Tootfinder

"Trump & Vance can destroy what others have built. They can push…United States past…breaking point. But they lack…alternative…They want fascism, &…don’t mind death of others…To get what they want, on…fascist model, they will have to…fight a major foreign war in which they manage to send off young people who oppose them to die, or…have to use government forces to kill Americans. I don’t think…these will…work; Vietnam &…Kent State shootings had…opposite effect."

Look on my works, ye Mighty
Labors of Destruction and Creation

Pose-Free 3D Quantitative Phase Imaging of Flowing Cellular Populations
Enze Ye, Wei Lin, Shaochi Ren, Yakun Liu, Xiaoping Li, Hao Wang, He Sun, Feng Pan
https://arxiv.org/abs/2509.04848

Pose-Free 3D Quantitative Phase Imaging of Flowing Cellular Populations
High-throughput 3D quantitative phase imaging (QPI) in flow cytometry enables label-free, volumetric characterization of individual cells by reconstructing their refractive index (RI) distributions from multiple viewing angles during flow through microfluidic channels. However, current imaging methods assume that cells undergo uniform, single-axis rotation, which require their poses to be known at each frame. This assumption restricts applicability to near-spherical cells and prevents accurate …

Reinforce-Ada: An Adaptive Sampling Framework for Reinforce-Style LLM Training
Wei Xiong, Chenlu Ye, Baohao Liao, Hanze Dong, Xinxing Xu, Christof Monz, Jiang Bian, Nan Jiang, Tong Zhang
https://arxiv.org/abs/2510.04996

Reinforce-Ada: An Adaptive Sampling Framework for Reinforce-Style LLM Training
Reinforcement learning applied to large language models (LLMs) for reasoning tasks is often bottlenecked by unstable gradient estimates due to fixed and uniform sampling of responses across prompts. Prior work such as GVM-RAFT addresses this by dynamically allocating inference budget per prompt to minimize stochastic gradient variance under a budget constraint. Inspired by this insight, we propose Reinforce-Ada, an adaptive sampling framework for online RL post-training of LLMs that continuousl…

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…

AI Agents for Web Testing: A Case Study in the Wild
Naimeng Ye, Xiao Yu, Ruize Xu, Tianyi Peng, Zhou Yu
https://arxiv.org/abs/2509.05197 https://arxiv.org/…

AI Agents for Web Testing: A Case Study in the Wild
Automated web testing plays a critical role in ensuring high-quality user experiences and delivering business value. Traditional approaches primarily focus on code coverage and load testing, but often fall short of capturing complex user behaviors, leaving many usability issues undetected. The emergence of large language models (LLM) and AI agents opens new possibilities for web testing by enabling human-like interaction with websites and a general awareness of common usability problems. In thi…

Hierarchical Deep Deterministic Policy Gradient for Autonomous Maze Navigation of Mobile Robots
Wenjie Hu, Ye Zhou, Hann Woei Ho
https://arxiv.org/abs/2508.04994 https://…

Hierarchical Deep Deterministic Policy Gradient for Autonomous Maze Navigation of Mobile Robots
Maze navigation is a fundamental challenge in robotics, requiring agents to traverse complex environments efficiently. While the Deep Deterministic Policy Gradient (DDPG) algorithm excels in control tasks, its performance in maze navigation suffers from sparse rewards, inefficient exploration, and long-horizon planning difficulties, often leading to low success rates and average rewards, sometimes even failing to achieve effective navigation. To address these limitations, this paper proposes an…

Exploring Student Choice and the Use of Multimodal Generative AI in Programming Learning
Xinying Hou, Ruiwei Xiao, Runlong Ye, Michael Liut, John Stamper
https://arxiv.org/abs/2510.05417

Exploring Student Choice and the Use of Multimodal Generative AI in Programming Learning
The broad adoption of Generative AI (GenAI) is impacting Computer Science education, and recent studies found its benefits and potential concerns when students use it for programming learning. However, most existing explorations focus on GenAI tools that primarily support text-to-text interaction. With recent developments, GenAI applications have begun supporting multiple modes of communication, known as multimodality. In this work, we explored how undergraduate programming novices choose and w…

Shrinking the Kernel Attack Surface Through Static and Dynamic Syscall Limitation
Dongyang Zhan (Harbin Institute of Technology), Zhaofeng Yu (Harbin Institute of Technology), Xiangzhan Yu (Harbin Institute of Technology), Hongli Zhang (Harbin Institute of Technology), Lin Ye (Harbin Institute of Technology)
https://arxiv.org/abs/2510.0372…

Shrinking the Kernel Attack Surface Through Static and Dynamic Syscall Limitation
Linux Seccomp is widely used by the program developers and the system maintainers to secure the operating systems, which can block unused syscalls for different applications and containers to shrink the attack surface of the operating systems. However, it is difficult to configure the whitelist of a container or application without the help of program developers. Docker containers block about only 50 syscalls by default, and lots of unblocked useless syscalls introduce a big kernel attack surfa…

OpenAI CFO Sarah Friar says an "IPO is not on the cards right now", and that OpenAI hopes the US government might backstop the financing of data center deals (Berber Jin/Wall Street Journal)
https://www.wsj.com/tech/ai/openai-isnt-yet-working-tow…

OptPipe: Memory- and Scheduling-Optimized Pipeline Parallelism for LLM Training
Hongpei Li, Han Zhang, Huikang Liu, Dongdong Ge, Yinyu Ye
https://arxiv.org/abs/2510.05186 https:…

OptPipe: Memory- and Scheduling-Optimized Pipeline Parallelism for LLM Training
Pipeline parallelism (PP) has become a standard technique for scaling large language model (LLM) training across multiple devices. However, despite recent progress in reducing memory consumption through activation offloading, existing approaches remain largely heuristic and coarse-grained, often overlooking the fine-grained trade-offs between memory, computation, and scheduling latency. In this work, we revisit the pipeline scheduling problem from a principled optimization perspective. We obser…

Calm local optimality for couple-constrained minimax problems
Xiaoxiao Ma, Jane Ye
https://arxiv.org/abs/2510.03861 https://arxiv.org/pdf/2510.03861…

Calm local optimality for couple-constrained minimax problems
Recently, a new local optimality concept for minimax problems, termed calm local minimax points, has been introduced. In this paper, we extend this concept to a general class of nonsmooth, nonconvex nonconcave minimax problems with coupled constraints, where the inner feasible set depends on the outer variable. We derive comprehensive first-order and second-order necessary and sufficient optimality conditions for calm local minimax points in the setting of nonsmooth, nonconvex nonconcave minima…

A Scalable Pipeline for Enabling Non-Verbal Speech Generation and Understanding
Runchuan Ye, Yixuan Zhou, Renjie Yu, Zijian Lin, Kehan Li, Xiang Li, Xin Liu, Guoyang Zeng, Zhiyong Wu
https://arxiv.org/abs/2508.05385

A Scalable Pipeline for Enabling Non-Verbal Speech Generation and Understanding
Human spoken communication involves not only lexical content but also non-verbal vocalizations (NVs) such as laughter, sighs, and coughs, which convey emotions, intentions, and social signals. However, most existing speech systems focus solely on verbal content and lack the ability to understand and generate such non-verbal cues, reducing the emotional intelligence and communicative richness of spoken interfaces. In this work, we introduce $\textbf{NonVerbalSpeech-38K}$, a large and diverse dat…

Bottom baryon decays into light meson and dark baryon within perturbative QCD approach
Ye Xing, Yu-Ji Shi, Xiao-Hui Hu
https://arxiv.org/abs/2508.05181 https://

