CPF-GCD enforces low-rank compositional structure on vision backbone features via spatial primitive fields so that novel categories emerge as new activation patterns over a shared vocabulary of reusable visual primitives.
hub
Proceedings of the IEEE/CVF international conference on computer vision , pages=
19 Pith papers cite this work. Polarity classification is still indexing.
19
Pith papers citing it
hub tools
representative citing papers
MolSight injects molecular graph topology and image-derived SVG annotations into a vision-language model, reporting state-of-the-art results on image-to-SMILES, captioning, descriptor, and bioactivity tasks.
SemiPrune uses a small labeled subset and semi-supervised pseudo-labeling to enable supervised dataset pruning methods, achieving state-of-the-art results on domain-specific, image-corrupted, and long-tailed datasets.
STELLAR trains up to 500M-parameter multi-modal models on 50M driving scenes and reports empirical scaling trends plus new state-of-the-art results on the Waymo Open Dataset.
GCE-MIL is a backbone-agnostic wrapper that directly optimizes MIL evidence for sufficiency, necessity, and recoverability, yielding modest gains in Macro-F1 and C-index plus more faithful patch selection across many backbones and datasets.
Standard MIL models for whole-slide pathology images exhibit spatial blindness under coordinate permutation; ResTopoMIL separates appearance and spatial learning to restore sensitivity and improve classification and survival prediction.
R-DMesh proposes a VAE-based disentanglement of base mesh, motion trajectories, and rectification offset plus Triflow Attention and rectified-flow diffusion to produce 4D meshes aligned to video despite initial pose mismatch.
Generative models learn rules before memorizing data, creating an innovation window whose width depends on dataset size and rule complexity, observed in both diffusion and autoregressive architectures.
MUSE decouples reconstruction and semantic learning in visual tokenization via topological orthogonality, yielding SOTA generation quality and improved semantic performance over its teacher model.
DINA is a dual-tower contrastive model that aligns images with mouse V1 neural activity to enable decoding and shows that low-level visual structure, not semantics or fine details, primarily supports the alignment.
LeJEPA derives an optimal isotropic Gaussian target for embeddings and enforces it via sketched regularization to deliver scalable, heuristics-free self-supervised pretraining with 79% ImageNet linear accuracy on ViT-H/14.
MVProbe is a multi-perspective probing framework for weight-space learning that combines first-order and Gram-based views and outperforms ProbeX on the Model Jungle benchmark.
Flow Mismatching detects anomalies via aggregated velocity mismatches along noise-to-image paths in a flow matching model trained only on normal data, yielding pixel heatmaps without reconstruction or test-time optimization.
PACD-Net uses pseudo-augmented contrastive distillation with a hybrid Swin Transformer-CNN backbone to estimate TAR, TIR, and TBR from sparse SMBG data and outperforms prior methods in accuracy and stability under sparse conditions.
TAPE applies temporal-aware token pruning with smoothing, reselection, and timestep scheduling to speed up video diffusion models while preserving visual fidelity and coherence.
A self-supervised approach uses consistent spatial relationships of anatomical structures across patients to improve 3D multi-modal medical image representations, yielding modest gains on segmentation and classification tasks.
SSL clustering is derived as KL-divergence optimization where a teacher-distribution constraint normalizes via inverse cluster priors and simplifies to batch centering by Jensen's inequality.
ESsEN is a parameter-efficient two-tower vision-language transformer that matches larger models on discriminative tasks after training end-to-end with limited data and resources.
Representations learned by large AI models are converging toward a shared statistical model of reality.
citing papers explorer
-
Identifying Latent Concepts and Structures for Generalized Category Discovery
CPF-GCD enforces low-rank compositional structure on vision backbone features via spatial primitive fields so that novel categories emerge as new activation patterns over a shared vocabulary of reusable visual primitives.
-
MolSight: A Graph-Aware Vision-Language Model for Unified Chemical Image Understanding
MolSight injects molecular graph topology and image-derived SVG annotations into a vision-language model, reporting state-of-the-art results on image-to-SMILES, captioning, descriptor, and bioactivity tasks.
