Provably Efficient Reward Transfer in Reinforcement Learning with Discrete Markov Decision Processescs.AI updates on arXiv.org arXiv:2503.13414v2 Announce Type: replace-cross
Abstract: In this paper, we propose a new solution to reward adaptation (RA) in reinforcement learning, where the agent adapts to a target reward function based on one or more existing source behaviors learned a priori under the same domain dynamics but different reward functions. While learning the target behavior from scratch is possible, it is often inefficient given the available source behaviors. Our work introduces a new approach to RA through the manipulation of Q-functions. Assuming the target reward function is a known function of the source reward functions, we compute bounds on the Q-function and present an iterative process (akin to value iteration) to tighten these bounds. Such bounds enable action pruning in the target domain before learning even starts. We refer to this method as “Q-Manipulation” (Q-M). The iteration process assumes access to a lite-model, which is easy to provide or learn. We formally prove that Q-M, under discrete domains, does not affect the optimality of the returned policy and show that it is provably efficient in terms of sample complexity in a probabilistic sense. Q-M is evaluated in a variety of synthetic and simulation domains to demonstrate its effectiveness, generalizability, and practicality.
arXiv:2503.13414v2 Announce Type: replace-cross
Abstract: In this paper, we propose a new solution to reward adaptation (RA) in reinforcement learning, where the agent adapts to a target reward function based on one or more existing source behaviors learned a priori under the same domain dynamics but different reward functions. While learning the target behavior from scratch is possible, it is often inefficient given the available source behaviors. Our work introduces a new approach to RA through the manipulation of Q-functions. Assuming the target reward function is a known function of the source reward functions, we compute bounds on the Q-function and present an iterative process (akin to value iteration) to tighten these bounds. Such bounds enable action pruning in the target domain before learning even starts. We refer to this method as “Q-Manipulation” (Q-M). The iteration process assumes access to a lite-model, which is easy to provide or learn. We formally prove that Q-M, under discrete domains, does not affect the optimality of the returned policy and show that it is provably efficient in terms of sample complexity in a probabilistic sense. Q-M is evaluated in a variety of synthetic and simulation domains to demonstrate its effectiveness, generalizability, and practicality. Read More
How To Set Business Goals You’ll Actually Reach (Sponsored)KDnuggets What you need is a system to support the formation of goals within a structure that enables turning these broad ambitions into concrete, achievable targets. This article will provide a simple three-step framework to do so.
What you need is a system to support the formation of goals within a structure that enables turning these broad ambitions into concrete, achievable targets. This article will provide a simple three-step framework to do so. Read More
Implementing the Fourier Transform Numerically in Python: A Step-by-Step GuideTowards Data Science What if the FFT functions in NumPy and SciPy don’t actually compute the Fourier transform you think they do?
The post Implementing the Fourier Transform Numerically in Python: A Step-by-Step Guide appeared first on Towards Data Science.
What if the FFT functions in NumPy and SciPy don’t actually compute the Fourier transform you think they do?
The post Implementing the Fourier Transform Numerically in Python: A Step-by-Step Guide appeared first on Towards Data Science. Read More
5 Useful Python Scripts for Busy Data AnalystsKDnuggets As a data analyst, your time is better spent on insights, not repetitive tasks. These five Python scripts help you work faster, cleaner, and smarter.
As a data analyst, your time is better spent on insights, not repetitive tasks. These five Python scripts help you work faster, cleaner, and smarter. Read More
From Observations to Parameters: Detecting Changepoint in Nonlinear Dynamics with Simulation-based Inferencecs.AI updates on arXiv.org arXiv:2510.17933v1 Announce Type: cross
Abstract: Detecting regime shifts in chaotic time series is hard because observation-space signals are entangled with intrinsic variability. We propose Parameter–Space Changepoint Detection (Param–CPD), a two–stage framework that first amortizes Bayesian inference of governing parameters with a neural posterior estimator trained by simulation-based inference, and then applies a standard CPD algorithm to the resulting parameter trajectory. On Lorenz–63 with piecewise-constant parameters, Param–CPD improves F1, reduces localization error, and lowers false positives compared to observation–space baselines. We further verify identifiability and calibration of the inferred posteriors on stationary trajectories, explaining why parameter space offers a cleaner detection signal. Robustness analyses over tolerance, window length, and noise indicate consistent gains. Our results show that operating in a physically interpretable parameter space enables accurate and interpretable changepoint detection in nonlinear dynamical systems.
