{"total":51,"rows":[{"id":"2503.20762","title":"ASGO: Adaptive Structured Gradient Optimization","created":"2025-03-26","cited_by_count":57,"area":null},{"id":"2502.10940","title":"CoLA: Compute-Efficient Pre-Training of LLMs via Low-Rank Activation","created":"2025-02-16","cited_by_count":28,"area":null},{"id":"2412.13148","title":"SWAN: SGD with Normalization and Whitening Enables Stateless LLM Training","created":"2024-12-17","cited_by_count":20,"area":null},{"id":"2505.24749","title":"SUMO: Subspace-Aware Moment-Orthogonalization for Accelerating Memory-Efficient LLM Training","created":"2025-05-30","cited_by_count":19,"area":null},{"id":"2502.07445","title":"Forget What You Know about LLMs Evaluations -- LLMs are Like a Chameleon","created":"2025-02-11","cited_by_count":13,"area":null},{"id":"2506.16659","title":"Memory-Efficient LLM Pretraining via Minimalist Optimizer Design","created":"2025-06-20","cited_by_count":13,"area":null},{"id":"2508.02668","title":"LOST: Low-rank and Sparse Pre-training for Large Language Models","created":"2025-08-04","cited_by_count":10,"area":null},{"id":"2502.06742","title":"Gradient Multi-Normalization for Stateless and Scalable LLM Training","created":"2025-02-10","cited_by_count":9,"area":null},{"id":"2505.24275","title":"GradPower: Powering Gradients for Faster Language Model Pre-Training","created":"2025-05-30","cited_by_count":8,"area":null},{"id":"2506.01933","title":"E3D-Bench: A Benchmark for End-to-End 3D Geometric Foundation Models","created":"2025-06-02","cited_by_count":7,"area":null},{"id":"2509.18993","title":"CR-Net: Scaling Parameter-Efficient Training with Cross-Layer Low-Rank Structure","created":"2025-09-23","cited_by_count":7,"area":null},{"id":"2602.15322","title":"On Surprising Effectiveness of Masking Updates in Adaptive Optimizers","created":"2026-02-17","cited_by_count":7,"area":null},{"id":"2502.01378","title":"CE-LoRA: Computation-Efficient LoRA Fine-Tuning for Language Models","created":"2025-02-03","cited_by_count":6,"area":null},{"id":"2602.14208","title":"Fast Catch-Up, Late Switching: Optimal Batch Size Scheduling via Functional Scaling Laws","created":"2026-02-15","cited_by_count":6,"area":null},{"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":"2505.22922","title":"Scalable Parameter and Memory Efficient Pretraining for LLM: Recent Algorithmic Advances and Benchmarking","created":"2025-05-28","cited_by_count":5,"area":null},{"id":"2509.24218","title":"Conda: Column-Normalized Adam for Training Large Language Models Faster","created":"2025-09-29","cited_by_count":5,"area":null},{"id":"2602.23349","title":"FlashOptim: Optimizers for Memory-Efficient Training","created":"2026-02-26","cited_by_count":5,"area":null},{"id":"2603.05500","title":"POET-X: Memory-efficient LLM Training by Scaling Orthogonal Transformation","created":"2026-03-05","cited_by_count":5,"area":null},{"id":"2507.08091","title":"Low-rank Momentum Factorization for Memory Efficient Training","created":"2025-07-10","cited_by_count":4,"area":null},{"id":"2508.00619","title":"DACTYL: Diverse Adversarial Corpus of Texts Yielded from Large Language Models","created":"2025-08-01","cited_by_count":3,"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":"2509.23472","title":"Memory-Efficient Fine-Tuning via Low-Rank Activation Compression","created":"2025-09-27","cited_by_count":2,"area":null},{"id":"2512.12131","title":"BOOST: BOttleneck-Optimized Scalable Training Framework for Low-Rank Large Language Models","created":"2025-12-13","cited_by_count":2,"area":null},{"id":"2602.09169","title":"Train Less, Infer Faster: Efficient Model Finetuning and Compression via Structured Sparsity","created":"2026-02-09","cited_by_count":2,"area":null},{"id":"2605.09176","title":"Navigating LLM Valley: From AdamW to Memory-Efficient and Matrix-Based Optimizers","created":"2026-05-09","cited_by_count":2,"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":"2501.07237","title":"GWT: Scalable Optimizer State Compression for Large Language Model Training","created":"2025-01-13","cited_by_count":1,"area":null},{"id":"2505.01744","title":"Memory-Efficient LLM Training by Various-Grained Low-Rank Projection of Gradients","created":"2025-05-03","cited_by_count":1,"area":null},{"id":"2512.07112","title":"FOAM: Blocked State Folding for Memory-Efficient LLM Training","created":"2025-12-08","cited_by_count":1,"area":null},{"id":"2602.23111","title":"PRAC: Principal-Random Subspace for LLM Activation Compression and Memory-Efficient Training","created":"2026-02-26","cited_by_count":1,"area":null},{"id":"2604.07663","title":"SAGE: Sign-Adaptive Gradient for Memory-Efficient LLM Optimization","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2607.10611","title":"M+Adam: Low-Precision Training via Additive-Multiplicative Optimization","created":"2026-07-12","cited_by_count":1,"area":null},{"id":"2505.11170","title":"Gaussian Weight Sampling for Scalable, Efficient and Stable Pseudo-Quantization Training","created":"2025-05-16","cited_by_count":0,"area":null},{"id":"2505.16333","title":"Understanding Differential Transformer Unchains Pretrained Self-Attentions","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2512.17109","title":"Bridging Training and Merging Through Momentum-Aware Optimization","created":"2025-12-18","cited_by_count":0,"area":null},{"id":"2602.01233","title":"Lotus: Efficient LLM Training by Randomized Low-Rank Gradient Projection with Adaptive Subspace Switching","created":"2026-02-01","cited_by_count":0,"area":null},{"id":"2602.06208","title":"Emergent Low-Rank Training Dynamics in MLPs with Smooth Activations","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2604.11867","title":"Disposition Distillation at Small Scale: A Three-Arc Negative Result","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2605.10288","title":"BROS: Bias-Corrected Randomized Subspaces for Memory-Efficient Single-Loop Bilevel Optimization","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.21177","title":"ChunkFT: Byte-Streamed Optimization for Memory-Efficient Full Fine-Tuning","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2606.00145","title":"Completion at the Boundary (CaB): Deployable Switching with Completion-Aware Control under Limited Calibration","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2607.05872","title":"No Subspace to Track: Non-Identifiability and Optimizer State in Low-Rank Training","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2608.16760","title":"On the Principles Behind Neural Network Optimizers","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.22322","title":"Beyond Dense Adam States: Adaptive Log-Space Quantization for Memory-Efficient Optimizers","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2609.15037","title":"MoARa: Module-Aware Rank Allocation and Structure-Preserving Decomposition for Low-Rank LLM Pre-training","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.33016","title":"Relative Generalization Invariance of LLM Pretraining","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.35701","title":"MeqMuon: Matrix-Equilibrating Muon for LLM Pretraining","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.02199","title":"TACO: Ternary Absolute-max Column-wise One-sparse Optimizer for LLM Fine-Tuning","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.04204","title":"Clean: Second-order LLM Training at Linear Memory Cost via Nystr{\\\"o}m Sketching","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.19844","title":"Memory-Efficient Subspace Optimization with Residual Correction: From Momentum SGD to Muon","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}