This paper argues for more realistic human models in RL.
problem Current RL models oversimplify human feedback, ignoring personal, contextual, and dynamic aspects.
method Calls for interdisciplinary research on human feedback in RL.
result Realistic human models are needed for robust human-in-the-loop RL systems.
Paper tackles RLHF with DCPPO method, proving near-optimal suboptimality.
problem Challenges in offline RLHF with limited human feedback and bounded rationality.
method DCPPO method involving three stages: MLE, reward function recovery, and pessimistic value iteration.
result DCPPO's suboptimality almost matches classical pessimistic offline RL in terms of distribution shift and dimension.
RFC enhances humanoid control to imitate complex human motions.
problem Dynamics mismatch between humanoid models and real humans.
method Residual Force Control (RFC) augments control policies with external forces.
result RFC outperforms state-of-the-art methods in convergence speed and motion quality.
Recent studies in the field of human vision science suggest that the human responses to the stimuli on a visual display are non-deterministic. People may attend to different locations on the same visual input at the same time. Based on this knowledge, we propose a new stochastic model of visual attention by introducing…
Paper proposes a new RLHF framework for human preference learning.
problem Handling dependent online human preference outcomes with dynamic contexts.
method Two-stage algorithm with ε-greedy followed by exploitation; anti-concentration inequalities and matrix martingale concentration techniques. result Our method achieves optimal regret bound and asymptotic normality of estimators.
Many real-valued stochastic time-series are locally linear (Gassian), but globally non-linear. For example, the trajectory of a human hand gesture can be viewed as a linear dynamic system driven by a nonlinear dynamic system that represents muscle actions. We present a mixed-state dynamic graphical model in which a hid…
Proposes using Dynamic Mode Decomposition with delays for short-term human motion anticipation.
problem Lack of interpretability and explainability in neural network-based motion anticipation methods.
method Dynamic Mode Decomposition with delays for motion representation and prediction.
result Anticipation errors comparable or better than recurrent neural networks for very short times.
DAFT models attention as a dynamical system to make neural networks more interpretable.
problem Uninterpretable features learned by neural networks without human priors.
method DAFT models attention as a continuous dynamical system using neural ODEs.
result DAFT reduces the number of reasoning steps while maintaining similar performance.
DMGNN predicts 3D human motions using adaptive multiscale graphs.
problem Predicting 3D skeleton-based human motions accurately.
method Dynamic multiscale graph neural networks (DMGNN) with adaptive multiscale graphs and MGCU.
result DMGNN outperforms state-of-the-art methods in short and long-term predictions.
New simulation model predicts financial market dynamics with high accuracy.
problem Extreme difficulty in financial market projections due to human behavioural complexity.
method Agent-based modeling with a hierarchical knowledge architecture to simulate diverse human groups.
result Simulator achieves 13.29% deviation in crisis scenarios and lower mean square error under normal conditions.
TRIBE model uses LLMs to simulate human trading behavior in bond markets.
problem Complexities in decentralized bond market transactions.
method Agent-based model augmented with LLMs to simulate human-like decision-making.
result Slight trade aversion in LLMs can lead to complete market collapse.
GraphKKE learns fixed-length feature vectors from time-evolving graphs of human microbiome data.
problem Understanding dynamic changes in human microbiome graphs over time.
method Spectral analysis of transfer operators and graph kernels.
result GraphKKE captures temporal changes in human microbiome graphs.
Unified model forecasts epidemics with spatial and temporal dynamics.
problem Limited accuracy in traditional models and lack of interpretability in deep learning models.
method CSTGNN integrates Spatio-Contact SIR model with Graph Neural Networks.
result Effective spatiotemporal epidemic forecasting with interpretability.
Model infers temporal connections in dynamic graphs from node interactions.
problem Challenges in reasoning about evolving graphs, especially with human-specified edges.
method Temporal point processes and variational autoencoders with bilinear interactions.
result Model outperforms baselines and infers semantically interpretable connections.
MT-VAE learns motion transitions for generating diverse future motions.
problem Learning long-term human motion sequences with transitions.
method Jointly learns motion mode embeddings and transitions using Variational Auto-Encoders.
result Generates multiple plausible future motion sequences from input.
Trust-aware MAB improves learning performance by accounting for human deviation.
problem Learning performance suffers when humans deviate from recommended policies due to lack of trust.
method Integrates a dynamic trust model into MAB framework, establishing minimax regret and proposing a two-stage trust-aware procedure.
result Proves near-optimal statistical guarantees for trust-aware MAB algorithms.
