Formalizes video world models as group actions on states and uses latent regularization with synthesized supervision to enforce consistency, introducing GAC and GAR metrics that improve structural correctness in SOTA models.
Rapid exploration for open-world navigation with latent goal models
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
roles
dataset 1polarities
use dataset 1representative citing papers
DRATS derives a minimax objective from a feasibility formulation of MTRL to adaptively sample tasks with the largest return gaps, leading to better worst-task performance on MetaWorld benchmarks.
3D-Belief maintains and updates explicit 3D beliefs about partially observed environments to enable multi-hypothesis imagination and improved performance on embodied tasks.
STRNet improves goal-conditioned visual navigation by replacing simplistic encoders and pooling with a spatio-temporal fusion module that performs spatial graph reasoning and hybrid temporal modeling.
NavWM unifies latent world tokens and anchor-based multimodal trajectory forecasting into a closed-loop planner that improves future state generation and zero-shot navigation.
AR Forcing trains diffusion world models by integrating standard noise prediction loss into an autoregressive loop that uses self-generated predictions as context, reducing train-inference mismatch for improved long-horizon image consistency and trajectory accuracy on navigation datasets.
QHyer replaces return-to-go with a state-conditioned Q-estimator and adds a gated hybrid attention-mamba backbone to achieve state-of-the-art performance in offline goal-conditioned RL on both Markovian and non-Markovian datasets.
FeudalNav decomposes visual navigation into hierarchical levels with a visual-similarity latent memory, delivering competitive Habitat AI results without any odometry.
COMPASS is a manipulation-aware active sensing framework that raises simulated manipulation success rates by 24.25% over information-gain-only baselines in a new four-level confined-space benchmark.
GoViG decomposes goal-conditioned navigation instruction generation into visual state prediction and instruction synthesis using an autoregressive multimodal LLM with one-pass and interleaved reasoning, showing gains on a new R2R-Goal dataset.
A generative navigation world model that uses sparse anchored rollout with epipolar constraints to reduce perceptual and geometric drift.
citing papers explorer
-
World Models as Group Actions
Formalizes video world models as group actions on states and uses latent regularization with synthesized supervision to enforce consistency, introducing GAC and GAR metrics that improve structural correctness in SOTA models.
-
Distributionally Robust Multi-Task Reinforcement Learning via Adaptive Task Sampling
DRATS derives a minimax objective from a feasibility formulation of MTRL to adaptively sample tasks with the largest return gaps, leading to better worst-task performance on MetaWorld benchmarks.
-
3D-Belief: Embodied Belief Inference via Generative 3D World Modeling
3D-Belief maintains and updates explicit 3D beliefs about partially observed environments to enable multi-hypothesis imagination and improved performance on embodied tasks.
-
STRNet: Visual Navigation with Spatio-Temporal Representation through Dynamic Graph Aggregation
STRNet improves goal-conditioned visual navigation by replacing simplistic encoders and pooling with a spatio-temporal fusion module that performs spatial graph reasoning and hybrid temporal modeling.
-
NavWM: A Unified Navigation World Model for Foresight-Driven Planning
NavWM unifies latent world tokens and anchor-based multimodal trajectory forecasting into a closed-loop planner that improves future state generation and zero-shot navigation.
-
AR Forcing: Towards Long-Horizon Robot Navigation World Model
AR Forcing trains diffusion world models by integrating standard noise prediction loss into an autoregressive loop that uses self-generated predictions as context, reducing train-inference mismatch for improved long-horizon image consistency and trajectory accuracy on navigation datasets.
-
QHyer: Q-conditioned Hybrid Attention-mamba Transformer for Offline Goal-conditioned RL
QHyer replaces return-to-go with a state-conditioned Q-estimator and adds a gated hybrid attention-mamba backbone to achieve state-of-the-art performance in offline goal-conditioned RL on both Markovian and non-Markovian datasets.
-
FeudalNav: A Simple Framework for Visual Navigation
FeudalNav decomposes visual navigation into hierarchical levels with a visual-similarity latent memory, delivering competitive Habitat AI results without any odometry.
-
COMPASS: Confined-space Manipulation Planning with Active Sensing Strategy
COMPASS is a manipulation-aware active sensing framework that raises simulated manipulation success rates by 24.25% over information-gain-only baselines in a new four-level confined-space benchmark.
-
GoViG: Goal-Conditioned Visual Navigation Instruction Generation via Multimodal Reasoning
GoViG decomposes goal-conditioned navigation instruction generation into visual state prediction and instruction synthesis using an autoregressive multimodal LLM with one-pass and interleaved reasoning, showing gains on a new R2R-Goal dataset.
-
Drift-Resistant Navigation World Model with Anchored Epipolar Guidance
A generative navigation world model that uses sparse anchored rollout with epipolar constraints to reduce perceptual and geometric drift.