相关论文: Optimizing RLHF Training for Large Language Models…

Traditional recommendation systems often grapple with "filter bubbles", underutilization of external knowledge, and a disconnect between model optimization and business policy iteration. To address these limitations, this paper introduces…

Recent advancements in generative modeling have significantly enhanced the reconstruction of audio waveforms from various representations. While diffusion models are adept at this task, they are hindered by latency issues due to their…

Language models (LMs) often exhibit undesirable text generation behaviors, including generating false, toxic, or irrelevant outputs. Reinforcement learning from human feedback (RLHF) - where human preference judgments on LM outputs are…

Federated fine-tuning enables Large Language Models (LLMs) to adapt to downstream tasks while preserving data privacy, but its resource-intensive nature limits deployment on edge devices. In this paper, we introduce Developmental Federated…

Neural networks are rapidly gaining popularity in scientific research, but training the models is often very time-consuming. Particularly when the training data samples are large high-dimensional arrays, efficient training methodologies…

Large language models (LLMs) have been applied to a wide range of tasks, including text summarization, web navigation, and chatbots. They have benefitted from supervised fine-tuning (SFT) and reinforcement learning from human feedback…

Maximizing training throughput and cost-efficiency of RL for LLMs is essential to democratize this advanced technique. One promising but challenging approach is to deploy such a computational workflow over heterogeneous GPUs. Unlike…

Addressing the critical need for robust safety in Large Language Models (LLMs), particularly against adversarial attacks and in-distribution errors, we introduce Reinforcement Learning with Backtracking Feedback (RLBF). This framework…

Diffusion models have revolutionized generative modeling in continuous domains like image, audio, and video synthesis. However, their iterative sampling process leads to slow generation and inefficient training, challenges that are further…

Large language models (LLMs) trained via pretraining and supervised fine-tuning (SFT) can still produce harmful and misaligned outputs, or struggle in domains like math and coding. Reinforcement learning (RL)-based post-training methods,…

Reinforcement learning from human feedback (RLHF) has emerged as a powerful technique to make large language models (LLMs) easier to use and more effective. A core piece of the RLHF process is the training and utilization of a model of…

Large language models (LLMs) are popular around the world due to their powerful understanding capabilities. As the core component of LLMs, accelerating Transformer through parallelization has gradually become a hot research topic. Mask…

Group-based reinforcement learning algorithms such as Group Reward Policy Optimization (GRPO) have proven effective for fine-tuning large language models (LLMs) with human feedback. However, generating and storing multiple responses per…

Conversational recommender systems (CRS) based on Large Language Models (LLMs) need to constantly be aligned to the user preferences to provide satisfying and context-relevant item recommendations. The traditional supervised fine-tuning…

Large Language Models (LLMs) have achieved remarkable success through imitation learning on vast text corpora, but this paradigm creates a training-generation gap and limits robust reasoning. Reinforcement learning (RL) offers a more…

Computational modeling of human multimodal language is an emerging research area in natural language processing spanning the language, visual and acoustic modalities. Comprehending multimodal language requires modeling not only the…

Recent advances in vision-language-action (VLA) models have motivated the extension of their capabilities to embodied settings, where reinforcement learning (RL) offers a principled way to optimize task success through interaction. However,…

Large deep learning models have demonstrated strong ability to solve many tasks across a wide range of applications. Those large models typically require training and inference to be distributed. Tensor parallelism is a common technique…

Pipeline parallelism is a key technique for scaling large-model training, but modern workloads exhibit runtime variability in computation and communication. Existing pipeline systems typically consume static, profiled, or adaptively…

Currently, training large-scale deep learning models is typically achieved through parallel training across multiple GPUs. However, due to the inherent communication overhead and synchronization delays in traditional model parallelism…