VNLA uses vision and language to guide agents in finding objects in indoor environments.
problem Guiding agents in finding objects in indoor environments via language.
method Developed I3L framework for imitation learning with indirect intervention.
result Significantly improved success rate of learning agents over baselines.
A new method for optimizing language-based agentic systems using semantic backpropagation.
problem Lack of proper feedback assignment in optimizing agentic systems.
method Formalization of semantic backpropagation with semantic gradients and semantic gradient descent.
result Our method outperforms existing state-of-the-art methods for solving GASO problems.
AudioPaLM combines text and speech models to improve speech processing and translation.
problem Improving speech understanding and generation models.
method Unified multimodal architecture combining text and speech models.
result AudioPaLM significantly outperforms existing speech translation systems.
Enhances reward specification in RL with a novel language-based approach.
problem Reward specification in RL can lead to unintended, potentially harmful behaviours.
method Developed a novel class of language-based Reward Machines using RML's built-in memory.
result Can specify non-regular, non-Markovian reward functions for complex tasks.
Natural language instructions improve reinforcement learning efficiency.
problem Designing effective reward functions for reinforcement learning is difficult and time-consuming.
method Proposes LanguagE-Action Reward Network (LEARN) to map natural language instructions to intermediate rewards.
result Language-based rewards lead to successful task completion 60% more often than without language.
We introduce and demonstrate a new approach to inference in expressive probabilistic programming languages based on particle Markov chain Monte Carlo. Our approach is simple to implement and easy to parallelize. It applies to Turing-complete probabilistic programming languages and supports accurate inference in models …
ChemBoost predicts protein-ligand binding affinity using SMILES syntax.
problem Predicting high affinity drug-target interactions from sequence similarity alone.
method ChemBoost uses SMILES syntax to represent ligands as documents and proteins as sequences or ligand-centric features. It learns chemical word embeddings and predicts affinities using eXtreme Gradient Boosting.
result ChemBoost outperforms state-of-the-art systems in predicting protein-ligand affinities.
We introduce the value iteration network (VIN): a fully differentiable neural network with a `planning module' embedded within. VINs can learn to plan, and are suitable for predicting outcomes that involve planning-based reasoning, such as policies for reinforcement learning. Key to our approach is a novel differentiab…
Machine learning automates proof generation in Coq proof assistant.
problem Automating proof construction in proof assistants.
method Developed ASTactic, a deep learning model generating tactics as ASTs.
result ASTactic can generate effective tactics and prove new theorems.
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.
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 uses clustering to identify food assistance deserts in Ohio.
problem Food insecurity and accessibility issues in Ohio.
method Gaussian Mixture Model (GMM) clustering technique.
result Identifies food assistance deserts within Ohio.
Framework allows organizations to collaborate on learning tasks securely.
problem Limited collaboration due to security constraints.
method Assisted Learning framework for supervised learning tasks.
result Near-oracle learning performance achieved without revealing sensitive information.
A robot assists a human in a bandit task to learn and improve performance.
problem Learning preferences in humans when they are also learning.
method Introduces assistive multi-armed bandit, where a robot helps a human maximize cumulative reward.
result Human performance can be better when effectively communicating observed rewards to the robot, not just by learning optimally.
Improved accuracy in a commercial assistant by smartly selecting new training data.
problem Expensive and time-consuming to annotate new data for ML systems.
method Automatically identifies new helpful examples suitable for human annotation.
result The proposed method leads to higher accuracy improvements with a fixed annotation budget.
Improves survey sampling with unbiased machine learning methods.
problem Design-consistent model-assisted estimation lacks a general theory for machine learning.
method Proposes a subsampling Rao-Blackwell method for design-unbiased estimation.
result Yields efficiency gains over standard methods while ensuring valid estimation.
Language-based methods improve human similarity approximations without requiring many human judgments.
problem Approximating human similarity judgments using pre-trained deep neural networks (DNNs) is challenging and expensive.
method Developed language-based methods to approximate human similarity judgments, validated with adaptive tag collection pipeline.
result Language-based methods significantly improve performance over DNN-based methods with fewer human judgments.
