Archives AI News

arXiv:2306.11246v3 Announce Type: replace Abstract: We argue that inventory management presents unique opportunities for the reliable application of deep reinforcement learning (DRL). To enable this, we emphasize and test two complementary techniques. The first is Hindsight Differentiable Policy Optimization (HDPO), which uses pathwise gradients from offline counterfactual simulations to directly and efficiently optimize policy performance. Unlike standard policy gradient methods that rely on high-variance score-function estimators, HDPO computes gradients by differentiating through the known system dynamics. Via extensive benchmarking, we show that HDPO recovers near-optimal policies in settings with known or bounded optima, is more robust than variants of the REINFORCE algorithm, and significantly outperforms generalized newsvendor heuristics on problems using real time series data. Our second technique aligns neural policy architectures with the topology of the inventory network. We exploit Graph Neural Networks (GNNs) as a natural inductive bias for encoding supply chain structure, demonstrate that they can represent optimal and near-optimal policies in two theoretical settings, and empirically show that they reduce data requirements across six diverse inventory problems. A key obstacle to progress in this area is the lack of standardized benchmark problems. To address this gap, we open-source a suite of benchmark environments, along with our full codebase, to promote transparency and reproducibility. All resources are available at github.com/MatiasAlvo/Neural_inventory_control.

arXiv:2509.09208v1 Announce Type: new Abstract: Constrained Reinforcement Learning (RL) aims to maximize the return while adhering to predefined constraint limits, which represent domain-specific safety requirements. In continuous control settings, where learning agents govern system actions, balancing the trade-off between reward maximization and constraint satisfaction remains a significant challenge. Policy optimization methods often exhibit instability near constraint boundaries, resulting in suboptimal training performance. To address this issue, we introduce a novel approach that integrates an adaptive incentive mechanism in addition to the reward structure to stay within the constraint bound before approaching the constraint boundary. Building on this insight, we propose Incrementally Penalized Proximal Policy Optimization (IP3O), a practical algorithm that enforces a progressively increasing penalty to stabilize training dynamics. Through empirical evaluation on benchmark environments, we demonstrate the efficacy of IP3O compared to the performance of state-of-the-art Safe RL algorithms. Furthermore, we provide theoretical guarantees by deriving a bound on the worst-case error of the optimality achieved by our algorithm.

arXiv:2406.11703v3 Announce Type: replace Abstract: The phenomenon of double descent has challenged the traditional bias-variance trade-off in supervised learning but remains unexplored in unsupervised learning, with some studies arguing for its absence. In this study, we first demonstrate analytically that double descent does not occur in linear unsupervised autoencoders (AEs). In contrast, we show for the first time that both double and triple descent can be observed with nonlinear AEs across various data models and architectural designs. We examine the effects of partial sample and feature noise and highlight the importance of bottleneck size in influencing the double descent curve. Through extensive experiments on both synthetic and real datasets, we uncover model-wise, epoch-wise, and sample-wise double descent across several data types and architectures. Our findings indicate that over-parameterized models not only improve reconstruction but also enhance performance in downstream tasks such as anomaly detection and domain adaptation, highlighting their practical value in complex real-world scenarios.

arXiv:2509.09214v1 Announce Type: new Abstract: Agro-tourism serves as a strategic economic model designed to facilitate rural development by diversifying income streams for local communities like farmers while promoting the conservation of indigenous cultural heritage and traditional agricultural practices. As a very booming subdomain of tourism, there is a need to study the strategies for the growth of Agro-tourism in detail. The current study has identified the important indicators for the growth and enhancement of agro-tourism. The study is conducted in two phases: identification of the important indicators through a comprehensive literature review and in the second phase state-of-the-art techniques were used to identify the important indicators for the growth of agro-tourism. The indicators are also called features synonymously, the machine learning models for feature selection were applied and it was observed that the Least Absolute Shrinkage and Selection Operator (LASSO) method combined with, the machine Learning Classifiers such as Logistic Regression (LR), Decision Trees (DT), Random Forest (RF) Tree, and Extreme Gradient Boosting (XGBOOST) models were used to suggest the growth of the agro-tourism. The results show that with the LASSO method, LR model gives the highest classification accuracy of 98% in 70-30% train-test data followed by RF with 95% accuracy. Similarly, in the 80-20% train-test data LR maintains the highest accuracy at 99%, while DT and XGBoost follow with 97% accuracy.

