GLADOS reconstructs 3D geometry from disjoint views by generating intermediate perspectives, performing robust coarse alignment that tolerates generative inconsistencies, and iteratively expanding context for consistency.
hub Mixed citations
Vggt: Visual geometry grounded transformer
Mixed citation behavior. Most common role is method (57%).
30
Pith papers citing it
150
external citations · OpenAlex
Method
57% of classified citations
hub tools
citation-role summary
method 4
background 2
baseline 1
citation-polarity summary
years
2026 30representative citing papers
ReMatch corrects train-test residual distribution mismatch in probabilistic downscaling via optimal transport in low-dimensional PCA space, reducing under-dispersion and improving SSR and CRPS on HRRR-ERA5 wind data.
Geo-Align applies RL with a perceptual reward derived from 3D camera trajectory estimation to improve controllability and fidelity in video generation without paired training data.
Mamba-VGGT introduces a Sliding Window Mamba memory module and Zero-Init Spatial Memory Injector to enable persistent long-range geometric reasoning in VGGT for extended video sequences.
A training-free method reformulates camera control as geometric displacement fields applied via differentiable latent resampling, enabling control and bias probing in video diffusion models.
TurboVGGT uses adaptive sparse global attention with varying sparsity levels across frames and layers plus frame attention to enable faster multi-view 3D reconstruction while keeping competitive quality versus prior state-of-the-art methods.
VEGA improves spatial reasoning in VLA models for robotics by aligning visual encoder features with 3D-supervised DINOv2 representations via a temporary projector and cosine similarity loss.
ViSRA boosts MLLM 3D spatial reasoning performance by up to 28.9% on unseen tasks via a plug-and-play video-based agent that extracts explicit spatial cues from expert models without any post-training.
Cross3R performs feed-forward 3D reconstruction and 6-DoF pose estimation from any combination of satellite, UAV, and ground images, outperforming baselines on a new 278K-image tri-view dataset.
The first survey on Attention Sink in Transformers structures the literature around fundamental utilization, mechanistic interpretation, and strategic mitigation.
A feed-forward feature-Gaussian plus one-step geometry-aware pixel-flow simulator converts large image collections into 20K interactive scenes and 10M+ navigation samples that improve zero-shot Habitat and real-robot performance.
DPPE decouples rotation and translation in camera positional encodings for multi-view transformers to resolve late-stage training stagnation and improve generalization in novel view synthesis.
A transformer-based neural renderer that transfers arbitrary PBR lighting to single images via shared intrinsic conditioning extracted from both multi-illumination photos and path-traced coarse 3D renders.
A closed-form scalar frame-level gate α_t derived from internal feature changes extends effective memory in recurrent 3D reconstruction and improves accuracy on long sequences up to 4541 frames.
DepthVLM converts a standard VLM into a dense metric depth predictor by attaching a lightweight head and training under unified vision-text supervision, outperforming prior VLMs and some pure vision models on a new indoor-outdoor benchmark.
CoWorld-VLA extracts semantic, geometric, dynamic, and trajectory expert tokens from multi-source supervision and feeds them into a diffusion-based hierarchical planner, achieving competitive collision avoidance and trajectory accuracy on the NAVSIM v1 benchmark.
TriRelVLA introduces triadic object-hand-task relational representations and a task-grounded graph transformer with a relational bottleneck to improve generalization in robotic manipulation across scenes, objects, and tasks.
The Robust 4D Visual Geometry Transformer with Uncertainty-Aware Priors outperforms prior methods on dynamic benchmarks by cutting Mean Accuracy error 13.43% and raising segmentation F-measure 10.49% via three uncertainty mechanisms while keeping feed-forward speed.
A feed-forward model regresses accurate Gaussian surfel geometry from sparse views using Nyquist-guided cross-view feature aggregation, achieving 100x speedup over optimization-based 3DGS surface methods on DTU benchmarks.
HD-VGGT achieves state-of-the-art high-resolution 3D reconstruction from image collections via a dual-branch architecture that predicts coarse geometry at low resolution and refines details at high resolution while modulating unreliable features.
OmniView-Space framework with MPSM, tool-guided reasoning, and distillation achieves SOTA on spatial reasoning benchmarks for MLLMs while reducing external geometry dependencies.
