We present an approach for building an active agent that learns to segment its visual observations into individual objects by interacting with its environment in a completely self-supervised manner. The agent uses its current segmentation model to infer pixels that constitute objects and refines the segmentation model …
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.
169,051 papers · 148 categories
Trend · papers per month
48 results for “object interaction”
Modeling interacting objects with latent Gaussian process ODEs.
problem Time uncertainty-aware modeling of continuous-time dynamics of interacting objects.
method A new model using latent Gaussian process ordinary differential equations to infer independent dynamics and interactions.
result Our model improves long-term predictions and successfully encapsulates independent dynamics and interactions.
A model learns object representations for physical scene understanding without direct supervision.
problem Learning object-centric representations without direct supervision of object properties.
method Object-Oriented Prediction and Planning (O2P2) model that learns perception, physics interaction, and rendering functions.
result The model can predict physical interactions and build block towers more complex than those seen during training.
End-to-end multi-object tracking learns object interactions.
problem Object tracking ignores interactions between objects.
method End-to-end relational reasoning model MOHART.
result Relational reasoning improves tracking and prediction.
R-SQAIR adds relational bias to sequential object attention models for better object interactions.
problem Traditional sequential multi-object attention models struggle with relational inferences.
method Proposes R-SQAIR, a relational extension of SQAIR with a parallel pairwise interaction module.
result Demonstrates gains in object relations and combinatorial generalization over sequential mechanisms.
Generative model learns to compose images of objects from different distributions.
problem Capturing complex interactions between objects in scenes.
method Composition-by-Decomposition (CoDe) network.
result Model generates realistic composite images capturing interactions between input objects.
STOVE predicts convincing physical behavior in videos.
problem Learning models from videos with objects and interactions.
method Compositional state-space model combining image and dynamics models.
result Predicts videos with convincing physical behavior over hundreds of timesteps.
SPARTAN learns sparse interaction graphs between objects in scenes.
problem Capturing structured interactions between entities in complex settings remains challenging.
method SPARTAN is a Transformer-based world model that learns sparse, context-dependent interaction graphs through sparsity regularization on attention patterns.
result SPARTAN achieves significantly improved few-shot adaptation to dynamics changes and robustness against distractors.
KINet learns object interactions without supervision for robotic pushing.
problem Lack of supervised data for object-centric forward prediction.
method End-to-end unsupervised framework using keypoint representation and contrastive estimation.
result Automatically generalizes to unseen scenarios and accurately predicts future states.
The paper introduces a new method to measure the shape relations between biological objects using r-parallel sets.
problem The influence of neighboring objects on the shape and function of biological objects.
method The authors develop a theory based on spatial point processes to measure the geometrical interaction between objects.
result The proposed measures provide detailed information about the shape of individual objects and their interactions.
AXIOM learns games quickly with simple object models.
problem Data inefficiency in reinforcement learning.
method Expanding object-centric models with active inference.
result AXIOM learns games in 10,000 steps with minimal parameters.
GENESIS generates and samples 3D scenes by capturing object interactions.
problem Lack of models that explicitly capture object interactions in scene generation.
method Object-centric latent variables, spatial GMM, amortized inference, autoregressive prior.
result First object-centric generative model of 3D visual scenes.
A Braid Boxmath.HO
Interactive art piece shows braid groups and plane motions.
problem Understanding braid groups and their actions.
method Interactive art piece illustrating two braid group definitions and their action on free group.
result Demonstrates all plane motions in a single subspace.
Simplified interactive image segmentation using kNN graphs.
problem Interactive image segmentation with user-provided labels.
method Undirected kNN graphs for label propagation.
result Effective interactive segmentation with significant accuracy.
A new method learns object hierarchies from images to reason about physical interactions.
problem Learning about the interactions of complex objects and their dynamics.
method Unsupervised learning of object hierarchies from raw visual images.
result Improves over a strong baseline at modeling synthetic and real-world videos.
This work discovers latent field effects governing interacting dynamical systems.
problem Discovering field effects governing interacting dynamical systems.
method Proposes neural fields to learn latent force fields from observed dynamics, disentangling local object interactions and global field effects.
result Accurately discovers latent field effects in various dynamical systems.
Algorithm for agents to agree on a single objective in multi-task networks.
problem Decentralized decision-making in multi-task networks with multiple objectives.
method Distributed decision-making algorithm for agents observing different models.
result Agents reach agreement on which model to track for network performance enhancement.
