Tootfinder

Alibaba halves Qwen3-Max prices, from $0.861 to $0.459 per 1M input tokens and $3.441 to $1.836 per 1M output tokens for API users, amid China's AI price wars (Vincent Chow/South China Morning Post)
https://www.scmp.com/tech/big-tech/article

Alibaba slashes Qwen3-Max model charges up to 50% amid latest AI price war
The new pricing strategy reflects heightened competition in China’s foundational model market.

Tiny-R1V: Lightweight Multimodal Unified Reasoning Model via Model Merging
Qixiang Yin, Huanjin Yao, Jianghao Chen, Jiaxing Huang, Zhicheng Zhao, Fei Su
https://arxiv.org/abs/2510.08987

Tiny-R1V: Lightweight Multimodal Unified Reasoning Model via Model Merging
Although Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities across diverse tasks, they encounter numerous challenges in terms of reasoning efficiency, such as large model size, overthinking, and compromised accuracy in lightweight scenarios. However, research on the reasoning capabilities of lightweight MLLMs is quite lacking. To this end, we propose Tiny-R1V, a novel lightweight 3B model that achieves faster inference and higher accuracy via a two-stage optimiza…

FLAMMABLE: A Multi-Model Federated Learning Framework with Multi-Model Engagement and Adaptive Batch Sizes
Shouxu Lin, Zimeng Pan, Yuhang Yao, Haeyoung Noh, Pei Zhang, Carlee Joe-Wong
https://arxiv.org/abs/2510.10380

FLAMMABLE: A Multi-Model Federated Learning Framework with Multi-Model Engagement and Adaptive Batch Sizes
Multi-Model Federated Learning (MMFL) is an emerging direction in Federated Learning (FL) where multiple models are trained in parallel, generally on various datasets. Optimizing the models' accuracies and training times in the MMFL setting requires adapting to data and system heterogeneity across clients as in single-model FL; these challenges are amplified in the MMFL setting due to additional heterogeneity across models. Neither existing solutions nor naïve extensions of single-model FL fra…

Advanced computer model makes NFL against the spread, over/under and money-line picks for each Week 2 game

https://www.cbssports.com/nfl/news/advance…

Nice analysis of the Russian Gerbera drone, used in Poland by Russia.
#osint #drones

OSMP: Gerbera series
A tool for researchers, journalists and practitioners trying to learn more about munitions and their use and impact in conflicts.

MMAudioSep: Taming Video-to-Audio Generative Model Towards Video/Text-Queried Sound Separation
Akira Takahashi, Shusuke Takahashi, Yuki Mitsufuji
https://arxiv.org/abs/2510.09065

MMAudioSep: Taming Video-to-Audio Generative Model Towards Video/Text-Queried Sound Separation
We introduce MMAudioSep, a generative model for video/text-queried sound separation that is founded on a pretrained video-to-audio model. By leveraging knowledge about the relationship between video/text and audio learned through a pretrained audio generative model, we can train the model more efficiently, i.e., the model does not need to be trained from scratch. We evaluate the performance of MMAudioSep by comparing it to existing separation models, including models based on both deterministic…

Weak solutions and weak-strong uniqueness for a compressible power-law-Oldroyd--B fluid model
Yong Lu, Milan Pokorny
https://arxiv.org/abs/2510.10096 https://

Weak solutions and weak-strong uniqueness for a compressible power-law-Oldroyd--B fluid model
We consider a model of a viscoelastic compressible flow in $R^{3}$ which is additionally shear thickening (the stress tensor corresponds to the power law model, however, the divergence of the velocity is due to the model bounded). We prove existence of a weak solution to this model provided the growth in the power law model is larger or equal than $\frac 52$. We also prove that any sufficiently smooth solution of this model is unique in the class of weak solution, provided extra integrability o…

Model-Based Lookahead Reinforcement Learning for in-hand manipulation
Alexandre Lopes, Catarina Barata, Plinio Moreno
https://arxiv.org/abs/2510.08884 https://

Model-Based Lookahead Reinforcement Learning for in-hand manipulation
In-Hand Manipulation, as many other dexterous tasks, remains a difficult challenge in robotics by combining complex dynamic systems with the capability to control and manoeuvre various objects using its actuators. This work presents the application of a previously developed hybrid Reinforcement Learning (RL) Framework to In-Hand Manipulation task, verifying that it is capable of improving the performance of the task. The model combines concepts of both Model-Free and Model-Based Reinforcement L…

Uncertainty-Aware, Risk-Adaptive Access Control for Agentic Systems using an LLM-Judged TBAC Model
Charles Fleming, Ashish Kundu, Ramana Kompella
https://arxiv.org/abs/2510.11414

Uncertainty-Aware, Risk-Adaptive Access Control for Agentic Systems using an LLM-Judged TBAC Model
The proliferation of autonomous AI agents within enterprise environments introduces a critical security challenge: managing access control for emergent, novel tasks for which no predefined policies exist. This paper introduces an advanced security framework that extends the Task-Based Access Control (TBAC) model by using a Large Language Model (LLM) as an autonomous, risk-aware judge. This model makes access control decisions not only based on an agent's intent but also by explicitly considerin…

Active Model Selection for Large Language Models
Yavuz Durmazkeser, Patrik Okanovic, Andreas Kirsch, Torsten Hoefler, Nezihe Merve G\"urel
https://arxiv.org/abs/2510.09418 …

Active Model Selection for Large Language Models
We introduce LLM SELECTOR, the first framework for active model selection of Large Language Models (LLMs). Unlike prior evaluation and benchmarking approaches that rely on fully annotated datasets, LLM SELECTOR efficiently identifies the best LLM with limited annotations. In particular, for any given task, LLM SELECTOR adaptively selects a small set of queries to annotate that are most informative about the best model for the task. To further reduce annotation cost, we leverage a judge-based or…

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

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

Defensive Model Expansion for Robust Bayesian Inference
Antonio R. Linero
https://arxiv.org/abs/2510.09598 https://arxiv.org/pdf/2510.09598

Defensive Model Expansion for Robust Bayesian Inference
Some applied researchers hesitate to use nonparametric methods, worrying that they will lose power in small samples or overfit the data when simpler models are sufficient. We argue that at least some of these concerns are unfounded when nonparametric models are strongly shrunk towards parametric submodels. We consider expanding a parametric model with a nonparametric component that is heavily shrunk toward zero. This construction allows the model to adapt automatically: if the parametric model …

Mitigating Model Drift in Developing Economies Using Synthetic Data and Outliers
Ilyas Varshavskiy, Bonu Boboeva, Shuhrat Khalilbekov, Azizjon Azimi, Sergey Shulgin, Akhlitdin Nizamitdinov, Haitz Saez de Ocariz Borde
https://arxiv.org/abs/2510.09294

Mitigating Model Drift in Developing Economies Using Synthetic Data and Outliers
Machine Learning models in finance are highly susceptible to model drift, where predictive performance declines as data distributions shift. This issue is especially acute in developing economies such as those in Central Asia and the Caucasus - including Tajikistan, Uzbekistan, Kazakhstan, and Azerbaijan - where frequent and unpredictable macroeconomics shocks destabilize financial data. To the best of our knowledge, this is among the first studies to examine drift mitigation methods on financi…

