{"total":54,"rows":[{"id":"2503.10657","title":"RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMs","created":"2025-03-08","cited_by_count":61,"area":null},{"id":"2406.10260","title":"Flextron: Many-in-One Flexible Large Language Model","created":"2024-06-11","cited_by_count":45,"area":null},{"id":"2508.15884","title":"Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search","created":"2025-08-21","cited_by_count":41,"area":null},{"id":"2406.14479","title":"Tracing Representation Progression: Analyzing and Enhancing Layer-Wise Similarity","created":"2024-06-20","cited_by_count":36,"area":null},{"id":"2502.04506","title":"When One LLM Drools, Multi-LLM Collaboration Rules","created":"2025-02-06","cited_by_count":28,"area":null},{"id":"2506.08228","title":"Scaling Laws of Motion Forecasting and Planning -- Technical Report","created":"2025-06-09","cited_by_count":19,"area":null},{"id":"2407.02348","title":"Agreement-Based Cascading for Efficient Inference","created":"2024-07-02","cited_by_count":16,"area":null},{"id":"2508.12491","title":"Cost-Aware Contrastive Routing for LLMs","created":"2025-08-17","cited_by_count":16,"area":null},{"id":"2502.06786","title":"Matryoshka Quantization","created":"2025-02-10","cited_by_count":14,"area":null},{"id":"2409.17978","title":"HydraViT: Stacking Heads for a Scalable ViT","created":"2024-09-26","cited_by_count":11,"area":null},{"id":"2402.05913","title":"Efficient Stagewise Pretraining via Progressive Subnetworks","created":"2024-02-08","cited_by_count":10,"area":null},{"id":"2410.06718","title":"MatMamba: A Matryoshka State Space Model","created":"2024-10-09","cited_by_count":7,"area":null},{"id":"2507.10800","title":"ThinkingViT: Matryoshka Thinking Vision Transformer for Elastic Inference","created":"2025-07-14","cited_by_count":7,"area":null},{"id":"2507.19360","title":"EA-ViT: Efficient Adaptation for Elastic Vision Transformer","created":"2025-07-25","cited_by_count":7,"area":null},{"id":"2310.12126","title":"SHARCS: Efficient Transformers through Routing with Dynamic Width Sub-networks","created":"2023-10-18","cited_by_count":6,"area":null},{"id":"2411.17299","title":"2D Matryoshka Training for Information Retrieval","created":"2024-11-26","cited_by_count":6,"area":null},{"id":"2412.04786","title":"Slicing Vision Transformer for Flexible Inference","created":"2024-12-06","cited_by_count":6,"area":null},{"id":"2512.08819","title":"Do Depth-Grown Models Overcome the Curse of Depth? An In-Depth Analysis","created":"2025-12-09","cited_by_count":6,"area":null},{"id":"2502.12325","title":"From Dense to Dynamic: Token-Difficulty Driven MoEfication of Pre-Trained LLMs","created":"2025-02-17","cited_by_count":5,"area":null},{"id":"2503.05005","title":"Balcony: A Lightweight Approach to Dynamic Inference of Generative Language Models","created":"2025-03-06","cited_by_count":5,"area":null},{"id":"2509.17874","title":"Deep Hierarchical Learning with Nested Subspace Networks for Large Language Models","created":"2025-09-22","cited_by_count":5,"area":null},{"id":"2405.18400","title":"Superposed Decoding: Multiple Generations from a Single Autoregressive Inference Pass","created":"2024-05-28","cited_by_count":4,"area":null},{"id":"2410.11878","title":"Neural Metamorphosis","created":"2024-10-10","cited_by_count":4,"area":null},{"id":"2502.00382","title":"Masked Generative Nested Transformers with Decode Time Scaling","created":"2025-02-01","cited_by_count":4,"area":null},{"id":"2510.17700","title":"Elastic ViTs from Pretrained Models without Retraining","created":"2025-10-20","cited_by_count":4,"area":null},{"id":"2502.01717","title":"Choose Your Model Size: Any Compression of Large Language Models Without Re-Computation","created":"2025-02-03","cited_by_count":3,"area":null},{"id":"2506.04174","title":"FlexGS: Train Once, Deploy Everywhere with Many-in-One Flexible 3D Gaussian Splatting","created":"2025-06-04","cited_by_count":3,"area":null},{"id":"2506.09316","title":"On-the-Fly