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
Segment anything
Mixed citation behavior. Most common role is background (44%).
20
Pith papers citing it
Background
44% of classified citations
hub tools
citation-role summary
background 4
baseline 2
dataset 2
method 1
citation-polarity summary
representative citing papers
Introduces RAM-W600, the first public multi-task dataset of wrist conventional radiographs with instance segmentation annotations and Sharp/van der Heijde bone erosion scores for rheumatoid arthritis research.
Presents CUActSpot benchmark and renderer-LLM data synthesis that lets a 4B model outperform larger open-source models on complex computer interactions.
TOC-Bench is a new diagnostic benchmark that reveals major weaknesses in temporal object consistency for Video-LLMs, including event counting, ordering, identity reasoning, and hallucination avoidance.
AVA-Bench evaluates vision foundation models by disentangling 14 atomic visual abilities with aligned training-test distributions to reveal precise ability fingerprints.
TrackCue uses dense image-space trajectories from point tracking and ego-motion compensation to improve static-dynamic classification and supervision for LiDAR scene flow estimation.
An audit of 152 papers reveals that geospatial foundation models lack standardized evaluations, training controls, and weight releases, so no one knows the state of the art.
Exploiting linear structure in VLM embeddings, a synthetic-data pre-training method yields background-invariant representations that exceed 90% worst-group accuracy on Waterbirds even under 100% spurious correlation with no minority examples in training.
ViewSAM achieves state-of-the-art weakly supervised performance on cross-view referring multi-object tracking by refining SAM tracklets via affinity-guided re-prompting and modeling view-induced variations as learnable conditions on SAM2.
UniBCI is a unified pretrained model for invasive neural spike data that uses CST tokenization, IAA attention, and self-supervised masked reconstruction to achieve SOTA downstream performance with better generalization and efficiency.
Reinforcement learning sensorimotor policies enable quadrotors to traverse narrow gaps at extreme tilts with 5 cm clearance using only vision and proprioception, including reactive traversal of moving gaps.
Generative video models exhibit emergent zero-shot capabilities across perception, manipulation, and basic reasoning tasks.
ImgEdit supplies 1.2 million curated edit pairs and a three-part benchmark that let a VLM-based model outperform prior open-source editors on adherence, quality, and detail preservation.
RadGenome-Anatomy is a large-scale chest radiograph dataset with anatomy labels obtained by projecting 3D CT masks into 2D radiographic space for 210 structures in 25,692 studies.
HarmoGS adds semantic consistency-guided masking and dual-view orthogonal gradient harmonization to 3D Gaussian Splatting to reduce artifacts from distractors and cross-view illumination inconsistencies.
FusionProxy is a distilled diffusion-based fusion module that adds thermal awareness to RGB vision systems in real time as an independent plug-and-play component.
MoGe-2 recovers metric-scale 3D point maps with fine details from single images via data refinement and extension of affine-invariant predictions.
LENS is a new multi-level benchmark dataset for evaluating MLLMs on perception-to-reasoning tasks using the same images across all levels with recent social media content.
BLIP3-o uses a diffusion transformer to generate CLIP image features and a sequential pretraining strategy to build open models that perform strongly on both image understanding and generation benchmarks.
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.
-
RAM-W600: A Multi-Task Wrist Dataset and Benchmark for Rheumatoid Arthritis
Introduces RAM-W600, the first public multi-task dataset of wrist conventional radiographs with instance segmentation annotations and Sharp/van der Heijde bone erosion scores for rheumatoid arthritis research.
-
Covering Human Action Space for Computer Use: Data Synthesis and Benchmark
Presents CUActSpot benchmark and renderer-LLM data synthesis that lets a 4B model outperform larger open-source models on complex computer interactions.
-
TOC-Bench: A Temporal Object Consistency Benchmark for Video Large Language Models
TOC-Bench is a new diagnostic benchmark that reveals major weaknesses in temporal object consistency for Video-LLMs, including event counting, ordering, identity reasoning, and hallucination avoidance.