An adaptive time-stepping strategy for the modified phase field crystal model with a strong nonlinear vacancy potential
Wanrong Hao, Yunqing Huang
https://arxiv.org/abs/2510.11475

An adaptive time-stepping strategy for the modified phase field crystal model with a strong nonlinear vacancy potential
This paper develops three linear and energy-stable schemes for a modified phase field crystal model with a strong nonlinear vacancy potential (VMPFC model). This sixth-order phase-field model enables realistic crystal growth simulation. Starting from a Crank-Nicolson scheme based on the stabilized-SAV (S-SAV) method, we optimize it via the generalized positive auxiliary variable (GPAV) and modified exponential scalar auxiliary variable (ESAV) methods, thereby reducing computational complexity o…

Localizing the Ising CFT from the ground state of the Ising model on the fuzzy sphere
Kay Joerg Wiese
https://arxiv.org/abs/2510.09482 https://arxiv.org/pd…

Localizing the Ising CFT from the ground state of the Ising model on the fuzzy sphere
We locate the phase-transition line for the Ising model on the fuzzy sphere from a finite-size scaling analysis of its ground-state energy. This is similar to what was used to locate the complex CFT of the 5-state Potts model in dimension $d=2$ [PRL 133 (2024) 077101]. There it was shown that a CFT is characterized by a stationarity condition for the measured effective central charge. Our strategy is to write the ground-state energy as $E_{\rm GS}(N)/N_m = E_{0} + E_1 /N_m + E_{3/2}/N_m^{3/2}+ …

Assurance of Frontier AI Built for National Security
Matteo Pistillo, Charlotte Stix
https://arxiv.org/abs/2510.08792 https://arxiv.org/pdf/2510.08792

Assurance of Frontier AI Built for National Security
This memorandum presents four recommendations aimed at strengthening the principles of AI model reliability and AI model governability, as DoW, ODNI, NIST, and CAISI refine AI assurance frameworks under the AI Action Plan. Our focus concerns the open scientific problem of misalignment and its implications on AI model behavior. Specifically, misalignment and scheming capabilities can be a red flag indicating AI model insufficient reliability and governability. To address the national security th…

Google announces Gemma 3 270M, a compact model designed for task-specific fine-tuning with strong capabilities in instruction following and text structuring (Google Developers Blog)
https://developers.googleblog.com/en/introducing-gemma-3-270m/

Introducing Gemma 3 270M: The compact model for hyper-efficient AI- Google Developers Blog
Explore Gemma 3 270M, a compact, energy-efficient AI model for task-specific fine-tuning, offering strong instruction-following and production-ready quantization.

Spinless glueballs in generalized linear sigma model
Amir H. Fariborz
https://arxiv.org/abs/2508.09474 https://arxiv.org/pdf/2508.09474

Spinless glueballs in generalized linear sigma model
Within the framework of the generalized linear sigma model, a comprehensive analysis of scalar and pseudoscalar glueballs and their mixing with mesons is presented. The Lagrangian of the model contains two chiral nonets, a quark-antiquark type and a two-quark two-antiquark type. The pseudoscalar and scalar glueballs are introduced through their connections with the axial and the trace anomalies of QCD, respectively. It is found that in order to satisfy the axial anomaly and at the same time acc…

A Hybrid I/O Relation Estimation Scheme for Zak-OTFS Receivers
Sai Pradeep Muppaneni, Vineetha Yogesh, A. Chockalingam
https://arxiv.org/abs/2510.09215 https://

A Hybrid I/O Relation Estimation Scheme for Zak-OTFS Receivers
In this paper, we consider the problem of estimating the delay-Doppler (DD) domain input-output (I/O) relation in Zak-OTFS modulation, which is needed for signal detection. Two approaches, namely, model-dependent and model-free approaches, can be employed for this purpose. The model-dependent approach requires explicit estimation of the physical channel parameters (path delays, Dopplers, and gains) to obtain the I/O relation. Such an explicit estimation is not required in the model-free approac…

Observability and parameter estimation of a generic model for aggregated distributed energy resources
Bukunmi Gabriel Odunlami, Marcos Netto
https://arxiv.org/abs/2510.10892 htt…

Observability and parameter estimation of a generic model for aggregated distributed energy resources
We propose a novel framework for estimating the parameters of an aggregated distributed energy resources (der_a) model. First, we introduce a rigorous method to determine whether all model parameters are estimable. When they are not, our approach identifies the subset of parameters that can be estimated. The proposed framework offers new insights into the number and specific parameters that can be reliably estimated based on commonly available measurements. It also highlights the limitations of…

Lifted Heston Model: Efficient Monte Carlo Simulation with Large Time Steps
Nicola F. Zaugg, Lech A. Grzelak
https://arxiv.org/abs/2510.08805 https://arxiv…

Lifted Heston Model: Efficient Monte Carlo Simulation with Large Time Steps
The lifted Heston model is a stochastic volatility model emerging as a Markovian lift of the rough Heston model and the class of rough volatility processes. The model encodes the path dependency of volatility on a set of N square-root state processes driven by a common stochastic factor. While the system is Markovian, simulation schemes such as the Euler scheme exist, but require a small-step, multidimensional simulation of the state processes and are therefore numerically challenging. We propo…

Cosmological implications of LRS Bianchi type-I cosmological model in $f(T)$ gravity
Shivangi Rathore, S. Surendra Singh
https://arxiv.org/abs/2510.10428 https://

Cosmological implications of LRS Bianchi type-I cosmological model in $f(T)$ gravity
We perform the dynamical system analysis of the Locally Rotationally Symmetric (LRS) Bianchi type-I cosmological model in f(T) gravity in the presence of energy interaction . A cosmologically viable form of $f(T)$ is chosen (where $T$ is the torsion scalar in teleparallelism) in the background of homogenous and anisotropic. For our model, we take $f(T) = T+ζT^{2}$ where $ζ$ is a constant. The evolution equations are reduced to the autonomous system of differential equations by suitable transf…

Week 2 NFL betting guide, props, lines: Model, expert, parlay, DFS and best season-long fantasy picks unveiled

https://www.cbssports.com/nfl/news/week-2-

Investigating the $w$CDM Model with Latest DESI BAO Observations
Manisg Yadav, Archana Dixit, M. S. Barak, Anirudh Pradhan
https://arxiv.org/abs/2510.09074 https://

Investigating the $w$CDM Model with Latest DESI BAO Observations
In this study, we explore the impact of various combinations of CMB-independent datasets, including the recent DESI BAO measurements, on the equation of state (EoS) of dark energy and other cosmological parameters within the framework of the dynamical dark energy model ($w$CDM). Assuming a constant EoS parameter for dark energy, we derive constraints on the free parameters of the model using observational datasets such as DESI BAO, BBN, Observational Hubble Data (OHD), and Pantheon Plus (SN$^+$…