Adaptive Distillation of Transformer to Dual-State Linear Attention","created":"2025-06-11","cited_by_count":3,"area":null},{"id":"2511.05313","title":"Controllably Efficient Language Models","created":"2025-11-07","cited_by_count":3,"area":null},{"id":"2410.10267","title":"big.LITTLE Vision Transformer for Efficient Visual Recognition","created":"2024-10-14","cited_by_count":2,"area":null},{"id":"2505.11820","title":"Chain-of-Model Learning for Language Model","created":"2025-05-17","cited_by_count":2,"area":null},{"id":"2505.23337","title":"Matryoshka Model Learning for Improved Elastic Student Models","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2509.23963","title":"Evaluating the Robustness of Chinchilla Compute-Optimal Scaling","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2601.22488","title":"Elastic Spectral State Space Models for Train-Once Budgeted Inference","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2602.02680","title":"FlexRank: Nested Low-Rank Knowledge Decomposition for Adaptive Model Deployment","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2606.23670","title":"Tapered Language Models","created":"2026-06-22","cited_by_count":2,"area":null},{"id":"2508.14302","title":"GLASS: Global-Local Aggregation for Inference-time Sparsification of LLMs","created":"2025-08-19","cited_by_count":1,"area":null},{"id":"2511.18105","title":"AdaPerceiver: Transformers with Adaptive Width, Depth, and Tokens","created":"2025-11-22","cited_by_count":1,"area":null},{"id":"2602.00942","title":"SALAAD: Sparse And Low-Rank Adaptation via ADMM for Large Language Model Inference","created":"2026-02-01","cited_by_count":1,"area":null},{"id":"2605.19568","title":"m3BERT: A Modern, Multi-lingual, Matryoshka Bidirectional Encoder","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2402.05033","title":"Majority Kernels: An Approach to Leverage Big Model Dynamics for Efficient Small Model Training","created":"2024-02-07","cited_by_count":0,"area":null},{"id":"2504.12513","title":"AdaVid: Adaptive Video-Language Pretraining","created":"2025-04-16","cited_by_count":0,"area":null},{"id":"2505.04850","title":"ORXE: Orchestrating Experts for Dynamically Configurable Efficiency","created":"2025-05-07","cited_by_count":0,"area":null},{"id":"2508.09223","title":"Hierarchical Adaptive networks with Task vectors for Test-Time Adaptation","created":"2025-08-11","cited_by_count":0,"area":null},{"id":"2509.07909","title":"Uncovering Scaling Laws for Large Language Models via Inverse Problems","created":"2025-09-09","cited_by_count":0,"area":null},{"id":"2602.21379","title":"MrBERT: Modern Multilingual Encoders via Vocabulary, Domain, and Dimensional Adaptation","created":"2026-02-24","cited_by_count":0,"area":null},{"id":"2605.12491","title":"Do Vision Transformers Need All-to-All Attention? Global Communication Through Elastic Learned Cores","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.13869","title":"Elastic Spiking Transformers for Efficient Gesture Understanding","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2605.22677","title":"Slimmable ConvNeXt: Width-Adaptive Inference for Efficient Multi-Device Deployment","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2607.27766","title":"Gradient-free Task-Conditioned Retrieval for On-Device In-Context Learning","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.28151","title":"Nested Byte-Level Vocabularies Are Cheap to Deploy and Expensive to Share: A Pre-Registered Negative Result","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.10018","title":"Elastoformer: Enabling Dynamic Adaptivity via Elastic Model Transformation","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2610.14324","title":"EV-JEPA: Elastic V-JEPA for Any Device and Cross-Device Inference","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.20588","title":"Your Transformer Is Secretly Elastic","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}