-
Label-Efficient Dataset Pruning via Semi-Supervised Pseudo-Labeling
SemiPrune uses a small labeled subset and semi-supervised pseudo-labeling to enable supervised dataset pruning methods, achieving state-of-the-art results on domain-specific, image-corrupted, and long-tailed datasets.
-
STELLAR: Scaling 3D Perception Large Models for Autonomous Driving
STELLAR trains up to 500M-parameter multi-modal models on 50M driving scenes and reports empirical scaling trends plus new state-of-the-art results on the Waymo Open Dataset.
-
GCE-MIL: Faithful and Recoverable Evidence for Multiple Instance Learning in Whole-Slide Imaging
GCE-MIL is a backbone-agnostic wrapper that directly optimizes MIL evidence for sufficiency, necessity, and recoverability, yielding modest gains in Macro-F1 and C-index plus more faithful patch selection across many backbones and datasets.
-
Spatial Blindness in Whole-Slide Multiple Instance Learning
Standard MIL models for whole-slide pathology images exhibit spatial blindness under coordinate permutation; ResTopoMIL separates appearance and spatial learning to restore sensitivity and improve classification and survival prediction.
-
R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow
R-DMesh proposes a VAE-based disentanglement of base mesh, motion trajectories, and rectification offset plus Triflow Attention and rectified-flow diffusion to produce 4D meshes aligned to video despite initial pose mismatch.
-
The two clocks and the innovation window: When and how generative models learn rules
Generative models learn rules before memorizing data, creating an innovation window whose width depends on dataset size and rule complexity, observed in both diffusion and autoregressive architectures.
-
MUSE: Resolving Manifold Misalignment in Visual Tokenization via Topological Orthogonality
MUSE decouples reconstruction and semantic learning in visual tokenization via topological orthogonality, yielding SOTA generation quality and improved semantic performance over its teacher model.
-
Interpreting V1 Population Activity via Image-Neural Latent Representation Alignment
DINA is a dual-tower contrastive model that aligns images with mouse V1 neural activity to enable decoding and shows that low-level visual structure, not semantics or fine details, primarily supports the alignment.
-
LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
LeJEPA derives an optimal isotropic Gaussian target for embeddings and enforces it via sketched regularization to deliver scalable, heuristics-free self-supervised pretraining with 79% ImageNet linear accuracy on ViT-H/14.
-
What Linear Probes Miss: Multi-View Probing for Weight-Space Learning
MVProbe is a multi-perspective probing framework for weight-space learning that combines first-order and Gram-based views and outperforms ProbeX on the Model Jungle benchmark.
-
Flow Mismatching: Unsupervised Anomaly Detection via Velocity Discrepancies in Flow Matching Models
Flow Mismatching detects anomalies via aggregated velocity mismatches along noise-to-image paths in a flow matching model trained only on normal data, yielding pixel heatmaps without reconstruction or test-time optimization.
-
PACD-Net: Pseudo-Augmented Contrastive Distillation for Glycemic Control Estimation from SMBG
PACD-Net uses pseudo-augmented contrastive distillation with a hybrid Swin Transformer-CNN backbone to estimate TAR, TIR, and TBR from sparse SMBG data and outperforms prior methods in accuracy and stability under sparse conditions.
-
Temporal Aware Pruning for Efficient Diffusion-based Video Generation
TAPE applies temporal-aware token pruning with smoothing, reselection, and timestep scheduling to speed up video diffusion models while preserving visual fidelity and coherence.
-
Beyond Instance-Level Self-Supervision in 3D Multi-Modal Medical Imaging
A self-supervised approach uses consistent spatial relationships of anatomical structures across patients to improve 3D multi-modal medical image representations, yielding modest gains on segmentation and classification tasks.
-
Information theoretic underpinning of self-supervised learning by clustering
SSL clustering is derived as KL-divergence optimization where a teacher-distribution constraint normalizes via inverse cluster priors and simplifies to batch centering by Jensen's inequality.
-
ESsEN: Training Compact Discriminative Vision-Language Transformers in a Low-Resource Setting
ESsEN is a parameter-efficient two-tower vision-language transformer that matches larger models on discriminative tasks after training end-to-end with limited data and resources.
-
The Platonic Representation Hypothesis
Representations learned by large AI models are converging toward a shared statistical model of reality.