabricated content) from legitimate interpretive differences. We developed an extraction platform using large language m…

PAnDA: Rethinking Metric Differential Privacy Optimization at Scale with Anchor-Based Approximation
Ruiyao Liu, Chenxi Qiu
https://arxiv.org/abs/2509.08720 https://

PAnDA: Rethinking Metric Differential Privacy Optimization at Scale with Anchor-Based Approximation
Metric Differential Privacy (mDP) extends the local differential privacy (LDP) framework to metric spaces, enabling more nuanced privacy protection for data such as geo-locations. However, existing mDP optimization methods, particularly those based on linear programming (LP), face scalability challenges due to the quadratic growth in decision variables. In this paper, we propose Perturbation via Anchor-based Distributed Approximation (PAnDA), a scalable two-phase framework for optimizing metric…

Unequal Uncertainty: Rethinking Algorithmic Interventions for Mitigating Discrimination from AI
Holli Sargeant, Mackenzie Jorgensen, Arina Shah, Adrian Weller, Umang Bhatt
https://arxiv.org/abs/2508.07872

Unequal Uncertainty: Rethinking Algorithmic Interventions for Mitigating Discrimination from AI
Uncertainty in artificial intelligence (AI) predictions poses urgent legal and ethical challenges for AI-assisted decision-making. We examine two algorithmic interventions that act as guardrails for human-AI collaboration: selective abstention, which withholds high-uncertainty predictions from human decision-makers, and selective friction, which delivers those predictions together with salient warnings or disclosures that slow the decision process. Research has shown that selective abstention b…

ACLA 26 - Law and Literature: Rethinking the Interdiscipline https://call-for-papers.sas.upenn.edu/cfp/2025/09/01/acla-26-law-and-literature-rethinking-the-interdiscipline

VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction
Weijie Wang, Yeqing Chen, Zeyu Zhang, Hengyu Liu, Haoxiao Wang, Zhiyuan Feng, Wenkang Qin, Zheng Zhu, Donny Y. Chen, Bohan Zhuang
https://arxiv.org/abs/2509.19297

Replaced article(s) found for cs.CR. https://arxiv.org/list/cs.CR/new
[2/2]:
- Rethinking Backdoor Detection Evaluation for Language Models
Jun Yan, Wenjie Jacky Mo, Xiang Ren, Robin Jia

Mind Meets Space: Rethinking Agentic Spatial Intelligence from a Neuroscience-inspired Perspective
Bui Duc Manh, Soumyaratna Debnath, Zetong Zhang, Shriram Damodaran, Arvind Kumar, Yueyi Zhang, Lu Mi, Erik Cambria, Lin Wang
https://arxiv.org/abs/2509.09154

Mind Meets Space: Rethinking Agentic Spatial Intelligence from a Neuroscience-inspired Perspective
Recent advances in agentic AI have led to systems capable of autonomous task execution and language-based reasoning, yet their spatial reasoning abilities remain limited and underexplored, largely constrained to symbolic and sequential processing. In contrast, human spatial intelligence, rooted in integrated multisensory perception, spatial memory, and cognitive maps, enables flexible, context-aware decision-making in unstructured environments. Therefore, bridging this gap is critical for advan…

Rethinking Knowledge Distillation: A Data Dependent Regulariser With a Negative Asymmetric Payoff
Israel Mason-Williams, Gabryel Mason-Williams, Helen Yannakoudakis
https://arxiv.org/abs/2510.12615

Rethinking Knowledge Distillation: A Data Dependent Regulariser With a Negative Asymmetric Payoff
Knowledge distillation is often considered a compression mechanism when judged on the resulting student's accuracy and loss, yet its functional impact is poorly understood. In this work, we quantify the compression capacity of knowledge distillation and the resulting knowledge transfer from a functional perspective, decoupling compression from architectural reduction, which provides an improved understanding of knowledge distillation. We employ hypothesis testing, controls, and random control d…

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking
Haoxiang Jin, Ronghan Li, Qiguang Miao, Zixiang Lu
https://arxiv.org/abs/2509.06472

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking
Large Language Models (LLMs) often generate inaccurate responses (hallucinations) when faced with questions beyond their knowledge scope. Retrieval-Augmented Generation (RAG) addresses this by leveraging external knowledge, but a critical challenge remains: determining whether retrieved contexts effectively enhance the model`s ability to answer specific queries. This challenge underscores the importance of knowledge boundary awareness, which current methods-relying on discrete labels or limited…

AvatarSync: Rethinking Talking-Head Animation through Autoregressive Perspective
Yuchen Deng, Xiuyang Wu, Hai-Tao Zheng, Suiyang Zhang, Yi He, Yuxing Han
https://arxiv.org/abs/2509.12052

