{"total":62,"rows":[{"id":"2506.02314","title":"ResearchCodeBench: Benchmarking LLMs on Implementing Novel Machine Learning Research Code","created":"2025-06-02","cited_by_count":36,"area":null},{"id":"2505.18738","title":"AuroRA: Breaking Low-Rank Bottleneck of LoRA with Nonlinear Mapping","created":"2025-05-24","cited_by_count":23,"area":null},{"id":"2601.22966","title":"A Unified View of Attention and Residual Sinks: Outlier-Driven Rescaling is Essential for Transformer Training","created":"2026-01-30","cited_by_count":23,"area":null},{"id":"2504.12711","title":"NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results","created":"2025-04-17","cited_by_count":22,"area":null},{"id":"2506.23424","title":"Accurate Parameter-Efficient Test-Time Adaptation for Time Series Forecasting","created":"2025-06-29","cited_by_count":14,"area":null},{"id":"2512.10938","title":"Stronger Normalization-Free Transformers","created":"2025-12-11","cited_by_count":13,"area":null},{"id":"2505.20524","title":"Towards Fully FP8 GEMM LLM Training at Scale","created":"2025-05-26","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":"2506.16506","title":"Subspace-Boosted Model Merging","created":"2025-06-19","cited_by_count":9,"area":null},{"id":"2509.16195","title":"FocalCodec-Stream: Streaming Low-Bitrate Speech Coding via Causal Distillation","created":"2025-09-19","cited_by_count":9,"area":null},{"id":"2505.22014","title":"Learning in Compact Spaces with Approximately Normalized Transformer","created":"2025-05-28","cited_by_count":6,"area":null},{"id":"2509.22445","title":"Bridging Kolmogorov Complexity and Deep Learning: Asymptotically Optimal Description Length Objectives for Transformers","created":"2025-09-26","cited_by_count":6,"area":null},{"id":"2510.22777","title":"SeeDNorm: Self-Rescaled Dynamic Normalization","created":"2025-10-26","cited_by_count":6,"area":null},{"id":"2506.01153","title":"Weight-Space Linear Recurrent Neural Networks","created":"2025-06-01","cited_by_count":5,"area":null},{"id":"2601.12519","title":"Learning Relativistic Geodesics and Chaotic Dynamics via Stabilized Lagrangian Neural Networks","created":"2026-01-18","cited_by_count":5,"area":null},{"id":"2508.19445","title":"On Surjectivity of Neural Networks: Can you elicit any behavior from your model?","created":"2025-08-26","cited_by_count":4,"area":null},{"id":"2602.10408","title":"Gated Normalization Removal and Scale Anchoring in Pre-Norm Transformers","created":"2026-02-11","cited_by_count":4,"area":null},{"id":"2605.26895","title":"Negligible in Size, Significant in Effect: On Scale Vectors in Large Language Models","created":"2026-05-26","cited_by_count":4,"area":null},{"id":"2505.20155","title":"Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs","created":"2025-05-26","cited_by_count":3,"area":null},{"id":"2508.07577","title":"Exploiting Layer Normalization Fine-tuning in Visual Transformer Foundation Models for Classification","created":"2025-08-11","cited_by_count":3,"area":null},{"id":"2510.23641","title":"Spatially Aware Linear Transformer (SAL-T) for Particle Jet Tagging","created":"2025-10-24","cited_by_count":3,"area":null},{"id":"2602.00654","title":"PHAT: Modeling Period Heterogeneity for Multivariate Time Series Forecasting","created":"2026-01-31","cited_by_count":3,"area":null},{"id":"2605.18613","title":"SAME: A Semantically-Aligned Music Autoencoder","created":"2026-05-18","cited_by_count":3,"area":null},{"id":"2504.05356","title":"DyTTP: Trajectory Prediction with Normalization-Free Transformers","created":"2025-04-07","cited_by_count":2,"area":null},{"id":"2505.14512","title":"Just One Layer Norm Guarantees Stable Extrapolation","created":"2025-05-20","cited_by_count":2,"area":null},{"id":"2506.01049","title":"Taming LLMs by Scaling Learning Rates with Gradient Grouping","created":"2025-06-01","cited_by_count":2,"area":null},{"id":"2510.03989","title":"A Mathematical Explanation of Transformers","created":"2025-10-05","cited_by_count":2,"area":null},{"id":"2601.09719","title":"Bounded Hyperbolic Tangent: A Stable and Efficient Alternative to Pre-Layer Normalization in Large Language Models","created":"2025-12-26","cited_by_count":2,"area":null},{"id":"2603.04766","title":"Evaluating and Correcting Human Annotation Bias in Dynamic Micro-Expression Recognition","created":"2026-03-05","cited_by_count":2,"area":null},{"id":"2605.31577","title":"SurGe: Improved Surface Geometry in Point Maps","created":"2026-05-29","cited_by_count":2,"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":"2505.16372","title":"Temporal and Spatial Feature Fusion Framework for Dynamic Micro Expression Recognition","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2506.12697","title":"MGDFIS: Multi-scale Global-detail Feature Integration Strategy for