Multiparty equality in the local broadcast model
Louis Esperet, Jean-Florent Raymond
https://arxiv.org/abs/2510.09143 https://arxiv.org/pdf/2510.09143

Multiparty equality in the local broadcast model
In this paper we consider the multiparty equality problem in graphs, where every vertex of a graph $G$ is given an input, and the goal of the vertices is to decide whether all inputs are equal. We study this problem in the local broadcast model, where a message sent by a vertex is received by all its neighbors and the total cost of a protocol is the sum of the lengths of the messages sent by the vertices. This setting was studied by Khan and Vaidya, who gave in 2021 a protocol achieving a 4-app…

Cross-BCI, A Cross-BCI-Paradigm Classifica-tion Model Towards Universal BCI Applications
Gaojie Zhou, Junhua Li
https://arxiv.org/abs/2508.09242 https://ar…

Cross-BCI, A Cross-BCI-Paradigm Classifica-tion Model Towards Universal BCI Applications
Classification models used in brain-computer interface (BCI) are usually designed for a single BCI paradigm. This requires the redevelopment of the model when applying it to a new BCI paradigm, resulting in repeated costs and effort. Moreover, less complex deep learning models are desired for practical usage, as well as for deployment on portable devices. In or-der to fill the above gaps, we, in this study, proposed a light-weight and unified decoding model for cross-BCI-paradigm classification…

A framework for realisable data-driven active flow control using model predictive control applied to a simplified truck wake
Alberto Solera-Rico, Carlos Sanmiguel Vila, Stefano Discetti
https://arxiv.org/abs/2510.11600

A framework for realisable data-driven active flow control using model predictive control applied to a simplified truck wake
We present an efficient and realisable active flow control framework with few non-intrusive sensors. The method builds upon data-driven, reduced-order predictive models based on Long-Short-Term Memory (LSTM) networks and efficient gradient-based Model Predictive Control (MPC). The model uses only surface-mounted pressure probes to infer the wake state, and is trained entirely offline on a dataset built with open-loop actuations, thus avoiding the complexities of online learning. Sparsification …

From Primordial Stars to Early Galaxies: A Semi-Analytic Model Calibrated with Aeos and Renaissance
Ryan Hazlett, Jennifer Mead, Eli Visbal, Greg L. Bryan, Mordecai-Mark Mac Low, Mihir Kulkarni, Eric P. Andersson, Kaley Brauer, John H. Wise
https://arxiv.org/abs/2510.11629

From Primordial Stars to Early Galaxies: A Semi-Analytic Model Calibrated with Aeos and Renaissance
We present an extension of our semi-analytic model that follows the formation of Population III stars and their metal-enriched descendants, incorporating dark matter halo merger trees from cosmological $N$-body simulations and feedback from reionization. Our extended model is calibrated using two complementary cosmological hydrodynamical simulations: Aeos, which resolves individual Population III and II stars to $z\sim14.6$, and Renaissance, which is lower resolution but follows large-scale met…

PyPSA-DE: Open-source German energy system model reveals savings from integrated planning
Michael Lindner, Julian Geis, Toni Seibold, Tom Brown
https://arxiv.org/abs/2510.09414 …

PyPSA-DE: Open-source German energy system model reveals savings from integrated planning
Germany has set an ambitious target of reaching net zero greenhouse gas emissions by 2045. We explore how integrated cross-sectoral planning can reduce costs compared to existing national plans. Our new linear optimization model PyPSA-DE simulates the electricity and hydrogen transmission networks, as well as supply, demand, and storage in all sectors of the energy system in Germany and its neighboring countries with high spatial and temporal resolution. While our new model shows strong electri…

LLMC : Benchmarking Vision-Language Model Compression with a Plug-and-play Toolkit
Chengtao Lv, Bilang Zhang, Yang Yong, Ruihao Gong, Yushi Huang, Shiqiao Gu, Jiajun Wu, Yumeng Shi, Jinyang Guo, Wenya Wang
https://arxiv.org/abs/2508.09981

LLMC+: Benchmarking Vision-Language Model Compression with a Plug-and-play Toolkit
Large Vision-Language Models (VLMs) exhibit impressive multi-modal capabilities but suffer from prohibitive computational and memory demands, due to their long visual token sequences and massive parameter sizes. To address these issues, recent works have proposed training-free compression methods. However, existing efforts often suffer from three major limitations: (1) Current approaches do not decompose techniques into comparable modules, hindering fair evaluation across spatial and temporal r…

Multimodal Fusion And Sparse Attention-based Alignment Model for Long Sequential Recommendation
Yongrui Fu, Jian Liu, Tao Li, Zonggang Wu, Shouke Qin, Hanmeng Liu
https://arxiv.org/abs/2508.09664

Multimodal Fusion And Sparse Attention-based Alignment Model for Long Sequential Recommendation
Recent advances in multimodal recommendation enable richer item understanding, while modeling users' multi-scale interests across temporal horizons has attracted growing attention. However, effectively exploiting multimodal item sequences and mining multi-grained user interests to substantially bridge the gap between content comprehension and recommendation remain challenging. To address these issues, we propose MUFASA, a MUltimodal Fusion And Sparse Attention-based Alignment model for long seq…

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

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

Grid Restoration Under Uncertainty Considering Coupled Transportation-Power Networks
Harshal D. Kaushik, Roshni Anna Jacob, Souma Chowdhury, Jie Zhang
https://arxiv.org/abs/2510.10399

Grid Restoration Under Uncertainty Considering Coupled Transportation-Power Networks
A stochastic mixed-integer programming model is developed to address the power distribution system repair and restoration following failures caused by extreme events such as natural disasters. This model addresses the complex challenge of efficiently assigning and dispatching repair crews to minimize both downtime and the extent of outages, following the crew sequence constraints. By incorporating a realistic transportation network, our model accounts for uncertainties in repair times, repair d…

Comparing Symmetrized Determinant Neural Quantum States for the Hubbard Model
Louis Sharma, Ahmedeo Shokry, Rajah Nutakki, Olivier Simard, Michel Ferrero, Filippo Vicentini
https://arxiv.org/abs/2510.11710

Comparing Symmetrized Determinant Neural Quantum States for the Hubbard Model
Accurate simulations of the Hubbard model are crucial to understanding strongly correlated phenomena, where small energy differences between competing orders demand high numerical precision. In this work, Neural Quantum States are used to probe the strongly coupled and underdoped regime of the square-lattice Hubbard model. We systematically compare the Hidden Fermion Determinant State and the Jastrow-Backflow ansatz, parametrized by a Vision Transformer, finding that in practice, their accuracy…

KORMo: Korean Open Reasoning Model for Everyone
Minjun Kim, Hyeonseok Lim, Hangyeol Yoo, Inho Won, Seungwoo Song, Minkyung Cho, Junhun Yuk, Changsu Choi, Dongjae Shin, Huige Lee, Hoyun Song, Alice Oh, Kyungtae Lim
https://arxiv.org/abs/2510.09426

