arXiv AI
Aug 3
Beyond Component Testing: Validating Agentic AI Systems
arXiv:2607. 29405v1 Announce Type: new Abstract: Agentic AI systems act through multi-step trajectories that combine planning, tool use, memory, interaction, and adaptation.
AI safety and alignment
Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv AI
Aug 3
Don't Mix Rewards, Mix Policies: Policy Decomposition and Optimization for Multi-Reward RL
arXiv:2607. 29246v1 Announce Type: new Abstract: Modern large language models (LLMs) are expected not just to answer correctly, but to adapt their behavior to different human values and use cases.
arXiv Machine Learning
Aug 3
Analytical and Bootstrap Confidence Intervals of Double Machine Learning: Simulation studies and an application to rural-urban difference in obesity prevalence
arXiv:2607. 29456v1 Announce Type: cross Abstract: Double Machine Learning (DML) is a popular approach for treatment effect estimation in various settings, which allows a wide range of flexible machine learning methods to be used for nuisance parameter estimation while preserving valid inference.
arXiv Machine Learning
Aug 3
RTLCurator: Label-Efficient Data Curation for RTL Generation
arXiv:2607. 29283v1 Announce Type: cross Abstract: Training large language models (LLMs) to write register-transfer level (RTL) requires large corpora of paired specifications and code, and such data is scarce enough that most public corpora are now synthesized.
arXiv Machine Learning
Aug 3
Expert-Data Alignment Governs Generation Quality in Decentralized Diffusion Models
arXiv:2602. 02685v3 Announce Type: replace Abstract: Decentralized Diffusion Models (DDMs) route denoising through experts trained independently on disjoint data clusters, which can strongly disagree in their predictions.
arXiv Machine Learning
Aug 3
Shapley-Value-Based Feature Attribution for Data Masking
arXiv:2607. 28946v1 Announce Type: new Abstract: Despite its many benefits, widespread access to individuals' personal data also causes severe privacy concerns for consumers, companies, and policymakers.
arXiv Machine Learning
Aug 3
Who Wins Where? Conformal Model Comparison for Local Superiority
arXiv:2607. 29053v1 Announce Type: new Abstract: Standard model comparison is global, aggregating losses across the covariate space to declare a single winner.
arXiv Machine Learning
Aug 3
A Novel XAI-Enhanced Quantum Adversarial Networks for Velocity Dispersion Modeling in MaNGA Galaxies
arXiv:2510. 24598v2 Announce Type: replace Abstract: Current quantum machine learning approaches often face challenges balancing predictive accuracy, robustness, and interpretability.
arXiv Machine Learning
Aug 3
Quotient Semivalues for False-Name-Resistant Data Attribution
arXiv:2605. 07663v2 Announce Type: replace-cross Abstract: Data valuation methods allocate payments and audit training data's contribution to machine-learning pipelines; however, they often assume passive contributors.
arXiv AI
Aug 3
Predict-then-Diffuse: Adaptive Response Length for Compute-Budgeted Inference in Diffusion LLMs
arXiv:2605. 04215v3 Announce Type: replace-cross Abstract: Diffusion-based Large Language Models (D-LLMs) represent a promising frontier in generative AI, offering fully parallel token generation that can lead to significant throughput advantages and superior GPU utilization over the traditional autoregressive paradigm.
arXiv AI
Aug 3
ViSAGE: Constructing Self-Correcting Memories for Long-Form Video Understanding
arXiv:2607. 28678v1 Announce Type: new Abstract: Multimodal agents operating in long-horizon environments must build and continually update multimedia memories to support entity-consistent, temporally grounded reasoning.
arXiv AI
Aug 3
Preconditioned Test-Time Adaptation for Out-of-Distribution Debiasing in Narrative Generation
arXiv:2603. 13683v4 Announce Type: replace-cross Abstract: Although debiased large language models (LLMs) excel at handling known or low-bias prompts, they often fail on unfamiliar and high-bias prompts.
arXiv AI
Aug 3
Evaluating the Alignment Between GeoAI Explanations and Domain Knowledge in Satellite-Based Flood Mapping
arXiv:2604. 26051v2 Announce Type: replace-cross Abstract: The increasing number of satellites has improved the temporal resolution of Earth observation, making satellite-based flood mapping a promising approach for operational flood monitoring.
arXiv AI
Aug 3
DRIP-R: A Benchmark for Decision-Making and Reasoning Under Real-World Policy Ambiguity in the Retail Domain
arXiv:2605. 07699v2 Announce Type: replace-cross Abstract: LLM-based agents are increasingly deployed for routine but consequential tasks in real-world domains, where their behavior is governed by inherently ambiguous domain policies that admit multiple valid interpretations.
arXiv Machine Learning
Aug 3
In-situ Autoguidance: Eliciting Self-Correction in Diffusion Models
arXiv:2510. 17136v2 Announce Type: replace Abstract: The generation of high-quality, diverse, and prompt-aligned images is a central goal in image-generating diffusion models.
arXiv AI
Aug 3
When Model Priors Conflict with Visual Evidence: Mitigating Commonsense-Driven Hallucinations by Selective Prior Calibration
arXiv:2607. 29240v1 Announce Type: cross Abstract: In vision--language models, commonsense-driven hallucination (CDH) occurs when a model's commonsense prior overrides clear visual evidence of an atypical state.
arXiv AI
Aug 3
TraceViT: Grounded Trace Supervision for Visual Abstract Reasoning
arXiv:2607. 29586v1 Announce Type: cross Abstract: The Abstraction and Reasoning Corpus (ARC) tests whether a model can infer an unseen transformation from a few input-output examples and apply it to a new grid.
arXiv AI
Aug 3
The Theoretical Foundation of Socratic Tests: Dynamic, Multimodal, Conversational Examinations
arXiv:2607. 29624v1 Announce Type: cross Abstract: Traditional static assessments rely on a subtractive, deficit-based grading model that often penalizes ambition and obscures diagnostic feedback.
arXiv Machine Learning
Aug 3
Structured Neural Chaos: An Adaptive Surrogate Modeling Framework for Functional Uncertainty Quantification and Global Sensitivity Analysis
arXiv:2607. 28903v1 Announce Type: cross Abstract: Variance-based global sensitivity analysis (GSA) plays a key role in uncertainty quantification by identifying the contributions of uncertain inputs to the variability of the model response.
arXiv Machine Learning
Aug 3
Fisher Information, Training and Bias in Fourier Regression Models
arXiv:2510. 06945v2 Announce Type: replace Abstract: Motivated by the growing interest in quantum machine learning, in particular quantum neural networks (QNNs), we study how recently introduced evaluation metrics based on the Fisher information matrix (FIM) are effective for predicting their training and prediction performance.