WildBox provides over 237k 3D wildlife annotations from drone video and benchmarks reveal zero-shot 3D detection at 0 AP but fine-tuned performance of 8.68 AP-BEV and 13.17 AP3D, with depth estimation causing most errors.
hub Mixed citations
Lee, Matthew Tan, Yuke Zhu, and Jeannette Bohg
Mixed citation behavior. Most common role is background (67%).
69
Pith papers citing it
1,044
external citations · external index
Background
67% of classified citations
hub tools
citation-role summary
background 4
method 2
citation-polarity summary
representative citing papers
Uni-Mo generates 7,488 language-annotated quadruped motions via LLM prompts and video diffusion, lifts them to 3D trajectories, and trains policies achieving 96.7% real-robot success on 392 sampled motions.
VLM-PBRS trains a potential function from small-VLM preferences to enable PBRS in RL, improving sample efficiency in Meta-World and Franka Kitchen without reward hacking.
MPC-Injection biases off-policy RL locomotion policies toward controller-induced behavior basins by injecting MPC transitions into the replay buffer.
A matrix-free, GPU-compatible PyTorch implementation of phase-field fracture with explicit dynamics, custom differentiable implicit damage solve, benchmarks on dynamic and quasi-static cases, and inverse recovery of fracture energy G_c via L-BFGS.
WireCraft is a new configurable simulation benchmark for industrial DLO manipulation with three task families, dual physics models, and shared evaluation of RL, IL, and VLA policies showing high success under privileged state but bottlenecks for vision-based methods.
CHORUS adapts a single VLA backbone for decentralized control of diverse robot teams, achieving 64-point gains over from-scratch decentralized baselines and outperforming centralized methods in real-world tasks using only local observations.
NDR-SHKF replaces the static forgetting factor in Sage-Husa Kalman Filters with a learned vector-valued memory attenuation policy from a bifurcated recurrent network trained end-to-end on whitened innovations to minimize estimation error.
DiffLNS uses a discrete diffusion initializer to produce warm-start plans that lift LNS2 success rates to 95.8% across 20 congested MAPF settings, generalizing from 96 to 312 agents.
Pose graph optimization is recast as damped Riemannian dynamics on Lie groups, enabling a fully distributed algorithm with a semi-implicit integrator that converges under both synchronous and asynchronous communication.
LLM-Foraging uses off-the-shelf LLMs for decentralized tactical decisions in CPFA-based swarm foraging, collecting more resources than GA-tuned baselines across 36 varied configurations while showing greater consistency.
SPARCS uses a differentiable contact model and sparse Hessian solver to jointly optimize shapes and poses of up to five interacting objects, producing physically valid simulation-ready reconstructions.
Combines offline behavioral cloning with online Real-Time Recurrent RL fine-tuning on LrcSSM models to adapt autonomous driving policies to distribution shifts, validated in simulation and on a real 1:10-scale robot with event camera.
AID trains diffusion policies via behavior cloning on existing MAIPP planners followed by RL fine-tuning to achieve faster execution and higher information gain in multi-agent coordination.
QuickLAP combines physical corrections with LLM-parsed natural language in a closed-form Bayesian update, reducing reward-learning error in simulated driving and improving user ratings in a 15-person study.
Guided RL using Bezier curves and UARM model enables efficient, explainable omnidirectional jumping in quadruped robots.
INSANE releases multiple MAV datasets with cross-environment trajectories, rich multi-IMU and camera suites, high-rate vibration data, and sub-centimeter RTK GNSS ground truth for localization research.
Oriented per-voxel height images plus map-informed dual-resolution sampling yield robust real-time LiDAR-inertial odometry where standard LIO diverges.
A learned feedback policy replaces manual parameter tuning in distributed Riemannian optimization over matrix Lie groups, achieving lower objective values on multi-robot mapping benchmarks.
Symmetric (even highly) pessimistic value functions can generalize optimally in GTI-ZSPT offline RL while mildly pessimistic asymmetric ones cannot; DAC-Output during extraction is the strongest DA method tested.
CI-MSE improves Spearman's rank correlation between offline validation error and real rollout performance from -0.61 (raw MSE) to -0.87 across policy checkpoints in simulation and real-world robot manipulation experiments.
Causal Spectral Policy decomposes actions spectrally into coarse motion from obs/language and conditional fine corrections, outperforming baselines on precision manipulation tasks.
MAGR-BB matches exhaustive search accuracy on multi-agent Blocksworld while reducing hypothesis evaluations by orders of magnitude via RL scoring inside factorized branch-and-bound.
