13 papers · 1 filter
Elastic MoE: Unlocking the Inference-Time Scalability of Mixture-of-Experts
Naibin Gu, Zhenyu Zhang, Yuchen Feng +8
Mixture-of-Experts (MoE) models typically fix the number of activated experts at both training and inference. However, real-world deployments often face heterogeneous hardware,…
Orthogonal Finetuning for Direct Preference Optimization
Chenxu Yang, Ruipeng Jia, Naibin Gu +7
DPO is an effective preference optimization algorithm. However, the DPO-tuned models tend to overfit on the dispreferred samples, manifested as overly long generations lacking dive…
BeamLoRA: Beam-Constraint Low-Rank Adaptation
Naibin Gu, Zhenyu Zhang, Xiyu Liu +7
Due to the demand for efficient fine-tuning of large language models, Low-Rank Adaptation (LoRA) has been widely adopted as one of the most effective parameter-efficient fine-tunin…
Curiosity-Driven Reinforcement Learning from Human Feedback
Haoran Sun, Yekun Chai, Shuohuan Wang +3
Reinforcement learning from human feedback (RLHF) has proven effective in aligning large language models (LLMs) with human preferences, but often at the cost of reduced output dive…
Advantageous Parameter Expansion Training Makes Better Large Language Models
Naibin Gu, Yilong Chen, Zhenyu Zhang +7
Although scaling up the number of trainable parameters can effectively improve the training performance of large language models, it also leads to increased computational overhead.…
Inner Thinking Transformer: Leveraging Dynamic Depth Scaling to Foster Adaptive Internal Thinking
Yilong Chen, Junyuan Shang, Zhenyu Zhang +7
Large language models (LLMs) face inherent performance bottlenecks under parameter constraints, particularly in processing critical tokens that demand complex reasoning. Empirical…