VISReg introduces a novel regularization technique that combines variance control with a Sliced-Wasserstein-based sketching objective to stabilize self-supervised learning, achieving state-of-the-art…

The paper introduces BRo-JEPA, a latent world model that successfully learns modular arithmetic (like addition modulo 10) by explicitly imposing the circular structure of the problem into the latent s…

The paper proposes a novel layer and point-wise projection mapping combined with LoRA injection to efficiently distill knowledge from a large teacher model to a small student model, significantly impr…

The paper analyzes low-degree estimation thresholds for recovering hidden signals in planted hypergraphs and tensor PCA, establishing sharp phase transitions and providing polynomial-time recovery alg…

The paper introduces CalArena, a large-scale, standardized benchmark covering nearly 2000 experiments to comprehensively evaluate post-hoc calibration methods, finding that smooth calibration function…

The paper introduces and analyzes several novel data appraisal metrics, including the Vendi Score and matrix spectral functions, demonstrating that efficient optimization techniques make these metrics…

The paper identifies a fundamental mismatch between standard pairwise ranking metrics (like AP and FPR-95) and the true assignment objective in multi-view object association, proposing a Sinkhorn-base…

This paper provides the first non-vacuous generalization analysis for the Stochastic Variance Reduced Gradient (SVRG) method by establishing sharp, data-dependent algorithmic stability bounds, thereby…

The paper introduces PRISM, a novel representation learning framework that learns isometric embeddings by explicitly modeling the intrinsic geodesic metric of 3D surfaces, achieving superior performan…

The paper proposes a novel geometric embedding hashing method to recover object correspondences (vector links) between two embedding clouds generated by different black-box encoders using only a small…

Clark Hash is a stateless, deterministic quantization method that significantly reduces the storage size of neural embeddings while maintaining high accuracy for cosine similarity search.

LALE introduces a novel lightweight architecture that efficiently combines local convolutional features and global transformer context for land-cover segmentation, achieving superior efficiency and pe…

The paper investigates applying Riemannian optimization techniques to low-rank matrix parameters for deep learning, but finds that the proposed methods do not conclusively outperform the AdamW baselin…

The paper introduces Entropic Projection Alignment (EPA), a unified framework that estimates, explains, and improves model performance under distribution shift by aligning source and target distributi…

The paper proposes a unified framework to systematically redefine instance matching for Panoptic Quality evaluation, moving beyond the standard One-to-One matching to accommodate complex scenarios lik…

The paper theoretically analyzes the properties that optimal sparse autoencoder (SAE) dictionaries must satisfy, deriving constraints that explain observed SAE behaviors like hierarchical splitting an…

The paper proposes FedSAP, a framework that stabilizes federated prototype learning by delaying global alignment and enforcing inter-class structure, significantly improving representation quality und…

This paper identifies prediction bias, a failure mode of entropy minimization in test-time adaptation, and proposes Distribution Shift Bias Reduction (DSBR) to stabilize adaptation and prevent model c…