AvatarSync: Rethinking Talking-Head Animation through Autoregressive Perspective
Existing talking-head animation approaches based on Generative Adversarial Networks (GANs) or diffusion models often suffer from inter-frame flicker, identity drift, and slow inference. These limitations inherent to their video generation pipelines restrict their suitability for applications. To address this, we introduce AvatarSync, an autoregressive framework on phoneme representations that generates realistic and controllable talking-head animations from a single reference image, driven dire…

Sprouting technology otherwise, hospicing negative commons -- Rethinking technology in the transition to sustainability-oriented futures
Martin Deron
https://arxiv.org/abs/2508.05860

Sprouting technology otherwise, hospicing negative commons -- Rethinking technology in the transition to sustainability-oriented futures
Due to its significant and growing environmental harms, both directly through its materiality and indirectly through its pervasive integration into unsustainable economic systems, ICT will need to be radically redirected to align with sustainability-oriented futures. While the role of ICT in such futures will likely diverge significantly from current dynamics, it will probably not be entirely disconnected from the present. Instead, such transition involves complex dynamics of continuity, adapta…

FDC-Net: Rethinking the association between EEG artifact removal and multi-dimensional affective computing
Wenjia Dong, Xueyuan Xu, Tianze Yu, Junming Zhang, Li Zhuo
https://arxiv.org/abs/2508.05231

FDC-Net: Rethinking the association between EEG artifact removal and multi-dimensional affective computing
Electroencephalogram (EEG)-based emotion recognition holds significant value in affective computing and brain-computer interfaces. However, in practical applications, EEG recordings are susceptible to the effects of various physiological artifacts. Current approaches typically treat denoising and emotion recognition as independent tasks using cascaded architectures, which not only leads to error accumulation, but also fails to exploit potential synergies between these tasks. Moreover, conventio…

Flaw or Artifact? Rethinking Prompt Sensitivity in Evaluating LLMs
Andong Hua, Kenan Tang, Chenhe Gu, Jindong Gu, Eric Wong, Yao Qin
https://arxiv.org/abs/2509.01790 https://

Flaw or Artifact? Rethinking Prompt Sensitivity in Evaluating LLMs
Prompt sensitivity, referring to the phenomenon where paraphrasing (i.e., repeating something written or spoken using different words) leads to significant changes in large language model (LLM) performance, has been widely accepted as a core limitation of LLMs. In this work, we revisit this issue and ask: Is the widely reported high prompt sensitivity truly an inherent weakness of LLMs, or is it largely an artifact of evaluation processes? To answer this question, we systematically evaluate 7 L…

Rethinking Provenance Completeness with a Learning-Based Linux Scheduler
Jinsong Mao, Benjamin E. Ujcich, Shiqing Ma
https://arxiv.org/abs/2510.08479 https://

Rethinking Provenance Completeness with a Learning-Based Linux Scheduler
Provenance plays a critical role in maintaining traceability of a system's actions for root cause analysis of security threats and impacts. Provenance collection is often incorporated into the reference monitor of systems to ensure that an audit trail exists of all events, that events are completely captured, and that logging of such events cannot be bypassed. However, recent research has questioned whether existing state-of-the-art provenance collection systems fail to ensure the security guar…

UniSearch: Rethinking Search System with a Unified Generative Architecture
Jiahui Chen, Xiaoze Jiang, Zhibo Wang, Quanzhi Zhu, Junyao Zhao, Feng Hu, Kang Pan, Ao Xie, Maohua Pei, Zhiheng Qin, Hongjing Zhang, Zhixin Zhai, Xiaobo Guo, Runbin Zhou, Kefeng Wang, Mingyang Geng, Cheng Chen, Jingshan Lv, Yupeng Huang, Xiao Liang, Han Li
https://a…

UniSearch: Rethinking Search System with a Unified Generative Architecture
Modern search systems play a crucial role in facilitating information acquisition. Traditional search engines typically rely on a cascaded architecture, where results are retrieved through recall, pre-ranking, and ranking stages. The complexity of designing and maintaining multiple modules makes it difficult to achieve holistic performance gains. Recent advances in generative recommendation have motivated the exploration of unified generative search as an alternative. However, existing approach…

Rethinking Reasoning: A Survey on Reasoning-based Backdoors in LLMs
Man Hu, Xinyi Wu, Zuofeng Suo, Jinbo Feng, Linghui Meng, Yanhao Jia, Anh Tuan Luu, Shuai Zhao
https://arxiv.org/abs/2510.07697