Aerial robot estimates human pose and path using dynamic classifier selection.
problem Estimating human pose and trajectory from aerial video.
method Dynamic classifier selection architecture; perspective correction; HOG and CNN features; 64 pose-viewpoint classes.
result Dynamic classifier selection improves efficiency and accuracy.
Paper proposes self-supervised method for accurate speaker diarization.
problem Speaker diarization without massive labeling effort.
method Introduces dynamic triplet loss and multinomial loss for audio-video synchronization.
result Best model yields +8% F1-score improvement and diarization error rate reduction.
New framework solves dynamic bilevel optimization problems in reinforcement learning.
problem Dynamic objective functions in reinforcement learning and human feedback.
method Principled penalty-based methods for bilevel reinforcement learning.
result Demonstrated effectiveness of penalty-based algorithms in simulations.
UrbanRhythm reveals urban dynamics from mobility data.
problem Understanding changing urban activities over time.
method Extracting staying, leaving, arriving attributes; using Saak transform; clustering for city states; motif analysis for short-term regularity.
result Characterized urban dynamics as city state transformations over time.
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.
DFTerNet improves human activity recognition on portable devices with 2-bit quantization and dynamic fusion.
problem Resource constraints and unequal fusion strategies limit practical human activity recognition on portable devices.
method 2-bit Convolutional Neural Networks with dynamic fusion strategies for different activity types.
result Exceeds baseline model performance by up to ~5% on OPPORTUNITY and PAMAP2 datasets.
Paper proposes active learning for mining conflict dynamics from textual data.
problem Lack of detailed information on conflict dynamics in existing datasets.
method Active learning with a large, encoder-only language model.
result Performance similar to human coding with reduced human annotation.
Autonomous systems can substantially enhance a human's efficiency and effectiveness in complex environments. Machines, however, are often unable to observe the preferences of the humans that they serve. Despite the fact that the human's and machine's objectives are aligned, asymmetric information, along with heterogene…
VFDS selects dynamic features for efficient HAR tasks, optimizing performance-cost trade-offs.
problem Optimizing feature selection for varying costs and dynamic contexts in machine learning tasks.
method Bayesian learning framework with variational dynamic selection policy.
result VFDS selects different features under changing contexts, saving sensory costs while maintaining HAR accuracy.
Teaches AI models to learn effectively through dynamic loss functions.
problem Optimizing machine learning models' performance through dynamic loss functions.
method Develops a method for a teacher model to dynamically output loss functions for a student model, enabling gradient-based optimization.
result Significantly improves the performance of various student models in real-world tasks.
Study reveals AI's spontaneous topic changes in text prediction.
problem AI's inability to spontaneously switch topics like humans.
method Defined topic as Token Priority Graphs (TPGs) and analyzed self-attention models.
result AI can only switch topics if lower-priority tokens outnumber higher-priority ones.
HCLM framework uses entropy regularization for open learning systems.
problem Real-world AI challenges and limitations of deep learning.
method Dynamical and information-theoretic framework with entropy regularization.
result Geometric entropy surrogates, especially log-determinant covariance entropy, induce stronger and more stable information forces.
This article outlines a method for automatically generating models of dynamic decision-making that both have strong predictive power and are interpretable in human terms. This is useful for designing empirically grounded agent-based simulations and for gaining direct insight into observed dynamic processes. We use an e…
Study on self-consuming generative models with diverse human curation, focusing on convergence and stability.
problem Analyzing self-consuming generative models with heterogeneous human curation.
method Investigates the asymptotic behavior of retraining dynamics using nonlinear Perron--Frobenius theory and Banach contraction mapping.
result Improves convergence results and provides stability and non-stability analyses for the model.
In this paper we propose the use of quantum genetic algorithm to optimize the support vector machine (SVM) for human action recognition. The Microsoft Kinect sensor can be used for skeleton tracking, which provides the joints' position data. However, how to extract the motion features for representing the dynamics of a…
The problem of human activity recognition is central for understanding and predicting the human behavior, in particular in a prospective of assistive services to humans, such as health monitoring, well being, security, etc. There is therefore a growing need to build accurate models which can take into account the varia…
Three ways synchronization in financial markets can cause contagion, using models of decision-making and oscillators.
problem Contagion in financial markets caused by synchronization of decision-making.
method Agent-based modeling, integrate-and-fire oscillators, and communication models.
result Synchronization in financial markets can lead to turbulent periods and contagion.