-
AVA-Bench: Atomic Visual Ability Benchmark for Vision Foundation Models
AVA-Bench evaluates vision foundation models by disentangling 14 atomic visual abilities with aligned training-test distributions to reveal precise ability fingerprints.
-
Motion Cues from Image-based Point Tracking for LiDAR Scene Flow Estimation
TrackCue uses dense image-space trajectories from point tracking and ego-motion compensation to improve static-dynamic classification and supervision for LiDAR scene flow estimation.
-
No One Knows the State of the Art in Geospatial Foundation Models
An audit of 152 papers reveals that geospatial foundation models lack standardized evaluations, training controls, and weight releases, so no one knows the state of the art.
-
Birds of a Feather Flock Together: Background-Invariant Representations via Linear Structure in VLMs
Exploiting linear structure in VLM embeddings, a synthetic-data pre-training method yields background-invariant representations that exceed 90% worst-group accuracy on Waterbirds even under 100% spurious correlation with no minority examples in training.
-
ViewSAM: Learning View-aware Cross-modal Semantics for Weakly Supervised Cross-view Referring Multi-Object Tracking
ViewSAM achieves state-of-the-art weakly supervised performance on cross-view referring multi-object tracking by refining SAM tracklets via affinity-guided re-prompting and modeling view-induced variations as learnable conditions on SAM2.
-
UniBCI: Towards a Unified Pretrained Model for Invasive Brain-Computer Interfaces
UniBCI is a unified pretrained model for invasive neural spike data that uses CST tokenization, IAA attention, and self-supervised masked reconstruction to achieve SOTA downstream performance with better generalization and efficiency.
-
Precise Aggressive Aerial Maneuvers with Sensorimotor Policies
Reinforcement learning sensorimotor policies enable quadrotors to traverse narrow gaps at extreme tilts with 5 cm clearance using only vision and proprioception, including reactive traversal of moving gaps.
-
Video models are zero-shot learners and reasoners
Generative video models exhibit emergent zero-shot capabilities across perception, manipulation, and basic reasoning tasks.
-
ImgEdit: A Unified Image Editing Dataset and Benchmark
ImgEdit supplies 1.2 million curated edit pairs and a three-part benchmark that let a VLM-based model outperform prior open-source editors on adherence, quality, and detail preservation.
-
RadGenome-Anatomy: A Large-Scale Anatomy-Labeled Chest Radiograph Dataset via Physically Grounded Volumetric Projection
RadGenome-Anatomy is a large-scale chest radiograph dataset with anatomy labels obtained by projecting 3D CT masks into 2D radiographic space for 210 structures in 25,692 studies.
-
HarmoGS: Robust 3D Gaussian Splatting in the Wild via Conflict-Aware Gradient Harmonization
HarmoGS adds semantic consistency-guided masking and dual-view orthogonal gradient harmonization to 3D Gaussian Splatting to reduce artifacts from distractors and cross-view illumination inconsistencies.
-
Adding Thermal Awareness to Visual Systems in Real-Time via Distilled Diffusion Models
FusionProxy is a distilled diffusion-based fusion module that adds thermal awareness to RGB vision systems in real time as an independent plug-and-play component.
-
MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details
MoGe-2 recovers metric-scale 3D point maps with fine details from single images via data refinement and extension of affine-invariant predictions.
-
LENS: Multi-level Evaluation of Multimodal Reasoning with Large Language Models
LENS is a new multi-level benchmark dataset for evaluating MLLMs on perception-to-reasoning tasks using the same images across all levels with recent social media content.
-
BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset
BLIP3-o uses a diffusion transformer to generate CLIP image features and a sequential pretraining strategy to build open models that perform strongly on both image understanding and generation benchmarks.
- Beyond Interpretability: When, Why, and How Sparse Autoencoders Enable Label-Free Visual Steering