{"total":16,"rows":[{"id":"2606.06479","title":"Pretraining Recurrent Networks without Recurrence","created":"2026-06-04","cited_by_count":5,"area":null},{"id":"2605.30148","title":"Overcoming Forgetting in LLM Fine-Tuning with Evolution Strategies","created":"2026-05-28","cited_by_count":3,"area":null},{"id":"2605.31494","title":"Consolidating Rewarded Perturbations for LLM Post-Training","created":"2026-05-29","cited_by_count":3,"area":null},{"id":"2606.23357","title":"SOAP-Bubbles: Structured Weight Uncertainty for Neural Networks","created":"2026-06-22","cited_by_count":3,"area":null},{"id":"2607.01232","title":"Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training","created":"2026-07-01","cited_by_count":3,"area":null},{"id":"2605.28751","title":"Extrapolative Weight Averaging Reveals Correctness-Efficiency Frontiers in Code RL","created":"2026-05-27","cited_by_count":2,"area":null},{"id":"2608.12679","title":"Beyond the Best Guess: Improving LLM Solution Coverage with Evolution Strategies","created":"2026-08-13","cited_by_count":2,"area":null},{"id":"2608.09805","title":"Parameter Exploration for RLVR via Variational Learning","created":"2026-08-10","cited_by_count":1,"area":null},{"id":"2603.28858","title":"OptiMer: Optimal Distribution Vector Merging Is Better than Data Mixing for Continual Pre-Training","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2605.14738","title":"TAPIOCA: Why Task- Aware Pruning Improves OOD model Capability","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2607.14466","title":"Interleaved Noise Injection Improves Clean, Corrupted, and OOD Performance","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2609.08966","title":"Good Pretraining, Bad SFT: Checkpoint Quality Across the Training Stack","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.25745","title":"Modular Norm RandOpt: Population-Efficient Ensembling through Architecture-Aware Perturbations","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.38081","title":"Traversing the solution space of neural networks with Hessian Null Space Continuation","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.01934","title":"Learning to Predict Distributions over Weight Updates for Test-Time Adaptation","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.10368","title":"Input-Blind Controls Produce Substantial Oracle Headroom for Layer Programs in Multiple-Choice Evaluation","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":null}