{"total":24,"rows":[{"id":"2512.22382","title":"Completed Hyperparameter Transfer across Modules, Width, Depth, Batch and Duration","created":"2025-12-26","cited_by_count":27,"area":null},{"id":"2506.02267","title":"TransAct V2: Lifelong User Action Sequence Modeling on Pinterest Recommendation","created":"2025-06-02","cited_by_count":9,"area":null},{"id":"2508.00264","title":"Calibrated Language Models and How to Find Them with Label Smoothing","created":"2025-08-01","cited_by_count":7,"area":null},{"id":"2506.00304","title":"Can LLMs Understand Unvoiced Speech? Exploring EMG-to-Text Conversion with LLMs","created":"2025-05-30","cited_by_count":6,"area":null},{"id":"2512.14697","title":"Spherical Leech Quantization for Visual Tokenization and Generation","created":"2025-12-16","cited_by_count":6,"area":null},{"id":"2605.19269","title":"CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs","created":"2026-05-19","cited_by_count":5,"area":null},{"id":"2510.12210","title":"DiSTAR: Diffusion over a Scalable Token Autoregressive Representation for Speech Generation","created":"2025-10-14","cited_by_count":3,"area":null},{"id":"2512.00384","title":"Efficient and Programmable Exploration of Synthesizable Chemical Space","created":"2025-11-29","cited_by_count":3,"area":null},{"id":"2603.15854","title":"FlashSampling: Fast and Memory-Efficient Exact Sampling","created":"2026-03-16","cited_by_count":3,"area":null},{"id":"2606.22932","title":"FORGE: Fused On-Register Gradient Elimination for Memory-Efficient LLM Training","created":"2026-06-22","cited_by_count":2,"area":null},{"id":"2503.00329","title":"ABC: Achieving Better Control of Multimodal Embeddings using VLMs","created":"2025-03-01","cited_by_count":1,"area":null},{"id":"2510.03425","title":"Memory-Efficient Backpropagation for Fine-Tuning LLMs on Resource-Constrained Mobile Devices","created":"2025-10-03","cited_by_count":1,"area":null},{"id":"2510.17001","title":"Vocab Diet: Reshaping the Vocabulary of LLMs via Vector Arithmetic","created":"2025-10-19","cited_by_count":1,"area":null},{"id":"2602.06694","title":"NanoQuant: Efficient Sub-1-Bit Quantization of Large Language Models","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2501.00692","title":"Adjoint sharding for very long context training of state space models","created":"2025-01-01","cited_by_count":0,"area":null},{"id":"2605.21442","title":"torchtune: PyTorch native post-training library","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2606.02834","title":"Large Byte Model: Teaching Language Models About Compiled Code","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.15216","title":"Spokes: Optimizing for Diverse Pretraining Data Selection","created":"2026-06-13","cited_by_count":0,"area":null},{"id":"2608.11061","title":"Batch Size or Negatives? A Selection Rule for Memory-Constrained Recommender Training","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.24079","title":"Keeping the Index Open: The Recommendation-Side Cost of Shared Search and Recommendation","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2609.11936","title":"One Simple Trick for Improving the Performance of Energy-Limited Local Inference and Training","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2610.00053","title":"Format-Aware Fusion for Fast FP4 Pretraining","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2610.05559","title":"Cut Binary Cross Entropy: Efficient Large-Vocabulary Loss and Gradient Kernels for Sequential Recommendation","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.15864","title":"Personalized LLM Recommendation with Semantic IDs: Autoregressive Beam Search vs. Multi-Token Prediction","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}