KORMo: Korean Open Reasoning Model for Everyone
This work presents the first large-scale investigation into constructing a fully open bilingual large language model (LLM) for a non-English language, specifically Korean, trained predominantly on synthetic data. We introduce KORMo-10B, a 10.8B-parameter model trained from scratch on a Korean-English corpus in which 68.74% of the Korean portion is synthetic. Through systematic experimentation, we demonstrate that synthetic data, when carefully curated with balanced linguistic coverage and diver…

The inevitable AI links, Swiss Open Source model apertus:
https://news.itsfoss.com/apertus/

Verify Distributed Deep Learning Model Implementation Refinement with Iterative Relation Inference
Zhanghan Wang, Ding Ding, Hang Zhu, Haibin Lin, Aurojit Panda
https://arxiv.org/abs/2508.09505

Verify Distributed Deep Learning Model Implementation Refinement with Iterative Relation Inference
Distributed machine learning training and inference is common today because today's large models require more memory and compute than can be provided by a single GPU. Distributed models are generally produced by programmers who take a sequential model specification and apply several distribution strategies to distribute state and computation across GPUs. Unfortunately, bugs can be introduced in the process, and a distributed model implementation's outputs might differ from the sequential model'…

Baidu stock fell as much as 9.8% in Hong Kong on Friday after its latest AI model Ernie 5.0 fails to impress investors (Bloomberg)
https://www.bloomberg.com/news/articles/2025-11-14/baidu-slumps-as-latest-ai-model-fails-to-im…

Ego-Vision World Model for Humanoid Contact Planning
Hang Liu, Yuman Gao, Sangli Teng, Yufeng Chi, Yakun Sophia Shao, Zhongyu Li, Maani Ghaffari, Koushil Sreenath
https://arxiv.org/abs/2510.11682

Ego-Vision World Model for Humanoid Contact Planning
Enabling humanoid robots to exploit physical contact, rather than simply avoid collisions, is crucial for autonomy in unstructured environments. Traditional optimization-based planners struggle with contact complexity, while on-policy reinforcement learning (RL) is sample-inefficient and has limited multi-task ability. We propose a framework combining a learned world model with sampling-based Model Predictive Control (MPC), trained on a demonstration-free offline dataset to predict future outco…

2025 Week 2 NFL picks, odds, best bets from proven computer model: This 5-way football parlay pays around 25-1

https://www.cbssports.com/nfl/news/2025-we…

Large Language Model Prompt Datasets: An In-depth Analysis and Insights
Yuanming Zhang, Yan Lin, Arijit Khan, Huaiyu Wan
https://arxiv.org/abs/2510.09316 https://

Large Language Model Prompt Datasets: An In-depth Analysis and Insights
A prompt is a natural language instruction that defines a specific task for a large language model (LLM) and serves as the primary interface for human-LLM interaction. With the growing deployment of LLMs, diverse prompt datasets are emerging from platforms such as GitHub and social media. These datasets span a wide array of applications and content types, facilitating both broader LLM utilization and improved prompt engineering. In this work, we--for the first time--have compiled an extensive l…

Titans Revisited: A Lightweight Reimplementation and Critical Analysis of a Test-Time Memory Model
Gavriel Di Nepi, Federico Siciliano, Fabrizio Silvestri
https://arxiv.org/abs/2510.09551

Titans Revisited: A Lightweight Reimplementation and Critical Analysis of a Test-Time Memory Model
By the end of 2024, Google researchers introduced Titans: Learning at Test Time, a neural memory model achieving strong empirical results across multiple tasks. However, the lack of publicly available code and ambiguities in the original description hinder reproducibility. In this work, we present a lightweight reimplementation of Titans and conduct a comprehensive evaluation on Masked Language Modeling, Time Series Forecasting, and Recommendation tasks. Our results reveal that Titans does not …

And more to read in your freetime, if you are interested in AI, from Bluesky, Phillip Isola.
"Over the past year, my lab has been working on fleshing out theory applications of the Platonic Representation Hypothesis.
Today I want to share two new works on this topic:"
Eliciting higher alignment:
https://arxiv.org/…

Words That Make Language Models Perceive
Large language models (LLMs) trained purely on text ostensibly lack any direct perceptual experience, yet their internal representations are implicitly shaped by multimodal regularities encoded in language. We test the hypothesis that explicit sensory prompting can surface this latent structure, bringing a text-only LLM into closer representational alignment with specialist vision and audio encoders. When a sensory prompt tells the model to 'see' or 'hear', it cues the model to resolve its next…

A Model-Driven Engineering Approach to AI-Powered Healthcare Platforms
Mira Raheem, Amal Elgammal, Michael Papazoglou, Bernd Kr\"amer, Neamat El-Tazi
https://arxiv.org/abs/2510.09308

A Model-Driven Engineering Approach to AI-Powered Healthcare Platforms
Artificial intelligence (AI) has the potential to transform healthcare by supporting more accurate diagnoses and personalized treatments. However, its adoption in practice remains constrained by fragmented data sources, strict privacy rules, and the technical complexity of building reliable clinical systems. To address these challenges, we introduce a model driven engineering (MDE) framework designed specifically for healthcare AI. The framework relies on formal metamodels, domain-specific lang…

Consistency assessment and regional sample size calculation for MRCTs under random effects model
Xinru Ren, Jin Xu
https://arxiv.org/abs/2508.09443 https://

Consistency assessment and regional sample size calculation for MRCTs under random effects model
Multi-regional clinical trials (MRCTs) have become common practice for drug development and global registration. Once overall significance is established, demonstrating regional consistency is critical for local health authorities. Methods for evaluating such consistency and calculating regional sample sizes have been proposed based on the fixed effects model using various criteria. To better account for the heterogeneity of treatment effects across regions, the random effects model naturally a…

Vikings vs. Falcons props, picks, SportsLine Machine Learning Model AI predictions: Robinson over 65.5 yards

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

Structure-preserving finite element approximations of a hybrid relativistic cold fluid-particle model
Tileuzhan Mukhamet, Katharina Kormann
https://arxiv.org/abs/2510.11500 http…

Structure-preserving finite element approximations of a hybrid relativistic cold fluid-particle model
We derive mixed finite element discretizations of a cold relativistics fluid model from approximations of the Poisson bracket that preserve mass, energy and the divergence constraints. For time-discretization we derive an implicit energy-conserving average-vector field method or apply an explicit strong-stability preserving Runge-Kutta scheme. We also consider a coupling of the fluid model to relativistic particles. We perform a numerical study of the scheme which shows convergence and conserva…

DITTO: A Spoofing Attack Framework on Watermarked LLMs via Knowledge Distillation
Hyeseon Ahn, Shinwoo Park, Yo-Sub Han
https://arxiv.org/abs/2510.10987 https://

DITTO: A Spoofing Attack Framework on Watermarked LLMs via Knowledge Distillation
The promise of LLM watermarking rests on a core assumption that a specific watermark proves authorship by a specific model. We demonstrate that this assumption is dangerously flawed. We introduce the threat of watermark spoofing, a sophisticated attack that allows a malicious model to generate text containing the authentic-looking watermark of a trusted, victim model. This enables the seamless misattribution of harmful content, such as disinformation, to reputable sources. The key to our attack…