LIST3R reconnects fragmented video subsequences using persistent instance anchors with semantic and geometric evidence to produce consistent global 3D reconstructions.
A hierarchical multi-agent framework converts a single sentence into a short drama using debate-based scripting, 3D-grounded first frames for spatial consistency, and multi-stage reviewer loops.
SANA-WM is a 2.6B-parameter efficient world model that synthesizes minute-scale 720p videos with 6-DoF camera control, trained on 213K public clips in 15 days on 64 H100s and runnable on single GPUs at 36x higher throughput than prior open baselines.
citing papers explorer
-
Mind the Gap: Geometrically Accurate Generative Reconstruction from Disjoint Views
GLADOS reconstructs 3D geometry from disjoint views by generating intermediate perspectives, performing robust coarse alignment that tolerates generative inconsistencies, and iteratively expanding context for consistency.
-
Mind the Residual Gap: Probabilistic Downscaling under Real-World Bias
ReMatch corrects train-test residual distribution mismatch in probabilistic downscaling via optimal transport in low-dimensional PCA space, reducing under-dispersion and improving SSR and CRPS on HRRR-ERA5 wind data.
-
Geo-Align: Video Generation Alignment via Metric Geometry Reward
Geo-Align applies RL with a perceptual reward derived from 3D camera trajectory estimation to improve controllability and fidelity in video generation without paired training data.
-
Mamba-VGGT: Persistent Long-Sequence Video Geometry Grounded Transformer via External Sliding Window Mamba Memory
Mamba-VGGT introduces a Sliding Window Mamba memory module and Zero-Init Spatial Memory Injector to enable persistent long-range geometric reasoning in VGGT for extended video sequences.
-
Probing into Camera Control of Video Models
A training-free method reformulates camera control as geometric displacement fields applied via differentiable latent resampling, enabling control and bias probing in video diffusion models.
-
TurboVGGT: Fast Visual Geometry Reconstruction with Adaptive Alternating Attention
TurboVGGT uses adaptive sparse global attention with varying sparsity levels across frames and layers plus frame attention to enable faster multi-view 3D reconstruction while keeping competitive quality versus prior state-of-the-art methods.
-
VEGA: Visual Encoder Grounding Alignment for Spatially-Aware Vision-Language-Action Models
VEGA improves spatial reasoning in VLA models for robotics by aligning visual encoder features with 3D-supervised DINOv2 representations via a temporary projector and cosine similarity loss.
-
ViSRA: A Video-based Spatial Reasoning Agent for Multi-modal Large Language Models
ViSRA boosts MLLM 3D spatial reasoning performance by up to 28.9% on unseen tasks via a plug-and-play video-based agent that extracts explicit spatial cues from expert models without any post-training.
-
Seeing Across Skies and Streets: Feedforward 3D Reconstruction from Satellite, Drone, and Ground Images
Cross3R performs feed-forward 3D reconstruction and 6-DoF pose estimation from any combination of satellite, UAV, and ground images, outperforming baselines on a new 278K-image tri-view dataset.
-
Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation
The first survey on Attention Sink in Transformers structures the literature around fundamental utilization, mechanistic interpretation, and strategic mitigation.
-
Image2Sim: Scaling Embodied Navigation via Generative Neural Simulator
A feed-forward feature-Gaussian plus one-step geometry-aware pixel-flow simulator converts large image collections into 20K interactive scenes and 10M+ navigation samples that improve zero-shot Habitat and real-robot performance.
-
DPPE: Rethinking Camera-Based Positional Encoding for Scaling Multi-View Transformers
DPPE decouples rotation and translation in camera positional encodings for multi-view transformers to resolve late-stage training stagnation and improve generalization in novel view synthesis.
-
PIXLRelight: Controllable Relighting via Intrinsic Conditioning
A transformer-based neural renderer that transfers arbitrary PBR lighting to single images via shared intrinsic conditioning extracted from both multi-illumination photos and path-traced coarse 3D renders.
-
Rethinking the State Update Gate for Long-Sequence Recurrent 3D Reconstruction
A closed-form scalar frame-level gate α_t derived from internal feature changes extends effective memory in recurrent 3D reconstruction and improves accuracy on long sequences up to 4541 frames.