Inferring intent from observed behavior has been studied extensively within the frameworks of Bayesian inverse planning and inverse reinforcement learning. These methods infer a goal or reward function that best explains the actions of the observed agent, typically a human demonstrator. Another agent can use this infer…
Kernel test evaluates dynamical system data streams.
problem Evaluate if data streams from dynamical systems are from the same distribution.
method Proposes a novel kernel two-sample test for dynamical systems, addressing independence and autocorrelation challenges.
result Data-driven method with theoretical guarantees for anomaly detection.
Framework learns stochastic dynamics from endpoint and intermediate distributions using soft energy constraints.
problem Learning stochastic dynamics from endpoint and intermediate distributional observations.
method Formulates generation as a McKean-Vlasov control problem with soft energy constraints, solving it through FBSDE.
result Model learns coherent stochastic trajectories matching prescribed marginal laws.
New approach uses graphs for sign language recognition.
problem Challenges in recognizing sign language for deaf individuals.
method Spatial-Temporal Graph Convolutional Network.
result Improved sign language recognition using human skeletal movements.
Paper introduces new tasks and a model class that can solve them, using mixtures of stochastic vector fields.
problem Neural ODEs cannot solve fundamental tasks even with high-capacity vector fields.
method Proposes mixtures of stochastic vector fields and dynamic vector field selection.
result Demonstrates that the proposed model class can capture natural dynamics of human behavior.
Improved real-time visualizations of conversation turns using dynamic attention weights.
problem Uniform attention weights in sequential analysis tasks prevent meaningful visualization.
method Developed a method to track changes in turn importance over time.
result More informative real-time visuals confirmed by human reviewers.
Reproductive success and survival are influenced by wealth in human populations. Wealth is transmitted to offsprings and strategies of transmission vary over time and among populations, the main variation being how equally wealth is transmitted to children. Here we propose a model where we simulate both the dynamics of…
Researchers develop a neural network that learns like humans, overcoming forgetting and structure issues.
problem Catastrophic forgetting and structure limitations in neural networks.
method Memory playback strategy and dynamic structure extension using conditional variational autoencoder (CVAE).
result The method effectively prevents forgetting and allows for dynamic network growth.
LLMs mimic human traders in finance, but not as much as expected.
problem Evaluating how LLMs behave in financial markets.
method Adapted experimental design with LLMs and human traders, analyzed in single and mixed model settings.
result LLMs tend to price assets near their fundamental value, but not as much as humans, and show less trading strategy variance.
We propose a neural superstatistics method to estimate dynamic cognitive models from time series data.
problem Memoryless cognitive models ignore parameter fluctuations, leading to inaccurate predictions.
method Developed a simulation-based deep learning method for Bayesian inference of superstatistical models.
result Deep learning method efficiently recovers time-varying and time-invariant parameters.
A machine learning system identifies dynamic gestures from accelerometer data.
problem Identifying dynamic gestures from accelerometer data.
method Machine learning approach using tri-axial acceleration data from uWave and Sony datasets.
result The system can classify gestures at varying speeds with minimal preprocessing and runs on a low-cost platform.
We present an adversarial active exploration for inverse dynamics model learning, a simple yet effective learning scheme that incentivizes exploration in an environment without any human intervention. Our framework consists of a deep reinforcement learning (DRL) agent and an inverse dynamics model contesting with each …
Human stablecoin transactions predict political risk in cryptocurrency markets.
problem Predicting political risk in cryptocurrency markets.
method Structural break analysis and surrogate-based robustness tests.
result Human-driven stablecoin transactions shift significantly before major political events.
Proposes a new model for time series that considers smooth transitions between states.
problem Models assume instantaneous transitions between discrete states, ignoring gradual changes.
method Dynamical Wasserstein Barycentric (DWB) model that estimates system state and pure state distributions over time.
result Accurately learns pure state distributions and improves state estimation for transition periods.
FinHEAR combines LLMs with human expertise for better financial decision-making.
problem Challenges in financial decision-making for language models.
method Multi-agent framework with specialized LLMs for historical analysis, event interpretation, and expert retrieval.
result FinHEAR outperforms baselines in financial tasks with higher accuracy and risk-adjusted returns.