Paper defines human progress, highlighting both positive and negative impacts.
problem Equating economic growth with human progress overlooks negative effects.
method Pragmatic approach to define human progress as an endless pursuit of wellbeing.
result Human progress leads to both positive and negative outcomes.
Improved human-like speech synthesis using WaveGAN extensions.
problem Generating realistic speech from limited data.
method Extensions to WaveGAN for audio generation, including preprocessing, skip connections, and progressive structures.
result Moderate improvement in human likeness (Cohen's d coefficient of 0.65) in synthetic speech samples.
Intelli-Paint improves painting efficiency and naturalness.
problem Artwork generation is time-consuming and requires high proficiency.
method Intelli-Paint uses a progressive layering and sequential brushstroke guidance strategy.
result The approach reduces brushstrokes by ~60-80% without compromising quality.
Deep learning's success requires vast computing power, making future progress unsustainable.
problem Deep learning's success is heavily dependent on computing power, making future progress unsustainable.
method Cataloging and extrapolating the dependency on computing power for various deep learning applications.
result Continued progress in deep learning applications will require more computationally-efficient methods.
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.
Alpha-GPT 2.0 integrates human insights into AI-driven investment research.
problem Efficiency and precision in quantitative investment research.
method Iterative Human-AI interaction using large language models.
result Enhanced efficiency and precision in quantitative investment research.
Deep neural networks solve Raven's Progressive Matrices with high accuracy.
problem Testing relational reasoning in machine learning systems.
method Combining Wild Relation Networks with Multi-Layer Relation Networks and introducing Magnitude Encoding.
result Deep neural networks achieve 98.0 percent accuracy, significantly improving over previous methods.
This work designs an active world model learning system with progress-based curiosity.
problem Learning compact world models from visual exploration.
method Constructs a curious agent in a 3D environment, using γ-Progress as a curiosity signal. result The γ-Progress-driven controller outperforms state-of-the-art exploration strategies. Recent progress in artificial intelligence (AI) has renewed interest in building systems that learn and think like people. Many advances have come from using deep neural networks trained end-to-end in tasks such as object recognition, video games, and board games, achieving performance that equals or even beats humans …
Automatically evaluates image quality based on human judgment.
problem Difficulty in rigorously evaluating generated image quality.
method Generative model embeddings, human labels regression, and statistical matching.
result 66% accuracy in predicting human scores of image realism.
AlphaZero reveals new chess concepts learnable by top experts.
problem Extracting and understanding hidden knowledge from AI systems.
method Proposed method to extract new chess concepts from AlphaZero.
result Top chess grandmasters show improvements in learning new concepts.
Humans outperform DNNs on image degradations, especially when signals weaken.
problem Comparing human and DNN robustness in object recognition under various image manipulations.
method Comparison of robustness between humans and DNNs (ResNet-152, VGG-19, GoogLeNet) on object recognition under 12 types of image degradations.
result Humans consistently outperform DNNs on object recognition, especially under weaker signals.
AURA: Adaptive Uncertainty-aware Refinement for LLM-as-a-Judge Auditing
problem Auditing LLM-as-a-Judge decisions
method Adaptive uncertainty-aware refinement
result Human-consistent signal learning and evidence propagation
Quriosity analyzes curiosity-driven questions from diverse sources.
problem Understanding and analyzing human curiosity-driven questions.
method Collection of 13.5K questions from various sources, development of an iterative prompt improvement framework.
result 42% of questions are causal, revealing unique linguistic properties.
Bayesian Neural Networks show similar developmental stages as human learning.
problem Comparing human and machine learning stages.
method Operationalized developmental stages as data-set size, analyzed on three tasks.
result Bayesian Neural Networks exhibit similar developmental patterns to human learning.
Survey of automated neural architecture search methods.
problem Manual development of neural architectures is time-consuming and error-prone.
method Categorizes existing automated neural architecture search methods.
result Growing interest in automated methods due to manual development's limitations.
Deep learning improves human affect recognition in natural settings.
problem Automatic recognition of human emotions in real-world scenarios.
method Review and analysis of 233 studies using deep neural networks.
result Deep learning significantly enhances affect recognition from multimodal sensor data.
