Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,181 papers · 148 categories

Trend · papers per month

4182123164 · Jun 202019922001200920182026
48 results for AI goals

AI systems learn complex goals via debate with human judges.

problem Complex human goals and preferences for AI systems.
method Training agents via self-play on a debate game, where humans judge which agent gives more true, useful information.
result Boosted classifier accuracy from 48.2% to 85.2% given 4 pixels, and from 59.4% to 88.9% given 6 pixels.

Framework enhances AI explainability by aligning with human cognitive models.

problem Lack of explainability in AI models hinders trust and accountability.
method Integrates explainability techniques with Malle's five category model of behavior explanation.
result Demonstrates practical relevance in credit risk assessment and regulatory analysis.

Study shows AI can learn to conform to logical restraining specifications.

problem Learning AI goals to match logical restraining specifications.
method Reinforcement learning with LTLf/LDLf specifications.
result AI can learn to conform to logical restraining specifications under general circumstances.

The paper integrates AI and expert knowledge to optimize radiotherapy decisions.

problem Optimizing radiation dose planning considering patient-specific information.
method Integrating Gaussian process models with deep neural networks to quantify uncertainty.
result Improves AI model performance and guides clinical decision making.

Study causal effects on humans in mixed human-AI systems with unobserved unit types.

problem Estimating causal effects on humans in systems with unobserved unit types and interaction networks.
method Assumed human-AI prior, causal message passing (CMP) framework, subpopulation analysis.
result Consistently recover human-specific causal effects using subpopulations with varying expected human composition and treatment exposure.

This work advances collaborative decision making by combining human and AI strengths in uncertainty quantification.

problem Current AI lacks robust decision-making capabilities under uncertainty, especially in high-stakes contexts.
method Introduces Human AI Collaborative Uncertainty Quantification (HACUQ) framework, formalizing AI-human collaboration and developing calibration algorithms.
result Optimal collaborative prediction sets follow a two-threshold structure, and online adaptation algorithms can adapt to evolving human behavior.

Review of AI tools for physicists, focusing on neural networks and decision processes.

problem Gaps between AI and physics, especially in unsupervised learning.
method Examination of deep learning models and Markov decision processes.
result Neural networks can construct physical theories without prior knowledge.

Universal AI seeks high-optionality states through empowerment and curiosity.

problem Understanding and optimizing AI behavior in uncertain environments.
method Unified framework combining AIXI and variational empowerment, showing how universal AI agents balance goal-directed behavior with uncertainty reduction curiosity.
result Self-AIXI asymptotically converges to AIXI performance and exhibits power-seeking behavior due to intrinsic motivations.

Research tackles distribution shift issues in ML to improve AI reliability.

problem Distribution shift limits ML reliability and trustworthiness.
method Study three distribution shifts (perturbation, domain, modality) and investigate robustness, explainability, adaptability.
result Proposes effective solutions and fundamental insights for enhancing ML robustness, adaptability, and safety.

AVEC 2019 challenges AI in detecting depression and cross-cultural emotions.

problem Detecting depression and cross-cultural emotions from audiovisual data.
method Comparison of machine learning methods under standardized conditions.
result Baseline system performance on state-of-mind, depression, and cross-cultural tasks.

Paper proposes a new AI design philosophy for distributed learning.

problem Designing AI systems that mimic human cognitive capabilities.
method Democratized learning (Dem-AI) with self-organized hierarchical agents.
result Self-organized learning systems can perform complex tasks more efficiently.

New theory tackles AGI by breaking data constraints and minimizing global risk.

problem Current AI's limitations in handling complex real-world data and making reasonable judgments.
method Developed subjectivity learning theory to break data constraints and minimize global risk.
result Subjectivity learning holds a lower risk bound than traditional machine learning.

New RL environments help AI learn causal relationships from visual data.

problem Learning causal relationships from visual data for AI agents.
method Designing benchmark RL environments and evaluating representation learning algorithms.
result Explicitly incorporating structure and modularity improves causal induction in model-based RL.

Vanguard uses AI to create personalized financial plans.

problem Challenges in choosing features for complex financial planning.
method Reinforcement learning for identifying optimal savings rates.
result Trains algorithms to model financial success trajectories.

This paper introduces glocal explanations for expected goal models in soccer.

problem Limited interpretability of expected goal models trained with black-box methods.
method Proposes glocal explanations using aggregated SHAP values and partial dependence profiles.
result Extracts knowledge from expected goal models for teams and players, enhancing performance analysis.

New approach to algorithmic fairness for human-AI collaboration considers compliance with human decisions.

problem Current fairness approaches assume perfect human compliance, but real-world compliance is often poor.
method Defines compliance-robustly fair algorithms and proposes an optimization strategy to improve fairness.
result Algorithmic recommendations can improve fairness even if humans do not fully comply with fair algorithms.

CRL uses causality to build interpretable AI models from complex data.

problem Interpreting deep neural networks' implicit representations.
method Causal representation learning (CRL) synthesizing latent variable models, causal graphical models, and nonparametric statistics.
result CRL can improve interpretability of generative AI models.

Research aims to make AI decisions in digital pathology more understandable to pathologists.

problem Making AI decisions in digital pathology more understandable and interpretable.
method Combining machine learning with human intelligence to balance AI and human capabilities.
result Combining AI and human intelligence to improve diagnostic accuracy and understanding.

A new method improves AI fairness assessment by estimating performance across intersectional subgroups.

problem Limited evaluation of AI systems across intersectional subgroups due to small sample sizes.
method Structured regression approach to disaggregated evaluation.
result Our method yields more accurate performance estimates, especially for small subgroups.

Agent-to-agent finance aims to manage payments and trust for AI agents.

problem Managing financial interactions between autonomous AI agents.
method Develops agent-to-agent finance concept and explores blockchain solutions.
result Agent-to-agent finance can address coordination frictions in financial markets.

New approach uses text generation to boost AI agent development.

problem Lack of training data hinders AI agent development.
method Used encoder-decoder generative models, focusing on conditional variational auto-encoders.
result Significantly improved AI agent performance in low-resource cases.

DAIS improves AIS for differentiable marginal likelihood estimation.

problem Differentiable marginal likelihood estimation for complex models.
method Proposes Differentiable Annealed Importance Sampling (DAIS) to make AIS differentiable.
result DAIS achieves convergence and consistency in Bayesian linear regression.

Adapts IRL for dual-system agents, correcting goal inference errors.

problem Inferring goals from dual-system decision-making behaviors.
method Generalized dual-system framework, optimal plan computation, adapted IRL algorithm.
result Correct goal inference for dual-system agents improves overall utility.

New method improves dialogue agents focusing on simple utterances.

problem Dialogue agents often focus on simple utterances and suboptimal policies.
method Tempered Policy Gradient (TPG) methods to improve dialogue performance.
result Significant improvements in dialogue performance, especially in producing convincing utterances.