{"total":18,"rows":[{"id":"2405.19592","title":"Why Larger Language Models Do In-context Learning Differently?","created":"2024-05-30","cited_by_count":45,"area":null},{"id":"2407.15720","title":"Do Large Language Models Have Compositional Ability? An Investigation into Limitations and Scalability","created":"2024-07-22","cited_by_count":40,"area":null},{"id":"2408.09503","title":"Out-of-distribution generalization via composition: a lens through induction heads in Transformers","created":"2024-08-18","cited_by_count":28,"area":null},{"id":"2410.11268","title":"Bypassing the Exponential Dependency: Looped Transformers Efficiently Learn In-context by Multi-step Gradient Descent","created":"2024-10-15","cited_by_count":22,"area":null},{"id":"2407.13621","title":"Differential Privacy Mechanisms in Neural Tangent Kernel Regression","created":"2024-07-18","cited_by_count":14,"area":null},{"id":"2410.24018","title":"Bayesian-guided Label Mapping for Visual Reprogramming","created":"2024-10-31","cited_by_count":12,"area":null},{"id":"2505.11892","title":"Fast RoPE Attention: Combining the Polynomial Method and Fast Fourier Transform","created":"2025-05-17","cited_by_count":9,"area":null},{"id":"2507.14240","title":"HuggingGraph: Understanding the Supply Chain of LLM Ecosystem","created":"2025-07-17","cited_by_count":8,"area":null},{"id":"2505.16284","title":"Only Large Weights (And Not Skip Connections) Can Prevent the Perils of Rank Collapse","created":"2025-05-22","cited_by_count":7,"area":null},{"id":"2505.23489","title":"SGD as Free Energy Minimization: A Thermodynamic View on Neural Network Training","created":"2025-05-29","cited_by_count":4,"area":null},{"id":"2409.16645","title":"Task Addition in Multi-Task Learning by Geometrical Alignment","created":"2024-09-25","cited_by_count":2,"area":null},{"id":"2504.15323","title":"HyperFlow: Gradient-Free Emulation of Few-Shot Fine-Tuning","created":"2025-04-21","cited_by_count":2,"area":null},{"id":"2506.14765","title":"Scaling Laws for Geospatial Foundation Models: A case study on PhilEO Bench","created":"2025-06-17","cited_by_count":2,"area":null},{"id":"2412.08147","title":"Variational Model Merging for Pareto Front Estimation in Multitask Finetuning","created":"2024-12-11","cited_by_count":1,"area":null},{"id":"2410.06442","title":"MaD-Scientist: AI-based Scientist solving Convection-Diffusion-Reaction Equations Using Massive PINN-Based Prior Data","created":"2024-10-09","cited_by_count":0,"area":null},{"id":"2506.13909","title":"Few-Shot Learning for Industrial Time Series: A Comparative Analysis Using the Example of Screw-Fastening Process Monitoring","created":"2025-06-16","cited_by_count":0,"area":null},{"id":"2510.22993","title":"Can Language Models Compose Skills In-Context?","created":"2025-10-27","cited_by_count":0,"area":null},{"id":"2609.14097","title":"Bridging the Synthetic-to-Real Gap for Few-Shot Cryo-ET Classification","created":"2026-09-12","cited_by_count":0,"area":null}],"next_cursor":null}