We present a novel human-aware navigation approach, where the robot learns to mimic humans to navigate safely in crowds. The presented model, referred to as DeepMoTIon, is trained with pedestrian surveillance data to predict human velocity in the environment. The robot processes LiDAR scans via the trained network to n…
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.
168,742 papers · 148 categories
Trend · papers per month
48 results for “human experiments”
For a safe, natural and effective human-robot social interaction, it is essential to develop a system that allows a robot to demonstrate the perceivable responsive behaviors to complex human behaviors. We introduce the Multimodal Deep Attention Recurrent Q-Network using which the robot exhibits human-like social intera…
Reward shaping speeds up human learning through IRL.
problem Slow learning in humans, especially for challenging tasks.
method Extended IRL algorithm with kernel methods, conducted experiments with online game players.
result Players learn desired policies more quickly with reward shaping.
The paper offers a checklist for comparing human and machine visual perception.
problem Comparing human and machine visual perception.
method Designing, conducting, and interpreting experiments to investigate mechanisms.
result Feedback mechanisms may not be necessary for visual reasoning tasks.
Mixed likelihood GPs improve model performance in human-in-the-loop experiments.
problem Lack of auxiliary information in traditional GPs for human responses.
method Propose mixed likelihood variational GPs to leverage auxiliary information.
result Modeling performance improvements across diverse applications.
Human Attention in Visual Question Answering: Do Humans and Deep Networks Look at the Same Regions?stat.ML
We conduct large-scale studies on `human attention' in Visual Question Answering (VQA) to understand where humans choose to look to answer questions about images. We design and test multiple game-inspired novel attention-annotation interfaces that require the subject to sharpen regions of a blurred image to answer a qu…
The Human Kernelcs.LG
Bayesian nonparametric models, such as Gaussian processes, provide a compelling framework for automatic statistical modelling: these models have a high degree of flexibility, and automatically calibrated complexity. However, automating human expertise remains elusive; for example, Gaussian processes with standard kerne…
Designs algorithms to assist humans without affecting their decisions.
problem Algorithms often fail to improve human decisions.
method Formalizes algorithm design using potential outcomes framework and monotonicity assumption.
result Derives minimax optimal recommendation algorithms for limited data.
Study compares DSPy teleprompter algorithms for aligning LLM evaluations with human annotations.
problem Aligning LLM evaluation metrics with human annotations.
method Comparative analysis of five teleprompter algorithms within the DSPy framework.
result Certain teleprompters outperform others in detecting hallucinations.
AI systems are being deployed to support human decision making in high-stakes domains. In many cases, the human and AI form a team, in which the human makes decisions after reviewing the AI's inferences. A successful partnership requires that the human develops insights into the performance of the AI system, including …
Algorithmic collusion is an emerging concept in current artificial intelligence age. Whether algorithmic collusion is a creditable threat remains as an argument. In this paper, we propose an algorithm which can extort its human rival to collude in a Cournot duopoly competing market. In experiments, we show that, the al…
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.
Experiment shows cognitive biases impact human-AI collaboration, highlighting the need for diverse evaluator samples.
problem Cognitive biases affect human-AI collaboration, leading to suboptimal outcomes.
method Randomized experiment with 2,784 participants, manipulating AI suggestion quality, task burden, and financial incentives.
result Individual attitudes toward AI are the strongest predictor of performance, influencing accuracy and overcorrection.
New research shows machine-assisted decisions can still be unfair even when the algorithm is fair.
problem Ensuring fairness in decisions made with machine-assisted human input.
method Formal model and lab experiment to analyze how machine predictions affect human decisions.
result Excluding information about protected groups from machine predictions can increase disparities.
A test measures artificial agents' human-like behavior in video games.
problem Measuring the believability of artificial agents' human-like behavior.
method Developed a non-parametric two-sample hypothesis test.
result The -value correlates with human judgment of human-like behavior.
Random forests classify Pokemon names based on evolutionary status.
problem Classifying Pokemon names into pre-evolution and post-evolution categories.
method Trained random forests using sound symbolism from Pokemon names, conducted experiments with human participants.
result Random forests outperform human participants in classifying Pokemon names.
