Collections
Discover the best community collections!
Collections including paper arxiv:2412.08905
-
Phi-4 Technical Report
Paper • 2412.08905 • Published • 82 -
Evaluating and Aligning CodeLLMs on Human Preference
Paper • 2412.05210 • Published • 47 -
Evaluating Language Models as Synthetic Data Generators
Paper • 2412.03679 • Published • 43 -
Yi-Lightning Technical Report
Paper • 2412.01253 • Published • 22
-
Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering
Paper • 2411.11504 • Published • 19 -
Top-nσ: Not All Logits Are You Need
Paper • 2411.07641 • Published • 18 -
Adaptive Decoding via Latent Preference Optimization
Paper • 2411.09661 • Published • 10 -
When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context Training
Paper • 2411.13476 • Published • 14
-
Differential Transformer
Paper • 2410.05258 • Published • 167 -
PaliGemma 2: A Family of Versatile VLMs for Transfer
Paper • 2412.03555 • Published • 116 -
VisionZip: Longer is Better but Not Necessary in Vision Language Models
Paper • 2412.04467 • Published • 103 -
o1-Coder: an o1 Replication for Coding
Paper • 2412.00154 • Published • 39
-
Scaling Laws for Neural Language Models
Paper • 2001.08361 • Published • 6 -
Scaling Laws for Autoregressive Generative Modeling
Paper • 2010.14701 • Published -
Training Compute-Optimal Large Language Models
Paper • 2203.15556 • Published • 10 -
A Survey on Data Selection for Language Models
Paper • 2402.16827 • Published • 4