An image generator is instruction-tuned to perform diverse vision tasks by representing task outputs as RGB images, achieving SOTA on segmentation and depth estimation.
Depthlm: Metric depth from vision language models
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 9roles
background 2polarities
background 2representative citing papers
TAIHRI is the first task-aware VLM for close-range HRI that localizes metric-scale 3D coordinates of critical keypoints by quantizing space and performing 2D keypoint reasoning via next-token prediction.
KITScenes LongTail supplies multimodal driving data and multilingual expert reasoning traces to benchmark models on rare scenarios beyond basic safety metrics.
Leading VLMs show high cross-view consistency paired with low metric accuracy on distance queries, indicating evidence-insensitive reasoning rather than geometric grounding.
SOCO is a new benchmark for semantic object correspondence that provides taxonomy, annotations, and language labels to evaluate part-level understanding in vision and multimodal foundation models.
Standard VLMs achieve expert-level 3D performance on depth estimation, pose estimation, and object understanding via three simple techniques without architecture changes or regression losses.
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.
Freezing a VLM backbone and routing its layers through Mixture-of-Layers plus a Meta-Skill memory yields higher success and stronger zero-shot generalization than fine-tuned VLAs on LIBERO and real robots.
An 8B embodied foundation model trained on 15B tokens with multi-task RL and a Planner-Grounder-Corrector loop claims SOTA on 16/24 embodied VLM benchmarks and strong VLA/real-robot transfer.
citing papers explorer
-
Image Generators are Generalist Vision Learners
An image generator is instruction-tuned to perform diverse vision tasks by representing task outputs as RGB images, achieving SOTA on segmentation and depth estimation.
-
TAIHRI: Task-Aware 3D Human Keypoints Localization for Close-Range Human-Robot Interaction
TAIHRI is the first task-aware VLM for close-range HRI that localizes metric-scale 3D coordinates of critical keypoints by quantizing space and performing 2D keypoint reasoning via next-token prediction.
-
LongTail Driving Scenarios with Reasoning Traces: The KITScenes LongTail Dataset
KITScenes LongTail supplies multimodal driving data and multilingual expert reasoning traces to benchmark models on rare scenarios beyond basic safety metrics.
-
Consistent Yet Wrong: Evidence Insensitivity in Spatial Vision-Language Models
Leading VLMs show high cross-view consistency paired with low metric accuracy on distance queries, indicating evidence-insensitive reasoning rather than geometric grounding.
-
SOCO: Benchmarking Semantic Object Correspondence in Vision Foundation Models
SOCO is a new benchmark for semantic object correspondence that provides taxonomy, annotations, and language labels to evaluate part-level understanding in vision and multimodal foundation models.
-
VLM3: Vision Language Models Are Native 3D Learners
Standard VLMs achieve expert-level 3D performance on depth estimation, pose estimation, and object understanding via three simple techniques without architecture changes or regression losses.
-
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.
-
$M^2$-VLA: Boosting Vision-Language Models for Generalizable Manipulation via Layer Mixture and Meta-Skills
Freezing a VLM backbone and routing its layers through Mixture-of-Layers plus a Meta-Skill memory yields higher success and stronger zero-shot generalization than fine-tuned VLAs on LIBERO and real robots.
-
Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models
An 8B embodied foundation model trained on 15B tokens with multi-task RL and a Planner-Grounder-Corrector loop claims SOTA on 16/24 embodied VLM benchmarks and strong VLA/real-robot transfer.