-
Unlocking Dense Metric Depth Estimation in VLMs
DepthVLM converts a standard VLM into a dense metric depth predictor by attaching a lightweight head and training under unified vision-text supervision, outperforming prior VLMs and some pure vision models on a new indoor-outdoor benchmark.
-
CoWorld-VLA: Thinking in a Multi-Expert World Model for Autonomous Driving
CoWorld-VLA extracts semantic, geometric, dynamic, and trajectory expert tokens from multi-source supervision and feeds them into a diffusion-based hierarchical planner, achieving competitive collision avoidance and trajectory accuracy on the NAVSIM v1 benchmark.
-
TriRelVLA: Triadic Relational Structure for Generalizable Embodied Manipulation
TriRelVLA introduces triadic object-hand-task relational representations and a task-grounded graph transformer with a relational bottleneck to improve generalization in robotic manipulation across scenes, objects, and tasks.
-
Robust 4D Visual Geometry Transformer with Uncertainty-Aware Priors
The Robust 4D Visual Geometry Transformer with Uncertainty-Aware Priors outperforms prior methods on dynamic benchmarks by cutting Mean Accuracy error 13.43% and raising segmentation F-measure 10.49% via three uncertainty mechanisms while keeping feed-forward speed.
-
SurfelSplat: Learning Efficient and Generalizable Gaussian Surfel Representations for Sparse-View Surface Reconstruction
A feed-forward model regresses accurate Gaussian surfel geometry from sparse views using Nyquist-guided cross-view feature aggregation, achieving 100x speedup over optimization-based 3DGS surface methods on DTU benchmarks.
-
HD-VGGT: High-Resolution Visual Geometry Transformer
HD-VGGT achieves state-of-the-art high-resolution 3D reconstruction from image collections via a dual-branch architecture that predicts coarse geometry at low resolution and refines details at high resolution while modulating unreliable features.
-
OmniView-Space: Reinforcing Spatial Reasoning via Multi-Perspective Spatial Mapping
OmniView-Space framework with MPSM, tool-guided reasoning, and distillation achieves SOTA on spatial reasoning benchmarks for MLLMs while reducing external geometry dependencies.
-
LIST3R: Long-sequence Instance-aware 3D Reconstruction
LIST3R reconnects fragmented video subsequences using persistent instance anchors with semantic and geometric evidence to produce consistent global 3D reconstructions.
-
One Sentence, One Drama: Personalized Short-Form Drama Generation via Multi-Agent Systems
A hierarchical multi-agent framework converts a single sentence into a short drama using debate-based scripting, 3D-grounded first frames for spatial consistency, and multi-stage reviewer loops.
-
SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer
SANA-WM is a 2.6B-parameter efficient world model that synthesizes minute-scale 720p videos with 6-DoF camera control, trained on 213K public clips in 15 days on 64 H100s and runnable on single GPUs at 36x higher throughput than prior open baselines.
-
4DVGGT-D: 4D Visual Geometry Transformer with Improved Dynamic Depth Estimation
A training-free two-pass adaptation of VGGT, with attention-based motion masking and inverse-variance depth fusion, improves dynamic-scene point-cloud reconstruction on DyCheck.
-
Context Unrolling in Omni Models
Omni is a multimodal model whose native training on diverse data types enables context unrolling, allowing explicit reasoning across modalities to better approximate shared knowledge and improve downstream performance.
-
FrameVGGT: Coherence-Preserving Memory for Bounded Streaming Geometry
FrameVGGT maintains stable long-horizon 3D reconstruction, depth, and pose under fixed memory by organizing history as complementary frame-wise KV prototypes plus sparse anchors.
-
Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Model
Evo-Depth is a compact VLA model using a lightweight implicit depth encoder from RGB views plus progressive alignment to boost manipulation performance without added hardware.
-
JoyAI-Image: Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation
JoyAI-Image unifies visual understanding and generation via an MLLM-MMDiT architecture with spatial training signals to reach competitive benchmark performance and stronger spatial intelligence.
-
OpenWorldLib: A Unified Codebase and Definition of Advanced World Models
OpenWorldLib defines world models as perception-centered systems with interaction and long-term memory, and provides a modular inference codebase unifying interactive video, 3D, reasoning, and VLA tasks.