Rethinking Reasoning: A Survey on Reasoning-based Backdoors in LLMs
With the rise of advanced reasoning capabilities, large language models (LLMs) are receiving increasing attention. However, although reasoning improves LLMs' performance on downstream tasks, it also introduces new security risks, as adversaries can exploit these capabilities to conduct backdoor attacks. Existing surveys on backdoor attacks and reasoning security offer comprehensive overviews but lack in-depth analysis of backdoor attacks and defenses targeting LLMs' reasoning abilities. In this…

RefineShot: Rethinking Cinematography Understanding with Foundational Skill Evaluation
Hang Wu, Yujun Cai, Haonan Ge, Hongkai Chen, Ming-Hsuan Yang, Yiwei Wang
https://arxiv.org/abs/2510.02423

RefineShot: Rethinking Cinematography Understanding with Foundational Skill Evaluation
Cinematography understanding refers to the ability to recognize not only the visual content of a scene but also the cinematic techniques that shape narrative meaning. This capability is attracting increasing attention, as it enhances multimodal understanding in real-world applications and underpins coherent content creation in film and media. As the most comprehensive benchmark for this task, ShotBench spans a wide range of cinematic concepts and VQA-style evaluations, with ShotVL achieving sta…

Drawing Conclusions from Draws: Rethinking Preference Semantics in Arena-Style LLM Evaluation
Raphael Tang, Crystina Zhang, Wenyan Li, Carmen Lai, Pontus Stenetorp, Yao Lu
https://arxiv.org/abs/2510.02306

Drawing Conclusions from Draws: Rethinking Preference Semantics in Arena-Style LLM Evaluation
In arena-style evaluation of large language models (LLMs), two LLMs respond to a user query, and the user chooses the winning response or deems the "battle" a draw, resulting in an adjustment to the ratings of both models. The prevailing approach for modeling these rating dynamics is to view battles as two-player game matches, as in chess, and apply the Elo rating system and its derivatives. In this paper, we critically examine this paradigm. Specifically, we question whether a draw genuinely m…

Federated Unlearning in the Wild: Rethinking Fairness and Data Discrepancy
ZiHeng Huang, Di Wu, Jun Bai, Jiale Zhang, Sicong Cao, Ji Zhang, Yingjie Hu
https://arxiv.org/abs/2510.07022

Federated Unlearning in the Wild: Rethinking Fairness and Data Discrepancy
Machine unlearning is critical for enforcing data deletion rights like the "right to be forgotten." As a decentralized paradigm, Federated Learning (FL) also requires unlearning, but realistic implementations face two major challenges. First, fairness in Federated Unlearning (FU) is often overlooked. Exact unlearning methods typically force all clients into costly retraining, even those uninvolved. Approximate approaches, using gradient ascent or distillation, make coarse interventions that can…

NaViL: Rethinking Scaling Properties of Native Multimodal Large Language Models under Data Constraints
Changyao Tian, Hao Li, Gen Luo, Xizhou Zhu, Weijie Su, Hanming Deng, Jinguo Zhu, Jie Shao, Ziran Zhu, Yunpeng Liu, Lewei Lu, Wenhai Wang, Hongsheng Li, Jifeng Dai
https://arxiv.org/abs/2510.08565 …

NaViL: Rethinking Scaling Properties of Native Multimodal Large Language Models under Data Constraints
Compositional training has been the de-facto paradigm in existing Multimodal Large Language Models (MLLMs), where pre-trained vision encoders are connected with pre-trained LLMs through continuous multimodal pre-training. However, the multimodal scaling property of this paradigm remains difficult to explore due to the separated training. In this paper, we focus on the native training of MLLMs in an end-to-end manner and systematically study its design space and scaling property under a practica…

Rethinking Langevin Thompson Sampling from A Stochastic Approximation Perspective
Weixin Wang, Haoyang Zheng, Guang Lin, Wei Deng, Pan Xu
https://arxiv.org/abs/2510.05023 https:…

Rethinking Langevin Thompson Sampling from A Stochastic Approximation Perspective
Most existing approximate Thompson Sampling (TS) algorithms for multi-armed bandits use Stochastic Gradient Langevin Dynamics (SGLD) or its variants in each round to sample from the posterior, relaxing the need for conjugacy assumptions between priors and reward distributions in vanilla TS. However, they often require approximating a different posterior distribution in different round of the bandit problem. This requires tricky, round-specific tuning of hyperparameters such as dynamic learning …

Temporal Prompting Matters: Rethinking Referring Video Object Segmentation
Ci-Siang Lin, Min-Hung Chen, I-Jieh Liu, Chien-Yi Wang, Sifei Liu, Yu-Chiang Frank Wang
https://arxiv.org/abs/2510.07319