Alibaba releases Qwen3-Next, a new model architecture optimized for long-context understanding, large parameter scale, and better computational efficiency (Crystal Liu/Alizila)
https://www.alizila.com/qwen3-next-a-new-generation-of-ultra-ef…

Qwen3-Next: A New Generation of Ultra-Efficient Model Architecture Unveiled
Alibaba has launched Qwen3-Next, a brand-new model architecture optimized for long-context understanding, large parameter scale, and unprecedented

Learning magic in the Schwinger model
Samuel Crew, Hsueh Hao Lu
https://arxiv.org/abs/2508.09640 https://arxiv.org/pdf/2508.09640

Learning magic in the Schwinger model
We demonstrate the use of variational neural network quantum states to study non-stabilizerness in qubit-regularised quantum field theory. Applying the methodology recently introduced by Sinibaldi et al., we numerically compute the stabilizer Rényi entropy of ground states of the Schwinger model with a topological term. We examine how the magic content of these states depends on the separation between external probe charges, providing insight into the classical hardness of simulating gauge the…

Breaking the Likelihood Trap: Consistent Generative Recommendation with Graph-structured Model
Qiya Yang, Xiaoxi Liang, Zeping Xiao, Yingjie Deng, Yalong Wang, Yongqi Liu, Han Li
https://arxiv.org/abs/2510.10127

Breaking the Likelihood Trap: Consistent Generative Recommendation with Graph-structured Model
Reranking, as the final stage of recommender systems, demands real-time inference, accuracy, and diversity. It plays a crucial role in determining the final exposure, directly influencing user experience. Recently, generative reranking has gained increasing attention for its strong ability to model complex dependencies among items. However, most existing methods suffer from the "likelihood trap", where high-likelihood sequences are often perceived as low-quality by humans. These models tend to …

How many samples to label for an application given a foundation model? Chest X-ray classification study
Nikolay Nechaev, Evgenia Przhezdzetskaya, Viktor Gombolevskiy, Dmitry Umerenkov, Dmitry Dylov
https://arxiv.org/abs/2510.11553

How many samples to label for an application given a foundation model? Chest X-ray classification study
Chest X-ray classification is vital yet resource-intensive, typically demanding extensive annotated data for accurate diagnosis. Foundation models mitigate this reliance, but how many labeled samples are required remains unclear. We systematically evaluate the use of power-law fits to predict the training size necessary for specific ROC-AUC thresholds. Testing multiple pathologies and foundation models, we find XrayCLIP and XraySigLIP achieve strong performance with significantly fewer labeled …

Context-Aware Model-Based Reinforcement Learning for Autonomous Racing
Emran Yasser Moustafa, Ivana Dusparic
https://arxiv.org/abs/2510.11501 https://arxiv…

Context-Aware Model-Based Reinforcement Learning for Autonomous Racing
Autonomous vehicles have shown promising potential to be a groundbreaking technology for improving the safety of road users. For these vehicles, as well as many other safety-critical robotic technologies, to be deployed in real-world applications, we require algorithms that can generalize well to unseen scenarios and data. Model-based reinforcement learning algorithms (MBRL) have demonstrated state-of-the-art performance and data efficiency across a diverse set of domains. However, these algori…

A Parametric Power Model of Upper Mid-Band (FR3) Base Stations for 6G
Emanuele Peschiera, Sangbu Yun, Youngjoo Lee, Liesbet Van der Perre, Fran\c{c}ois Rottenberg
https://arxiv.org/abs/2510.10647

A Parametric Power Model of Upper Mid-Band (FR3) Base Stations for 6G
Increasing attention is given to the upper mid-band or Frequency Range 3 (FR3), from 7 to 24 GHz, in the research towards sixth-generation (6G) networks. Promises of offering large data rates at favorable propagation conditions are leading to novel FR3 base station (BS) architectures, with up to thousands of antenna elements and radio-frequency (RF) chains. This work investigates the power consumption of prospective FR3 BSs and its relation to the delivered data rates. We model the power consum…

SS-DPPN: A self-supervised dual-path foundation model for the generalizable cardiac audio representation
Ummy Maria Muna, Md Mehedi Hasan Shawon, Md Jobayer, Sumaiya Akter, Md Rakibul Hasan, Md. Golam Rabiul Alam
https://arxiv.org/abs/2510.10719

SS-DPPN: A self-supervised dual-path foundation model for the generalizable cardiac audio representation
The automated analysis of phonocardiograms is vital for the early diagnosis of cardiovascular disease, yet supervised deep learning is often constrained by the scarcity of expert-annotated data. In this paper, we propose the Self-Supervised Dual-Path Prototypical Network (SS-DPPN), a foundation model for cardiac audio representation and classification from unlabeled data. The framework introduces a dual-path contrastive learning based architecture that simultaneously processes 1D waveforms and …

Scattering and Absorption of Standard Model Fields by Brane-Localized Schwarzschild--de Sitter Black Holes
Alexey Dubinsky
https://arxiv.org/abs/2510.11643 https://

Scattering and Absorption of Standard Model Fields by Brane-Localized Schwarzschild--de Sitter Black Holes
We investigate the propagation and absorption of Standard Model fields -- scalar, electromagnetic, and Dirac -- on a 3+1-dimensional brane embedded in a higher-dimensional Schwarzschild--de Sitter (SdS) spacetime. Using the effective four-dimensional projection of the Tangherlini metric, we compute grey-body factors (GBFs) and absorption cross-sections for each spin sector by means of the sixth-order WKB method and, independently, via the recently proposed correspondence between quasinormal mod…

Can We Reliably Rank Model Performance across Domains without Labeled Data?
Veronica Rammouz, Aaron Gonzalez, Carlos Cruzportillo, Adrian Tan, Nicole Beebe, Anthony Rios
https://arxiv.org/abs/2510.09519

Can We Reliably Rank Model Performance across Domains without Labeled Data?
Estimating model performance without labels is an important goal for understanding how NLP models generalize. While prior work has proposed measures based on dataset similarity or predicted correctness, it remains unclear when these estimates produce reliable performance rankings across domains. In this paper, we analyze the factors that affect ranking reliability using a two-step evaluation setup with four base classifiers and several large language models as error predictors. Experiments on t…

Inclusive processes in the modified Quark-Gluon String Model
M. N. Sergeenko
https://arxiv.org/abs/2510.09284 https://arxiv.org/pdf/2510.09284

Inclusive processes in the modified Quark-Gluon String Model
Inclusive processes at high energies are studied in a non-perturbative approach in QCD using a modified Quark-Gluon String Model. Theoretical and experimental aspects of diffraction dissociation are discussed. In the calculations of cross sections, the parameters of complex nonlinear trajectories of Pomeranchuk and Reggeons are used. Particular attention is paid to elastic and inelastic processes at LHC energies.

