{"total":58,"rows":[{"id":"2602.15902","title":"Doc-to-LoRA: Learning to Instantly Internalize Contexts","created":"2026-02-13","cited_by_count":43,"area":"lr"},{"id":"2602.06358","title":"SHINE: A Scalable In-Context Hypernetwork for Mapping Context to LoRA in a Single Pass","created":"2026-02-06","cited_by_count":25,"area":null},{"id":"2510.16282","title":"Instant Personalized Large Language Model Adaptation via Hypernetwork","created":"2025-10-18","cited_by_count":18,"area":null},{"id":"2603.01097","title":"Understanding LoRA as Knowledge Memory: An Empirical Analysis","created":"2026-03-01","cited_by_count":12,"area":null},{"id":"2606.06087","title":"LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents","created":"2026-06-04","cited_by_count":10,"area":"agents"},{"id":"2606.16769","title":"Skill-to-LoRA: From Using Skills to Learning Behaviors for Token-Efficient LLM Agents","created":"2026-06-15","cited_by_count":10,"area":"agents"},{"id":"2602.06204","title":"Learning Rate Scaling across LoRA Ranks and Transfer to Full Finetuning","created":"2026-02-05","cited_by_count":9,"area":null},{"id":"2602.06964","title":"Learning a Generative Meta-Model of LLM Activations","created":"2026-02-06","cited_by_count":8,"area":"mechinterp"},{"id":"2605.18632","title":"Position: Weight Space Should Be a First-Class Generative AI Modality","created":"2026-05-18","cited_by_count":6,"area":null},{"id":"2605.28889","title":"Context Distillation as Latent Memory Management","created":"2026-05-27","cited_by_count":6,"area":null},{"id":"2510.09561","title":"TC-LoRA: Temporally Modulated Conditional LoRA for Adaptive Diffusion Control","created":"2025-10-10","cited_by_count":5,"area":"diffusion"},{"id":"2510.19733","title":"Zhyper: Factorized Hypernetworks for Conditioned LLM Fine-Tuning","created":"2025-10-22","cited_by_count":5,"area":null},{"id":"2601.15968","title":"HyperAlign: Hypernetwork for Efficient Test-Time Alignment of Diffusion Models","created":"2026-01-22","cited_by_count":4,"area":"diffusion"},{"id":"2608.05475","title":"KV-Skill: Forging Expertise in the Model's Native Language","created":"2026-08-05","cited_by_count":4,"area":null},{"id":"2605.09778","title":"Nectar: Neural Estimation of Cached-Token Attention via Regression","created":"2026-05-10","cited_by_count":3,"area":null},{"id":"2605.30260","title":"How LoRA Remembers? A Parametric Memory Law for LLM Finetuning","created":"2026-05-28","cited_by_count":3,"area":null},{"id":"2606.19172","title":"User as Engram: Internalizing Per-User Memory as Local Parametric Edits","created":"2026-06-17","cited_by_count":3,"area":"lr"},{"id":"2606.30015","title":"Parametric Skills","created":"2026-06-29","cited_by_count":3,"area":null},{"id":"2608.03275","title":"MoEGen: Mixture-of-Experts for Instance-Adaptive LoRA Generation","created":"2026-08-04","cited_by_count":3,"area":"moe"},{"id":"2604.23750","title":"The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM Adaptation","created":"2026-04-26","cited_by_count":2,"area":null},{"id":"2605.18474","title":"Prompt2Fingerprint: Plug-and-Play LLM Fingerprinting via Text-to-Weight Generation","created":"2026-05-18","cited_by_count":2,"area":null},{"id":"2606.06492","title":"Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution","created":"2026-06-04","cited_by_count":2,"area":null},{"id":"2509.22621","title":"IA2: Alignment with ICL Activations Improves Supervised Fine-Tuning","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2511.07457","title":"GRIP: In-Parameter Graph Reasoning through Fine-Tuning Large Language Models","created":"2025-11-06","cited_by_count":1,"area":"lr"},{"id":"2601.06471","title":"PRISP: Privacy-Safe Few-Shot Personalization via Lightweight Adaptation","created":"2026-01-10","cited_by_count":1,"area":null},{"id":"2603.06662","title":"DynaTokens: Controlling Token Dynamics for Continual Video-Language Understanding","created":"2026-03-02","cited_by_count":1,"area":"mllm"},{"id":"2607.02512","title":"Program-as-Weights: A Programming Paradigm for Fuzzy Functions","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2610.03039","title":"HyperThink: Text-to-Parameter Hypernetworks for Efficient Reasoning","created":"2026-10-02","cited_by_count":1,"area":"lr"},{"id":"2510.13259","title":"Hypernetworks for Perspectivist Adaptation","created":"2025-10-15","cited_by_count":0,"area":null},{"id":"2601.15912","title":"TeNet: Text-to-Network for Compact Policy Synthesis","created":"2026-01-22","cited_by_count":0,"area":null},{"id":"2605.01973","title":"Learn-To-Learn on Arbitrary Textual Conditioning: A