Bottom baryon decays into light meson and dark baryon within perturbative QCD approach
In the work, we study the production of dark baryon $ψ$ with the bottom-baryon decays $Λ_b\to M ψ$ under the perturbative QCD approach. For the Type-I/II models in B-Mesogenesis scenarios, we calculate the form factors for bottom-baryon decays into meson. Using these results, we obtain branching ratios for $Λ_b\to M ψ$ decays. The PQCD approach calculations show these branching ratios reach $\mathcal{O}(10^{-5})$ in both models, with $\mathcal{B}(Λ_b\to Kψ)$ specifically reaching $\mathc…

Physicochemically Informed Dual-Conditioned Generative Model of T-Cell Receptor Variable Regions for Cellular Therapy
Jiahao Ma, Hongzong Li, Ye-Fan Hu, Jian-Dong Huang
https://arxiv.org/abs/2510.05747

Physicochemically Informed Dual-Conditioned Generative Model of T-Cell Receptor Variable Regions for Cellular Therapy
Physicochemically informed biological sequence generation has the potential to accelerate computer-aided cellular therapy, yet current models fail to \emph{jointly} ensure novelty, diversity, and biophysical plausibility when designing variable regions of T-cell receptors (TCRs). We present \textbf{PhysicoGPTCR}, a large generative protein Transformer that is \emph{dual-conditioned} on peptide and HLA context and trained to autoregressively synthesise TCR sequences while embedding residue-level…

Uniqueness Result For Semi-linear Wave Equations With Sources
Dong Qiu, Xiang Xu, Yeqiong Ye, Ting Zhou
https://arxiv.org/abs/2510.04810 https://arxiv.org/…

Uniqueness Result For Semi-linear Wave Equations With Sources
This paper addresses the inverse problem of simultaneously recovering multiple unknown parameters for semilinear wave equations from boundary measurements. We consider an initial-boundary value problem for a wave equation with a general semilinear term and an internal source. The inverse problem is to determine the nonlinear coefficients (potentials), the source term, and the initial data from the Dirichlet-to-Neumann (DtN) map. Our approach combines higher-order linearization and the construct…

Bridging Brains and Models: MoE-Based Functional Lesions for Simulating and Rehabilitating Aphasia
Yifan Wang, Jingyuan Sun, Jichen Zheng, Yunhao Zhang, Chunyu Ye, Jixing Li, Chengqing Zong, Shaonan Wang
https://arxiv.org/abs/2508.04749

Bridging Brains and Models: MoE-Based Functional Lesions for Simulating and Rehabilitating Aphasia
The striking alignment between large language models (LLMs) and human brain activity positions them as powerful models of healthy cognition. This parallel raises a fundamental question: if LLMs can model the intact brain, can we lesion them to simulate the linguistic deficits of the injured brain? In this work, we introduce a methodology to model aphasia - a complex language disorder caused by neural injury - by selectively disabling components in a modular Mixture-of-Experts (MoE) language mod…

🦠 Ready for market: Engineered yeast boosts clean, cost-efficient chemical production
#biotech

Ready for market: Engineered yeast boosts clean, cost-efficient chemical production
Building on their success developing a cleaner way to make valuable organic acids, researchers from the Center for Advanced Bioenergy and Bioproducts Innovation (CABBI) have pushed one product closer to commercialization with a major upgrade in yield.

Agent P: Guiding UI Agents via Symbolic Planning
Shang Ma, Xusheng Xiao, Yanfang Ye
https://arxiv.org/abs/2510.06042 https://arxiv.org/pdf/2510.06042

Agent+P: Guiding UI Agents via Symbolic Planning
Large Language Model (LLM)-based UI agents show great promise for UI automation but often hallucinate in long-horizon tasks due to their lack of understanding of the global UI transition structure. To address this, we introduce AGENT+P, a novel framework that leverages symbolic planning to guide LLM-based UI agents. Specifically, we model an app's UI transition structure as a UI Transition Graph (UTG), which allows us to reformulate the UI automation task as a pathfinding problem on the UTG. Th…

Topological pumping of light governed by Fibonacci numbers
Ruihan Peng, Kai Yang, Qidong Fu, Yanli Chen, Peng Wang, Yaroslav V. Kartashov, Vladimir V. Konotop, Fangwei Ye
https://arxiv.org/abs/2509.04910

Topological pumping of light governed by Fibonacci numbers
Topological pumping refers to transfer of a physical quantity governed by the systemtopology, resulting in quantized amounts of the transferred quantities. It is a ubiqui-tous wave phenomenon typically considered subject to exactly periodic adiabatic vari-ation of the system parameters. Recently, proposals for generalizing quasi-periodictopological pumping and identifying possible physical settings for its implementa-tion have emerged. In a strict sense, pumping with incommensurate frequencies …

Diverse Text-to-Image Generation via Contrastive Noise Optimization
Byungjun Kim, Soobin Um, Jong Chul Ye
https://arxiv.org/abs/2510.03813 https://arxiv.or…

Diverse Text-to-Image Generation via Contrastive Noise Optimization
Text-to-image (T2I) diffusion models have demonstrated impressive performance in generating high-fidelity images, largely enabled by text-guided inference. However, this advantage often comes with a critical drawback: limited diversity, as outputs tend to collapse into similar modes under strong text guidance. Existing approaches typically optimize intermediate latents or text conditions during inference, but these methods deliver only modest gains or remain sensitive to hyperparameter tuning. …

🇺🇦 #NowPlaying on KEXP's #SeekAndDestroy
Veilburner:
🎵 Da'ath Ye Shadow Portrait
#Veilburner
https://veilburnerband.bandcamp.com/track/daath-ye-shadow-portrait
https://open.spotify.com/track/58UXBzz3ovboIwZaIFxAGN

Improving Discrete Diffusion Unmasking Policies Beyond Explicit Reference Policies
Chunsan Hong, Seonho An, Min-Soo Kim, Jong Chul Ye
https://arxiv.org/abs/2510.05725 https://…

Improving Discrete Diffusion Unmasking Policies Beyond Explicit Reference Policies
Masked diffusion models (MDMs) have recently emerged as a novel framework for language modeling. MDMs generate sentences by iteratively denoising masked sequences, filling in [MASK] tokens step by step. Although MDMs support any-order sampling, performance is highly sensitive to the choice of which position to unmask next. Prior work typically relies on rule-based schedules (e.g., max-confidence, max-margin), which provide ad hoc improvements. In contrast, we replace these heuristics with a lea…

Replaced article(s) found for cond-mat.soft. https://arxiv.org/list/cond-mat.soft/new
[1/1]:
- Brownian motion near a soft surface
Yilin Ye, Yacine Amarouchene, Rapha\"el Sarfati, David S. Dean, Thomas Salez

Crosslisted article(s) found for q-bio.BM. https://arxiv.org/list/q-bio.BM/new
[1/1]:
- Physicochemically Informed Dual-Conditioned Generative Model of T-Cell Receptor Variable Regions ...
Jiahao Ma, Hongzong Li, Ye-Fan Hu, Jian-Dong Huang

Crosslisted article(s) found for physics.bio-ph. https://arxiv.org/list/physics.bio-ph/new
[1/1]:
- Pose-Free 3D Quantitative Phase Imaging of Flowing Cellular Populations
Enze Ye, Wei Lin, Shaochi Ren, Yakun Liu, Xiaoping Li, Hao Wang, He Sun, Feng Pan

The Path of Self-Evolving Large Language Models: Achieving Data-Efficient Learning via Intrinsic Feedback
Hangfan Zhang, Siyuan Xu, Zhimeng Guo, Huaisheng Zhu, Shicheng Liu, Xinrun Wang, Qiaosheng Zhang, Yang Chen, Peng Ye, Lei Bai, Shuyue Hu
https://arxiv.org/abs/2510.02752

The Path of Self-Evolving Large Language Models: Achieving Data-Efficient Learning via Intrinsic Feedback
Reinforcement learning (RL) has demonstrated potential in enhancing the reasoning capabilities of large language models (LLMs), but such training typically demands substantial efforts in creating and annotating data. In this work, we explore improving LLMs through RL with minimal data. Our approach alternates between the LLM proposing a task and then attempting to solve it. To minimize data dependency, we introduce two novel mechanisms grounded in self-awareness: (1) self-aware difficulty predi…

