Generative world models used as closed-loop test oracles require a five-level admissibility ladder (L0-L4) because visual fidelity does not predict action-robustness.
DriveArena: A Closed-loop Generative Simulation Platform for Autonomous Driving
20 Pith papers cite this work. Polarity classification is still indexing.
20
Pith papers citing it
years
2026 20representative citing papers
RESOLVE provides a controlled multi-resolution LiDAR and camera benchmark for evaluating 3D detection and tracking under point sparsity variations in roadside cooperative perception.
An asynchronous architecture decouples incremental voxel-based mapping from VLM-based semantic enrichment to produce queryable open-vocabulary 3D scene graphs that match or exceed prior methods on segmentation and grounding benchmarks.
Task-conditioned language and vision models omit co-present safety-critical signals they report when unconstrained, decoupling benchmark safety from deployment safety.
The paper defines the 4DVLT task for worldline-centered 4D scene understanding, releases Instruct-4D with 129.4K QA pairs, and presents 4DTrack achieving 62.68 TGA_Top1, outperforming adapted baselines by 19.62 points.
LMM-Track4D formulates a trajectory-grounded dialogue task, releases Track4D-Bench with 526 samples, and proposes RTGE encoding, TRK state token, and OSK-RA decoder to elicit better 4D spatiotemporal reasoning in LMMs.
A two-stage diffusion framework generates a layout-controllable low-resolution blueprint to guide parallel high-resolution artwork outpainting, achieving 2.4× speedup and improved fidelity over sequential baselines.
NURBS Splatting represents rational splines as continuous Gaussian fields sampled along the curve to enable stable differentiable rendering of vector graphics.
PRP introduces proactive routing via Draft Rating Learning and Joint Rating Learning to route queries early between draft and target models for efficient multimodal reasoning.
CORE-MTL introduces causal orthogonal representations to factorize shared MTL features into semantic and residual streams, claiming tighter OOD bounds and reduced gradient interference.
SpectralEarth-FM is a multisensor hierarchical transformer pretrained on a 40TB co-located HSI-MSI-SAR dataset using a JEPA-style objective and reports state-of-the-art results on hyperspectral and standard EO benchmarks.
MooD introduces continuous valence-arousal modeling with VA-aware retrieval and perception-enhanced guidance for efficient, controllable affective image editing, plus a new AffectSet dataset.
FSDC-DETR improves small-object AP by 6.8–6.9 points on VisDrone and AITODv2 by explicit frequency-spatial fusion and wavelet-style downsampling inside a DETR hybrid encoder.
MapDreamer synthesizes lane-level maps from aerial imagery via VAE latent encoding, transformer latent diffusion conditioned on aerial features, a lane cardinality module with ghost latents, and sliding-window graph aggregation, showing improved fidelity on UrbanLaneGraph data.
LinStereo uses Position-Aware Linear Attention, Hierarchical Semantic Cost Volumes, and Depth Prior Initialization to enable global aggregation in iterative stereo matching at linear complexity, showing improved performance on standard and underwater benchmarks.
A reinforcement-learning agent that picks high-error trajectory segments during consistency distillation improves few-step text-to-image generation on FLUX and SDXL.
RPC is a post-hoc calibration technique that augments flow-based anomaly scores with nearest-prototype deviation in the frozen latent space, gated by keypoint confidence, yielding consistent AUROC gains on video anomaly detection tasks.
SpaCE derives four theoretical results on spatial capacity, sample complexity, generalization, and bias-variance trade-offs for multi-frame MLLM reasoning, validated on MultiSPA, CA-VQA, and SpatialRGPT.
Survey organizing world models for robotic manipulation into representation families, a functional taxonomy, and infrastructure roles across pretraining, post-training, and inference, while reviewing 34 datasets and evaluation protocols.
Automation in embodied benchmark construction shifts costs from acquisition toward validation, auditability, version control, and long-term governance instead of simply lowering total cost.
citing papers explorer
-
Validate the Dream Before You Trust Its Verdict: Admissibility for World-Model Simulators
Generative world models used as closed-loop test oracles require a five-level admissibility ladder (L0-L4) because visual fidelity does not predict action-robustness.
-
RESOLVE: A Multi-Resolution and Multi-Modal Dataset for Roadside Cooperative Perception
RESOLVE provides a controlled multi-resolution LiDAR and camera benchmark for evaluating 3D detection and tracking under point sparsity variations in roadside cooperative perception.
-
Think While You Map: Asynchronous Vision-Language Agents for Incremental 3D Scene Graphs
An asynchronous architecture decouples incremental voxel-based mapping from VLM-based semantic enrichment to produce queryable open-vocabulary 3D scene graphs that match or exceed prior methods on segmentation and grounding benchmarks.