We use deep learning to model interactions across two or more sets of objects, such as user-movie ratings, protein-drug bindings, or ternary user-item-tag interactions. The canonical representation of such interactions is a matrix (or a higher-dimensional tensor) with an exchangeability property: the encoding's meaning…
CAZSL learns to generalize physical interactions from context.
problem Designing models that can generalize over unknown objects during manipulation.
method Context-aware zero-shot learning using Siamese network architecture, embedding space masking, and regularization.
result CAZSL models can generalize to different parameters or features of interacting objects.
A novel clustering method uses torque balance to group objects.
problem Grouping similar objects in various scientific fields.
method Inspired by gravitational interactions, a parameter-free clustering algorithm based on mass and distance.
result The algorithm effectively clusters objects regardless of their shape, size, or density.
The paper introduces metrics for robust unsupervised learning of vehicle interactions.
problem Robust representation learning of temporal dynamic interactions in robotics.
method Geometric approach using Procrustes distance and optimal transport for comparing interaction distributions.
result Metrics for assessing stability and comparing interaction learning algorithms.
A game-theoretic framework identifies influential hyperparameters for neural networks.
problem Understanding which hyperparameters are most important for neural network performance.
method Employing Shapley Effects for global sensitivity analysis and Pareto front sets for identifying effective configurations.
result Reveals which hyperparameters are most influential for different objectives in neural networks.
VR enables professionals to develop deep learning models by moving virtual objects.
problem Challenges in understanding and developing deep learning models.
method Built a VR-based DL development environment where users interact with tangible objects to construct neural networks.
result Users can develop and understand DL models intuitively through VR, with real-time accuracy feedback.
Unsupervised learning of latent object properties from interactions.
problem Discovering latent physical properties of objects without labeled data.
method Perception-Prediction Network (PPN) framework.
result PPN can accurately simulate and translate latent object properties.
Introduces R-SSM for modeling multi-object dynamics with GNNs and normalizing flows.
problem Complex interactions and evolutions in multi-object systems are hard to model.
method Relational state-space model (R-SSM) using graph neural networks (GNNs) and normalizing flows.
result Empirically validated on synthetic and real datasets.
Dreamer 4 learns Minecraft tasks from videos alone.
problem Accurately predicting object interactions in complex environments.
method Reinforcement learning inside a fast, accurate world model.
result Dreamer 4 outperforms previous models in Minecraft, learning from only offline data.
Proposes Deep Scenes for interaction-aware scene understanding in reinforcement learning for autonomous driving.
problem Leveraging deep reinforcement learning for high-level decision making in autonomous driving requires handling variable-length sequences of different object types and interactions.
method Introduces Deep Scenes architecture, an extension of Deep Sets or Graph Convolutional Networks, to learn complex interaction-aware scene representations.
result Graph-Q and DeepScene-Q algorithms outperform state-of-the-art methods in evaluations with SUMO.
New method provides fine-grained feedback on interactive student programs.
problem Time-consuming manual grading of interactive student programs.
method Meta-exploration approach using reinforcement learning.
result 94.3% accuracy in providing fine-grained feedback.
OP3 models entities for better task generalization in reinforcement learning.
problem Generalizing to unseen physical tasks with combinatorial complexity.
method Object-centric perception, prediction, and planning (OP3) framework.
result OP3 outperforms oracle models and state-of-the-art video prediction models.
CLIC learns to control objects in non-rewarding environments by imitating a mentor.
problem Learning in non-rewarding, multi-object environments with non-observable intentions.
method Curriculum Learning and Imitation (CLIC) for Control.
result CLIC effectively learns and imitates a mentor's interactions to control objects.
Self-Predictive Representations improves data-efficient reinforcement learning from limited interaction.
problem Efficient reinforcement learning from limited data.
method Train agents to predict future latent state representations using self-supervised objectives.
result Achieves a median human-normalized score of 0.415 on Atari with 100k steps of interaction, 55% improvement over previous state-of-the-art.
Quantifying Model Complexity via Functional Decomposition for Better Post-Hoc Interpretabilitystat.ML
New method quantifies model complexity for better interpretation.
problem Complex models produce misleading interpretation results.
method Functional decomposition to quantify model complexity.
result Post-hoc interpretation of complex models is more reliable and compact.