Crosslisted article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[2/17]:
- MindCraft: How Concept Trees Take Shape In Deep Models
Bowei Tian, Yexiao He, Wanghao Ye, Ziyao Wang, Meng Liu, Ang Li

High-Efficiency Quantum-State Detection of ThF$^ $ with Resonance-Enhanced Multiphoton Asymmetric Dissociation
Kia Boon Ng, Sun Yool Park, Anzhou Wang, Addison Hartman, Patricia Hector Hernandez, Rohan Kompella, Lan Cheng, Stephan Malbrunot-Ettenauer, Jun Ye, Eric A. Cornell
https://arxiv.org/abs/2508.04949…

GhostShell: Streaming LLM Function Calls for Concurrent Embodied Programming
Jian Gong, Youwei Huang, Bo Yuan, Ming Zhu, Juncheng Zhan, Jinke Wang, Hang Shu, Mingyue Xiong, Yanjun Ye, Yufan Zu, Yang Zhou, Yihan Ding, Xuannian Chen, Xingyu Lu, Runjie Ban, Bingchao Huang, Fusen Liu
https://arxiv.org/abs/2508.05298

GhostShell: Streaming LLM Function Calls for Concurrent Embodied Programming
We present GhostShell, a novel approach that leverages Large Language Models (LLMs) to enable streaming and concurrent behavioral programming for embodied systems. In contrast to conventional methods that rely on pre-scheduled action sequences or behavior trees, GhostShell drives embodied systems to act on-the-fly by issuing function calls incrementally as tokens are streamed from the LLM. GhostShell features a streaming XML function token parser, a dynamic function interface mapper, and a mult…

Universal relations between thermoelectrics and noise in mesoscopic transport across a tunnel junction
Andrei I. Pavlov, Mikhail N. Kiselev
https://arxiv.org/abs/2508.05413 http…

Universal relations between thermoelectrics and noise in mesoscopic transport across a tunnel junction
We develop a unified theory of weakly probed differential observables for currents and noise in transport experiments. Our findings uncover a set of universal transport relations between thermoelectric and noise properties of a system probed through a tunnel contact, with the Wiedemann-Franz law being just one example of such universality between charge and heat currents. We apply this theory to various quantum dot systems, including multichannel Kondo, quantum Hall and Sachdev-Ye-Kitaev quantu…

Securing Operating Systems Through Fine-grained Kernel Access Limitation for IoT Systems
Dongyang Zhan (Harbin Institute of Technology), Zhaofeng Yu (Harbin Institute of Technology), Xiangzhan Yu (Harbin Institute of Technology), Hongli Zhang (Harbin Institute of Technology), Lin Ye (Harbin Institute of Technology), Likun Liu (Harbin Institute of Technology)
ht…

Securing Operating Systems Through Fine-grained Kernel Access Limitation for IoT Systems
With the development of Internet of Things (IoT), it is gaining a lot of attention. It is important to secure the embedded systems with low overhead. The Linux Seccomp is widely used by developers to secure the kernels by blocking the access of unused syscalls, which introduces less overhead. However, there are no systematic Seccomp configuration approaches for IoT applications without the help of developers. In addition, the existing Seccomp configuration approaches are coarse-grained, which c…

Crosslisted article(s) found for cs.HC. https://arxiv.org/list/cs.HC/new
[1/1]:
- MADS: Multi-Agent Dialogue Simulation for Diverse Persuasion Data Generation
Mingjin Li, Yu Liu, Huayi Liu, Xiang Ye, Chao Jiang, Hongguang Zhang

Symbol Timing Synchronization and Signal Detection for Ambient Backscatter Communication
Yuxin Li, Guangyue Lu, Yinghui Ye, Zehui Xiong, Liqin Shi
https://arxiv.org/abs/2510.02981

Symbol Timing Synchronization and Signal Detection for Ambient Backscatter Communication
Ambient backscatter communication (AmBC) enables ambient Internet of Things (AIoT) devices to achieve ultra-low-power, low-cost, and massive connectivity. Most existing AmBC studies assume ideal synchronization between the backscatter device (BD) and the backscatter receiver (BR). However, in practice, symbol timing offset (STO) occurs due to both the propagation delay and the BR activation latency, which leads to unreliable symbol recovery at the BR. Moreover, the uncontrollable nature of the …

The Implicit Barrier of Utility Maximization: An Interior-Point Approach for Market Equilibria
Chuwen Zhang, Chang He, Bo Jiang, Yinyu Ye
https://arxiv.org/abs/2508.04822 https:…

The Implicit Barrier of Utility Maximization: An Interior-Point Approach for Market Equilibria
We study the computation of equilibria in exchange markets with divisible goods and players endowed with heterogeneous utilities. In this paper, we revisit the polynomial-time interior-point strategies that update \emph{only} the prices, mirroring the tâtonnement process. The key ingredient is the \emph{implicit barrier} inherent in the utility maximization: the utility turns unbounded when the goods are almost free of charge. Focusing on a ubiquitous class of utilities, we formalize this obse…

LARA-Gen: Enabling Continuous Emotion Control for Music Generation Models via Latent Affective Representation Alignment
Jiahao Mei, Xuenan Xu, Zeyu Xie, Zihao Zheng, Ye Tao, Yue Ding, Mengyue Wu
https://arxiv.org/abs/2510.05875

LARA-Gen: Enabling Continuous Emotion Control for Music Generation Models via Latent Affective Representation Alignment
Recent advances in text-to-music models have enabled coherent music generation from text prompts, yet fine-grained emotional control remains unresolved. We introduce LARA-Gen, a framework for continuous emotion control that aligns the internal hidden states with an external music understanding model through Latent Affective Representation Alignment (LARA), enabling effective training. In addition, we design an emotion control module based on a continuous valence-arousal space, disentangling emo…

Inoculation Prompting: Instructing LLMs to misbehave at train-time improves test-time alignment
Nevan Wichers, Aram Ebtekar, Ariana Azarbal, Victor Gillioz, Christine Ye, Emil Ryd, Neil Rathi, Henry Sleight, Alex Mallen, Fabien Roger, Samuel Marks
https://arxiv.org/abs/2510.05024

Inoculation Prompting: Instructing LLMs to misbehave at train-time improves test-time alignment
Large language models are sometimes trained with imperfect oversight signals, leading to undesired behaviors such as reward hacking and sycophancy. Improving oversight quality can be expensive or infeasible, motivating methods that improve learned behavior despite an imperfect training signal. We introduce Inoculation Prompting (IP), a simple but counterintuitive technique that prevents learning of an undesired behavior by modifying training prompts to explicitly request it. For example, to ino…

Replaced article(s) found for hep-ph. https://arxiv.org/list/hep-ph/new
[2/2]:
- Sub-GeV Right-Handed Neutrino as a Probe of Neutrino Mass Generation in the Minimal Left-Right Sy...
Gang Li, Ying-Ying Li, Sida Lu, Ye-Ling Zhou

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[1/4]:
- MMoE: Robust Spoiler Detection with Multi-modal Information and Domain-aware Mixture-of-Experts
Zinan Zeng, Sen Ye, Zijian Cai, Heng Wang, Yuhan Liu, Haokai Zhang, Minnan Luo

A federal judge dismissed seven of the 14 charges filed against reporter Tim Burke for allegedly obtaining and selling unaired Fox News footage in 2022 (Jack Prator/Tampa Bay Times)
https://www.tampabay.com/news/crime/2025/09/26/tim-burke-fox-…

Federal judge dismisses half of the charges against Tim Burke
U.S. District Judge Kathryn Kimball Mizelle ruled that the law used to indict the Tampa media figure violates the First Amendment.