-
The inattentional gap in task conditioned AI models that omit otherwise reportable safety critical signals
Task-conditioned language and vision models omit co-present safety-critical signals they report when unconstrained, decoupling benchmark safety from deployment safety.
-
4DVLT: Dynamic Scene Understanding with Worldline-Centered Vision-Language Tracking
The paper defines the 4DVLT task for worldline-centered 4D scene understanding, releases Instruct-4D with 129.4K QA pairs, and presents 4DTrack achieving 62.68 TGA_Top1, outperforming adapted baselines by 19.62 points.
-
LMM-Track4D: Eliciting 4D Dynamic Reasoning in LMMs via Trajectory-Grounded Dialogue
LMM-Track4D formulates a trajectory-grounded dialogue task, releases Track4D-Bench with 526 samples, and proposes RTGE encoding, TRK state token, and OSK-RA decoder to elicit better 4D spatiotemporal reasoning in LMMs.
-
High-Resolution Artwork Outpainting with Global Blueprint Guidance and Layout Control
A two-stage diffusion framework generates a layout-controllable low-resolution blueprint to guide parallel high-resolution artwork outpainting, achieving 2.4× speedup and improved fidelity over sequential baselines.
-
NURBS Splatting: A Unified Differentiable Rendering Framework for Vector Graphics
NURBS Splatting represents rational splines as continuous Gaussian fields sampled along the curve to enable stable differentiable rendering of vector graphics.
-
Before Thinking, Learn to Decide: Proactive Routing for Efficient Visual Reasoning
PRP introduces proactive routing via Draft Rating Learning and Joint Rating Learning to route queries early between draft and target models for efficient multimodal reasoning.
-
CORE-MTL: Rethinking Gradient Balancing via Causal Orthogonal Representations
CORE-MTL introduces causal orthogonal representations to factorize shared MTL features into semantic and residual streams, claiming tighter OOD bounds and reduced gradient interference.
-
SpectralEarth-FM: Bringing Hyperspectral Imagery into Multimodal Earth Observation Pretraining
SpectralEarth-FM is a multisensor hierarchical transformer pretrained on a 40TB co-located HSI-MSI-SAR dataset using a JEPA-style objective and reports state-of-the-art results on hyperspectral and standard EO benchmarks.
-
MooD: Perception-Enhanced Efficient Affective Image Editing via Continuous Valence-Arousal Modeling
MooD introduces continuous valence-arousal modeling with VA-aware retrieval and perception-enhanced guidance for efficient, controllable affective image editing, plus a new AffectSet dataset.
-
FSDC-DETR: A Frequency-Spatial Domain Collaborative DETR for Small Object Detection
FSDC-DETR improves small-object AP by 6.8–6.9 points on VisDrone and AITODv2 by explicit frequency-spatial fusion and wavelet-style downsampling inside a DETR hybrid encoder.
-
MapDreamer: Aerial Imagery Conditioned Latent Diffusion for Lane-Level Map Generation
MapDreamer synthesizes lane-level maps from aerial imagery via VAE latent encoding, transformer latent diffusion conditioned on aerial features, a lane cardinality module with ghost latents, and sliding-window graph aggregation, showing improved fidelity on UrbanLaneGraph data.
-
LinStereo: Linear-Complexity Global Attention for Multi-Scale Iterative Stereo Matching
LinStereo uses Position-Aware Linear Attention, Hierarchical Semantic Cost Volumes, and Depth Prior Initialization to enable global aggregation in iterative stereo matching at linear complexity, showing improved performance on standard and underwater benchmarks.
-
Curvature-Adaptive Consistency Flow Matching: Autonomous Trajectory Optimization via Reinforcement Learning
A reinforcement-learning agent that picks high-error trajectory segments during consistency distillation improves few-step text-to-image generation on FLUX and SDXL.
-
Reliability-Aware Prototype Calibration for Frozen Pose-Flow Video Anomaly Detection
RPC is a post-hoc calibration technique that augments flow-based anomaly scores with nearest-prototype deviation in the frozen latent space, gated by keypoint confidence, yielding consistent AUROC gains on video anomaly detection tasks.
-
SpaCE: Rethinking Spatial Capacity and Generalization in Multi-Frame Multimodal Large Language Models
SpaCE derives four theoretical results on spatial capacity, sample complexity, generalization, and bias-variance trade-offs for multi-frame MLLM reasoning, validated on MultiSPA, CA-VQA, and SpatialRGPT.
-
World Models for Robotic Manipulation: A Survey
Survey organizing world models for robotic manipulation into representation families, a functional taxonomy, and infrastructure roles across pretraining, post-training, and inference, while reviewing 34 datasets and evaluation protocols.
-
Intelligent Automation for Embodied Benchmark Construction: Pipelines, Embodiments, Simulators, and Trends
Automation in embodied benchmark construction shifts costs from acquisition toward validation, auditability, version control, and long-term governance instead of simply lowering total cost.