arXiv:2509.01106v2 Announce Type: replace Abstract: We introduce Robix, a unified model that integrates robot reasoning, task planning, and natural language interaction within a single vision-language architecture. Acting as the high-level cognitive layer in a hierarchical robot system, Robix dynamically generates atomic commands for the low-level controller and verbal responses for human interaction, enabling robots to follow complex instructions, plan long-horizon tasks, and interact naturally with human within an end-to-end framework. Robix further introduces novel capabilities such as proactive dialogue, real-time interruption handling, and context-aware commonsense reasoning during task execution. At its core, Robix leverages chain-of-thought reasoning and adopts a three-stage training strategy: (1) continued pretraining to enhance foundational embodied reasoning abilities including 3D spatial understanding, visual grounding, and task-centric reasoning; (2) supervised finetuning to model human-robot interaction and task planning as a unified reasoning-action sequence; and (3) reinforcement learning to improve reasoning-action consistency and long-horizon task coherence. Extensive experiments demonstrate that Robix outperforms both open-source and commercial baselines (e.g., GPT-4o and Gemini 2.5 Pro) in interactive task execution, demonstrating strong generalization across diverse instruction types (e.g., open-ended, multi-stage, constrained, invalid, and interrupted) and various user-involved tasks such as table bussing, grocery shopping, and dietary filtering.

arXiv:2509.09597v1 Announce Type: cross Abstract: Graph alignment-the problem of identifying corresponding nodes across multiple graphs-is fundamental to numerous applications. Most existing unsupervised methods embed node features into latent representations to enable cross-graph comparison without ground-truth correspondences. However, these methods suffer from two critical limitations: the degradation of node distinctiveness due to oversmoothing in GNN-based embeddings, and the misalignment of latent spaces across graphs caused by structural noise, feature heterogeneity, and training instability, ultimately leading to unreliable node correspondences. We propose a novel graph alignment framework that simultaneously enhances node distinctiveness and enforces geometric consistency across latent spaces. Our approach introduces a dual-pass encoder that combines low-pass and high-pass spectral filters to generate embeddings that are both structure-aware and highly discriminative. To address latent space misalignment, we incorporate a geometry-aware functional map module that learns bijective and isometric transformations between graph embeddings, ensuring consistent geometric relationships across different representations. Extensive experiments on graph benchmarks demonstrate that our method consistently outperforms existing unsupervised alignment baselines, exhibiting superior robustness to structural inconsistencies and challenging alignment scenarios. Additionally, comprehensive evaluation on vision-language benchmarks using diverse pretrained models shows that our framework effectively generalizes beyond graph domains, enabling unsupervised alignment of vision and language representations.