HilDA pre-trains LiDAR backbones via multi-layer and global distillation from vision models plus temporal occupancy diffusion, yielding SOTA results on detection, flow, and occupancy tasks.
citing papers explorer
-
WildBox: A Dataset and Benchmark for Aerial Monocular 3D Detection of African Savanna Wildlife
WildBox provides over 237k 3D wildlife annotations from drone video and benchmarks reveal zero-shot 3D detection at 0 AP but fine-tuned performance of 8.68 AP-BEV and 13.17 AP3D, with depth estimation causing most errors.
-
Unleashing Infinite Motion: Scaling Expressive Quadrupedal Motion via Generative Video Priors
Uni-Mo generates 7,488 language-annotated quadruped motions via LLM prompts and video diffusion, lifts them to 3D trajectories, and trains policies achieving 96.7% real-robot success on 392 sampled motions.
-
Automating Potential-based Reward Shaping with Vision Language Model Guidance
VLM-PBRS trains a potential function from small-VLM preferences to enable PBRS in RL, improving sample efficiency in Meta-World and Franka Kitchen without reward hacking.
-
MPC-Injection: Biasing Off-Policy Locomotion RL Toward Controller-Induced Behavior Basins
MPC-Injection biases off-policy RL locomotion policies toward controller-induced behavior basins by injecting MPC transitions into the replay buffer.
-
A matrix-free, differentiable PyTorch solver for phase-field fracture: Formulation, benchmarks, and inverse analysis
A matrix-free, GPU-compatible PyTorch implementation of phase-field fracture with explicit dynamics, custom differentiable implicit damage solve, benchmarks on dynamic and quasi-static cases, and inverse recovery of fracture energy G_c via L-BFGS.
-
WireCraft: A Simulation Benchmark for Industrial DLO Manipulation
WireCraft is a new configurable simulation benchmark for industrial DLO manipulation with three task families, dual physics models, and shared evaluation of RL, IL, and VLA policies showing high success under privileged state but bottlenecks for vision-based methods.
-
CHORUS: Decentralized Multi-Embodiment Collaboration with One VLA Policy
CHORUS adapts a single VLA backbone for decentralized control of diverse robot teams, achieving 64-point gains over from-scratch decentralized baselines and outperforming centralized methods in real-world tasks using only local observations.
-
Learned Memory Attenuation in Sage-Husa Kalman Filters for Robust UAV State Estimation
NDR-SHKF replaces the static forgetting factor in Sage-Husa Kalman Filters with a learned vector-valued memory attenuation policy from a bifurcated recurrent network trained end-to-end on whitened innovations to minimize estimation error.
-
Discrete Diffusion for Complex and Congested Multi-Agent Path Finding with Sparse Social Attention
DiffLNS uses a discrete diffusion initializer to produce warm-start plans that lift LNS2 success rates to 95.8% across 20 congested MAPF settings, generalizing from 96 to 312 agents.
-
Distributed Pose Graph Optimization via Continuous Riemannian Dynamics
Pose graph optimization is recast as damped Riemannian dynamics on Lie groups, enabling a fully distributed algorithm with a semi-implicit integrator that converges under both synchronous and asynchronous communication.
-
LLM-Foraging: Large Language Models for Decentralized Swarm Robot Foraging
LLM-Foraging uses off-the-shelf LLMs for decentralized tactical decisions in CPFA-based swarm foraging, collecting more resources than GA-tuned baselines across 36 varied configurations while showing greater consistency.
-
Simulation-Ready Cluttered Scene Estimation via Physics-aware Joint Shape and Pose Optimization
SPARCS uses a differentiable contact model and sparse Hessian solver to jointly optimize shapes and poses of up to five interacting objects, producing physically valid simulation-ready reconstructions.
-
Adaptive Control in Autonomous Driving via Real-Time Recurrent RL
Combines offline behavioral cloning with online Real-Time Recurrent RL fine-tuning on LrcSSM models to adapt autonomous driving policies to distribution shifts, validated in simulation and on a real 1:10-scale robot with event camera.
-
AID: Agent Intent from Diffusion for Multi-Agent Informative Path Planning
AID trains diffusion policies via behavior cloning on existing MAIPP planners followed by RL fine-tuning to achieve faster execution and higher information gain in multi-agent coordination.
-
QuickLAP: Quick Language-Action Preference Learning for Semi-Autonomous Agents
QuickLAP combines physical corrections with LLM-parsed natural language in a closed-form Bayesian update, reducing reward-learning error in simulated driving and improving user ratings in a 15-person study.