Computer-assisted method finds new Einstein metrics on spheres.
problem Finding new Einstein metrics on spheres.
method Simple computer-assisted procedure to construct invariant cohomogeneity one Einstein metrics.
result New Einstein metrics on S11, S12, S13 and S7imesS3. Improves Bayesian neural learning efficiency with surrogate-assisted parallel tempering.
problem Challenges in Bayesian neural learning due to large models and data.
method Combines parallel tempering MCMC with surrogate-assisted optimization for computationally expensive models.
result Significantly lowers computational cost while maintaining quality in decision making.
System identifies and responds to help queries in personal assistants.
problem Difficulty in remembering command structures for various tasks in personal assistants.
method Proposes a C-BiLSTM based classifier and semantic ANN module to detect and respond to help queries.
result System outperforms other approaches in returning relevant responses for help queries.
System optimizes retrieval for personal assistants using reinforcement learning.
problem Needing a neural retrieval-based Q&A system for user memory.
method Direct optimization of F1-score using reinforcement learning.
result Improved retrieval performance on test sets.
Study evaluates the impact of academic support center's face-to-face assistance on student performance.
problem Underestimation of Academic Support Center's true impact due to group bias.
method Applied causal inference theory and T-learner to evaluate conditional average treatment effect (CATE) of F2F personal assistance.
result Developed a new CATE function that depends on the number of F2F sessions, predicting improved CATE performance.
AI assistants often give convincing but incorrect responses to match user beliefs.
problem Sycophancy in AI assistants that use human feedback.
method Examined five AI assistants across four tasks, analyzed human preference data, and compared model outputs against preference models.
result Sycophancy is a general behavior of AI assistants, driven in part by human preference judgments.
Develops a two-layer model to design mortgage assistance products.
problem Designing effective mortgage assistance products to improve household resilience.
method Two-layer approach: simulation and optimization.
result Shows how the approach can design and evaluate mortgage assistance products.
The AMIDST Toolbox is a software for scalable probabilistic machine learning with a spe- cial focus on (massive) streaming data. The toolbox supports a flexible modeling language based on probabilistic graphical models with latent variables and temporal dependencies. The specified models can be learnt from large data s…
Helps visually impaired users make better decisions by adjusting their observations.
problem Systematic biases in users' perception and processing of visual information.
method Synthesizes new observations based on true observations to correct user biases.
result Significant improvement in task performance for users with various biases.
Paper proposes a visual tool for analyzing financial markets.
problem Rational negligence in financial markets during the 2008 crisis.
method Visual declarative language based on port-graph rewriting.
result Visual tool for analyzing asset-backed securities.
Robust Bayes-Assisted Conformal Prediction improves prediction set sizes.
problem Misspecification of Bayesian working model and prior misalignment.
method RoBAS (Robust Bayes-Assisted Shrinkage) framework with two instantiations.
result Improves prediction set sizes in shifted settings.
Robust Bayes-Assisted Conformal Prediction improves prediction set sizes.
problem Misspecification of Bayesian working model and prior misalignment.
method RoBAS (Robust Bayes-Assisted Shrinkage) framework with two instantiations.
result Proposed scores adapt to prior quality, reducing interval widths in shifted settings.
Proposes a method to align language and image data.
problem Aligning language and image data for better understanding.
method Uses triplet loss to learn consistent embeddings of language and images.
result Outperforms four baselines across multiple metrics.
A new framework improves LSTM performance without adding more parameters.
problem Improving LSTM performance without increasing model complexity.
method A unifying framework of bilinear LSTMs that balances hidden state vector size and weight matrix approximation quality.
result Bilinear LSTMs achieve superior performance compared to linear LSTMs without additional parameters.
Improved knowledge distillation using a teacher assistant to bridge the gap between student and teacher networks.
problem Large neural networks are hard to deploy on edge devices due to size constraints.
method Introduce multi-step knowledge distillation with an intermediate-sized teacher assistant.
result The proposed multi-step distillation method improves student network performance.
AI-assisted interviews allow respondents to describe experiences naturally, but mapping those accounts into structured survey variables is fallible.
problem Mapping AI-assisted interview responses into structured survey variables is fallible.
method Adaptive Matrix Validation (AMV) is proposed, which involves mapping responses into tabular data and using a small set of structured questions for statistical adjustment.
result The estimator calibrates mapped values using validation answers from other respondents and corrects remaining error with validation answers observed for the target respondent.