Replaced article(s) found for q-bio.NC. https://arxiv.org/list/q-bio.NC/new
[1/1]:
- Optimal Transport for Brain-Image Alignment: Unveiling Redundancy and Synergy in Neural Informati...
Yang Xiao, Wang Lu, Jie Ji, Ruimeng Ye, Gen Li, Xiaolong Ma, Bo Hui

Med-K2N: Flexible K-to-N Modality Translation for Medical Image Synthesis
Feng Yuan, Yifan Gao, Yuehua Ye, Haoyue Li, Xin Gao
https://arxiv.org/abs/2510.02815 https://

Med-K2N: Flexible K-to-N Modality Translation for Medical Image Synthesis
Cross-modal medical image synthesis research focuses on reconstructing missing imaging modalities from available ones to support clinical diagnosis. Driven by clinical necessities for flexible modality reconstruction, we explore K to N medical generation, where three critical challenges emerge: How can we model the heterogeneous contributions of different modalities to various target tasks? How can we ensure fusion quality control to prevent degradation from noisy information? How can we mainta…

Crosslisted article(s) found for cs.MA. https://arxiv.org/list/cs.MA/new
[1/1]:
- MADS: Multi-Agent Dialogue Simulation for Diverse Persuasion Data Generation
Mingjin Li, Yu Liu, Huayi Liu, Xiang Ye, Chao Jiang, Hongguang Zhang

Replaced article(s) found for cs.GR. https://arxiv.org/list/cs.GR/new
[1/1]:
- CHOICE: Coordinated Human-Object Interaction in Cluttered Environments for Pick-and-Place Actions
Jintao Lu, He Zhang, Yuting Ye, Takaaki Shiratori, Sebastian Starke, Taku Komura

Complexity of Quadratic Quantum Chaos
Pallab Basu, Suman Das, Pratik Nandy
https://arxiv.org/abs/2509.04075 https://arxiv.org/pdf/2509.04075

Complexity of Quadratic Quantum Chaos
We investigate minimal two-body Hamiltonians with random interactions that generate spectra resembling those of Gaussian random matrices, a phenomenon we term quadratic quantum chaos. Unlike integrable two-body fermionic systems, the corresponding hard-core boson models exhibit genuinely chaotic dynamics, closely paralleling the Sachdev-Ye-Kitaev (SYK) model in its spin representation. This chaotic behavior is diagnosed through spectral statistics and measures of operator growth, including Kryl…

🇺🇦 #NowPlaying on KEXP's #Continent
Burna Boy:
🎵 Ye
#BurnaBoy
https://hagan.bandcamp.com/track/burna-boy-ye-hagan-edit

Replaced article(s) found for cs.DL. https://arxiv.org/list/cs.DL/new
[1/1]:
- Is Artificial Intelligence Reshaping the Landscape of the International Academic Community of Geo...
Liang Li, Yuntian Li, Wenxin Zhao, Shan Ye, Yun Lu

Ding dong ditch gun = child murdered.
https://www.nbcnews.com/news/us-news/11-year-old-shot-dead-ringing-doorbell-running-houston-home-rcna228332

Preconditioned Regularized Wasserstein Proximal Sampling
Hong Ye Tan, Stanley Osher, Wuchen Li
https://arxiv.org/abs/2509.01685 https://arxiv.org/pdf/2509.…

Preconditioned Regularized Wasserstein Proximal Sampling
We consider sampling from a Gibbs distribution by evolving finitely many particles. We propose a preconditioned version of a recently proposed noise-free sampling method, governed by approximating the score function with the numerically tractable score of a regularized Wasserstein proximal operator. This is derived by a Cole--Hopf transformation on coupled anisotropic heat equations, yielding a kernel formulation for the preconditioned regularized Wasserstein proximal. The diffusion component o…

Align Your Query: Representation Alignment for Multimodality Medical Object Detection
Ara Seo, Bryan Sangwoo Kim, Hyungjin Chung, Jong Chul Ye
https://arxiv.org/abs/2510.02789 h…

Align Your Query: Representation Alignment for Multimodality Medical Object Detection
Medical object detection suffers when a single detector is trained on mixed medical modalities (e.g., CXR, CT, MRI) due to heterogeneous statistics and disjoint representation spaces. To address this challenge, we turn to representation alignment, an approach that has proven effective for bringing features from different sources into a shared space. Specifically, we target the representations of DETR-style object queries and propose a simple, detector-agnostic framework to align them with modal…

#CFP: The Gods and Monsters Conference 2026
https://ift.tt/G7tE1Vb
Details Call for Papers: The Gods and Monsters Conference 2026 March 26 - 29, 2026 Texas State…
via Input 4 RELCFP

#CFP: The Gods and Monsters Conference 2026
Details Call for Papers: The Gods and Monsters Conference 2026 March 26 - 29, 2026 Texas State University, San Marcos Texas, 78666

The Collaborations among Healthcare Systems, Research Institutions, and Industry on Artificial Intelligence Research and Development
Jiancheng Ye, Michelle Ma, Malak Abuhashish
https://arxiv.org/abs/2509.00068

The Collaborations among Healthcare Systems, Research Institutions, and Industry on Artificial Intelligence Research and Development
Objectives: The integration of Artificial Intelligence (AI) in healthcare promises to revolutionize patient care, diagnostics, and treatment protocols. Collaborative efforts among healthcare systems, research institutions, and industry are pivotal to leveraging AI's full potential. This study aims to characterize collaborative networks and stakeholders in AI healthcare initiatives, identify challenges and opportunities within these collaborations, and elucidate priorities for future AI research…

Whisker-based Tactile Flight for Tiny Drones
Chaoxiang Ye, Guido de Croon, Salua Hamaza
https://arxiv.org/abs/2510.03119 https://arxiv.org/pdf/2510.03119…

Whisker-based Tactile Flight for Tiny Drones
Tiny flying robots hold great potential for search-and-rescue, safety inspections, and environmental monitoring, but their small size limits conventional sensing-especially with poor-lighting, smoke, dust or reflective obstacles. Inspired by nature, we propose a lightweight, 3.2-gram, whisker-based tactile sensing apparatus for tiny drones, enabling them to navigate and explore through gentle physical interaction. Just as rats and moles use whiskers to perceive surroundings, our system equips d…

Evaluating noises of boson sampling with statistical benchmark methods
Yang Ji, Yongjin Ye, Qiao Wang, Shi Wang, Jie Hou, Yongzheng Wu, Zijian Wang, Bo Jiang
https://arxiv.org/abs/2510.00056

Evaluating noises of boson sampling with statistical benchmark methods
The lack of self-correcting codes hiders the development of boson sampling to be large-scale and robust. Therefore, it is important to know the noise levels in order to cautiously demonstrate the quantum computational advantage or realize certain tasks. Based on those statistical benchmark methods such as the correlators and the clouds, which are initially proposed to discriminate boson sampling and other mockups, we quantificationally evaluate noises of photon partial distinguishability and ph…

Godzilla Day is coming up on November 3, and knowing this in advance gives me time to maybe tidy up the collection to get a good shot by then. We'll see 😂
https://godzilla.com/blogs/news/how-to-celebrate-godzilla-day-2025

How to Celebrate Godzilla Day 2025
More than seven decades after producer Tomoyuki Tanaka, director Ishirō Honda, and special effects master Eiji Tsuburaya first unleashed Godzilla in Japanese theaters on November 3, 1954, the King of the Monsters remains a beloved symbol of imagination and cinematic innovation. Now, after a landmark 70th anniversary ye

Beyond Negative Transfer: Disentangled Preference-Guided Diffusion for Cross-Domain Sequential Recommendation
Xiaoxin Ye, Chengkai Huang, Hongtao Huang, Lina Yao
https://arxiv.org/abs/2509.00389