arXiv:2509.09679v1 Announce Type: cross Abstract: Large language models require massive memory footprints, severely limiting deployment on consumer hardware. Quantization reduces memory through lower numerical precision, but extreme 2-bit quantization suffers from catastrophic performance loss due to outliers in activations. Rotation-based methods such as QuIP and QuaRot apply orthogonal transforms to eliminate outliers before quantization, using computational invariance: $mathbf{y} = mathbf{Wx} = (mathbf{WQ}^T)(mathbf{Qx})$ for orthogonal $mathbf{Q}$. However, these methods use fixed transforms--Hadamard matrices achieving optimal worst-case coherence $mu = 1/sqrt{n}$--that cannot adapt to specific weight distributions. We identify that different transformer layers exhibit distinct outlier patterns, motivating layer-adaptive rotations rather than one-size-fits-all approaches. We propose ButterflyQuant, which replaces Hadamard rotations with learnable butterfly transforms parameterized by continuous Givens rotation angles. Unlike Hadamard's discrete ${+1, -1}$ entries that are non-differentiable and prohibit gradient-based learning, butterfly transforms' continuous parameterization enables smooth optimization while guaranteeing orthogonality by construction. This orthogonal constraint ensures theoretical guarantees in outlier suppression while achieving $O(n log n)$ computational complexity with only $frac{n log n}{2}$ learnable parameters. We further introduce a uniformity regularization on post-transformation activations to promote smoother distributions amenable to quantization. Learning requires only 128 calibration samples and converges in minutes on a single GPU--a negligible one-time cost. On LLaMA-2-7B with 2-bit quantization, ButterflyQuant achieves 15.4 perplexity versus 22.1 for QuaRot.

arXiv:2509.09127v1 Announce Type: new Abstract: Anti-money laundering (AML) actions and measurements are among the priorities of financial institutions, for which machine learning (ML) has shown to have a high potential. In this paper, we propose a comprehensive and systematic approach for developing ML pipelines to identify high-risk bank clients in a dataset curated for Task 1 of the University of Toronto 2023-2024 Institute for Management and Innovation (IMI) Big Data and Artificial Intelligence Competition. The dataset included 195,789 customer IDs, and we employed a 16-step design and statistical analysis to ensure the final pipeline was robust. We also framed the data in a SQLite database, developed SQL-based feature engineering algorithms, connected our pre-trained model to the database, and made it inference-ready, and provided explainable artificial intelligence (XAI) modules to derive feature importance. Our pipeline achieved a mean area under the receiver operating characteristic curve (AUROC) of 0.961 with a standard deviation (SD) of 0.005. The proposed pipeline achieved second place in the competition.

arXiv:2506.06485v2 Announce Type: replace-cross Abstract: Large Language Models require both contextual knowledge and parametric memory, but these sources can disagree. Prior investigations on contextual question answering tasks report a preference toward parametric knowledge under conflict, yet they focus almost exclusively on tasks that should always rely on the given passage, leaving open how this behavior manifests when tasks demand different amounts and kinds of knowledge. We study this question with a model-agnostic diagnostic framework that (i) automatically detects disagreements between a model's beliefs and a curated knowledge set, and (ii) injects controlled conflicts into tasks. The resulting datasets span two orthogonal dimensions: task knowledge reliance and conflict plausibility. Evaluating representative open-source LLMs, we find that: (1) performance degradation from conflict correlates with a task's knowledge reliance; (2) explanatory rationales and simple reiteration both increase context reliance-helpful for context-only tasks but harmful when parametric knowledge should dominate; (3) These behaviors raise concerns about the validity of model-based evaluation and underscore the need to account for knowledge conflict in the deployment of LLMs.

arXiv:2509.09066v1 Announce Type: new Abstract: The cold-start user issue further compromises the effectiveness of recommender systems in limiting access to the historical behavioral information. It is an effective pipeline to optimize instructional prompts on a few-shot large language model (LLM) used in recommender tasks. We introduce a context-conditioned prompt formulation method P(u, Ds) rightarrow Rwidehat, where u is a cold-start user profile, Ds is a curated support set, and Rwidehat is the predicted ranked list of items. Based on systematic experimentation with transformer-based autoregressive LLMs (BioGPT, LLaMA-2, GPT-4), we provide empirical evidence that optimal exemplar injection and instruction structuring can significantly improve the precision@k and NDCG scores of such models in low-data settings. The pipeline uses token-level alignments and embedding space regularization with a greater semantic fidelity. Our findings not only show that timely composition is not merely syntactic but also functional as it is in direct control of attention scales and decoder conduct through inference. This paper shows that prompt-based adaptation may be considered one of the ways to address cold-start recommendation issues in LLM-based pipelines.