Self-supervised inpainting with local neighbourhood tokenisation learns reusable priors for 3D fluid velocity fields that outperform supervised neural surrogates under boundary-condition and dataset shifts on intracranial aneurysm data.
hub
Proceedings of the IEEE international conference on computer vision , pages=
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 10roles
background 1polarities
unclear 1representative citing papers
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.
Events trigger on-the-fly LoRA module generation via hypernetworks over a shared team policy in MARL, paired with a Neural Manifold Diversity metric, enabling sequential role reassignment while preserving reward maximization.
ABGD parametrizes piecewise linear functions as difference of max-affine functions and converges linearly to an epsilon-accurate solution with O(d max(sigma/epsilon,1)^2) samples under sub-Gaussian noise, which is minimax optimal up to logs.
Scion is a new stochastic LMO-based optimizer family that unifies existing methods, supports unconstrained problems, and delivers hyperparameter transferability plus speedups on nanoGPT training.
XPERT extracts and reuses cross-domain expert knowledge from pre-trained MoE LLMs via inference analysis and tensor decomposition to improve performance and convergence in downstream language model training.
TLoRA jointly optimizes LoRA initialization via task-data SVD and sensitivity-driven rank allocation, delivering stronger results than standard LoRA across NLU, reasoning, math, code, and chat tasks while using fewer trainable parameters.
E-value sequential tests enable early stopping of MCMC sampling in Bayesian deep ensembles, often needing only a fraction of the full budget while improving over standard deep ensembles.
SPIN lets weak LLMs become strong by self-generating training data from previous model versions and training to prefer human-annotated responses over its own outputs, outperforming DPO even with extra GPT-4 data on benchmarks.
Neo, a cGAN, super-resolves HSC images to HST-like quality and improves galaxy morphological parameter accuracy by factors of 2-10.
citing papers explorer
-
Inpainting physics: self-supervised learning for context-driven fluid simulation
Self-supervised inpainting with local neighbourhood tokenisation learns reusable priors for 3D fluid velocity fields that outperform supervised neural surrogates under boundary-condition and dataset shifts on intracranial aneurysm data.
-
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.
-
Events as Triggers for Behavioral Diversity in Multi-Agent Reinforcement Learning
Events trigger on-the-fly LoRA module generation via hypernetworks over a shared team policy in MARL, paired with a Neural Manifold Diversity metric, enabling sequential role reassignment while preserving reward maximization.
-
Locally Near Optimal Piecewise Linear Regression in High Dimensions via Difference of Max-Affine Functions
ABGD parametrizes piecewise linear functions as difference of max-affine functions and converges linearly to an epsilon-accurate solution with O(d max(sigma/epsilon,1)^2) samples under sub-Gaussian noise, which is minimax optimal up to logs.
-
Training Deep Learning Models with Norm-Constrained LMOs
Scion is a new stochastic LMO-based optimizer family that unifies existing methods, supports unconstrained problems, and delivers hyperparameter transferability plus speedups on nanoGPT training.
-
XPERT: Expert Knowledge Transfer for Effective Training of Language Models
XPERT extracts and reuses cross-domain expert knowledge from pre-trained MoE LLMs via inference analysis and tensor decomposition to improve performance and convergence in downstream language model training.
-
TLoRA: Task-aware Low Rank Adaptation of Large Language Models
TLoRA jointly optimizes LoRA initialization via task-data SVD and sensitivity-driven rank allocation, delivering stronger results than standard LoRA across NLU, reasoning, math, code, and chat tasks while using fewer trainable parameters.
-
Towards E-Value Based Stopping Rules for Bayesian Deep Ensembles
E-value sequential tests enable early stopping of MCMC sampling in Bayesian deep ensembles, often needing only a fraction of the full budget while improving over standard deep ensembles.
-
Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models
SPIN lets weak LLMs become strong by self-generating training data from previous model versions and training to prefer human-annotated responses over its own outputs, outperforming DPO even with extra GPT-4 data on benchmarks.
-
Photometric Super-Resolution for Improving Galaxy Morphological Measurements using Conditional Generative Adversarial Networks
Neo, a cGAN, super-resolves HSC images to HST-like quality and improves galaxy morphological parameter accuracy by factors of 2-10.