12 papers
Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models
Xin Xu, Clive Bai, Kai Yang +7
Large-scale verifiable prompts underpin the success of Reinforcement Learning with Verifiable Rewards (RLVR), but they contain many uninformative examples and are costly to expand…
The Exploration of Error Bounds in Classification with Noisy Labels
Haixia Liu, Boxiao Li, Can Yang +1
Numerous studies have shown that label noise can lead to poor generalization performance, negatively affecting classification accuracy. Therefore, understanding the effectiveness o…
Progressive Residual Warmup for Language Model Pretraining
Tianhao Chen, Xin Xu, Lu Yin +4
Transformer architectures serve as the backbone for most modern Large Language Models, therefore their pretraining stability and convergence speed are of central concern. Motivated…
SyncTrack: Rhythmic Stability and Synchronization in Multi-Track Music Generation
Hongrui Wang, Fan Zhang, Zhiyuan Yu +4
Multi-track music generation has garnered significant research interest due to its precise mixing and remixing capabilities. However, existing models often overlook essential attri…
Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners
Xin Xu, Cliveb AI, Kai Yang +4
Reinforcement Learning with Verifiable Reward (RLVR) effectively solves complex tasks but demands extremely long context lengths during training, leading to substantial computation…
LTA-thinker: Latent Thought-Augmented Training Framework for Large Language Models on Complex Reasoning
Jiaqi Wang, Binquan Ji, Haibo Luo +7
Complex Reasoning in Large Language Models can be dynamically optimized using Test-Time Scaling (TTS) to mitigate Overthinking. Methods such as Coconut, SoftCoT and its variant are…