{"total":25,"rows":[{"id":"2512.24880","title":"mHC: Manifold-Constrained Hyper-Connections","created":"2025-12-31","cited_by_count":88,"area":null},{"id":"2409.19606","title":"Hyper-Connections","created":"2024-09-29","cited_by_count":84,"area":null},{"id":"2601.05732","title":"mHC-lite: You Don't Need 20 Sinkhorn-Knopp Iterations","created":"2026-01-09","cited_by_count":17,"area":null},{"id":"2503.04598","title":"HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid Normalization","created":"2025-03-06","cited_by_count":16,"area":null},{"id":"2407.02783","title":"52B to 1T: Lessons Learned via Tele-FLM Series","created":"2024-07-03","cited_by_count":11,"area":null},{"id":"2601.21579","title":"KromHC: Manifold-Constrained Hyper-Connections with Kronecker-Product Residual Matrices","created":"2026-01-29","cited_by_count":11,"area":null},{"id":"2602.08064","title":"SiameseNorm: Breaking the Barrier to Reconciling Pre/Post-Norm","created":"2026-02-08","cited_by_count":10,"area":null},{"id":"2309.07391","title":"EnCodecMAE: Leveraging neural codecs for universal audio representation learning","created":"2023-09-14","cited_by_count":9,"area":null},{"id":"2411.07176","title":"More Expressive Attention with Negative Weights","created":"2024-11-11","cited_by_count":9,"area":null},{"id":"2503.14125","title":"Frac-Connections: Fractional Extension of Hyper-Connections","created":"2025-03-18","cited_by_count":8,"area":null},{"id":"2306.01610","title":"Centered Self-Attention Layers","created":"2023-06-02","cited_by_count":7,"area":null},{"id":"2604.02309","title":"go-$m$HC: Direct Parameterization of Manifold-Constrained Hyper-Connections via Generalized Orthostochastic Matrices","created":"2026-04-02","cited_by_count":4,"area":null},{"id":"2502.15499","title":"Scale-Distribution Decoupling: Enabling Stable and Effective Training of Large Language Models","created":"2025-02-21","cited_by_count":3,"area":null},{"id":"2310.11609","title":"Reflection-Equivariant Diffusion for 3D Structure Determination from Isotopologue Rotational Spectra in Natural Abundance","created":"2023-10-17","cited_by_count":2,"area":null},{"id":"2312.01324","title":"MABViT -- Modified Attention Block Enhances Vision Transformers","created":"2023-12-03","cited_by_count":1,"area":null},{"id":"2503.23924","title":"Model Hemorrhage and the Robustness Limits of Large Language Models","created":"2025-03-31","cited_by_count":1,"area":null},{"id":"2603.05369","title":"Progressive Residual Warmup for Language Model Pretraining","created":"2026-03-05","cited_by_count":1,"area":null},{"id":"2604.19846","title":"Neural posterior estimation of the neutrino direction in IceCube using transformer-encoded normalizing flows on the sphere","created":"2026-04-21","cited_by_count":1,"area":null},{"id":"2601.11645","title":"IMSAHLO: Integrating Multi-Scale Attention and Hybrid Loss Optimization Framework for Robust Neuronal Brain Cell Segmentation","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2601.13564","title":"Multi-objective fluorescent molecule design with a data-physics dual-driven generative framework","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2601.18981","title":"Attention-Enhanced Graph Filtering for False Data Injection Attack Detection and Localization","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2603.19844","title":"Probing and Inducing Clinical Modality Grounding in Brain Tumor Segmentation","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2605.15793","title":"AOT-POT: Adaptive Operator Transformation for Large-Scale PDE Pre-training","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2606.16112","title":"Scaling Adaptive Depth with Norm-Agnostic Residual Networks","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2608.09417","title":"Why Post-Norm Transformers Collapse: Attention Amplification and Gradient Repair Failure","created":"2026-08-10","cited_by_count":0,"area":null}],"next_cursor":null}