arXiv:2510.17933v1 Announce Type: cross
Abstract: Detecting regime shifts in chaotic time series is hard because observation-space signals are entangled with intrinsic variability. We propose Parameter–Space Changepoint Detection (Param–CPD), a two–stage framework that first amortizes Bayesian inference of governing parameters with a neural posterior estimator trained by simulation-based inference, and then applies a standard CPD algorithm to the resulting parameter trajectory. On Lorenz–63 with piecewise-constant parameters, Param–CPD improves F1, reduces localization error, and lowers false positives compared to observation–space baselines. We further verify identifiability and calibration of the inferred posteriors on stationary trajectories, explaining why parameter space offers a cleaner detection signal. Robustness analyses over tolerance, window length, and noise indicate consistent gains. Our results show that operating in a physically interpretable parameter space enables accurate and interpretable changepoint detection in nonlinear dynamical systems. Read More
OpenAI Introduces ChatGPT Atlas: A Chromium-based browser with a built-in AI agentMarkTechPost OpenAI just launched ChatGPT Atlas, a new AI browser that embeds ChatGPT at the core of navigation, search, and on-page assistance. Atlas is available today for Free, Plus, Pro, and Go users, with a Business beta and Enterprise/Edu opt-in; Windows, iOS, and Android builds are “coming soon.” What ChatGPT Atlas is? Atlas is a Chromium-based
The post OpenAI Introduces ChatGPT Atlas: A Chromium-based browser with a built-in AI agent appeared first on MarkTechPost.
OpenAI just launched ChatGPT Atlas, a new AI browser that embeds ChatGPT at the core of navigation, search, and on-page assistance. Atlas is available today for Free, Plus, Pro, and Go users, with a Business beta and Enterprise/Edu opt-in; Windows, iOS, and Android builds are “coming soon.” What ChatGPT Atlas is? Atlas is a Chromium-based
The post OpenAI Introduces ChatGPT Atlas: A Chromium-based browser with a built-in AI agent appeared first on MarkTechPost. Read More
ZSPAPrune: Zero-Shot Prompt-Aware Token Pruning for Vision-Language Modelscs.AI updates on arXiv.org arXiv:2510.17197v1 Announce Type: cross
Abstract: As the capabilities of Vision-Language Models (VLMs) advance, they can process increasingly large inputs, which, unlike in LLMs, generates significant visual token redundancy and leads to prohibitive inference costs. While many methods aim to reduce these costs by pruning visual tokens, existing approaches, whether based on attention or diversity, typically neglect the guidance of the text prompt and thus fail to prioritize task relevance. In this work, we propose a novel, zero-shot method that reframes the problem by introducing a prompt-aware perspective, explicitly modeling visual token pruning as a balance between task relevance and information diversity. Our hierarchical approach first selects a core set of task-relevant visual tokens and then supplements them with diversity tokens to preserve broader context. Experiments across multiple models and benchmarks show that our method achieves performance that matches or surpasses the state-of-the-art with only minimal accuracy loss, even when pruning up to 90% of the tokens. Furthermore, these gains are accompanied by significant reductions in GPU memory footprint and inference latency.
