Attention and LoRA regression losses induce Poincaré inequalities under mild regularization, so SGD-mimicking SDEs converge to minimizers with no assumptions on data or model size.
hub
International Conference on Learning Representations , year=
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
hub tools
years
2026 10representative citing papers
LOFT unifies orthogonal PEFT by treating adaptation as low-rank subspace rotation and adds task-aware support selection that improves efficiency under fixed budgets.
A dual-phase framework using self-supervised ViT slots optimizes representations for class identity during training and composes them dynamically at inference to achieve state-of-the-art generalization to unseen concepts with minimal forgetting in continual few-shot learning.
LE-SAM inverts SAM by fixing the loss budget instead of the parameter-space radius, yielding better generalization across benchmarks.
SeBA is a joint-embedding framework that separates tabular data into two complementary views and aligns one view's representations to the nearest-neighbor structure of the other, improving feature-label relationships and achieving SOTA results in most benchmarks without relying on augmentations.
PHALAR achieves up to 70% relative accuracy gain in stem retrieval with under half the parameters and 7x faster training by using phasor-based equivariant representations, setting new SOTA on multiple datasets.
GridS reduces visual tokens in VLA models to under 10% of the original count via task-aware differentiable resampling, delivering 76% lower FLOPs with no drop in task success rate on benchmarks and real robots.
A frequency-enhanced Vision Transformer with FDSA, FGMLP, WAFF, and FCSB modules delivers superior volumetric medical image segmentation performance and efficiency over prior state-of-the-art methods.
A plug-and-play RL method adds batch-level distributional supervision via CCC rewards to reduce regression-to-the-mean in MLLMs on imbalanced regression benchmarks.
citing papers explorer
-
Convergent Stochastic Training of Attention and Understanding LoRA
Attention and LoRA regression losses induce Poincaré inequalities under mild regularization, so SGD-mimicking SDEs converge to minimizers with no assumptions on data or model size.
-
LOFT: Low-Rank Orthogonal Fine-Tuning via Task-Aware Support Selection
LOFT unifies orthogonal PEFT by treating adaptation as low-rank subspace rotation and adds task-aware support selection that improves efficiency under fixed budgets.
-
Unlocking Compositional Generalization in Continual Few-Shot Learning
A dual-phase framework using self-supervised ViT slots optimizes representations for class identity during training and composes them dynamically at inference to achieve state-of-the-art generalization to unseen concepts with minimal forgetting in continual few-shot learning.
-
Fix the Loss, Not the Radius: Rethinking the Adversarial Perturbation of Sharpness-Aware Minimization
LE-SAM inverts SAM by fixing the loss budget instead of the parameter-space radius, yielding better generalization across benchmarks.
-
SeBA: Semi-supervised few-shot learning via Separated-at-Birth Alignment for tabular data
SeBA is a joint-embedding framework that separates tabular data into two complementary views and aligns one view's representations to the nearest-neighbor structure of the other, improving feature-label relationships and achieving SOTA results in most benchmarks without relying on augmentations.
-
PHALAR: Phasors for Learned Musical Audio Representations
PHALAR achieves up to 70% relative accuracy gain in stem retrieval with under half the parameters and 7x faster training by using phasor-based equivariant representations, setting new SOTA on multiple datasets.
-
See What Matters: Differentiable Grid Sample Pruning for Generalizable Vision-Language-Action Model
GridS reduces visual tokens in VLA models to under 10% of the original count via task-aware differentiable resampling, delivering 76% lower FLOPs with no drop in task success rate on benchmarks and real robots.
-
FEFormer: Frequency-enhanced Vision Transformer for Generic Knowledge Extraction and Adaptive Feature Fusion in Volumetric Medical Image Segmentation
A frequency-enhanced Vision Transformer with FDSA, FGMLP, WAFF, and FCSB modules delivers superior volumetric medical image segmentation performance and efficiency over prior state-of-the-art methods.
-
Injecting Distributional Awareness into MLLMs via Reinforcement Learning for Deep Imbalanced Regression
A plug-and-play RL method adds batch-level distributional supervision via CCC rewards to reduce regression-to-the-mean in MLLMs on imbalanced regression benchmarks.
- PnP-Corrector: A Universal Correction Framework for Coupled Spatiotemporal Forecasting