Discovering interpretable piecewise nonlinear model predictive control laws via symbolic decision trees
Ilias Mitrai
https://arxiv.org/abs/2510.10411 https://

Discovering interpretable piecewise nonlinear model predictive control laws via symbolic decision trees
In this paper, we propose symbolic decision trees as surrogate models for approximating model predictive control laws. The proposed approach learns simultaneously the partition of the input domain (splitting logic) as well as local nonlinear expressions for predicting the control action leading to interpretable piecewise nonlinear control laws. The local nonlinear expressions are determined by the learning problem and are modeled using a set of basis functions. The learning task is posed as a m…

NFL player props, odds, lines: Week 2, 2025 NFL picks, SportsLine Machine Learning Model AI predictions, SGP

https://www.cbssports.com/nfl/news/nfl-pla…

A model for transport of soluble surfactants in two-phase flows
Suhas S. Jain
https://arxiv.org/abs/2510.10857 https://arxiv.org/pdf/2510.10857

A model for transport of soluble surfactants in two-phase flows
In this work, we propose a novel transport model for soluble surfactants in two-phase flows. In a two-phase flow, the soluble surfactants can adsorb/desorb from/into the bulk of any of the phases to the interface and can modify the interface properties. This results in sharp gradients in the surfactant concentration on the interface and also between the two phases in the bulk when there is selective adsorption/desorption, presenting a serious challenge for the numerical simulations. To overco…

Reactive Model Predictive Contouring Control for Robot Manipulators
Junheon Yoon, Woo-Jeong Baek, Jaeheung Park
https://arxiv.org/abs/2508.09502 https://ar…

Reactive Model Predictive Contouring Control for Robot Manipulators
This contribution presents a robot path-following framework via Reactive Model Predictive Contouring Control (RMPCC) that successfully avoids obstacles, singularities and self-collisions in dynamic environments at 100 Hz. Many path-following methods rely on the time parametrization, but struggle to handle collision and singularity avoidance while adhering kinematic limits or other constraints. Specifically, the error between the desired path and the actual position can become large when executi…

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…

Falcons vs. Vikings prediction, odds, time: 2025 NFL Week 2 Sunday Night Football picks by proven model

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

SP-MoE: Speculative Decoding and Prefetching for Accelerating MoE-based Model Inference
Liangkun Chen, Zijian Wen, Tian Wu, Xiaoxi Zhang, Chuan Wu
https://arxiv.org/abs/2510.10302

SP-MoE: Speculative Decoding and Prefetching for Accelerating MoE-based Model Inference
The Mixture-of-Experts (MoE) architecture has been widely adopted in large language models (LLMs) to reduce computation cost through model sparsity. Employing speculative decoding (SD) can further accelerate MoE inference by drafting multiple tokens per step and verifying them in parallel. However, combining MoE with SD inflates GPU memory and aggravates CPU-GPU bandwidth contention during multi-token verification. Existing MoE offloading systems are SD-agnostic and do not address this bottlene…

Near-Optimal Second-Order Guarantees for Model-Based Adversarial Imitation Learning
Shangzhe Li, Dongruo Zhou, Weitong Zhang
https://arxiv.org/abs/2510.09487 https://

Near-Optimal Second-Order Guarantees for Model-Based Adversarial Imitation Learning
We study online adversarial imitation learning (AIL), where an agent learns from offline expert demonstrations and interacts with the environment online without access to rewards. Despite strong empirical results, the benefits of online interaction and the impact of stochasticity remain poorly understood. We address these gaps by introducing a model-based AIL algorithm (MB-AIL) and establish its horizon-free, second-order sample-complexity guarantees under general function approximations for bo…

Fei-Fei Li's World Labs launches Marble, its first world model to let users turn prompts, photos, and other media into editable 3D environments, after a beta (Rebecca Bellan/TechCrunch)
https://techcrunch.com/2025/11/12/fei-

Fei-Fei Li's World Labs speeds up the world model race with Marble, its first commercial product | TechCrunch
Marble is different from competitors like Odyssey, Decart, and Google's Genie because it creates persistent, downloadable 3D environments rather than generating worlds on-the-fly as you explore.

Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Study
Mahdi Dhaini, Juraj Vladika, Ege Erdogan, Zineb Attaoui, Gjergji Kasneci
https://arxiv.org/abs/2508.09776

Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Study
In the rapidly evolving field of Explainable Natural Language Processing (NLP), textual explanations, i.e., human-like rationales, are pivotal for explaining model predictions and enriching datasets with interpretable labels. Traditional approaches rely on human annotation, which is costly, labor-intensive, and impedes scalability. In this work, we present an automated framework that leverages multiple state-of-the-art large language models (LLMs) to generate high-quality textual explanations. …

Repulsive Mixture Model with Projection Determinantal Point Process
Ziyi Song, Federico Camerlenghi, Weining Shen, Michele Guindani, Mario Beraha
https://arxiv.org/abs/2510.08838

Repulsive Mixture Model with Projection Determinantal Point Process
In many scientific domains, clustering aims to reveal interpretable latent structure that reflects relevant subpopulations or processes. Widely used Bayesian mixture models for model-based clustering often produce overlapping or redundant components because priors on cluster locations are specified independently, hindering interpretability. To mitigate this, repulsive priors have been proposed to encourage well-separated components, yet existing approaches face both computational and theoretica…

Humanoid Artificial Consciousness Designed with Large Language Model Based on Psychoanalysis and Personality Theory
Sang Hun Kim, Jongmin Lee, Dongkyu Park, So Young Lee, Yosep Chong
https://arxiv.org/abs/2510.09043

Humanoid Artificial Consciousness Designed with Large Language Model Based on Psychoanalysis and Personality Theory
Human consciousness is still a concept hard to define with current scientific understanding. Although Large Language Models (LLMs) have recently demonstrated significant advancements across various domains including translation and summarization, human consciousness is not something to imitate with current upfront technology owing to so-called hallucination. This study, therefore, proposes a novel approach to address these challenges by integrating psychoanalysis and the Myers-Briggs Type Indic…

Scattering in the dual regime of Yang-Baxter deformed O(2N) sigma models
Alexey Bychkov, Boris Nekrasov
https://arxiv.org/abs/2510.11429 https://arxiv.org/…

Scattering in the dual regime of Yang-Baxter deformed O(2N) sigma models
We continue to explore the previously suggested dual regime of Yang-Baxter (YB) deformed $\mathrm{O}(2N)$ sigma models, which is a new one-parametric deformation of the $\mathrm{O}(2N)$ model. It can be obtained from the conventional YB deformed $\mathrm{O}(2N+2)$ sigma model by freezing two isometries. The scattering matrix in the non-deformed $\mathrm{O}(n)$ model is known coincide with the rational $\mathfrak{so}_n$-invariant $R-$matrix. For $n = 2N$ this rational solution allows for two tri…

Data-driven analyses and model-independent fits for present $b\to s \ell \ell$ results
T. Hurth, F. Mahmoudi, Y. Monceaux, S. Neshatpour
https://arxiv.org/abs/2508.09986 https:/…

