Tootfinder

Temporal-Aware Iterative Speech Model for Dementia Detection
Chukwuemeka Ugwu, Oluwafemi Oyeleke
https://arxiv.org/abs/2510.00030 https://arxiv.org/pdf/251…

Temporal-Aware Iterative Speech Model for Dementia Detection
Deep learning systems often struggle with processing long sequences, where computational complexity can become a bottleneck. Current methods for automated dementia detection using speech frequently rely on static, time-agnostic features or aggregated linguistic content, lacking the flexibility to model the subtle, progressive deterioration inherent in speech production. These approaches often miss the dynamic temporal patterns that are critical early indicators of cognitive decline. In this pap…

GRAD: Generative Retrieval-Aligned Demonstration Sampler for Efficient Few-Shot Reasoning
Oussama Gabouj, Kamel Charaf, Ivan Zakazov, Nicolas Baldwin, Robert West
https://arxiv.org/abs/2510.01165

GRAD: Generative Retrieval-Aligned Demonstration Sampler for Efficient Few-Shot Reasoning
Large Language Models (LLMs) achieve strong performance across diverse tasks, but their effectiveness often depends on the quality of the provided context. Retrieval-Augmented Generation (RAG) enriches prompts with external information, but its reliance on static databases constrains adaptability and can result in irrelevant demonstrations. In this work, we propose a Generative Retrieval-Aligned Demonstrator (GRAD), a dynamic demonstration-based approach where an LLM model is trained to generat…

Face2Feel: Emotion-Aware Adaptive User Interface
Ismail Alihan Hadimlioglu, Siddharth Linga
https://arxiv.org/abs/2510.00489 https://arxiv.org/pdf/2510.004…

Face2Feel: Emotion-Aware Adaptive User Interface
This paper presents Face2Feel, a novel user interface (UI) model that dynamically adapts to user emotions and preferences captured through computer vision. This adaptive UI framework addresses the limitations of traditional static interfaces by integrating digital image processing, face recognition, and emotion detection techniques. Face2Feel analyzes user expressions utilizing a webcam or pre-installed camera as the primary data source to personalize the UI in real-time. Although dynamically c…

Finally #3dprinting again. Had some hotend nozzle clogging and learned about different methods to overcome that. Turns out 'cold pull' is best. Now only 2.5 more hours to go. ;)

Grounded AI for Code Review: Resource-Efficient Large-Model Serving in Enterprise Pipelines
Sayan Mandal, Hua Jiang
https://arxiv.org/abs/2510.10290 https://

Grounded AI for Code Review: Resource-Efficient Large-Model Serving in Enterprise Pipelines
Automated code review adoption lags in compliance-heavy settings, where static analyzers produce high-volume, low-rationale outputs, and naive LLM use risks hallucination and incurring cost overhead. We present a production system for grounded, PR-native review that pairs static-analysis findings with AST-guided context extraction and a single-GPU, on-demand serving stack (quantized open-weight model, multi-tier caching) to deliver concise explanations and remediation guidance. Evaluated on saf…

Likelihood-informed Model Reduction for Bayesian Inference of Static Structural Loads
Jakob Scheffels, Elizabeth Qian, Iason Papaioannou, Elisabeth Ullmann
https://arxiv.org/abs/2510.07950

Likelihood-informed Model Reduction for Bayesian Inference of Static Structural Loads
Bayesian inverse problems use data to update a prior probability distribution on uncertain parameter values to a posterior distribution. Such problems arise in many structural engineering applications, but computational solution of Bayesian inverse problems is often expensive because standard solution approaches require many evaluations of the forward model mapping the parameter value to predicted observations. In many settings, this forward model is expensive because it requires the solution o…

Point Cloud-Based Control Barrier Functions for Model Predictive Control in Safety-Critical Navigation of Autonomous Mobile Robots
Faduo Liang, Yunfeng Yang, Shi-Lu Dai
https://arxiv.org/abs/2510.02885

Point Cloud-Based Control Barrier Functions for Model Predictive Control in Safety-Critical Navigation of Autonomous Mobile Robots
In this work, we propose a novel motion planning algorithm to facilitate safety-critical navigation for autonomous mobile robots. The proposed algorithm integrates a real-time dynamic obstacle tracking and mapping system that categorizes point clouds into dynamic and static components. For dynamic point clouds, the Kalman filter is employed to estimate and predict their motion states. Based on these predictions, we extrapolate the future states of dynamic point clouds, which are subsequently me…

TC-LoRA: Temporally Modulated Conditional LoRA for Adaptive Diffusion Control
Minkyoung Cho, Ruben Ohana, Christian Jacobsen, Adityan Jothi, Min-Hung Chen, Z. Morley Mao, Ethem Can
https://arxiv.org/abs/2510.09561