Temporal Prompting Matters: Rethinking Referring Video Object Segmentation
Referring Video Object Segmentation (RVOS) aims to segment the object referred to by the query sentence in the video. Most existing methods require end-to-end training with dense mask annotations, which could be computation-consuming and less scalable. In this work, we rethink the RVOS problem and aim to investigate the key to this task. Based on existing foundation segmentation models, we decompose the RVOS task into referring, video, and segmentation factors, and propose a Temporal Prompt Gen…

Rethinking Layer-wise Gaussian Noise Injection: Bridging Implicit Objectives and Privacy Budget Allocation
Qifeng Tan (Xi'an Jiaotong University), Shusen Yang (Xi'an Jiaotong University), Xuebin Ren (Xi'an Jiaotong University), Yikai Zhang (Xi'an Jiaotong University)
https://arxiv.org/abs/2509.04232

Rethinking Layer-wise Gaussian Noise Injection: Bridging Implicit Objectives and Privacy Budget Allocation
Layer-wise Gaussian mechanisms (LGM) enhance flexibility in differentially private deep learning by injecting noise into partitioned gradient vectors. However, existing methods often rely on heuristic noise allocation strategies, lacking a rigorous understanding of their theoretical grounding in connecting noise allocation to formal privacy-utility tradeoffs. In this paper, we present a unified analytical framework that systematically connects layer-wise noise injection strategies with their im…

Rethinking the long-range dependency in Mamba/SSM and transformer models
Cong Ma, Kayvan Najarian
https://arxiv.org/abs/2509.04226 https://arxiv.org/pdf/25…

Rethinking the long-range dependency in Mamba/SSM and transformer models
Long-range dependency is one of the most desired properties of recent sequence models such as state-space models (particularly Mamba) and transformer models. New model architectures are being actively developed and benchmarked for prediction tasks requiring long-range dependency. However, the capability of modeling long-range dependencies of these models has not been investigated from a theoretical perspective, which hinders a systematic improvement on this aspect. In this work, we mathematical…

Rethinking Backbone Design for Lightweight 3D Object Detection in LiDAR
Adwait Chandorkar, Hasan Tercan, Tobias Meisen
https://arxiv.org/abs/2508.00744 https://

Rethinking Backbone Design for Lightweight 3D Object Detection in LiDAR
Recent advancements in LiDAR-based 3D object detection have significantly accelerated progress toward the realization of fully autonomous driving in real-world environments. Despite achieving high detection performance, most of the approaches still rely on a VGG-based or ResNet-based backbone for feature exploration, which increases the model complexity. Lightweight backbone design is well-explored for 2D object detection, but research on 3D object detection still remains limited. In this work,…

Transition Models: Rethinking the Generative Learning Objective
Zidong Wang, Yiyuan Zhang, Xiaoyu Yue, Xiangyu Yue, Yangguang Li, Wanli Ouyang, Lei Bai
https://arxiv.org/abs/2509.04394

Transition Models: Rethinking the Generative Learning Objective
A fundamental dilemma in generative modeling persists: iterative diffusion models achieve outstanding fidelity, but at a significant computational cost, while efficient few-step alternatives are constrained by a hard quality ceiling. This conflict between generation steps and output quality arises from restrictive training objectives that focus exclusively on either infinitesimal dynamics (PF-ODEs) or direct endpoint prediction. We address this challenge by introducing an exact, continuous-time…

TeRA: Rethinking Text-driven Realistic 3D Avatar Generation
Yanwen Wang, Yiyu Zhuang, Jiawei Zhang, Li Wang, Yifei Zeng, Xun Cao, Xinxin Zuo, Hao Zhu
https://arxiv.org/abs/2509.02466

TeRA: Rethinking Text-driven Realistic 3D Avatar Generation
In this paper, we rethink text-to-avatar generative models by proposing TeRA, a more efficient and effective framework than the previous SDS-based models and general large 3D generative models. Our approach employs a two-stage training strategy for learning a native 3D avatar generative model. Initially, we distill a decoder to derive a structured latent space from a large human reconstruction model. Subsequently, a text-controlled latent diffusion model is trained to generate photorealistic 3D…

Who Pays for Fairness? Rethinking Recourse under Social Burden
Ainhize Barrainkua, Giovanni De Toni, Jose Antonio Lozano, Novi Quadrianto
https://arxiv.org/abs/2509.04128 https:…

Who Pays for Fairness? Rethinking Recourse under Social Burden
Machine learning based predictions are increasingly used in sensitive decision-making applications that directly affect our lives. This has led to extensive research into ensuring the fairness of classifiers. Beyond just fair classification, emerging legislation now mandates that when a classifier delivers a negative decision, it must also offer actionable steps an individual can take to reverse that outcome. This concept is known as algorithmic recourse. Nevertheless, many researchers have exp…