Paper evaluates deep generative models' ability to generalize geometric concepts.
problem Measuring deep generative models' ability to generalize across different geometric tasks.
method Raven's Progressive Matrices analogy, Infinite World dataset, Zero-Shot Intelligence Metric ZSI.
result Identifies bottlenecks and proposes optimization methods for few-shot and zero-shot learning.
New benchmarks for offline RL from diverse datasets.
problem Measuring progress in offline RL due to lack of suitable benchmarks.
method Developed benchmarks tailored for offline RL, focusing on diverse dataset properties.
result Revealed deficiencies in existing offline RL algorithms.
Paper proposes a progressive ensemble network for zero-shot image recognition.
problem Challenges of zero-shot learning due to lack of labeled data and expanding categories.
method Proposes a progressive ensemble network with multiple projected label embeddings.
result Demonstrates improved zero-shot image recognition performance on multiple datasets.
Algorithm learns to solve tasks by gradually expanding policy space.
problem Reinforcement learning difficulty progression.
method Decreasingly constrained policy space expansion.
result Superior learning rate in Tetris tasks.
SentRNA improves RNA design by integrating human strategies.
problem Designing sequences for large or complex RNA targets.
method SentRNA uses a neural network trained on human-designed RNA sequences.
result SentRNA solves complex targets previously unsolvable by machines.
AI in finance uses quantum logic for better decision-making.
problem Improving financial decision-making models using AI.
method Application of quantum logic in machine learning techniques.
result Advantages of quantum-inspired neural networks in finance.
Study finds humans outperform DNNs in object recognition under degraded images.
problem Comparing human and DNN object recognition robustness under image manipulations.
method Comparative analysis of human and DNN generalization abilities towards image degradations.
result Humans show greater robustness in object recognition under image manipulations compared to DNNs.
New AI assistant for power grid operators simplifies complex decision-making.
problem Complexity and uncertainty in power grid operations.
method Unified human-machine interface and AI integration.
result Development of a new assistant framework for power grid operators.
A general theory of innovation and progress in human society is outlined, based on the combat between two opposite forces (conservatism/inertia and speculative herding "bubble" behavior). We contend that human affairs are characterized by ubiquitous ``bubbles'', which involve huge risks which would not otherwise be tak…
New approach improves human activity recognition with wearables.
problem Improving human activity recognition with wearables.
method Exploiting latent relationships between multi-channel sensor modalities, data-agnostic augmentation, and a classification loss criterion.
result Achieves new state-of-the-art performance on four diverse activity recognition benchmarks.
New metric for video generation models, addressing quality, coherence, and diversity.
problem Lack of metrics for evaluating generative models of video.
method Proposed Fréchet Video Distance (FVD) and StarCraft 2 Videos (SCV) benchmark.
result FVD correlates well with human judgment of generated videos.
Benchmark for math reasoning models from human proofs.
problem Measuring and accelerating machine learning models in high-level mathematical reasoning.
method Built a non-synthetic dataset from theorem prover proofs, defined a task for model to fill in missing propositions, used hierarchical transformer to improve performance.
result Neural models can capture non-trivial mathematical reasoning, hierarchical transformer outperforms baseline.
AGAN automates GAN design, outperforming human-designed models.
problem Designing effective GAN architectures requires human expertise and trial-and-error.
method Automated neural architecture search (AGAN) for deep generative models.
result AGAN finds architectures that outperform state-of-the-art models in unsupervised and supervised image generation tasks.
Bayesian Neural Networks improve uncertainty modeling in facial emotion recognition.
problem High aleatoric uncertainty and visual ambiguity in facial emotion recognition.
method Bayesian Neural Networks approximated using MC-Dropout, MC-DropConnect, or Ensemble methods.
result Bayesian Neural Networks produce more human-like output probabilities.
New method improves human mesh recovery for obese people.
problem Improving mesh recovery for obese people.
method Generative optimization of mesh parameters from 2D keypoints.
result Significant improvement in mesh recovery performance on obese person images.
