4 papers
Positional Encoding via Token-Aware Phase Attention
Yu Wang, Sheng Shen, Rémi Munos +2
We prove under practical assumptions that Rotary Positional Embedding (RoPE) introduces an intrinsic distance-dependent bias in attention scores that limits RoPE's ability to model…
Learning to Solve and Verify: A Self-Play Framework for Code and Test Generation
Zi Lin, Sheng Shen, Ilia Kulikov +3
Recent advances in large language models (LLMs) have improved their performance on coding benchmarks. However, improvement is plateauing due to the exhaustion of readily available…
Faster and Better Alignment for Flow Matching Models via Step-aware Advantages
Zhixiong Yue, Zixuan Ni, Feiyang Ye +4
Recent advances in flow matching models, particularly with reinforcement learning (RL), have significantly enhanced human preference alignment in few-step text-to-image generators.…
Multilingual Machine Translation with Open Large Language Models at Practical Scale: An Empirical Study
Menglong Cui, Pengzhi Gao, Wei Liu +2
Large language models (LLMs) have shown continuously improving multilingual capabilities, and even small-scale open-source models have demonstrated rapid performance enhancement. I…