-
Guided Reinforcement Learning for Omnidirectional 3D Jumping in Quadruped Robots
Guided RL using Bezier curves and UARM model enables efficient, explainable omnidirectional jumping in quadruped robots.
-
INSANE: Cross-Domain UAV Data Sets with Increased Number of Sensors for developing Advanced and Novel Estimators
INSANE releases multiple MAV datasets with cross-environment trajectories, rich multi-IMU and camera suites, high-rate vibration data, and sub-centimeter RTK GNSS ground truth for localization research.
-
BIEVR-LIO: Robust LiDAR-Inertial Odometry through Bump-Image-Enhanced Voxel Maps
Oriented per-voxel height images plus map-informed dual-resolution sampling yield robust real-time LiDAR-inertial odometry where standard LIO diverges.
-
Learning Adaptive Solvers for Distributed Factor Graph Optimization on Matrix Lie Groups
A learned feedback policy replaces manual parameter tuning in distributed Riemannian optimization over matrix Lie groups, achieving lower objective values on multi-robot mapping benchmarks.
-
Generalization in offline RL: The structure is more important than the amount of pessimism
Symmetric (even highly) pessimistic value functions can generalize optimally in GTI-ZSPT offline RL while mildly pessimistic asymmetric ones cannot; DAC-Output during extraction is the strongest DA method tested.
-
Critical Interval MSE: Toward Reliable Offline Validation for Robot Manipulation Policies
CI-MSE improves Spearman's rank correlation between offline validation error and real rollout performance from -0.61 (raw MSE) to -0.87 across policy checkpoints in simulation and real-world robot manipulation experiments.
-
Hierarchical Policy Learning via Spectral Decomposition
Causal Spectral Policy decomposes actions spectrally into coarse motion from obs/language and conditional fine corrections, outperforming baselines on precision manipulation tasks.
-
Multi-Agent Goal Recognition with Team- and Goal-Conditioned Reinforcement Learning and Factorized Branch-and-Bound
MAGR-BB matches exhaustive search accuracy on multi-agent Blocksworld while reducing hypothesis evaluations by orders of magnitude via RL scoring inside factorized branch-and-bound.
-
HilDA: Hierarchical Distillation with Diffusion for Advancing Self-Supervised LiDAR Pre-training
HilDA pre-trains LiDAR backbones via multi-layer and global distillation from vision models plus temporal occupancy diffusion, yielding SOTA results on detection, flow, and occupancy tasks.
-
FARM: Find Anything using Relational Spatial Memory
A real-time relational spatial memory that parses object queries into spatial predicates, scores them against per-object 3D Gaussians, and retrieves object instances with substantially higher top-K recall than prior scene-graph or video-VLM baselines.
-
Shield-Loco: Shielding Locomotion Policies with Predictive Safety Filtering
A post-hoc predictive safety filter adjusts RL policy contact locations for quadruped robots via sampling-based optimization on a full-physics model, reducing safety violations in cluttered environments with minimal performance deviation.
-
HORIZON: Recoverability-Governed Curriculum for Physical-Domain Scaling
HORIZON is a recoverability-governed checkpointed frontier curriculum for on-policy physical-domain scaling on quadruped locomotion that identifies three regularities: uneven widening, non-monotonic composition, and the necessity of joint on-policy interaction.
-
The Road Ahead in Autonomous Driving: The KITScenes Multimodal Dataset
KITScenes Multimodal presents a new multimodal autonomous driving dataset with complete HD maps and four benchmarks for spatial learning tasks including online map construction and end-to-end driving.
-
Permissive Safety Through Trusted Inference: Verifiable Belief-Space Neural Safety Filters for Assured Interactive Robotics
A conformal prediction certification for belief-space safety filters focuses verification on reliable inference regions to produce less conservative yet high-probability safe filters than standard baselines in human-vehicle simulations.
-
Enabling Extensible Embodied Capabilities with Tools
Introduces Embodied Tool Protocol and tool externalization to improve embodied AI performance on perception and cognition tasks, with measured gains but limits on execution capabilities.
-
VBT-MPC: Vision-Based Tactile MPC for Contour Following
VBT-MPC performs robotic contour following by running MPC directly in vision-based tactile contour feature space and is tested on varied geometries in simulation and real experiments.
-
ARC-RL: A Reinforcement Learning Playground Inspired by ARC Raiders
ARC-RL is a new suite of four MuJoCo continuous-control environments featuring game-inspired hexapod and quadruped morphologies, a single closed-form multi-component reward function, CPG demonstrators, and empirical comparisons of online and offline-to-online RL algorithms.
