The Appeal and Reality of Recycling LoRAs with Adaptive Merging Paper • 2602.12323 • Published Feb 12 • 1
A Gradient Perspective on RLVR Stability and Winner Advantage Policy Optimization Paper • 2606.16154 • Published Jun 15 • 8
Risk Under Pressure: Compute-Aware Evaluation of Adversarial Robustness in Language Models Paper • 2606.11409 • Published Jun 9 • 9
TokSuite: Measuring the Impact of Tokenizer Choice on Language Model Behavior Paper • 2512.20757 • Published Dec 23, 2025 • 18
TokSuite: Measuring the Impact of Tokenizer Choice on Language Model Behavior Paper • 2512.20757 • Published Dec 23, 2025 • 18
FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language Paper • 2506.20920 • Published Jun 26, 2025 • 79
Improving Dense Contrastive Learning with Dense Negative Pairs Paper • 2210.05063 • Published Oct 11, 2022
SimpleClick: Interactive Image Segmentation with Simple Vision Transformers Paper • 2210.11006 • Published Oct 20, 2022
GEXIA: Granularity Expansion and Iterative Approximation for Scalable Multi-grained Video-language Learning Paper • 2412.07704 • Published Dec 10, 2024
The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text Paper • 2506.05209 • Published Jun 5, 2025 • 64