Robots learn conservatively from human corrections, avoiding unintended changes to their objectives.
problem Robots learn from human corrections but may not align with the intended objectives due to misspecified hypothesis spaces.
method Robots reason in real-time about the relevance of human corrections to their hypothesis space, learning more conservatively.
result Robots can avoid unintended learning from human corrections, improving alignment with intended objectives.
Develops scalable differentiable physics for complex object interactions.
problem Limited scalability of existing differentiable physics solvers.
method Adopting meshes for arbitrary geometry, localized collision handling, and accelerated implicit differentiation.
result Significantly reduces memory and computation requirements compared to particle-based methods.
Reinforcement Learning AI commonly uses reward/penalty signals that are objective and explicit in an environment -- e.g. game score, completion time, etc. -- in order to learn the optimal strategy for task performance. However, Human-AI interaction for such AI agents should include additional reinforcement that is impl…
Bayesian method helps decision-makers find preferred solutions in multi-objective optimization.
problem Identifying preferred solutions from the Pareto set in multi-objective optimization problems.
method Bayesian model to estimate decision-maker's utility function based on pairwise comparisons, guided by a principled elicitation strategy.
result Superior performance in finding high-utility solutions with a small number of queries.
When encountering novel objects, humans are able to infer a wide range of physical properties such as mass, friction and deformability by interacting with them in a goal driven way. This process of active interaction is in the same spirit as a scientist performing experiments to discover hidden facts. Recent advances i…
Loss Data Analyticsq-fin.RM
Interactive book integrates probability models with big data analytics.
problem Lack of integration between classical loss data models and modern analytic tools.
method Combines classical loss data models with modern analytic tools and big data.
result Promotes deeper learning through interactive elements and multiple language support.
Decomposes game environments into controllable and non-controllable parts for faster learning.
problem Difficulties in end-to-end learning for complex environments.
method Modularization of the environment into controllable and non-controllable parts, using supervised and reinforcement learning.
result Human-level performance achieved in 10-15 minutes of game time with proper decomposition.
Observations consisting of measurements on relationships for pairs of objects arise in many settings, such as protein interaction and gene regulatory networks, collections of author-recipient email, and social networks. Analyzing such data with probabilisic models can be delicate because the simple exchangeability assu…
Bayesian optimization with preference learning identifies preferred solutions in multi-objective problems.
problem Optimizing multiple criteria with decision maker preferences in expensive functions.
method Bayesian optimization with interactive preference learning and active acquisition function.
result Identifies the most preferred solution with reduced interaction cost.
Proposes local coordinate frames for improving model performance in complex dynamical systems.
problem Improving model performance in complex, non-linear, and time-dependent dynamical systems.
method Introduces roto-translation invariant local coordinate frames for geometric graphs.
result The approach outperforms state-of-the-art models in various complex scenarios.
Infants are experts at playing, with an amazing ability to generate novel structured behaviors in unstructured environments that lack clear extrinsic reward signals. We seek to replicate some of these abilities with a neural network that implements curiosity-driven intrinsic motivation. Using a simple but ecologically …
Paper studies competitive networks where teams aim to minimize their own objectives, adapting to each other's strategies.
problem Competitive networks where teams have conflicting objectives.
method Proposes diffusion learning algorithms for two classes of network games: zero-sum and non-zero-sum.
result Stability performance of proposed algorithms analyzed and demonstrated through experiments.
Detect objects from motion without annotations.
problem Weakly supervised object detection.
method Train model on videos of moving objects and negative scenes.
result Detects objects in single images without annotations.
On Agents and Equilibriaq-fin.GN
This essay discusses the advantages of a probabilistic agent-based approach to questions in theoretical economics, from the nature of economic agents, to the nature of the equilibria supported by their interactions. One idea we propose is that "agents" are meta-individual, hierarchically structured objects, that includ…
A Human-in-the-Loop Bayesian Optimization Framework for Constraint-Aware Bioprocess Developmentcs.LG
A Human-in-the-Loop Bayesian Optimization framework for constraint-aware bioprocess development.
problem Bioprocess development
method Pareto Front Guided Sampling (PFGS) with Bayesian Optimization (BO)
result Systematic identification of high-performing, feasibility-compliant, and perturbation-resilient operating conditions.
Deep Sets improve reinforcement learning agent's object-centered navigation and generalization.
problem Improving reinforcement learning agents' ability to generalize to unseen objects and goals.
method Combining object-wise permutation invariant networks (Deep Sets) and gated-attention mechanisms.
result Agent demonstrates strong generalization to out-of-distribution goals in a procedurally-generated 2D world.