Data-driven analyses and model-independent fits for present $b\to s \ell \ell$ results
We present a critical assessment of the present $B$ anomalies in the exclusive $b \to s \ell\ell$ mode based on the QCD factorisation approach (QCDf). In particular, we analyse the impact of different local form factor calculations and of the largest bin in the low-$q^2$ region. We also present a model-independent analysis of the new results of the CMS experiment on the $B \to K^* μ^+μ^-$ angular observables and compare them with the corresponding LHCb data. In addition, we update the globa…

Integrating Structure-Aware Attention and Knowledge Graphs in Explainable Recommendation Systems
Shuangquan Lyu, Ming Wang, Huajun Zhang, Jiasen Zheng, Junjiang Lin, Xiaoxuan Sun
https://arxiv.org/abs/2510.10109

Integrating Structure-Aware Attention and Knowledge Graphs in Explainable Recommendation Systems
This paper designs and implements an explainable recommendation model that integrates knowledge graphs with structure-aware attention mechanisms. The model is built on graph neural networks and incorporates a multi-hop neighbor aggregation strategy. By integrating the structural information of knowledge graphs and dynamically assigning importance to different neighbors through an attention mechanism, the model enhances its ability to capture implicit preference relationships. In the proposed me…

iMoWM: Taming Interactive Multi-Modal World Model for Robotic Manipulation
Chuanrui Zhang, Zhengxian Wu, Guanxing Lu, Yansong Tang, Ziwei Wang
https://arxiv.org/abs/2510.09036 h…

iMoWM: Taming Interactive Multi-Modal World Model for Robotic Manipulation
Learned world models hold significant potential for robotic manipulation, as they can serve as simulator for real-world interactions. While extensive progress has been made in 2D video-based world models, these approaches often lack geometric and spatial reasoning, which is essential for capturing the physical structure of the 3D world. To address this limitation, we introduce iMoWM, a novel interactive world model designed to generate color images, depth maps, and robot arm masks in an autoreg…

ShiZhi: A Chinese Lightweight Large Language Model for Court View Generation
Zhitian Hou, Kun Zeng
https://arxiv.org/abs/2510.09297 https://arxiv.org/pdf/2…

ShiZhi: A Chinese Lightweight Large Language Model for Court View Generation
Criminal Court View Generation (CVG) is a fundamental task in legal artificial intelligence, aiming to automatically generate the "Court View" section of a legal case document. Generating court views is challenging due to the diversity and complexity of case facts, and directly generating from raw facts may limit performance. In this paper, we present ShiZhi, the first large language model (LLM) specifically designed for court view generation. We construct a Chinese Court View Generation datase…

Unifying Deductive and Abductive Reasoning in Knowledge Graphs with Masked Diffusion Model
Yisen Gao, Jiaxin Bai, Yi Huang, Xingcheng Fu, Qingyun Sun, Yangqiu Song
https://arxiv.org/abs/2510.11462

Unifying Deductive and Abductive Reasoning in Knowledge Graphs with Masked Diffusion Model
Deductive and abductive reasoning are two critical paradigms for analyzing knowledge graphs, enabling applications from financial query answering to scientific discovery. Deductive reasoning on knowledge graphs usually involves retrieving entities that satisfy a complex logical query, while abductive reasoning generates plausible logical hypotheses from observations. Despite their clear synergistic potential, where deduction can validate hypotheses and abduction can uncover deeper logical patte…

Effects of CPT violation on the neutrino charge radius in the Standard Model Extension
Yuridia Flores Orea, J. Jes\'us Toscano Ch\'avez
https://arxiv.org/abs/2508.09400 …

Effects of CPT violation on the neutrino charge radius in the Standard Model Extension
CPT-odd effects on the neutrino charge radius are studied within the Standard Model Extension. We consider CPT violation from the electroweak Yang-Mills sector, characterized by Lorentz-violating coefficients $(k_1)_μ$ and $(k_2)_μ$, which have positive mass units. The $\barννγ$ vertex arises at tree level via exchange of two $Z$ bosons. Although suppressed by $\frac{1}{m_Z^4}$, this process is notable. The vertex function $Γ_μ$ includes three independent gauge structures satisfying the …

Generalized Jeffreys's approximate objective Bayes factor: Model-selection consistency, finite-sample accuracy, and statistical evidence in 71,126 clinical trial findings
Puneet Velidi, Zhengxiao Wei, Shreena Nisha Kalaria, Yimeng Liu, C\'eline M. Laumont, Brad H. Nelson, Farouk S. Nathoo
https://arxiv.org/abs/2510.10358

Generalized Jeffreys's approximate objective Bayes factor: Model-selection consistency, finite-sample accuracy, and statistical evidence in 71,126 clinical trial findings
Concerns about the misuse and misinterpretation of p-values and statistical significance have motivated alternatives for quantifying evidence. We define a generalized form of Jeffreys's approximate objective Bayes factor (eJAB), a one-line calculation that is a function of the p-value, sample size, and parameter dimension. We establish conditions under which eJAB is model-selection consistent and verify them for ten statistical tests. We assess finite-sample accuracy by comparing eJAB with Mark…

Personalized Product Search Ranking: A Multi-Task Learning Approach with Tabular and Non-Tabular Data
Lalitesh Morishetti, Abhay Kumar, Jonathan Scott, Kaushiki Nag, Gunjan Sharma, Shanu Vashishtha, Rahul Sridhar, Rohit Chatter, Kannan Achan
https://arxiv.org/abs/2508.09636

Personalized Product Search Ranking: A Multi-Task Learning Approach with Tabular and Non-Tabular Data
In this paper, we present a novel model architecture for optimizing personalized product search ranking using a multi-task learning (MTL) framework. Our approach uniquely integrates tabular and non-tabular data, leveraging a pre-trained TinyBERT model for semantic embeddings and a novel sampling technique to capture diverse customer behaviors. We evaluate our model against several baselines, including XGBoost, TabNet, FT-Transformer, DCN-V2, and MMoE, focusing on their ability to handle mixed d…

Model-Assisted and Human-Guided: Perceptions and Practices of Software Professionals Using LLMs for Coding
Italo Santos, Cleyton Magalhaes, Ronnie de Souza Santos
https://arxiv.org/abs/2510.09058

Model-Assisted and Human-Guided: Perceptions and Practices of Software Professionals Using LLMs for Coding
Large Language Models have quickly become a central component of modern software development workflows, and software practitioners are increasingly integrating LLMs into various stages of the software development lifecycle. Despite the growing presence of LLMs, there is still a limited understanding of how these tools are actually used in practice and how professionals perceive their benefits and limitations. This paper presents preliminary findings from a global survey of 131 software practiti…

Joint Model-based Model-free Diffusion for Planning with Constraints
Wonsuhk Jung, Utkarsh A. Mishra, Nadun Ranawaka Arachchige, Yongxin Chen, Danfei Xu, Shreyas Kousik
https://arxiv.org/abs/2509.08775

