The paper presents a method for distilling a large 300‑million‑parameter geospatial foundation model (Prithvi‑EO‑2.0) into a compact 0.7‑million‑parameter EfficientViT‑B0 student for flood segmentation. By using the teacher to supervise additional unlabeled Sentinel‑2 imagery, the student’s training set expands without new manual labels, achieving competitive performance on Sen1Floods11 and STURM‑Flood while remaining smaller and faster. After quantization, the student runs as a 1.5‑MB INT8 TensorRT engine on a Jetson Xavier NX, processing 512×512 images in 5.57 ms with ~14 MB of memory.
arXiv:2604. 15622v3 Announce Type: replace-cross Abstract: Always-on contextual AI runs language-aligned vision foundation models (VFMs) on edge devices, where the on-device model is the dominant continuous compute cost under strict latency and power limits.
The paper presents a method for cross‑architecture knowledge distillation from a fine‑tuned DINOv2 Vision Transformer teacher to a lightweight bidirectional Visual State Space Model (LVSSM) student for tea leaf disease classification. By addressing training‑stability issues with a progressive convolutional stem and gated selective‑scan block, the 4.45 M‑parameter student achieves a mean test accuracy of 95.41%—a 3.09‑point improvement over the teacher’s 92.32%—while using only one‑fifth of the teacher’s parameters. Ablation studies show that simple logit‑level distillation outperforms intermediate feature alignment, and the gains are specific to students that start below the teacher’s performance.
arXiv:2607. 03949v1 Announce Type: cross Abstract: Pixel-wise Earth-observation (EO) foundation models are now achieving state-of-the-art performance via generated spatial embeddings.
arXiv:2610.34904v1 Announce Type: cross Abstract: Pretrained Earth observation models may reduce the effort needed to map surface water, but their value depends on the alternative against which they...
Pretrained Earth observation models may reduce the effort needed to map surface water, but their value depends on the alternative against which they are compared. We evaluated Prithvi-EO-2.0-Tiny usin...
arXiv:2603. 12478v2 Announce Type: replace-cross Abstract: Multimodal instruction tuning is often compute-inefficient because training budgets are spread across large mixed image-video pools whose utility is highly uneven.
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.
arXiv:2609.36374v1 Announce Type: new Abstract: Feed-forward 3D reconstruction models have achieved impressive performance by scaling model and dataset size, but their cost excludes most research gro...
PixelDense introduces a dual‑stream representation alignment for pixel diffusion, separating semantic and geometric teachers (DINOv2, SAM2, Depth Anything v2, Metric3D v2) into distinct projection spaces with an orthogonality penalty. The method improves dense‑prediction benchmarks, boosting PixelGen‑XXL’s GenEval score from 0.7927 to 0.8093, achieving significant gains in panoptic quality and depth accuracy, and accelerating training from random initialization. It also enhances SDEdit editing by preserving background structure and increasing PSNR.
arXiv:2603. 06741v2 Announce Type: replace-cross Abstract: Training frontier-scale diffusion models often requires substantial computational resources concentrated in tightly-coupled clusters, limiting participation to well-resourced institutions.
arXiv:2606. 24780v1 Announce Type: new Abstract: Progress in deep learning is, at scale, more a matter of systems engineering than of modelling: the behaviour of a model in training (its throughput, its memory footprint, and the numerical fidelity of the result) is determined less by the architecture itself than by how that architecture is expressed on the hardware.
The paper investigates using short polynomial approximations to accelerate special‑function operations in large language models on NVIDIA Blackwell GPUs. By replacing native sigmoid, tanh, and SiLU with degree‑3 or degree‑4 bfloat16 programs, the authors achieve up to 2.19× speed‑ups in isolated FP16 benchmarks and modest training‑step throughput gains (2.7–8.0%) across four integration tasks. The study also evaluates model behavior, finding negligible training‑loss differences within 100 billion tokens.