-
BoolXLLM: LLM-Assisted Explainability for Boolean Models
BoolXLLM augments an existing Boolean rule learner with LLMs for feature selection, discretization thresholds, and natural-language rule translation to improve interpretability while preserving accuracy.
-
TouchAnything: Diffusion-Guided 3D Reconstruction from Sparse Robot Touches
TouchAnything reconstructs accurate 3D object geometries from only a few tactile contacts by optimizing for consistency with a pretrained visual diffusion prior.
-
From Local Matches to Global Masks: Template-Guided Instance Detection and Segmentation in Open-World Scenes
L2G-Det detects and segments novel object instances in open scenes by using local template patch matches to generate points that prompt an augmented SAM for global masks.
-
House of Dextra: Cross-embodied Co-design for Dexterous Hands
A cross-embodied co-design framework learns task-specific hand morphologies and control policies, achieving sim-to-real rotation up to 3.3 rad/s and full fabrication in under 24 hours.
-
Learning Multi-Modal Whole-Body Control for Real-World Humanoid Robots
A single learned controller called MHC enables real humanoid robots to execute diverse whole-body behaviors from multi-modal inputs via masked target trajectories.
-
From Pixels to Temporal Correlations: Learning Informative Representations for Reinforcement Learning Pre-training
MTCL learns multi-scale temporal correlations in videos via contrastive learning to produce more informative representations that improve sample efficiency and performance in downstream RL tasks.
-
Regularized Model Predictive Control via Contractivity and Implicit Lur'e Analysis
Develops multiplier-based contraction framework and LMI conditions for stability of regularized MPC interpreted as implicit Lur'e systems across three classes of regularizers.
-
Discrete Geometric Modeling and Extended State Estimation of Continuum Robots
A fully discrete strain-based model for continuum robot dynamics via Lie group variational integrators, combined with an EKF-based observer for states and disturbances, validated on hardware.
-
AI Sandboxes: A Threat Model, Taxonomy, and Measurement Framework
The paper presents a threat model, taxonomy, and six-dimension measurement framework for AI sandboxes to clarify valid testing claims for safety, security, and regulatory assurance.
-
TAM: Torque Adaptation Module for Robust Motion Transfer in Manipulation
TAM is a policy-agnostic torque adaptation module trained in randomized simulation that improves zero-shot real-robot performance on dynamic manipulation tasks compared to system identification and RMA baselines.
-
Beyond Pure Sampling: Hybrid Optimization Mechanisms for Non-Convex Model Predictive Control
Hybrid ME-DDP variants combine deterministic DDP with inverse-Hessian sampling to improve success rates over pure DDP and MPPI in robotic navigation under non-convex costs.
-
AURA: Asymptotically Optimal Uncertainty-Robust Replanning Algorithm for Kinodynamic Systems
AURA combines online replanning and optimization into an asymptotically optimal framework that improves trajectory quality and tracking accuracy under uncertainty for kinodynamic systems.
-
Look Further: Socially-Compliant Navigation System in Residential Buildings
Proactive lane-changing at eight meters improves human ratings of robot motion in frontal hallway approaches according to a 42-participant study, with no advantage shown at intersections.
-
FusionSense: Tri-Stage Near-Sensor Learning for Runtime-Adaptive Multimodal Edge Intelligence
FusionSense uses server-side fusion learning, filter-out-safe labels, and edge compaction to enable runtime-adaptive multimodal sensing that cuts energy up to 33x while preserving task quality on RGB+Depth data.
-
Randomized Advantage Transformation (RAT): Computing Natural Policy Gradients via Direct Backpropagation
RAT estimates Tikhonov-regularized natural policy gradients by rewriting them with the Woodbury identity, approximating the transformed advantage via randomized block Kaczmarz, and applying it as a vanilla policy gradient surrogate.
-
Visibility-Aware Mobile Grasping in Dynamic Environments
A visibility-aware mobile grasping system with iterative whole-body planning and behavior-tree subgoal generation achieves 68.8% success in unknown static and 58% in dynamic environments, outperforming a baseline by 22.8% and 18%.
-
From Spherical to Gaussian: A Comparative Analysis of Point Cloud Cropping Strategies in Large-Scale 3D Environments
Gaussian and related cropping strategies for point cloud subclouds improve 3D neural network performance over spherical cropping on large outdoor scenes.
-
Hierarchical Awareness Adapters with Hybrid Pyramid Feature Fusion for Dense Depth Prediction
A multilevel perceptual CRF model using Swin Transformer, HPF fusion, HA adapters, and dynamic scaling attention achieves state-of-the-art monocular depth estimation on NYU Depth v2, KITTI, and MatterPort3D with reduced error and fast inference.