Pith. sign in

REVIEW 5 cited by

RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2412.07679 v2 pith:ZVAJEP5Y submitted 2024-12-10 cs.CV cs.AI

Greg Heinrich , Mike Ranzinger , Hongxu (Danny) Yin , Yao Lu , Jan Kautz , Andrew Tao , Bryan Catanzaro , Pavlo Molchanov This is my paper
classification cs.CVcs.AI
keywords modelsagglomerativeteachervisionfoundationimprovedtokentraining
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Agglomerative models have recently emerged as a powerful approach to training vision foundation models, leveraging multi-teacher distillation from existing models such as CLIP, DINO, and SAM. This strategy enables the efficient creation of robust models, combining the strengths of individual teachers while significantly reducing computational and resource demands. In this paper, we thoroughly analyze state-of-the-art agglomerative models, identifying critical challenges including resolution mode shifts, teacher imbalance, idiosyncratic teacher artifacts, and an excessive number of output tokens. To address these issues, we propose several novel solutions: multi-resolution training, mosaic augmentation, and improved balancing of teacher loss functions. Specifically, in the context of Vision Language Models, we introduce a token compression technique to maintain high-resolution information within a fixed token count. We release our top-performing variants at multiple scales (-B, -L, -H, and -g), along with inference code and pretrained weights

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. AVA-Bench: Atomic Visual Ability Benchmark for Vision Foundation Models

    cs.CV 2025-06 unverdicted novelty 7.0 of 10

    AVA-Bench evaluates vision foundation models by disentangling 14 atomic visual abilities with aligned training-test distributions to reveal precise ability fingerprints.

  2. Beyond Encoder Accumulation: Measuring Encoder Roles in Multi-Encoder VLMs

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    Retraining all 31 subsets of five vision encoders shows Capacity and Necessity are distinct, pre-projector effective rank predicts residual performance at fixed parameter count, and high-Capacity plus adaptive complem...

  3. Relighting as a Probe of Visual Priors via Augmented Latent Intrinsics

    cs.CV 2026-02 conditional novelty 6.0 of 10

    Semantic encoders can harm relighting, and ALI—fusing dense visual features with latent intrinsics—improves relighting on glossy and specular materials.

  4. FUS3DMaps: Scalable and Accurate Open-Vocabulary Semantic Mapping by 3D Fusion of Voxel- and Instance-Level Layers

    cs.RO 2026-05 unverdicted novelty 5.0 of 10

    FUS3DMaps fuses voxel- and instance-level open-vocabulary layers inside a shared 3D voxel map to improve both layers and enable scalable accurate semantic mapping.

  5. Image Recognition with Vision and Language Embeddings of VLMs

    cs.CV 2025-09 conditional novelty 4.0 of 10

    A benchmark of dual-encoder VLMs finds text and image embeddings give complementary class accuracy, and a per-class precision fusion rule adds about 0.4% accuracy over either alone on ImageNet.

Pith tools