Hypernetwork-Driven Meta-Gated LLM","created":"2026-05-03","cited_by_count":0,"area":null},{"id":"2605.08254","title":"HyperTransport: Amortized Conditioning of T2I Generative Models","created":"2026-05-07","cited_by_count":0,"area":"mechinterp"},{"id":"2605.08423","title":"Queryable LoRA: Instruction-Regularized Routing Over Shared Low-Rank Update Atoms","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.14055","title":"PEML: Parameter-efficient Multi-Task Learning with Optimized Continuous Prompts","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.18226","title":"Context Memorization for Efficient Long Context Generation","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2606.06154","title":"Amortizing Federated Adaptation: Hypernetwork Driven LoRA for Personalized Foundation Models","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.12942","title":"PRISMR: Overcoming Parse Collapse in Multimodal Listwise Ranking via Parameterized Representation Internalization","created":"2026-06-11","cited_by_count":0,"area":"mllm"},{"id":"2606.13971","title":"Prompt2Effect: Training-Free Image-to-Video Model Specialization via LoRA Generation","created":"2026-06-11","cited_by_count":0,"area":"diffusion"},{"id":"2607.05306","title":"Biologically Informed Deep Neural Networks for Multi-Omic Integration, Pathway Activity Inference and Risk Stratification in Cancer","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.13425","title":"Data-Efficient Adaptation of LLMs via Attention Head Reweighting","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2607.17467","title":"DA-MergeLoRA: Hypernetwork-Based LoRA Merging for Few-Shot Test-Time Domain Adaptation","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2608.01807","title":"Parameter-Dynamic Adaptive Fusion and Calibration Network for RGBT Tracking","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.05151","title":"Simulator-Grounded Large Language Models for Industrial Causal Reasoning: Tool-Use, Structured Injection, and Plant-Portable Retrieval for Wastewater Treatment Decision Support","created":"2026-05-20","cited_by_count":0,"area":"lr"},{"id":"2609.12278","title":"Amortized Low-Rank Adaptation for Model-Based Reinforcement Learning","created":"2026-09-10","cited_by_count":0,"area":"wm"},{"id":"2609.18842","title":"Infinite-Parameter LLMs: Generating and Adapting Weights from Live Data","created":"2026-09-16","cited_by_count":0,"area":"moe"},{"id":"2609.24657","title":"Circuit Hypernetworks for Quantum-Augmented Diffusion Language Models","created":"2026-09-21","cited_by_count":0,"area":"diffusion"},{"id":"2609.34054","title":"PReCache: Efficient KV Cache Sharing for Multi-LoRA Agents via Low-Rank Precomputation and Neutral Reconstruction","created":"2026-09-28","cited_by_count":0,"area":"inference"},{"id":"2609.36357","title":"HyperZip: Efficient Data Compression through Personalized Diffusion LLMs with Hypernetworks","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.38374","title":"Doc2LoRA Provides Decodable Representations of Scientific Ideas","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39382","title":"SkillFM: Generating Skills for LLM Agents via Latent Flow Matching","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.00820","title":"On-the-fly Weight Generation: A Hypernetwork Proof of Concept on ARC-1D","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.02793","title":"PAPER2LLM++: Continual Self-Evolution of LLMs from Research Papers","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.03163","title":"Predicting Steering Vectors and Adapter Weights for Few-Shot Author-Style Transfer","created":"2026-10-02","cited_by_count":0,"area":"mechinterp"},{"id":"2610.08630","title":"Towards In-Parameter Memory Augmentation for Large Language Models","created":"2026-10-06","cited_by_count":0,"area":"agents"},{"id":"2610.13000","title":"Hindsight Structured Advice Distillation: Steering Executor Agents with Advisors Trained on Their Failures and Task Characteristics","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.13599","title":"EchoTab: Learning Measurement-Grounded Representations for Echocardiographic Diagnosis through Tabular Reconstruction","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.15677","title":"Knowledge Interaction in Hypernetwork-based Continual Learning: Conflict and Composition","created":"2026-10-11","cited_by_count":0,"area":null},{"id":"2610.17355","title":"WIRE: Weight Space Implicit Representation Encoding of Frozen Video LLMs","created":"2026-10-12","cited_by_count":0,"area":"inference"}],"next_cursor":null}