Knowing and modelling the migration phenomena and especially the social and economic consequences have a theoretical and practical importance, being related to their consequences for development, economic progress (or as appropriate, regression), environmental influences etc. One of the causes of migration, especially …
This paper proposes an ADMM-based method for progressive weight pruning of deep neural networks.
problem Large model size of deep neural networks hinder their applications on edge devices.
method Progressive weight pruning using ADMM for non-convex optimization problems.
result Achieves up to 34 times pruning rate for ImageNet and 167 times for MNIST datasets.
HAR-Net combines deep features with traditional hand-crafted features for better human activity recognition.
problem Challenges in traditional HAR methods, especially feature extraction.
method Combines deep learning and traditional feature engineering.
result Performance improvement of 0.9% compared to traditional SVM.
Iterated Amplification uses subproblem solutions to build training signals for complex tasks.
problem Learning complex tasks when humans can't directly evaluate performance.
method Progressively builds training signal by combining solutions to easier subproblems.
result Efficiently learns complex behaviors in algorithmic environments.
Agents learn to play a first-person multiplayer game at human level performance.
problem Training AI agents for complex, multi-agent, real-time environments.
method Population-based deep reinforcement learning with concurrent training of multiple agents.
result Achieved human-level performance in a first-person multiplayer game.
Compared to machines, humans are extremely good at classifying images into categories, especially when they possess prior knowledge of the categories at hand. If this prior information is not available, supervision in the form of teaching images is required. To learn categories more quickly, people should see important…
Novel algorithm improves poultry welfare by classifying chicken behaviors.
problem Classifying chicken behaviors from sparse and noisy data.
method Time series dictionary learning algorithm.
result Robustly learns from weakly labeled data sources.
SPIN converts weak LLMs to strong ones using self-play.
problem Growing strong LLMs without human-annotated data.
method Self-play fine-tuning (SPIN) starting from a supervised fine-tuned model.
result SPIN significantly improves LLM performance across benchmarks.
New method uses game theory to rate generative models.
problem Evaluating generative models' performance.
method Tournaments between generators and discriminators to summarize outcomes.
result Tournament win rate and skill rating provide effective model evaluations.
Boosted trees improve reinforcement learning solutions that are easy to understand.
problem Creating accurate reinforcement learning solutions that are also easy to understand.
method Using boosted regression trees to combine multiple regression trees.
result Boosted regression trees produce solutions that are as accurate as other methods but are also easy to understand.
EDINET-Bench evaluates LLMs on complex financial tasks using Japanese financial statements.
problem Challenges in evaluating LLMs on financial tasks due to specialized expertise and scarce benchmarks.
method Developed EDINET-Bench, an open-source Japanese financial benchmark for LLMs on tasks like fraud detection and earnings forecasting.
result State-of-the-art LLMs perform only marginally better than logistic regression in financial tasks, highlighting the need for more realistic benchmarks.
The last decade has seen huge progress in the development of advanced machine learning models; however, those models are powerless unless human users can interpret them. Here we show how the mind's construction of concepts and meaning can be used to create more interpretable machine learning models. By proposing a nove…
Machine learning is the science of discovering statistical dependencies in data, and the use of those dependencies to perform predictions. During the last decade, machine learning has made spectacular progress, surpassing human performance in complex tasks such as object recognition, car driving, and computer gaming. H…
Survey of LLMs in finance tasks, highlighting progress and challenges.
problem Transforming financial practices with advanced LLMs.
method Exploration of various financial tasks, categorization, and analysis of methodologies.
result Unlocking novel opportunities for financial applications with LLMs.
Deep models can be fooled by maliciously crafted examples.
problem Deep learning models are vulnerable to adversarial examples that can mislead predictions without being noticed by humans.
method Reviews adversarial example generation methods and defenses, discusses their limitations and future prospects.
result Adversarial examples can mislead deep learning models without being distinguishable by humans.
Paper reviews the evolution of alpha from human insight to AI-powered systems.
problem Exceeding market benchmarks in finance.
method Five-stage taxonomy integrating representation learning, multimodal data fusion, and LLM agents.
result Unified framework for evaluating and developing next-gen alpha systems.