Embodied cognition states that semantics is encoded in the brain as firing patterns of neural circuits, which are learned according to the statistical structure of human multimodal experience. However, each human brain is idiosyncratically biased, according to its subjective experience history, making this biological s…
Counterfactual learning from human bandit feedback describes a scenario where user feedback on the quality of outputs of a historic system is logged and used to improve a target system. We show how to apply this learning framework to neural semantic parsing. From a machine learning perspective, the key challenge lies i…
Learning preferences implicit in the choices humans make is a well studied problem in both economics and computer science. However, most work makes the assumption that humans are acting (noisily) optimally with respect to their preferences. Such approaches can fail when people are themselves learning about what they wa…
While we would like agents that can coordinate with humans, current algorithms such as self-play and population-based training create agents that can coordinate with themselves. Agents that assume their partner to be optimal or similar to them can converge to coordination protocols that fail to understand and be unders…
AI safety via debatestat.ML
To make AI systems broadly useful for challenging real-world tasks, we need them to learn complex human goals and preferences. One approach to specifying complex goals asks humans to judge during training which agent behaviors are safe and useful, but this approach can fail if the task is too complicated for a human to…
AI enhances financial services but humans are irreplaceable for empathy, presence, and ethics.
problem AI's limitations in financial services, especially with small datasets and human judgment.
method EPOCH framework highlighting five irreplaceable human capabilities: Empathy, Presence, Opinion, Creativity, and Hope.
result Humans are essential for trust, innovation, and consumer experience in financial services.
We present an approach to interactive-predictive neural machine translation that attempts to reduce human effort from three directions: Firstly, instead of requiring humans to select, correct, or delete segments, we employ the idea of learning from human reinforcements in form of judgments on the quality of partial tra…
Decisions are increasingly taken by both humans and machine learning models. However, machine learning models are currently trained for full automation -- they are not aware that some of the decisions may still be taken by humans. In this paper, we take a first step towards the development of machine learning models th…
Study models human investors' sub-rational behavior in financial markets.
problem Lack of a comprehensive model for human sub-rationality in financial markets.
method Flexible reinforcement learning model incorporating five human sub-rational aspects.
result Model accurately reproduces human behavior and reveals insights into market dynamics.
In this work, we introduce a novel framework that employs cluster annotation to boost active learning by reducing the number of human interactions required to train deep neural networks. Instead of annotating single samples individually, humans can also label clusters, producing a higher number of annotated samples wit…
Active IRL selects optimal human demonstrations for learning AI preferences.
problem Costly human demonstrations in IRL for autonomous systems.
method Information-theoretic acquisition function for selecting informative human demonstrations.
result Efficiently reduces human effort in learning AI preferences.
Representation of human actions as a sequence of human body movements or action attributes enables the development of models for human activity recognition and summarization. We present an extension of the low-rank representation (LRR) model, termed the clustering-aware structure-constrained low-rank representation (CS…
Meena is a chatbot trained on social media data, achieving human-like conversation quality.
problem Creating a chatbot that can have human-like conversations in an open-domain setting.
method End-to-end training of a 2.6B parameter neural network on social media data, using perplexity and a human evaluation metric (SSA) to assess quality.
result Meena achieves a high human-like conversation quality (79% SSA) when compared to existing chatbots.
Deep reinforcement learning (DRL) has shown incredible performance in learning various tasks to the human level. However, unlike human perception, current DRL models connect the entire low-level sensory input to the state-action values rather than exploiting the relationship between and among entities that constitute t…
We proposed a probabilistic approach to joint modeling of participants' reliability and humans' regularity in crowdsourced affective studies. Reliability measures how likely a subject will respond to a question seriously; and regularity measures how often a human will agree with other seriously-entered responses coming…
Biological evolution has distilled the experiences of many learners into the general learning algorithms of humans. Our novel meta reinforcement learning algorithm MetaGenRL is inspired by this process. MetaGenRL distills the experiences of many complex agents to meta-learn a low-complexity neural objective function th…
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.
