Image de couverture de livre

JPmHC Dynamical Isometry via Orthogonal Hyper-Connections

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Sengupta, Biswa, Wang, Jinhua, Brunswic, Leo
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

HARBOR: Automated Harness Optimization
par: Sengupta, Biswa, et autres
Publié: (2026)

Representation Without Reward: A JEPA Audit for LLM Fine-Tuning
par: Sengupta, Biswa
Publié: (2026)

mHC: Manifold-Constrained Hyper-Connections
par: Xie, Zhenda, et autres
Publié: (2025)

mHC-GNN: Manifold-Constrained Hyper-Connections for Graph Neural Networks
par: Mishra, Subhankar
Publié: (2026)

From Translation to Superset: Benchmark-Driven Evolution of a Production AI Agent from Rust to Python
par: Wang, Jinhua, et autres
Publié: (2026)

Learning Multi-Agent Communication with Contrastive Learning
par: Lo, Yat Long, et autres
Publié: (2023)

Frac-Connections: Fractional Extension of Hyper-Connections
par: Zhu, Defa, et autres
Publié: (2025)

Parametric Feature Transfer: One-shot Federated Learning with Foundation Models
par: Beitollahi, Mahdi, et autres
Publié: (2024)

Ablate and Rescue: A Causal Analysis of Residual Stream Hyper-Connections
par: Peng, William, et autres
Publié: (2026)

Isometry pursuit
par: Koelle, Samson, et autres
Publié: (2024)

Beyond the Birkhoff Polytope: Spectral-Sphere-Constrained Hyper-Connections
par: Liu, Zhaoyi, et autres
Publié: (2026)

FIRE: Frobenius-Isometry Reinitialization for Balancing the Stability-Plasticity Tradeoff
par: Han, Isaac, et autres
Publié: (2026)

HC-GAE: The Hierarchical Cluster-based Graph Auto-Encoder for Graph Representation Learning
par: Xu, Zhuo, et autres
Publié: (2024)

mHC-lite: You Don't Need 20 Sinkhorn-Knopp Iterations
par: Yang, Yongyi, et autres
Publié: (2026)

Orthogonalized Policy Optimization:Policy Optimization as Orthogonal Projection in Hilbert Space
par: Zixian, Wang
Publié: (2026)

Generative Models in Decision Making: A Survey
par: Shao, Xinyu, et autres
Publié: (2025)

Omni-Thinker: Scaling Multi-Task RL in LLMs with Hybrid Reward and Task Scheduling
par: Li, Derek, et autres
Publié: (2025)

mHC-SSM: Manifold-Constrained Hyper-Connections for State Space Language Models with Stream-Specialized Adapters
par: Mutlu, Abdulvahap, et autres
Publié: (2026)

Group Orthogonalized Policy Optimization:Group Policy Optimization as Orthogonal Projection in Hilbert Space
par: Zixian, Wang
Publié: (2026)

UNO: Unlearning via Orthogonalization in Generative models
par: Mandal, Pinak, et autres
Publié: (2025)

Hyper-Compression: Model Compression via Hyperfunction
par: Fan, Fenglei, et autres
Publié: (2024)

Integrating Boosted learning with Differential Evolution (DE) Optimizer: A Prediction of Groundwater Quality Risk Assessment in Odisha
par: Subudhi, Sonalika, et autres
Publié: (2025)

HyperMono: A Monotonicity-aware Approach to Hyper-Relational Knowledge Representation
par: Hu, Zhiwei, et autres
Publié: (2024)

HyperMoE: Towards Better Mixture of Experts via Transferring Among Experts
par: Zhao, Hao, et autres
Publié: (2024)

HyperNAS: Enhancing Architecture Representation for NAS Predictor via Hypernetwork
par: Lv, Jindi, et autres
Publié: (2025)

HyperCore: Coreset Selection under Noise via Hypersphere Models
par: Moser, Brian B., et autres
Publié: (2025)

Network-Aware Bilinear Tokenization for Brain Functional Connectivity Representation Learning
par: Milecki, Leo, et autres
Publié: (2026)

HyperVLA: Efficient Inference in Vision-Language-Action Models via Hypernetworks
par: Xiong, Zheng, et autres
Publié: (2025)

Uncertain Multi-Objective Recommendation via Orthogonal Meta-Learning Enhanced Bayesian Optimization
par: Wang, Hongxu, et autres
Publié: (2025)

Generative Representation Learning on Hyper-relational Knowledge Graphs via Masked Discrete Diffusion
par: Lee, Jaejun, et autres
Publié: (2026)

Bit-Identical Medical Deep Learning via Structured Orthogonal Initialization
par: Shkolnikov, Yakov Pyotr
Publié: (2026)

HyperGCL: Multi-Modal Graph Contrastive Learning via Learnable Hypergraph Views
par: Saifuddin, Khaled Mohammed, et autres
Publié: (2025)

Preventing Dimensional Collapse in Self-Supervised Learning via Orthogonality Regularization
par: He, Junlin, et autres
Publié: (2024)

Neural Isometries: Taming Transformations for Equivariant ML
par: Mitchel, Thomas W., et autres
Publié: (2024)

Wireless Federated Multi-Task LLM Fine-Tuning via Sparse-and-Orthogonal LoRA
par: Yang, Nuocheng, et autres
Publié: (2026)

FedAGHN: Personalized Federated Learning with Attentive Graph HyperNetworks
par: Song, Jiarui, et autres
Publié: (2025)

Q-Star Meets Scalable Posterior Sampling: Bridging Theory and Practice via HyperAgent
par: Li, Yingru, et autres
Publié: (2024)

Scalable Heterogeneous Graph Learning via Heterogeneous-aware Orthogonal Prototype Experts
par: Zhou, Wei, et autres
Publié: (2026)

ODICE: Revealing the Mystery of Distribution Correction Estimation via Orthogonal-gradient Update
par: Mao, Liyuan, et autres
Publié: (2024)

HyperFast: Instant Classification for Tabular Data
par: Bonet, David, et autres
Publié: (2024)