arXiv:2510.17197v1 Announce Type: cross
Abstract: As the capabilities of Vision-Language Models (VLMs) advance, they can process increasingly large inputs, which, unlike in LLMs, generates significant visual token redundancy and leads to prohibitive inference costs. While many methods aim to reduce these costs by pruning visual tokens, existing approaches, whether based on attention or diversity, typically neglect the guidance of the text prompt and thus fail to prioritize task relevance. In this work, we propose a novel, zero-shot method that reframes the problem by introducing a prompt-aware perspective, explicitly modeling visual token pruning as a balance between task relevance and information diversity. Our hierarchical approach first selects a core set of task-relevant visual tokens and then supplements them with diversity tokens to preserve broader context. Experiments across multiple models and benchmarks show that our method achieves performance that matches or surpasses the state-of-the-art with only minimal accuracy loss, even when pruning up to 90% of the tokens. Furthermore, these gains are accompanied by significant reductions in GPU memory footprint and inference latency. Read More
DAMSDAN: Distribution-Aware Multi-Source Domain Adaptation Network for Cross-Domain EEG-based Emotion Recognitioncs.AI updates on arXiv.org arXiv:2510.17475v1 Announce Type: cross
Abstract: Significant inter-individual variability limits the generalization of EEG-based emotion recognition under cross-domain settings. We address two core challenges in multi-source adaptation: (1) dynamically modeling distributional heterogeneity across sources and quantifying their relevance to a target to reduce negative transfer; and (2) achieving fine-grained semantic consistency to strengthen class discrimination. We propose a distribution-aware multi-source domain adaptation network (DAMSDAN). DAMSDAN integrates prototype-based constraints with adversarial learning to drive the encoder toward discriminative, domain-invariant emotion representations. A domain-aware source weighting strategy based on maximum mean discrepancy (MMD) dynamically estimates inter-domain shifts and reweights source contributions. In addition, a prototype-guided conditional alignment module with dual pseudo-label interaction enhances pseudo-label reliability and enables category-level, fine-grained alignment, mitigating noise propagation and semantic drift. Experiments on SEED and SEED-IV show average accuracies of 94.86% and 79.78% for cross-subject, and 95.12% and 83.15% for cross-session protocols. On the large-scale FACED dataset, DAMSDAN achieves 82.88% (cross-subject). Extensive ablations and interpretability analyses corroborate the effectiveness of the proposed framework for cross-domain EEG-based emotion recognition.
arXiv:2510.17475v1 Announce Type: cross
Abstract: Significant inter-individual variability limits the generalization of EEG-based emotion recognition under cross-domain settings. We address two core challenges in multi-source adaptation: (1) dynamically modeling distributional heterogeneity across sources and quantifying their relevance to a target to reduce negative transfer; and (2) achieving fine-grained semantic consistency to strengthen class discrimination. We propose a distribution-aware multi-source domain adaptation network (DAMSDAN). DAMSDAN integrates prototype-based constraints with adversarial learning to drive the encoder toward discriminative, domain-invariant emotion representations. A domain-aware source weighting strategy based on maximum mean discrepancy (MMD) dynamically estimates inter-domain shifts and reweights source contributions. In addition, a prototype-guided conditional alignment module with dual pseudo-label interaction enhances pseudo-label reliability and enables category-level, fine-grained alignment, mitigating noise propagation and semantic drift. Experiments on SEED and SEED-IV show average accuracies of 94.86% and 79.78% for cross-subject, and 95.12% and 83.15% for cross-session protocols. On the large-scale FACED dataset, DAMSDAN achieves 82.88% (cross-subject). Extensive ablations and interpretability analyses corroborate the effectiveness of the proposed framework for cross-domain EEG-based emotion recognition. Read More
Exploring the Potential of Citiverses for Regulatory Learningcs.AI updates on arXiv.org arXiv:2510.15959v1 Announce Type: new
Abstract: Citiverses hold the potential to support regulatory learning by offering immersive, virtual environments for experimenting with policy scenarios and technologies. This paper proposes a science-for-policy agenda to explore the potential of citiverses as experimentation spaces for regulatory learning, grounded in a consultation with a high-level panel of experts, including policymakers from the European Commission, national government science advisers and leading researchers in digital regulation and virtual worlds. It identifies key research areas, including scalability, real-time feedback, complexity modelling, cross-border collaboration, risk reduction, citizen participation, ethical considerations and the integration of emerging technologies. In addition, the paper analyses a set of experimental topics, spanning transportation, urban planning and the environment/climate crisis, that could be tested in citiverse platforms to advance regulatory learning in these areas. The proposed work is designed to inform future research for policy and emphasizes a responsible approach to developing and using citiverses. It prioritizes careful consideration of the ethical, economic, ecological and social dimensions of different regulations. The paper also explores essential preliminary steps necessary for integrating citiverses into the broader ecosystems of experimentation spaces, including test beds, living labs and regulatory sandboxes