TC-LoRA: Temporally Modulated Conditional LoRA for Adaptive Diffusion Control
Current controllable diffusion models typically rely on fixed architectures that modify intermediate activations to inject guidance conditioned on a new modality. This approach uses a static conditioning strategy for a dynamic, multi-stage denoising process, limiting the model's ability to adapt its response as the generation evolves from coarse structure to fine detail. We introduce TC-LoRA (Temporally Modulated Conditional LoRA), a new paradigm that enables dynamic, context-aware control by c…

Dissecting the moat regime at low energies I: Renormalization and the phase structure
Fabian Rennecke, Shi Yin
https://arxiv.org/abs/2510.06712 https://arx…

Dissecting the moat regime at low energies I: Renormalization and the phase structure
Dense QCD matter can feature a moat regime, where the static energy of mesons is minimal at nonzero momentum. Valuable insights into this regime can be gained using low-energy models. This, however, requires a careful assessment of model artifacts. We therefore study the effects of renormalization and in-medium modifications of quark-meson interaction on the moat regime. To capture the main effects, we use a two-flavor quark-meson model at finite temperature and baryon density in the random pha…

Anomalous Criticality of Absorbing State Transition toward Jamming
He-Da Wang, Bo Wang, Qun-Li Lei, Yu-Qiang Ma
https://arxiv.org/abs/2510.06641 https://ar…

Anomalous Criticality of Absorbing State Transition toward Jamming
The jamming transition is traditionally regarded as a geometric transition governed by static contact networks. Recently, dynamic phase transitions of athermal particles under periodic shear provide a new lens on this problem, leading to a conjecture that jamming transition corresponds to an absorbing-state transition within the Manna (conserved directed percolation) universality class. Here, by re-examing the biased random organization model, a minimal model for particles under periodic sheari…

Continual Release of Densest Subgraphs: Privacy Amplification & Sublinear Space via Subsampling
Felix Zhou
https://arxiv.org/abs/2510.11640 https://arx…

Continual Release of Densest Subgraphs: Privacy Amplification & Sublinear Space via Subsampling
We study the sublinear space continual release model for edge-differentially private (DP) graph algorithms, with a focus on the densest subgraph problem (DSG) in the insertion-only setting. Our main result is the first continual release DSG algorithm that matches the additive error of the best static DP algorithms and the space complexity of the best non-private streaming algorithms, up to constants. The key idea is a refined use of subsampling that simultaneously achieves privacy amplification…

Microlensing of non-singular black holes at finite size: a ray tracing approach
Jens Boos, Hao Hu
https://arxiv.org/abs/2510.10282 https://arxiv.org/pdf/25…

Microlensing of non-singular black holes at finite size: a ray tracing approach
We study the gravitational microlensing of various static and spherically symmetric non-singular black holes (and horizonless, non-singular compact objects of similar size). For pointlike sources we extend the parametrized post-Newtonian lensing framework to fourth order, whereas for extended sources we develop a ray tracing approach via a simple radiative transfer model. Modelling non-relativistic proper motion of the lens in front of a background star we record the apparent brightness as a fu…

Time-To-Inconsistency: A Survival Analysis of Large Language Model Robustness to Adversarial Attacks
Yubo Li, Ramayya Krishnan, Rema Padman
https://arxiv.org/abs/2510.02712 http…

Time-To-Inconsistency: A Survival Analysis of Large Language Model Robustness to Adversarial Attacks
Large Language Models (LLMs) have revolutionized conversational AI, yet their robustness in extended multi-turn dialogues remains poorly understood. Existing evaluation frameworks focus on static benchmarks and single-turn assessments, failing to capture the temporal dynamics of conversational degradation that characterize real-world interactions. In this work, we present the first comprehensive survival analysis of conversational AI robustness, analyzing 36,951 conversation turns across 9 stat…

A Vision for Access Control in LLM-based Agent Systems
Xinfeng Li, Dong Huang, Jie Li, Hongyi Cai, Zhenhong Zhou, Wei Dong, XiaoFeng Wang, Yang Liu
https://arxiv.org/abs/2510.11108

A Vision for Access Control in LLM-based Agent Systems
The autonomy and contextual complexity of LLM-based agents render traditional access control (AC) mechanisms insufficient. Static, rule-based systems designed for predictable environments are fundamentally ill-equipped to manage the dynamic information flows inherent in agentic interactions. This position paper argues for a paradigm shift from binary access control to a more sophisticated model of information governance, positing that the core challenge is not merely about permission, but about…

Optimal parallelisation strategies for flat histogram Monte Carlo sampling
Hubert J. Naguszewski, Christopher D. Woodgate, David Quigley
https://arxiv.org/abs/2510.11562 https:/…