Paper improves voice trigger detection for privacy-centric smart assistants.
problem Mitigating false triggers in voice-activated smart assistants.
method Analyzing ASR lattices using graph neural networks (GNN).
result GNNs effectively reduce false triggers by ~87% at 99% true positive rate.
We study data-driven assistants that provide congestion forecasts to users of shared facilities (roads, cafeterias, etc.), to support coordination between them, and increase efficiency of such collective systems. Key questions are: (1) when and how much can (accurate) predictions help for coordination, and (2) which as…
Generative AI boosts productivity and improves customer service quality.
problem Productivity and quality of customer support agents.
method Staggered introduction of a generative AI-based conversational assistant in customer support.
result AI increases productivity by 15% on average, with significant heterogeneity across workers.
A green simulation-assisted reinforcement learning method for biomanufacturing.
problem Complexity, high variability, lead time, and limited historical data in biopharmaceutical manufacturing.
method Quantifies model risk, uses posterior distribution, and selectively reuses simulation data.
result Demonstrates promising performance in online learning and decision making.
PixL2R maps natural language to pixel-based rewards for RL, improving sample efficiency.
problem Sparse reward settings in RL limit applicability to complex problems.
method Directly maps natural language descriptions to pixel-based rewards for guiding RL.
result Language-based rewards significantly improve sample efficiency in policy learning.
We provide a computer-assisted proof of the holomorphy of the quartic and the octic meromorphic differentials arising in the main Theorem 4.11 of our paper 'The Classification of Branched Willmore spheres in the 3-Sphere and the 4-Sphere' (arXiv:1706.01405), using the free mathematical software Sage.
New method combines randomization tests and flexible models for valid inference without splitting data.
problem Valid inference in randomized panel experiments with complex effect heterogeneity.
method Model-assisted randomization tests that estimate unsigned CATE from residualized outcomes.
result CATE-assisted tests control Type I error and achieve higher power than alternatives.
A new method uses MCMC-assisted normalizing flows for efficient Bayesian sampling.
problem Sampling from complex posterior distributions in Bayesian statistics.
method Training a normalizing flow using direct KL divergence and MCMC assistance.
result The method improves sampling efficiency for complicated posterior distributions.
Paper proposes i-vector approach for NLI with improved accuracy.
problem Identifying a speaker's native language from speech in a second language.
method i-vector approach using MFCC and GFCC features.
result Improved accuracy in NLI system, especially with GFCC features.
Associating image regions with text queries has been recently explored as a new way to bridge visual and linguistic representations. A few pioneering approaches have been proposed based on recurrent neural language models trained generatively (e.g., generating captions), but achieving somewhat limited localization accu…
Proposes a new method to control FDR using frequentist-assisted horseshoe for high-dimensional testing.
problem Designing tests with frequentist false discovery rate control using horseshoe prior.
method Frequentist-assisted horseshoe procedure for high-dimensional normal means testing.
result Consistently achieves robust finite-sample FDR control in various sparse cases.
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.
Neural Assistant integrates knowledge reasoning and dialogue generation in a single model.
problem Challenges in task-oriented dialog systems, including multi-turn language understanding and generation, knowledge retrieval and reasoning, and action prediction.
method Develops a single neural network model that jointly predicts text responses and actions from conversation history and external knowledge.
result The model learns to reason on external knowledge with weak supervision, improving factual accuracy and language generation performance.
The paper enhances a virtual assistant's humor to improve user satisfaction.
problem Improving a virtual assistant's ability to deliver humorous responses.
method Combines traditional NLP techniques with self-attentional networks and multi-task learning, using implicit feedback for labeling.
result Deep-learning models outperform heuristic methods in real-world user satisfaction.
Improved speech recognition for voice assistants by analyzing speech data.
problem Reducing false triggers in speech-enabled assistants.
method Post-processing LVCSR hypothesis lattice with a Bidirectional Lattice Recurrent Neural Network (LatticeRNN).
result LatticeRNN significantly improves detection accuracy over traditional methods.