arXiv:2510.15959v1 Announce Type: new
Abstract: Citiverses hold the potential to support regulatory learning by offering immersive, virtual environments for experimenting with policy scenarios and technologies. This paper proposes a science-for-policy agenda to explore the potential of citiverses as experimentation spaces for regulatory learning, grounded in a consultation with a high-level panel of experts, including policymakers from the European Commission, national government science advisers and leading researchers in digital regulation and virtual worlds. It identifies key research areas, including scalability, real-time feedback, complexity modelling, cross-border collaboration, risk reduction, citizen participation, ethical considerations and the integration of emerging technologies. In addition, the paper analyses a set of experimental topics, spanning transportation, urban planning and the environment/climate crisis, that could be tested in citiverse platforms to advance regulatory learning in these areas. The proposed work is designed to inform future research for policy and emphasizes a responsible approach to developing and using citiverses. It prioritizes careful consideration of the ethical, economic, ecological and social dimensions of different regulations. The paper also explores essential preliminary steps necessary for integrating citiverses into the broader ecosystems of experimentation spaces, including test beds, living labs and regulatory sandboxes Read More
SketchMind: A Multi-Agent Cognitive Framework for Assessing Student-Drawn Scientific Sketchescs.AI updates on arXiv.org arXiv:2507.22904v2 Announce Type: replace-cross
Abstract: Scientific sketches (e.g., models) offer a powerful lens into students’ conceptual understanding, yet AI-powered automated assessment of such free-form, visually diverse artifacts remains a critical challenge. Existing solutions often treat sketch evaluation as either an image classification task or monolithic vision-language models, which lack interpretability, pedagogical alignment, and adaptability across cognitive levels. To address these limitations, we present SketchMind, a cognitively grounded, multi-agent framework for evaluating and improving student-drawn scientific sketches. SketchMind comprises modular agents responsible for rubric parsing, sketch perception, cognitive alignment, and iterative feedback with sketch modification, enabling personalized and transparent evaluation. We evaluate SketchMind on a curated dataset of 3,575 student-generated sketches across six science assessment items with different highest order of Bloom’s level that require students to draw models to explain phenomena. Compared to baseline GPT-4o performance without SRG (average accuracy: 55.6%), and with SRG integration achieves 77.1% average accuracy (+21.4% average absolute gain). We also demonstrate that multi-agent orchestration with SRG enhances SketchMind performance, for example, GPT-4.1 gains an average 8.9% increase in sketch prediction accuracy, outperforming single-agent pipelines across all items. Human evaluators rated the feedback and co-created sketches generated by textsc{SketchMind} with GPT-4.1, which achieved an average of 4.1 out of 5, significantly higher than those of baseline models (e.g., 2.3 for GPT-4o). Experts noted the system’s potential to meaningfully support conceptual growth through guided revision. Our code and (pending approval) dataset will be released to support reproducibility and future research in AI-driven education.
arXiv:2507.22904v2 Announce Type: replace-cross
Abstract: Scientific sketches (e.g., models) offer a powerful lens into students’ conceptual understanding, yet AI-powered automated assessment of such free-form, visually diverse artifacts remains a critical challenge. Existing solutions often treat sketch evaluation as either an image classification task or monolithic vision-language models, which lack interpretability, pedagogical alignment, and adaptability across cognitive levels. To address these limitations, we present SketchMind, a cognitively grounded, multi-agent framework for evaluating and improving student-drawn scientific sketches. SketchMind comprises modular agents responsible for rubric parsing, sketch perception, cognitive alignment, and iterative feedback with sketch modification, enabling personalized and transparent evaluation. We evaluate SketchMind on a curated dataset of 3,575 student-generated sketches across six science assessment items with different highest order of Bloom’s level that require students to draw models to explain phenomena. Compared to baseline GPT-4o performance without SRG (average accuracy: 55.6%), and with SRG integration achieves 77.1% average accuracy (+21.4% average absolute gain). We also demonstrate that multi-agent orchestration with SRG enhances SketchMind performance, for example, GPT-4.1 gains an average 8.9% increase in sketch prediction accuracy, outperforming single-agent pipelines across all items. Human evaluators rated the feedback and co-created sketches generated by textsc{SketchMind} with GPT-4.1, which achieved an average of 4.1 out of 5, significantly higher than those of baseline models (e.g., 2.3 for GPT-4o). Experts noted the system’s potential to meaningfully support conceptual growth through guided revision. Our code and (pending approval) dataset will be released to support reproducibility and future research in AI-driven education. Read More