Optimal parallelisation strategies for flat histogram Monte Carlo sampling
Flat histogram methods, such as Wang-Landau sampling, provide a means for high throughput calculation of phase diagrams of atomistic/lattice model systems. Many parallelisation schemes with varying degrees of complexity have been proposed to accelerate such sampling simulations. In this study, several widely used schemes are benchmarked - both in isolation and in combination - to establish best practice. The schemes studied include energy domain decomposition with both static sizing of energy s…

Slow-phonon control of spin Edelstein effect in Rashba $d$-wave altermagnets
Mohsen Yarmohammadi, Jacob Linder, James K. Freericks
https://arxiv.org/abs/2510.02451 https://

Slow-phonon control of spin Edelstein effect in Rashba $d$-wave altermagnets
Altermagnets have zero net magnetization yet feature spin-split bands that host spin-polarized states. Here, we investigate how slow lattice vibrations (phonons) influence both the intrinsic and externally induced spin polarizations in two-dimensional $d$-wave altermagnets. For the induced spin polarizations, we employ a Rashba continuum model with electron-phonon coupling (EPC) treated at the static-Holstein level and analyze the spin Edelstein effect using the Kubo linear-response formalism. …

Gate Voltage Tunable Second Harmonic Generation in Mono- and Bi-layer Black Phosphene
Yan Meng, Kainan Chang, Yanyan Qian, Luxia Wang, Jin Luo Cheng
https://arxiv.org/abs/2510.08014

Gate Voltage Tunable Second Harmonic Generation in Mono- and Bi-layer Black Phosphene
Black phosphorene (BP) has emerged as a promising platform for tunable nonlinear photonics due to its layer-dependent bandgap, high carrier mobility, and remarkable in-plane anisotropy. This study investigates the second-harmonic generation (SHG) of monolayer and bilayer BP under an external static electric field, with describing the electronic states by a tight-binding model and the dynamics by semiconductor Bloch equations. Our results reveal that BP exhibits large second-order nonlinear opti…

Dynamic Stress Detection: A Study of Temporal Progression Modelling of Stress in Speech
Vishakha Lall, Yisi Liu
https://arxiv.org/abs/2510.08586 https://ar…

Dynamic Stress Detection: A Study of Temporal Progression Modelling of Stress in Speech
Detecting psychological stress from speech is critical in high-pressure settings. While prior work has leveraged acoustic features for stress detection, most treat stress as a static label. In this work, we model stress as a temporally evolving phenomenon influenced by historical emotional state. We propose a dynamic labelling strategy that derives fine-grained stress annotations from emotional labels and introduce cross-attention-based sequential models, a Unidirectional LSTM and a Transformer…

An Adaptive Multi Agent Bitcoin Trading System
Aadi Singhi
https://arxiv.org/abs/2510.08068 https://arxiv.org/pdf/2510.08068…

An Adaptive Multi Agent Bitcoin Trading System
This paper presents a Multi Agent Bitcoin Trading system that utilizes Large Lan- guage Models (LLMs) for alpha generation and portfolio management in the cryptocur- rencies market. Unlike equities, cryptocurrencies exhibit extreme volatility and are heavily influenced by rapidly shifting market sentiments and regulatory announcements, making them difficult to model using static regression models or neural networks trained solely on historical data [53]. The proposed framework overcomes this by…

Are Large Reasoning Models Interruptible?
Tsung-Han Wu, Mihran Miroyan, David M. Chan, Trevor Darrell, Narges Norouzi, Joseph E. Gonzalez
https://arxiv.org/abs/2510.11713 https:…

Are Large Reasoning Models Interruptible?
Large Reasoning Models (LRMs) excel at complex reasoning but are traditionally evaluated in static, "frozen world" settings: model responses are assumed to be instantaneous, and the context of a request is presumed to be immutable over the duration of the response. While generally true for short-term tasks, the "frozen world" assumption breaks down in modern reasoning tasks such as assistive programming, where models may take hours to think through problems and code may change dramatically from…

The Finite-Temperature Behavior of a Triangular Heisenberg Antiferromagnet
Cecilie Glittum, Olav F. Sylju{\aa}sen
https://arxiv.org/abs/2510.02042 https://…

The Finite-Temperature Behavior of a Triangular Heisenberg Antiferromagnet
We investigate the classical antiferromagnetic Heisenberg model on the triangular lattice with up to third-nearest neighbor couplings using nematic bond theory. This approach allows us to compute the free energy and the neutron scattering static structure factor at finite temperatures. We map out the phase diagram with a particular emphasis on finite-temperature phase transitions that break lattice rotational symmetries, spiral spin liquids and the broad specific heat hump that is ubiquitous in…

