GEAR jointly trains VQ tokenizer and AR generator end-to-end via dual hard/soft read-out and representation alignment, achieving up to 10x faster ImageNet gFID convergence than LlamaGen-REPA while generalizing across quantizers and to text-to-image.
End-to-end object detection with transformers
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
citation-role summary
background 1
method 1
citation-polarity summary
representative citing papers
BloGDiT introduces blocked Gibbs-style denoising in diffusion transformers to enable large targeted edits for constraint satisfaction and optimization, matching or exceeding prior methods on Sudoku, graph coloring, MIS, and MaxCut.
SAM 3D Animal is the first promptable framework for multi-animal 3D reconstruction from single images, built on SMAL+ and trained on the new Herd3D dataset, achieving SOTA results on Animal3D, APTv2, and Animal Kingdom benchmarks.
An acoustic dimer of two subwavelength scatterers can achieve unidirectional transverse scattering (transverse Kerker effect) while maintaining strong overall scattering.
IC-Seg is a multi-turn clarification framework with hierarchical GRPO optimization that resolves ambiguous queries in referring video object segmentation and introduces the Ambi-RVOS benchmark.
LACE aligns human-robot visual features via semantic distribution matching on corresponding body parts plus Gram loss, yielding 65% better zero-shot policy transfer than baseline DINO.
Invaria trains point cloud encoders with next-resolution prediction to learn scale and density invariant features, yielding higher mIoU on ScanNet under lower resolution and scaled objects while using a smaller model.
XDecomposer uses set prediction and phase-query decomposition to jointly identify phases and reconstruct multiphase PXRD patterns without priors.
ViCrop-Det uses spatial attention entropy from the decoder to dynamically crop and refine small-object regions in transformer detectors during inference.
ORCA is an agentic reasoning framework that enhances factual accuracy and adversarial robustness of pretrained LVLMs via an Observe-Reason-Critique-Act loop with small vision models, reporting accuracy gains of up to 40% on hallucination benchmarks and 20% under adversarial perturbations.
TinyFormer adds Parallel Bi-fusion Module and Spatial Semantic Adapter to a YOLO-DETR hybrid, raising small-object AP by 1.6 points to 58.5% on MS COCO while keeping real-time speed.
Random label bridge training aligns LLM parameters with vision tasks, and partial training of certain layers often suffices due to their foundational properties.
citing papers explorer
-
GEAR: Guided End-to-End AutoRegression for Image Synthesis
GEAR jointly trains VQ tokenizer and AR generator end-to-end via dual hard/soft read-out and representation alignment, achieving up to 10x faster ImageNet gFID convergence than LlamaGen-REPA while generalizing across quantizers and to text-to-image.
-
Blocked Gibbs meets Diffusion Transformers: Unsupervised Learning for Constraint Optimization
BloGDiT introduces blocked Gibbs-style denoising in diffusion transformers to enable large targeted edits for constraint satisfaction and optimization, matching or exceeding prior methods on Sudoku, graph coloring, MIS, and MaxCut.
-
SAM 3D Animal: Promptable Animal 3D Reconstruction from Images in the Wild
SAM 3D Animal is the first promptable framework for multi-animal 3D reconstruction from single images, built on SMAL+ and trained on the new Herd3D dataset, achieving SOTA results on Animal3D, APTv2, and Animal Kingdom benchmarks.
-
FingerEye: Learning Dexterous Manipulation with Continuous Vision-Tactile Sensing
An acoustic dimer of two subwavelength scatterers can achieve unidirectional transverse scattering (transverse Kerker effect) while maintaining strong overall scattering.
-
Don't Guess, Just Ask: Resolving Ambiguity in Referring Segmentation via Multi-turn Clarification
IC-Seg is a multi-turn clarification framework with hierarchical GRPO optimization that resolves ambiguous queries in referring video object segmentation and introduces the Ambi-RVOS benchmark.
-
LACE: Latent Visual Representation for Cross-Embodiment Learning
LACE aligns human-robot visual features via semantic distribution matching on corresponding body parts plus Gram loss, yielding 65% better zero-shot policy transfer than baseline DINO.
-
Invaria: Learning Scale and Density Invariance in Point Clouds via Next-Resolution Prediction
Invaria trains point cloud encoders with next-resolution prediction to learn scale and density invariant features, yielding higher mIoU on ScanNet under lower resolution and scaled objects while using a smaller model.
-
XDecomposer: Learning Prior-Free Set Decomposition for Multiphase X-ray Diffraction
XDecomposer uses set prediction and phase-query decomposition to jointly identify phases and reconstruct multiphase PXRD patterns without priors.
-
ViCrop-Det: Spatial Attention Entropy Guided Cropping for Training-Free Small-Object Detection
ViCrop-Det uses spatial attention entropy from the decoder to dynamically crop and refine small-object regions in transformer detectors during inference.
-
ORCA: An Agentic Reasoning Framework for Hallucination and Adversarial Robustness in Vision-Language Models
ORCA is an agentic reasoning framework that enhances factual accuracy and adversarial robustness of pretrained LVLMs via an Observe-Reason-Critique-Act loop with small vision models, reporting accuracy gains of up to 40% on hallucination benchmarks and 20% under adversarial perturbations.
-
TinyFormer: Preserving Tiny Objects in YOLO-DETR Hybrid Real-time Detectors
TinyFormer adds Parallel Bi-fusion Module and Spatial Semantic Adapter to a YOLO-DETR hybrid, raising small-object AP by 1.6 points to 58.5% on MS COCO while keeping real-time speed.
-
Language-Pretraining-Induced Bias: A Strong Foundation for General Vision Tasks
Random label bridge training aligns LLM parameters with vision tasks, and partial training of certain layers often suffices due to their foundational properties.