IronViT proposes a new approach to building efficient generalist vision encoders by first consolidating the knowledge of multiple specialist teachers into a softmax attention bridge and then transferring this consolidated representation to a hybrid softmax‑linear attention architecture. This two‑stage distillation process, supported by a curated data pipeline, allows the model to capture semantic, spatial, language‑aligned, and action‑relevant cues while avoiding the high‑resolution cost of traditional softmax attention. Across tasks such as recognition, retrieval, dense prediction, multimodal understanding, and robotic learning, IronViT matches or exceeds the performance of leading specialist and generalist encoders, with the hybrid encoder offering increasing efficiency at higher resolutions.
By Jiaxi Huang, Yueqi Hu, Xin Zhu, Xiaopeng Zhang, Huiting Qiao, Yanglin Zhang, Zefeng Ji, Rongxue Li, Yifei Xu, Huiying Yu, Wei Liu, Jiayin Zheng, Yinggan Xu, Peipeng Chen, Yin Zhang, Jian Yao
arXiv:2607. 09526v1 Announce Type: cross Abstract: Foundation models are reshaping computational pathology, yet their capabilities remain shaped by pretraining objectives, data sources, and spatial scales, fragmenting complementary expertise across separate backbones.
By Jiawen Li, Tian Guan, Huijuan Shi, Xitong Ling, Mingxi Fu, Anjia Han, Chao He, Yonghong He
arXiv:2402. 14035v4 Announce Type: replace-cross Abstract: Knowledge distillation from foundation models to compact domain models is challenging due to substantial gaps in capacity, architecture, and modality.
By Zichang Liu, Qingyun Liu, Yuening Li, Liang Liu, Anshumali Shrivastava, Shuchao Bi, Lichan Hong, Ed H. Chi, Zhe Zhao
arXiv:2608.23850v1 Announce Type: new
Abstract: Foundational visual features such as DINO have played a critical role across modern computer vision, and have recently become key components in multi-v...
By Jeong-gi Kwak, Sho Kagami, Yuki Ono, Kwang Moo Yi
Dyna‑DINO introduces a curriculum for Vision Transformer (ViT) knowledge distillation that uses the teacher’s intermediate feature maps as progressively harder targets, enabling a student to build foundational representations before tackling higher‑level abstractions. The approach accelerates convergence and improves performance across multiple tasks: on ImageNet‑100 the distilled ViT‑S reaches 90.1% accuracy (+12.24% over baseline), while on ImageNet‑1K it yields +3.9% and +6.09% gains on Oxford and Paris retrieval, +1.93% on semantic segmentation, and notable classification improvements. Additionally, the curriculum reduces training FLOPs by 25.1% and training time by 21% on ImageNet‑100 through early‑stopping of teacher inference.
By Jiaqi Zhang, Ashton Lee, Anthony Wong, John Zou, Sami BuGhanem, Randall Balestriero
arXiv:2607. 14703v1 Announce Type: cross Abstract: Multiple instance learning (MIL) has become the main paradigm for whole-slide image (WSI) analysis in computational pathology.
By Mingxi Fu, Jiawen Li, Renao Yan, Jiali Hu, Qiehe Sun, Tian Guan, Yonghong He
Large 3D foundation models such as MASt3R achieve state-of-the-art stereo reconstruction but are computationally demanding for deployment under strict hardware constraints -- a critical limitation in domains such as planetary exploration, where onboard computing is severely restricted. We study how far such models can be compressed through knowledge distillation, using lunar stereo reconstruction as a challenging and practically relevant case study.
arXiv:2606. 20559v1 Announce Type: cross Abstract: Egocentric video understanding is inherently limited by the narrow perspective of wearable cameras: a single viewpoint, a single modality, a single model cannot capture the full richness of human action.
By Wenhao Chi, Arkaprava Sinha, Dominick Reilly, Hieu Le, Srijan Das
arXiv:2606. 27527v1 Announce Type: cross Abstract: Large Language Models (LLMs) possess broad conceptual knowledge acquired through large-scale text pretraining, yet their potential to supervise models in other modalities remains underexplored.
By Thomas Shih-Chao Liang, Zhuoran Yu, Yong Jae Lee
CLIP-RD introduces a relational distillation framework for efficient CLIP knowledge distillation, featuring Vertical Relational Distillation (VRD) and Cross Relational Distillation (XRD). VRD aligns intra‑modal similarity distributions between teacher and student, while XRD aligns cross‑modal similarity distributions to enforce bidirectional symmetry. This joint modeling of multidirectional relational structures improves the student’s embedding geometry, yielding a 1.8%p performance gain over CLIP‑KD across various architectures, tasks, and corruption settings with minimal training‑time overhead.
By Jeannie Chung, Hanna Jang, Ingyeong Yang, Uiwon Hwang, Jaehyeong Sim
arXiv:2609.07137v1 Announce Type: cross
Abstract: Recent image-to-3D generation models built on flow-matching diffusion Transformers (DiT) can produce high-fidelity meshes, yet their post-training st...
By Zhiwei Ning, Zhen Zhou, Puhua Jiang, Xintong Han, Gengming Zhang, Jie Yang, Zhonglong Zheng, Yuanjie Zheng, Wei Liu, Chunchao Guo
Vision Transformers underperform convolutional networks when training data is scarce, and distilling convolutional inductive biases from a CNN teacher is an effective remedy that leaves the deployed model unchanged. General-purpose feature distillation, however, transfers little in this setting.