New benchmark for non-rigid 3D human shape retrieval.
problem Distinguishing between body shapes of 3D human models.
method Extended benchmark with 145 new models and FAUST dataset.
result Improved comparison of 25 shape retrieval methods.
CPATTA uses conformal prediction for efficient test-time adaptation.
problem Low data selection efficiency in existing ATTA methods.
method Conformal Prediction, online weight-update algorithm, domain-shift detector, staged update scheme.
result CPATTA consistently outperforms state-of-the-art methods by 5% in accuracy.
Study shows how algorithmic prediction affects US housing market, reducing racial wealth disparities.
problem Impact of algorithmic prediction on housing market and racial wealth disparities.
method Natural experiment using digitization of housing records to study entry, allocation, and prices.
result Digitization leads to increased sale prices for minority-owned homes, reducing racial wealth disparities.
We present an effective technique for training deep learning agents capable of negotiating on a set of clauses in a contract agreement using a simple communication protocol. We use Multi Agent Reinforcement Learning to train both agents simultaneously as they negotiate with each other in the training environment. We al…
Deep reinforcement learning methods attain super-human performance in a wide range of environments. Such methods are grossly inefficient, often taking orders of magnitudes more data than humans to achieve reasonable performance. We propose Neural Episodic Control: a deep reinforcement learning agent that is able to rap…
Improved reinforcement learning in Minecraft with human demonstrations.
problem Sample inefficiency in reinforcement learning.
method Training policy networks on human demonstrations first, then fine-tuning with reinforcement learning.
result Best agent achieved a mean score of 48 in Minecraft.
Direct Density Ratio Optimization aligns LLMs with human preferences without assuming specific models.
problem Statistical inconsistency in aligning LLMs with human preferences.
method Direct Density Ratio Optimization (DDRO) estimates density ratio directly.
result DDRO is statistically consistent, converging to true human preferences as data grows.
Study shows trust and trustworthiness emerge through reinforcement learning.
problem Trust and trustworthiness are universal but not predicted by traditional economic models.
method Used Q-learning algorithm to simulate trust and trustworthiness dynamics in a trust game.
result High levels of trust and trustworthiness emerge when individuals consider both past and future experiences.
This research improves interpretability in sequential explanations using mental models.
problem Improving interpretability in sequential explanations between two parties.
method A reinforcement learning framework that selects explanations based on the explainee's mental model.
result Mental model-based policies increase interpretability over random selection in multiple sequential explanations.
Proposes PA-DSL for correcting noisy human labels in automated data labeling.
problem Noisy human labels in automated data labeling.
method Uses adjudicated cases to correct noisy human labels and debias analyses.
result Maintains nominal coverage and reduces RMSE by 10-17% relative to using only adjudicated labels.
Human activity recognition using smart home sensors is one of the bases of ubiquitous computing in smart environments and a topic undergoing intense research in the field of ambient assisted living. The increasingly large amount of data sets calls for machine learning methods. In this paper, we introduce a deep learnin…
Privacy-preserving reinforcement learning from human feedback using decoupled reward modeling.
problem Training large language models with sensitive user information while preserving privacy.
method Proposes a privacy-preserving framework that imposes differential privacy on reward learning only.
result Privacy contributes an additional additive term to the suboptimality gap, and the upper bound is rate-optimal up to logarithmic factors.
Training deep reinforcement learning agents complex behaviors in 3D virtual environments requires significant computational resources. This is especially true in environments with high degrees of aliasing, where many states share nearly identical visual features. Minecraft is an exemplar of such an environment. We hypo…
LLM evaluation suffers from systematic biases and lacks reliable positive judgments.
problem LLM evaluation suffers from systematic biases and lacks reliable positive judgments.
method Formulate LLM evaluation as a positive-unlabelled learning problem and propose a geometric auditing framework based on Partial Optimal Transport.
result Improved alignment with human preferences, increased robustness to presentation biases, and interpretable confidence estimates.
LoCo-RLHF models diverse human feedback with contextual information.
problem Heterogeneous human feedback from diverse contexts and preferences.
method Low-rank contextual preference model, PRS policy.
result LoCo-RLHF achieves tighter sub-optimality gap than existing methods.