Beyond Negative Transfer: Disentangled Preference-Guided Diffusion for Cross-Domain Sequential Recommendation
Cross-Domain Sequential Recommendation (CDSR) leverages user behaviors across domains to enhance recommendation quality. However, naive aggregation of sequential signals can introduce conflicting domain-specific preferences, leading to negative transfer. While Sequential Recommendation (SR) already suffers from noisy behaviors such as misclicks and impulsive actions, CDSR further amplifies this issue due to domain heterogeneity arising from diverse item types and user intents. The core challeng…

Mod $\ell$ non-vanishing of self-dual Hecke $L$-values over CM fields and applications
Ashay Burungale, Wei He, Ye Tian, Xiangdong Ye
https://arxiv.org/abs/2508.19706 https://…

Mod $\ell$ non-vanishing of self-dual Hecke $L$-values over CM fields and applications
Let $λ$ be a self-dual Hecke character over a CM field $K$. Let $\mathfrak{p}$ be a prime of the maximal totally real subfield $F$ of $K$ and $Γ_{\mathfrak{p}}$ the Galois group of the maximal anticyclotomic ${\mathbb{Z}}_{p}^{deg \mathfrak{p}}$-extension of $K$ unramified outside $\mathfrak{p}$. We prove that $$L(1,λν)\neq 0$$ for all but finitely many finite order characters $ν$ of $Γ_{\mathfrak{p}}$ such that $ε(λν)=+1$. For an ordinary prime $\ell$ with respect to the CM quadratic …

Sachdev-Ye-Kitaev Model in a Quantum Glassy Landscape
Surajit Bera, Jorge Kurchan, Marco Schiro
https://arxiv.org/abs/2509.22977 https://arxiv.org/pdf/2509…

Sachdev-Ye-Kitaev Model in a Quantum Glassy Landscape
We study a generalization of `Yukawa models' in which Majorana fermions, interacting via all-to-all random couplings as in the Sachdev-Ye-Kitaev (SYK) model, are parametrically coupled to disordered bosonic degrees of freedom described by a quantum $p-$spin model. The latter has its own non-trivial dynamics leading to quantum paramagnetic (or liquid) and glassy phases. At low temperatures, this setup results in SYK behavior within each metastable state of a rugged bosonic free energy landscape,…

🇺🇦 #NowPlaying on BBCRadio3's #Breakfast
Henry Purcell, John Toll, Nigel North, Richard Boothby & Nancy Argenta:
🎵 Fly Swift, Ye Hours, Z. 369
#HenryPurcell #JohnToll #NigelNorth #RichardBoothby #NancyArgenta

Distributional Inverse Reinforcement Learning
Feiyang Wu, Ye Zhao, Anqi Wu
https://arxiv.org/abs/2510.03013 https://arxiv.org/pdf/2510.03013

Distributional Inverse Reinforcement Learning
We propose a distributional framework for offline Inverse Reinforcement Learning (IRL) that jointly models uncertainty over reward functions and full distributions of returns. Unlike conventional IRL approaches that recover a deterministic reward estimate or match only expected returns, our method captures richer structure in expert behavior, particularly in learning the reward distribution, by minimizing first-order stochastic dominance (FSD) violations and thus integrating distortion risk mea…

Consolidating Reinforcement Learning for Multimodal Discrete Diffusion Models
Tianren Ma, Mu Zhang, Yibing Wang, Qixiang Ye
https://arxiv.org/abs/2510.02880 https://

Consolidating Reinforcement Learning for Multimodal Discrete Diffusion Models
Optimizing discrete diffusion model (DDM) with rewards remains a challenge: the non-autoregressive paradigm makes importance sampling intractable and rollout complex, puzzling reinforcement learning methods such as Group Relative Policy Optimization (GRPO). In this study, we introduce MaskGRPO, the first viable approach to enable scalable multimodal reinforcement learning in discrete diffusion with effective importance sampling and modality-specific adaptations. To this end, we first clarify th…

Crosslisted article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[4/5]:
- SCI-Verifier: Scientific Verifier with Thinking
Zheng, Huang, Yu, Yao, Ye, Chen, Luo, Ding, BAI, Cui, Ye

🤦🏿‍♂️ Uh Oh, It’s an ‘Unflinching’ Documentary About Kanye West
http://www.vulture.com/article/ye-documentary-in-whose-name-trailer.html
#mentalhealth

Kanye West Documentary ‘In Whose Name?’ Follows His Downfall
Ye’s upcoming documentary ‘In Whose Name?’ follows Kanye West throughout some of his most controversial stunts, the downfall of Yeezy, and his divorce from Kim Kardashian.

Team Xiaomi EV-AD VLA: Caption-Guided Retrieval System for Cross-Modal Drone Navigation - Technical Report for IROS 2025 RoboSense Challenge Track 4
Lingfeng Zhang, Erjia Xiao, Yuchen Zhang, Haoxiang Fu, Ruibin Hu, Yanbiao Ma, Wenbo Ding, Long Chen, Hangjun Ye, Xiaoshuai Hao
https://arxiv.org/abs/2510.02728…

Team Xiaomi EV-AD VLA: Caption-Guided Retrieval System for Cross-Modal Drone Navigation - Technical Report for IROS 2025 RoboSense Challenge Track 4
Cross-modal drone navigation remains a challenging task in robotics, requiring efficient retrieval of relevant images from large-scale databases based on natural language descriptions. The RoboSense 2025 Track 4 challenge addresses this challenge, focusing on robust, natural language-guided cross-view image retrieval across multiple platforms (drones, satellites, and ground cameras). Current baseline methods, while effective for initial retrieval, often struggle to achieve fine-grained semantic…

Chipmaker Cerebras Systems raised a $1.1B Series G from Fidelity, Trump Jr.'s 1789 Capital, and others at an $8.1B post-money valuation ahead of its planned IPO (Rebecca Szkutak/TechCrunch)
https://techcrunch.com/2025/09/30/a-year-…

A year after filing to IPO, still-private Cerebras Systems raises $1.1B | TechCrunch
Cerebras initially filed to go public in September 2024 but ran into several regulatory delays due to foreign investments.

Mycroft: Tracing Dependencies in Collective Communication Towards Reliable LLM Training
Yangtao Deng, Lei Zhang, Qinlong Wang, Xiaoyun Zhi, Xinlei Zhang, Zhuo Jiang, Haohan Xu, Lei Wang, Zuquan Song, Gaohong Liu, Yang Bai, Shuguang Wang, Wencong Xiao, Jianxi Ye, Minlan Yu, Hong Xu
https://arxiv.org/abs/2509.03018

Mycroft: Tracing Dependencies in Collective Communication Towards Reliable LLM Training
Reliability is essential for ensuring efficiency in LLM training. However, many real-world reliability issues remain difficult to resolve, resulting in wasted resources and degraded model performance. Unfortunately, today's collective communication libraries operate as black boxes, hiding critical information needed for effective root cause analysis. We propose Mycroft, a lightweight distributed tracing and root cause analysis system designed to address previously hidden reliability issues in c…

Private Realizable-to-Agnostic Transformation with Near-Optimal Sample Complexity
Bo Li, Wei Wang, Peng Ye
https://arxiv.org/abs/2510.01291 https://arxiv.o…

Private Realizable-to-Agnostic Transformation with Near-Optimal Sample Complexity
The realizable-to-agnostic transformation (Beimel et al., 2015; Alon et al., 2020) provides a general mechanism to convert a private learner in the realizable setting (where the examples are labeled by some function in the concept class) to a private learner in the agnostic setting (where no assumptions are imposed on the data). Specifically, for any concept class $\mathcal{C}$ and error parameter $α$, a private realizable learner for $\mathcal{C}$ can be transformed into a private agnostic le…