Robust Pricing and Hedging of American Options in Continuous Time
Ivan Guo, Jan Ob\l\'oj
https://arxiv.org/abs/2510.05463 https://arxiv.org/pdf/2510.05…

Robust Pricing and Hedging of American Options in Continuous Time
We consider the robust pricing and hedging of American options in a continuous time setting. We assume asset prices are continuous semimartingales, but we allow for general model uncertainty specification via adapted closed convex constraints on the volatility. We prove the robust pricing-hedging duality. When European options with given prices are available for static trading, we show that duality holds against richer models where these options are traded dynamically. Our proofs rely on probab…

CWM: An Open-Weights LLM for Research on Code Generation with World Models
FAIR CodeGen team, Quentin Carbonneaux, Gal Cohen, Jonas Gehring, Jacob Kahn, Jannik Kossen, Felix Kreuk, Emily McMilin, Michel Meyer, Yuxiang Wei, David Zhang, Kunhao Zheng, Jordi Armengol-Estap\'e, Pedram Bashiri, Maximilian Beck, Pierre Chambon, Abhishek Charnalia, Chris Cummins, Juliette Decugis, Zacharias V. Fisches, Fran\c{c}ois Fleuret, Fabian Gloeckle, Alex Gu, Michael Hassid, Daniel Haziza, Badr You…

CWM: An Open-Weights LLM for Research on Code Generation with World Models
We release Code World Model (CWM), a 32-billion-parameter open-weights LLM, to advance research on code generation with world models. To improve code understanding beyond what can be learned from training on static code alone, we mid-train CWM on a large amount of observation-action trajectories from Python interpreter and agentic Docker environments, and perform extensive multi-task reasoning RL in verifiable coding, math, and multi-turn software engineering environments. With CWM, we provide …

PRoH: Dynamic Planning and Reasoning over Knowledge Hypergraphs for Retrieval-Augmented Generation
Xiangjun Zai, Xingyu Tan, Xiaoyang Wang, Qing Liu, Xiwei Xu, Wenjie Zhang
https://arxiv.org/abs/2510.12434

PRoH: Dynamic Planning and Reasoning over Knowledge Hypergraphs for Retrieval-Augmented Generation
Knowledge Hypergraphs (KHs) have recently emerged as a knowledge representation for retrieval-augmented generation (RAG), offering a paradigm to model multi-entity relations into a structured form. However, existing KH-based RAG methods suffer from three major limitations: static retrieval planning, non-adaptive retrieval execution, and superficial use of KH structure and semantics, which constrain their ability to perform effective multi-hop question answering. To overcome these limitations, w…

Multi-State Modeling of Greenhouse Cucumber Yield Dynamics Under Microclimate Effects
Emiliano Seri, Francesco Biso, Gianluigi Bovesecchi, Nikolaos Katsoulas, Cristina Cornaro
https://arxiv.org/abs/2510.11485

Multi-State Modeling of Greenhouse Cucumber Yield Dynamics Under Microclimate Effects
Greenhouse decisions often rely on static thresholds, yet crop output switches among microclimate-driven regimes. We frame daily cucumber yield as transitions among three ordered states and fit a continuous-time, covariate-dependent multistate model. Data come from four greenhouse compartments in Volos, Greece (24 lines, 62 days). States are defined once from control tertiles and applied across compartments. Transition intensities depend on within-compartment z-scores of relative humidity (RH),…

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…

AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning
Haoyu Zhang, Jiaxian Guo, Yusuke Iwasawa, Yutaka Matsuo
https://arxiv.org/abs/2510.05478

AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning
Large Audio Language Models (LALMs) demonstrate impressive general audio understanding, but once deployed, they are static and fail to improve with new real-world audio data. As traditional supervised fine-tuning is costly, we introduce a novel framework for test-time audio understanding, AQA-TTRL, where an LALM evolves on-the-fly using only unlabeled test data. It first generates pseudo-labels from the prediction via majority voting, then optimizes the model via reinforcement learning. To hand…

Inverse Language Modeling towards Robust and Grounded LLMs
Davide Gabrielli, Simone Sestito, Iacopo Masi
https://arxiv.org/abs/2510.01929 https://arxiv.org…

Inverse Language Modeling towards Robust and Grounded LLMs
The current landscape of defensive mechanisms for LLMs is fragmented and underdeveloped, unlike prior work on classifiers. To further promote adversarial robustness in LLMs, we propose Inverse Language Modeling (ILM), a unified framework that simultaneously 1) improves the robustness of LLMs to input perturbations, and, at the same time, 2) enables native grounding by inverting model outputs to identify potentially toxic or unsafe input triggers. ILM transforms LLMs from static generators into …