Small Object Detection","created":"2025-06-15","cited_by_count":1,"area":null},{"id":"2507.17501","title":"DNT: a Deeply Normalized Transformer that can be trained by Momentum SGD","created":"2025-07-23","cited_by_count":1,"area":null},{"id":"2508.11197","title":"E-CaTCH: Event-Centric Cross-Modal Attention with Temporal Consistency and Class-Imbalance Handling for Misinformation Detection","created":"2025-08-15","cited_by_count":1,"area":null},{"id":"2509.21261","title":"Every Subtlety Counts: Fine-grained Person Independence Micro-Action Recognition via Distributionally Robust Optimization","created":"2025-09-25","cited_by_count":1,"area":null},{"id":"2604.01563","title":"Does Your Optimizer Care How You Normalize? Normalization-Optimizer Coupling in LLM Training","created":"2026-04-02","cited_by_count":1,"area":null},{"id":"2503.23016","title":"Towards Understanding the Optimization Mechanisms in Deep Learning","created":"2025-03-29","cited_by_count":0,"area":null},{"id":"2505.22226","title":"Expressive yet Efficient Feature Expansion with Adaptive Cross-Hadamard Products","created":"2025-05-28","cited_by_count":0,"area":null},{"id":"2506.01568","title":"Trajectory First: A Curriculum for Discovering Diverse Policies","created":"2025-06-02","cited_by_count":0,"area":null},{"id":"2506.12210","title":"Machine Intelligence on Wireless Edge Networks","created":"2025-06-13","cited_by_count":0,"area":null},{"id":"2507.03430","title":"Multi-Level Fusion Graph Neural Network for Molecule Property Prediction","created":"2025-07-04","cited_by_count":0,"area":null},{"id":"2508.19750","title":"Fractal Flow: Hierarchical and Interpretable Normalizing Flow via Topic Modeling and Recursive Strategy","created":"2025-08-27","cited_by_count":0,"area":null},{"id":"2509.12763","title":"DyGLNet: Hybrid Global-Local Feature Fusion with Dynamic Upsampling for Medical Image Segmentation","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2509.19779","title":"EfficienT-HDR: An Efficient Transformer-Based Framework via Multi-Exposure Fusion for HDR Reconstruction","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2509.23671","title":"Graph Neural Networks with Diversity-aware Neighbor Selection and Dynamic Multi-scale Fusion for Multivariate Time Series Forecasting","created":"2025-09-28","cited_by_count":0,"area":null},{"id":"2509.25037","title":"GateMABSA: Aspect-Image Gated Fusion for Multimodal Aspect-based Sentiment Analysis","created":"2025-09-29","cited_by_count":0,"area":null},{"id":"2510.09895","title":"Chain-of-Influence: Tracing Interdependencies Across Time and Features in Clinical Predictive Modelings","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2601.12279","title":"HCFT: Hierarchical Convolutional Fusion Transformer for EEG Decoding","created":"2026-01-18","cited_by_count":0,"area":null},{"id":"2604.21101","title":"A Hybridizable Neural Time Integrator for Stable Autoregressive Forecasting","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2604.23434","title":"When Does Removing LayerNorm Help? Activation Bounding as a Regime-Dependent Implicit Regularizer","created":"2026-04-25","cited_by_count":0,"area":null},{"id":"2605.14047","title":"Evolving Layer-Specific Scalar Functions for Hardware-Aware Transformer Adaptation","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2607.10593","title":"AutoNorm: Understanding Adaptive Normalization in Transformers through Differentiable Gating","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2607.18285","title":"Edge-Efficient Transformer for End-to-End RF Spectrum Monitoring","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2608.00087","title":"SymNet: A Multi-Task Network for Joint Radio Map Reconstruction and Transmitter Localization","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.02668","title":"Sphere Retraction Normalizations","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2608.20263","title":"Ultra-High-Definition Restoration Transformers with Correlation Matching Transformation","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2609.01730","title":"HEAT: Faster Fully Homomorphic Inference via Approximations-Weights Co-Adaptation","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.18856","title":"GrainSpeech: Less Context, More Detail for Compact Speech Synthesis","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.34493","title":"LLN: Learnable Lens Networks for Parameter-Efficient Long-Horizon Dynamical Prediction","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36860","title":"IronLLM: Forging Compact Edge-Native Language Models for Real-Time Embodied Intelligence","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.37921","title":"Pattern Formation in Transformers","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}