SSGaussian: Semantic-Aware and Structure-Preserving 3D Style Transfer
Jimin Xu, Bosheng Qin, Tao Jin, Zhou Zhao, Zhenhui Ye, Jun Yu, Fei Wu
https://arxiv.org/abs/2509.04379 http…

SSGaussian: Semantic-Aware and Structure-Preserving 3D Style Transfer
Recent advancements in neural representations, such as Neural Radiance Fields and 3D Gaussian Splatting, have increased interest in applying style transfer to 3D scenes. While existing methods can transfer style patterns onto 3D-consistent neural representations, they struggle to effectively extract and transfer high-level style semantics from the reference style image. Additionally, the stylized results often lack structural clarity and separation, making it difficult to distinguish between di…

Benchmarking and Studying the LLM-based Code Review
Zhengran Zeng, Ruikai Shi, Keke Han, Yixin Li, Kaicheng Sun, Yidong Wang, Zhuohao Yu, Rui Xie, Wei Ye, Shikun Zhang
https://arxiv.org/abs/2509.01494 …

Benchmarking and Studying the LLM-based Code Review
Automated Code Review (ACR) is crucial for software quality, yet existing benchmarks often fail to reflect real-world complexities, hindering the evaluation of modern Large Language Models (LLMs). Current benchmarks frequently focus on fine-grained code units, lack complete project context, and use inadequate evaluation metrics. To address these limitations, we introduce SWRBench , a new benchmark comprising 1000 manually verified Pull Requests (PRs) from GitHub, offering PR-centric review with…

UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning
Haoming Wang, Haoyang Zou, Huatong Song, Jiazhan Feng, Junjie Fang, Junting Lu, Longxiang Liu, Qinyu Luo, Shihao Liang, Shijue Huang, Wanjun Zhong, Yining Ye, Yujia Qin, Yuwen Xiong, Yuxin Song, Zhiyong Wu, Bo Li, Chen Dun, Chong Liu, Fuxing Leng, Hanbin Wang, Hao Yu, Haobin Chen, Hongyi Guo, Jing Su, Jingjia Huang, Kai Shen, Kaiyu Shi, Lin Yan, Peiyao Zhao, Pengfei Liu, Qinghao Ye, Renjie Zheng, Way…

UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning
The development of autonomous agents for graphical user interfaces (GUIs) presents major challenges in artificial intelligence. While recent advances in native agent models have shown promise by unifying perception, reasoning, action, and memory through end-to-end learning, open problems remain in data scalability, multi-turn reinforcement learning (RL), the limitations of GUI-only operation, and environment stability. In this technical report, we present UI-TARS-2, a native GUI-centered agent …

PagedEviction: Structured Block-wise KV Cache Pruning for Efficient Large Language Model Inference
Krishna Teja Chitty-Venkata, Jie Ye, Xian-He Sun, Anthony Kougkas, Murali Emani, Venkatram Vishwanath, Bogdan Nicolae
https://arxiv.org/abs/2509.04377

PagedEviction: Structured Block-wise KV Cache Pruning for Efficient Large Language Model Inference
KV caching significantly improves the efficiency of Large Language Model (LLM) inference by storing attention states from previously processed tokens, enabling faster generation of subsequent tokens. However, as sequence length increases, the KV cache quickly becomes a major memory bottleneck. To address this, we propose PagedEviction, a novel fine-grained, structured KV cache pruning strategy that enhances the memory efficiency of vLLM's PagedAttention. Unlike existing approaches that rely on …

Replaced article(s) found for quant-ph. https://arxiv.org/list/quant-ph/new
[2/2]:
- Efficient Non-Adaptive Quantum Algorithms for Tolerant Junta Testing
Zongbo Bao, Yuxuan Liu, Penghui Yao, Zekun Ye, Jialin Zhang

From Image Denoisers to Regularizing Imaging Inverse Problems: An Overview
Hong Ye Tan, Subhadip Mukherjee, Junqi Tang
https://arxiv.org/abs/2509.03475 https://

From Image Denoisers to Regularizing Imaging Inverse Problems: An Overview
Inverse problems lie at the heart of modern imaging science, with broad applications in areas such as medical imaging, remote sensing, and microscopy. Recent years have witnessed a paradigm shift in solving imaging inverse problems, where data-driven regularizers are used increasingly, leading to remarkably high-fidelity reconstruction. A particularly notable approach for data-driven regularization is to use learned image denoisers as implicit priors in iterative image reconstruction algorithms…

POLAR: Automating Cyber Threat Prioritization through LLM-Powered Assessment
Luoxi Tang, Yuqiao Meng, Ankita Patra, Weicheng Ma, Muchao Ye, Zhaohan Xi
https://arxiv.org/abs/2510.01552

POLAR: Automating Cyber Threat Prioritization through LLM-Powered Assessment
Large Language Models (LLMs) are intensively used to assist security analysts in counteracting the rapid exploitation of cyber threats, wherein LLMs offer cyber threat intelligence (CTI) to support vulnerability assessment and incident response. While recent work has shown that LLMs can support a wide range of CTI tasks such as threat analysis, vulnerability detection, and intrusion defense, significant performance gaps persist in practical deployments. In this paper, we investigate the intrins…

Replaced article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[4/4]:
- Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base ...
Wen, Liu, Zheng, Ye, Wu, Wang, Xu, Liang, Li, Miao, Bian, Yang

Beyond Divergence: Characterizing Co-exploration Patterns in Collaborative Design Processes
Xinhui Ye, Joep Frens, Jun Hu
https://arxiv.org/abs/2510.01188 https://

Beyond Divergence: Characterizing Co-exploration Patterns in Collaborative Design Processes
Exploration is crucial in the design process and is known for its essential role in fostering creativity and enhancing design outcomes. Within design teams, exploration evolves into co-exploration, a collaborative and dynamic practice that this study aims to unpack. To investigate this experience, we conducted a longitudinal observational study with 61 students across 16 design teams. Over five months of weekly diary-interviews, we uncovered the intricate dynamics of co-exploration. Our main co…

One-Embedding-Fits-All: Efficient Zero-Shot Time Series Forecasting by a Model Zoo
Hao-Nan Shi, Ting-Ji Huang, Lu Han, De-Chuan Zhan, Han-Jia Ye
https://arxiv.org/abs/2509.04208

One-Embedding-Fits-All: Efficient Zero-Shot Time Series Forecasting by a Model Zoo
The proliferation of Time Series Foundation Models (TSFMs) has significantly advanced zero-shot forecasting, enabling predictions for unseen time series without task-specific fine-tuning. Extensive research has confirmed that no single TSFM excels universally, as different models exhibit preferences for distinct temporal patterns. This diversity suggests an opportunity: how to take advantage of the complementary abilities of TSFMs. To this end, we propose ZooCast, which characterizes each model…

An Efficient and Adaptive Watermark Detection System with Tile-based Error Correction
Xinrui Zhong, Xinze Feng, Jingwei Zuo, Fanjiang Ye, Yi Mu, Junfeng Guo, Heng Huang, Myungjin Lee, Yuke Wang
https://arxiv.org/abs/2509.02447

An Efficient and Adaptive Watermark Detection System with Tile-based Error Correction
Efficient and reliable detection of generated images is critical for the responsible deployment of generative models. Existing approaches primarily focus on improving detection accuracy and robustness under various image transformations and adversarial manipulations, yet they largely overlook the efficiency challenges of watermark detection across large-scale image collections. To address this gap, we propose QRMark, an efficient and adaptive end-to-end method for detecting embedded image water…

RiverScope: High-Resolution River Masking Dataset
Rangel Daroya, Taylor Rowley, Jonathan Flores, Elisa Friedmann, Fiona Bennitt, Heejin An, Travis Simmons, Marissa Jean Hughes, Camryn L Kluetmeier, Solomon Kica, J. Daniel V\'elez, Sarah E. Esenther, Thomas E. Howard, Yanqi Ye, Audrey Turcotte, Colin Gleason, Subhransu Maji
https://arxi…