Joint Model-based Model-free Diffusion for Planning with Constraints
Model-free diffusion planners have shown great promise for robot motion planning, but practical robotic systems often require combining them with model-based optimization modules to enforce constraints, such as safety. Naively integrating these modules presents compatibility challenges when diffusion's multi-modal outputs behave adversarially to optimization-based modules. To address this, we introduce Joint Model-based Model-free Diffusion (JM2D), a novel generative modeling framework. JM2D fo…

2025 Week 7 NFL picks, odds, best bets from proven model: This 5-leg football parlay pays 25-1

https://www.cbssports.com/nfl/news/nfl-parlay-week-7-picks-odds-best-bets/

MATH-Beyond: A Benchmark for RL to Expand Beyond the Base Model
Prasanna Mayilvahanan, Ricardo Dominguez-Olmedo, Thadd\"aus Wiedemer, Wieland Brendel
https://arxiv.org/abs/2510.11653

MATH-Beyond: A Benchmark for RL to Expand Beyond the Base Model
With the advent of DeepSeek-R1, a new wave of reinforcement learning (RL) methods has emerged that seem to unlock stronger mathematical reasoning. However, a closer look at the open-source ecosystem reveals a critical limitation: with sufficiently many draws (e.g., $\texttt{pass@1024}$), many existing base models already solve nearly all questions on widely used math benchmarks such as MATH-500 and AIME 2024. This suggests that the RL fine-tuning methods prevalent in the LLM reasoning literatur…

Analyzing and Internalizing Complex Policy Documents for LLM Agents
Jiateng Liu, Zhenhailong Wang, Xiaojiang Huang, Yingjie Li, Xing Fan, Xiang Li, Chenlei Guo, Ruhi Sarikaya, Heng Ji
https://arxiv.org/abs/2510.11588

Analyzing and Internalizing Complex Policy Documents for LLM Agents
Large Language Model (LLM)-based agentic systems rely on in-context policy documents encoding diverse business rules. As requirements grow, these documents expand rapidly, causing high computational overhead. This motivates developing internalization methods that embed policy documents into model priors while preserving performance. Prior prompt compression work targets generic prompts, but agentic policy documents span multiple complexity levels and require deeper reasoning, making internaliza…

ByteDance launches Seedream 4.0, an AI image model it claims can beat Google's viral "nano banana" model in prompt adherence, alignment, and aesthetics (Vincent Chow/South China Morning Post)
https://www.scmp.com/tech/big-tech/article…

ByteDance unveils new AI image model to rival Google DeepMind’s ‘Nano Banana’
ByteDance claims that Seedream 4.0 beat Gemini 2.5 Flash Image for image generation and editing on its internal evaluation benchmark.

Week 7 NFL odds, lines, best bets, spreads: 2025 predictions: Proven model backs Vikings and Broncos

https://www.cbssports.com/nfl/news/nfl-odds-week-7-lines-best-bets-spreads-pr…

NFL Week 2 projected scores: Model predicts point spreads and totals for every game https://www.nytimes.com/athletic/6620906/2025/09/11/nfl-week-2-projected-scores-model-point-spreads-totals/

Incentivizing Time-Aware Fairness in Data Sharing
Jiangwei Chen, Kieu Thao Nguyen Pham, Rachael Hwee Ling Sim, Arun Verma, Zhaoxuan Wu, Chuan-Sheng Foo, Bryan Kian Hsiang Low
https://arxiv.org/abs/2510.09240

Incentivizing Time-Aware Fairness in Data Sharing
In collaborative data sharing and machine learning, multiple parties aggregate their data resources to train a machine learning model with better model performance. However, as the parties incur data collection costs, they are only willing to do so when guaranteed incentives, such as fairness and individual rationality. Existing frameworks assume that all parties join the collaboration simultaneously, which does not hold in many real-world scenarios. Due to the long processing time for data cle…

Whole Body Model Predictive Control for Spin-Aware Quadrupedal Table Tennis
David Nguyen, Zulfiqar Zaidi, Kevin Karol, Jessica Hodgins, Zhaoming Xie
https://arxiv.org/abs/2510.08754

Whole Body Model Predictive Control for Spin-Aware Quadrupedal Table Tennis
Developing table tennis robots that mirror human speed, accuracy, and ability to predict and respond to the full range of ball spins remains a significant challenge for legged robots. To demonstrate these capabilities we present a system to play dynamic table tennis for quadrupedal robots that integrates high speed perception, trajectory prediction, and agile control. Our system uses external cameras for high-speed ball localization, physical models with learned residuals to infer spin and pred…

Bengals vs. Steelers prediction, odds, time: 2025 NFL Week 7 Thursday Night Football picks by proven model

https://www.cbssports.com/nfl/news/bengals-steelers-pre…

Baidu unveils Ernie 5.0, an AI model to process and generate text, images, audio, and video, claiming it beats GPT-5-High and Gemini 2.5 Pro on some benchmarks (Carl Franzen/VentureBeat)
https://venturebeat.com/ai/baidu-unveils-proprietary-ern…

PracMHBench: Re-evaluating Model-Heterogeneous Federated Learning Based on Practical Edge Device Constraints
Yuanchun Guo, Bingyan Liu, Yulong Sha, Zhensheng Xian
https://arxiv.org/abs/2509.08750

PracMHBench: Re-evaluating Model-Heterogeneous Federated Learning Based on Practical Edge Device Constraints
Federating heterogeneous models on edge devices with diverse resource constraints has been a notable trend in recent years. Compared to traditional federated learning (FL) that assumes an identical model architecture to cooperate, model-heterogeneous FL is more practical and flexible since the model can be customized to satisfy the deployment requirement. Unfortunately, no prior work ever dives into the existing model-heterogeneous FL algorithms under the practical edge device constraints and p…

Google releases VaultGemma, a 1B-parameter model it says is the largest open LLM trained from scratch with differential privacy, on Hugging Face and Kaggle (Google Research)
https://research.google/blog/vaultgemma-the-worlds-most-capable-differenti…

VaultGemma: The world's most capable differentially private LLM

Computer model makes NFL against the spread, over/under and money-line picks for every Week 2 game

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

Anthropic open sources a method to score AI model political evenhandedness; Gemini 2.5 Pro got 97%, Grok 4 96%, Claude Opus 4.1 95%, GPT-5 89%, and Llama 4 66% (Ina Fried/Axios)
https://www.axios.com/2025/11/13/anthropic-bot-bias-data

Anthropic tries to measure bot bias
There's no consensus over what constitutes political bias in AI systems.

2025 Week 2 NFL picks, odds, best bets from proven model: This 5-way football parlay returns around 25-1

https://www.cbssports.com/nfl/news/2025-we

Week 2 NFL odds, lines, betting picks, spreads: 2025 predictions: Model loves Cowboys and Cardinals

https://www.cbssports.com/nfl/news/week-2-

Microsoft unveils MAI-Image-1, its first text-to-image AI model developed in house, and says it excels at photorealistic imagery, like lighting and landscapes (Andrew J. Hawkins/The Verge)
https://www.theverge.com/news/798923/microsoft-ai-image-generator-in-house…

Microsoft AI announces first image generator created in-house
Microsoft AI announced a new text-to-image generator developed in-house.