RiverScope: High-Resolution River Masking Dataset
Surface water dynamics play a critical role in Earth's climate system, influencing ecosystems, agriculture, disaster resilience, and sustainable development. Yet monitoring rivers and surface water at fine spatial and temporal scales remains challenging -- especially for narrow or sediment-rich rivers that are poorly captured by low-resolution satellite data. To address this, we introduce RiverScope, a high-resolution dataset developed through collaboration between computer science and hydrolog…

MelCap: A Unified Single-Codebook Neural Codec for High-Fidelity Audio Compression
Jingyi Li, Zhiyuan Zhao, Yunfei Liu, Lijian Lin, Ye Zhu, Jiahao Wu, Qiuqiang Kong, Yu Li
https://arxiv.org/abs/2510.01903

MelCap: A Unified Single-Codebook Neural Codec for High-Fidelity Audio Compression
Neural audio codecs have recently emerged as powerful tools for high-quality and low-bitrate audio compression, leveraging deep generative models to learn latent representations of audio signals. However, existing approaches either rely on a single quantizer that only processes speech domain, or on multiple quantizers that are not well suited for downstream tasks. To address this issue, we propose MelCap, a unified "one-codebook-for-all" neural codec that effectively handles speech, music, and …

Mirage Fools the Ear, Mute Hides the Truth: Precise Targeted Adversarial Attacks on Polyphonic Sound Event Detection Systems
Junjie Su, Weifei Jin, Yuxin Cao, Derui Wang, Kai Ye, Jie Hao
https://arxiv.org/abs/2510.02158

Mirage Fools the Ear, Mute Hides the Truth: Precise Targeted Adversarial Attacks on Polyphonic Sound Event Detection Systems
Sound Event Detection (SED) systems are increasingly deployed in safety-critical applications such as industrial monitoring and audio surveillance. However, their robustness against adversarial attacks has not been well explored. Existing audio adversarial attacks targeting SED systems, which incorporate both detection and localization capabilities, often lack effectiveness due to SED's strong contextual dependencies or lack precision by focusing solely on misclassifying the target region as th…

Exposing the Cracks: Vulnerabilities of Retrieval-Augmented LLM-based Machine Translation
Yanming Sun, Runzhe Zhan, Chi Seng Cheang, Han Wu, Xuebo Liu, Yuyao Niu, Fengying Ye, Kaixin Lan, Lidia S. Chao, Derek F. Wong
https://arxiv.org/abs/2510.00829

Exposing the Cracks: Vulnerabilities of Retrieval-Augmented LLM-based Machine Translation
\textbf{RE}trieval-\textbf{A}ugmented \textbf{L}LM-based \textbf{M}achine \textbf{T}ranslation (REAL-MT) shows promise for knowledge-intensive tasks like idiomatic translation, but its reliability under noisy retrieval contexts remains poorly understood despite this being a common challenge in real-world deployment. To address this gap, we propose a noise synthesis framework and new metrics to evaluate the robustness of REAL-MT systematically. Using this framework, we instantiate REAL-MT with Q…

IoT-MCP: Bridging LLMs and IoT Systems Through Model Context Protocol
Ningyuan Yang, Guanliang Lyu, Mingchen Ma, Yiyi Lu, Yiming Li, Zhihui Gao, Hancheng Ye, Jianyi Zhang, Tingjun Chen, Yiran Chen
https://arxiv.org/abs/2510.01260

IoT-MCP: Bridging LLMs and IoT Systems Through Model Context Protocol
The integration of Large Language Models (LLMs) with Internet-of-Things (IoT) systems faces significant challenges in hardware heterogeneity and control complexity. The Model Context Protocol (MCP) emerges as a critical enabler, providing standardized communication between LLMs and physical devices. We propose IoT-MCP, a novel framework that implements MCP through edge-deployed servers to bridge LLMs and IoT ecosystems. To support rigorous evaluation, we introduce IoT-MCP Bench, the first bench…

Crosslisted article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[8/15]:
- Reinforcement Learning Driven Generalizable Feature Representation for Cross-User Activity Recogn...
Xiaozhou Ye, Kevin I-Kai Wang

Beyond Correctness: Harmonizing Process and Outcome Rewards through RL Training
Chenlu Ye, Zhou Yu, Ziji Zhang, Hao Chen, Narayanan Sadagopan, Jing Huang, Tong Zhang, Anurag Beniwal
https://arxiv.org/abs/2509.03403

Beyond Correctness: Harmonizing Process and Outcome Rewards through RL Training
Reinforcement learning with verifiable rewards (RLVR) has emerged to be a predominant paradigm for mathematical reasoning tasks, offering stable improvements in reasoning ability. However, Outcome Reward Models (ORMs) in RLVR are too coarse-grained to distinguish flawed reasoning within correct answers or valid reasoning within incorrect answers. This lack of granularity introduces noisy and misleading gradients significantly and hinders further progress in reasoning process quality. While Proc…

Tightness of SDP and Burer-Monteiro Factorization for Phase Synchronization in High-Noise Regime
Anderson Ye Zhang
https://arxiv.org/abs/2510.01522 https://

Tightness of SDP and Burer-Monteiro Factorization for Phase Synchronization in High-Noise Regime
We study the difference between the maximum likelihood estimation (MLE) and its semi-definite programming (SDP) relaxation for the phase synchronization problem, where $n$ latent phases are estimated based on pairwise observations corrupted by Gaussian noise at a level $σ$. While previous studies have established that SDP coincides with the MLE when $σ\lesssim \sqrt{n / \log n}$, the behavior in the high-noise regime $σ\gtrsim \sqrt{n / \log n}$ remains unclear. We address this gap by quanti…

U-ARM : Ultra low-cost general teleoperation interface for robot manipulation
Yanwen Zou, Zhaoye Zhou, Chenyang Shi, Zewei Ye, Junda Huang, Yan Ding, Bo Zhao
https://arxiv.org/abs/2509.02437

U-ARM : Ultra low-cost general teleoperation interface for robot manipulation
We propose U-Arm, a low-cost and rapidly adaptable leader-follower teleoperation framework designed to interface with most of commercially available robotic arms. Our system supports teleoperation through three structurally distinct 3D-printed leader arms that share consistent control logic, enabling seamless compatibility with diverse commercial robot configurations. Compared with previous open-source leader-follower interfaces, we further optimized both the mechanical design and servo selecti…

Crosslisted article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[2/15]:
- The Collaborations among Healthcare Systems, Research Institutions, and Industry on Artificial In...
Jiancheng Ye, Michelle Ma, Malak Abuhashish

MedQ-Bench: Evaluating and Exploring Medical Image Quality Assessment Abilities in MLLMs
Jiyao Liu, Jinjie Wei, Wanying Qu, Chenglong Ma, Junzhi Ning, Yunheng Li, Ying Chen, Xinzhe Luo, Pengcheng Chen, Xin Gao, Ming Hu, Huihui Xu, Xin Wang, Shujian Gao, Dingkang Yang, Zhongying Deng, Jin Ye, Lihao Liu, Junjun He, Ningsheng Xu
https://arxiv…

MedQ-Bench: Evaluating and Exploring Medical Image Quality Assessment Abilities in MLLMs
Medical Image Quality Assessment (IQA) serves as the first-mile safety gate for clinical AI, yet existing approaches remain constrained by scalar, score-based metrics and fail to reflect the descriptive, human-like reasoning process central to expert evaluation. To address this gap, we introduce MedQ-Bench, a comprehensive benchmark that establishes a perception-reasoning paradigm for language-based evaluation of medical image quality with Multi-modal Large Language Models (MLLMs). MedQ-Bench d…

Social Welfare Function Leaderboard: When LLM Agents Allocate Social Welfare
Zhengliang Shi, Ruotian Ma, Jen-tse Huang, Xinbei Ma, Xingyu Chen, Mengru Wang, Qu Yang, Yue Wang, Fanghua Ye, Ziyang Chen, Shanyi Wang, Cixing Li, Wenxuan Wang, Zhaopeng Tu, Xiaolong Li, Zhaochun Ren, Linus
https://arxiv.org/abs/2510.01164

Social Welfare Function Leaderboard: When LLM Agents Allocate Social Welfare
Large language models (LLMs) are increasingly entrusted with high-stakes decisions that affect human welfare. However, the principles and values that guide these models when distributing scarce societal resources remain largely unexamined. To address this, we introduce the Social Welfare Function (SWF) Benchmark, a dynamic simulation environment where an LLM acts as a sovereign allocator, distributing tasks to a heterogeneous community of recipients. The benchmark is designed to create a persis…

A Geometric Method for Base Parameter Analysis in Robot Inertia Identification Based on Projective Geometric Algebra
Guangzhen Sun, Ye Ding, Xiangyang Zhu
https://arxiv.org/abs/2509.02071

A Geometric Method for Base Parameter Analysis in Robot Inertia Identification Based on Projective Geometric Algebra
This paper proposes a novel geometric method for analytically determining the base inertial parameters of robotic systems. The rigid body dynamics is reformulated using projective geometric algebra, leading to a new identification model named ``tetrahedral-point (TP)" model. Based on the rigid body TP model, coefficients in the regresoor matrix of the identification model are derived in closed-form, exhibiting clear geometric interpretations. Building directly from the dynamic model, three foun…

Diffusion Transformers for Imputation: Statistical Efficiency and Uncertainty Quantification
Zeqi Ye, Minshuo Chen
https://arxiv.org/abs/2510.02216 https://

Diffusion Transformers for Imputation: Statistical Efficiency and Uncertainty Quantification
Imputation methods play a critical role in enhancing the quality of practical time-series data, which often suffer from pervasive missing values. Recently, diffusion-based generative imputation methods have demonstrated remarkable success compared to autoregressive and conventional statistical approaches. Despite their empirical success, the theoretical understanding of how well diffusion-based models capture complex spatial and temporal dependencies between the missing values and observed ones…

Learning Compact Representations of LLM Abilities via Item Response Theory
Jianhao Chen, Chenxu Wang, Gengrui Zhang, Peng Ye, Lei Bai, Wei Hu, Yuzhong Qu, Shuyue Hu
https://arxiv.org/abs/2510.00844

Learning Compact Representations of LLM Abilities via Item Response Theory
Recent years have witnessed a surge in the number of large language models (LLMs), yet efficiently managing and utilizing these vast resources remains a significant challenge. In this work, we explore how to learn compact representations of LLM abilities that can facilitate downstream tasks, such as model routing and performance prediction on new benchmarks. We frame this problem as estimating the probability that a given model will correctly answer a specific query. Inspired by the item respon…

EvoWorld: Evolving Panoramic World Generation with Explicit 3D Memory
Jiahao Wang, Luoxin Ye, TaiMing Lu, Junfei Xiao, Jiahan Zhang, Yuxiang Guo, Xijun Liu, Rama Chellappa, Cheng Peng, Alan Yuille, Jieneng Chen
https://arxiv.org/abs/2510.01183

EvoWorld: Evolving Panoramic World Generation with Explicit 3D Memory
Humans possess a remarkable ability to mentally explore and replay 3D environments they have previously experienced. Inspired by this mental process, we present EvoWorld: a world model that bridges panoramic video generation with evolving 3D memory to enable spatially consistent long-horizon exploration. Given a single panoramic image as input, EvoWorld first generates future video frames by leveraging a video generator with fine-grained view control, then evolves the scene's 3D reconstruction …

StockBench: Can LLM Agents Trade Stocks Profitably In Real-world Markets?
Yanxu Chen, Zijun Yao, Yantao Liu, Jin Ye, Jianing Yu, Lei Hou, Juanzi Li
https://arxiv.org/abs/2510.02209

StockBench: Can LLM Agents Trade Stocks Profitably In Real-world Markets?
Large language models (LLMs) have recently demonstrated strong capabilities as autonomous agents, showing promise in reasoning, tool use, and sequential decision-making. While prior benchmarks have evaluated LLM agents in domains such as software engineering and scientific discovery, the finance domain remains underexplored, despite its direct relevance to economic value and high-stakes decision-making. Existing financial benchmarks primarily test static knowledge through question answering, bu…

Towards Robust In-Context Learning for Medical Image Segmentation via Data Synthesis
Jiesi Hu, Yanwu Yang, Zhiyu Ye, Chenfei Ye, Hanyang Peng, Jianfeng Cao, Ting Ma
https://arxiv.org/abs/2509.19711

Towards Robust In-Context Learning for Medical Image Segmentation via Data Synthesis
The rise of In-Context Learning (ICL) for universal medical image segmentation has introduced an unprecedented demand for large-scale, diverse datasets for training, exacerbating the long-standing problem of data scarcity. While data synthesis offers a promising solution, existing methods often fail to simultaneously achieve both high data diversity and a domain distribution suitable for medical data. To bridge this gap, we propose \textbf{SynthICL}, a novel data synthesis framework built upon …

Learning Compact Representations of LLM Abilities via Item Response Theory
Jianhao Chen, Chenxu Wang, Gengrui Zhang, Peng Ye, Lei Bai, Wei Hu, Yuzhong Qu, Shuyue Hu
https://arxiv.org/abs/2510.00844

Learning Compact Representations of LLM Abilities via Item Response Theory
Recent years have witnessed a surge in the number of large language models (LLMs), yet efficiently managing and utilizing these vast resources remains a significant challenge. In this work, we explore how to learn compact representations of LLM abilities that can facilitate downstream tasks, such as model routing and performance prediction on new benchmarks. We frame this problem as estimating the probability that a given model will correctly answer a specific query. Inspired by the item respon…

Hy-Facial: Hybrid Feature Extraction by Dimensionality Reduction Methods for Enhanced Facial Expression Classification
Xinjin Li, Yu Ma, Kaisen Ye, Jinghan Cao, Minghao Zhou, Yeyang Zhou
https://arxiv.org/abs/2509.26614

Hy-Facial: Hybrid Feature Extraction by Dimensionality Reduction Methods for Enhanced Facial Expression Classification
Facial expression classification remains a challenging task due to the high dimensionality and inherent complexity of facial image data. This paper presents Hy-Facial, a hybrid feature extraction framework that integrates both deep learning and traditional image processing techniques, complemented by a systematic investigation of dimensionality reduction strategies. The proposed method fuses deep features extracted from the Visual Geometry Group 19-layer network (VGG19) with handcrafted local d…

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[7/9]:
- Scaling RL to Long Videos
Chen, Huang, Shi, Hu, Ye, Zhu, Liu, Molchanov, Kautz, Qi, Liu, Yin, Lu, Han

Crosslisted article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[1/5]:
- PCPO: Proportionate Credit Policy Optimization for Aligning Image Generation Models
Jeongjae Lee, Jong Chul Ye

VideoAnchor: Reinforcing Subspace-Structured Visual Cues for Coherent Visual-Spatial Reasoning
Zhaozhi Wang, Tong Zhang, Mingyue Guo, Yaowei Wang, Qixiang Ye
https://arxiv.org/abs/2509.25151

VideoAnchor: Reinforcing Subspace-Structured Visual Cues for Coherent Visual-Spatial Reasoning
Multimodal Large Language Models (MLLMs) have achieved impressive progress in vision-language alignment, yet they remain limited in visual-spatial reasoning. We first identify that this limitation arises from the attention mechanism: visual tokens are overshadowed by language tokens, preventing the model from consistently recognizing the same visual cues across frames. To address this challenge, we draw a novel connection between the self-expressiveness property in sparse subspace clustering an…