…Interactive world models require controllable, causal, and low-latency rollout , which in practice demands a full pipeline spanning data construction, controllable fine-tuning, autoregressive training, few-step distillation, and streaming inference. In…
…Yuxiang Ji , , , , , , , , Abstract Agentic reinforcement learning for large language models leverages action data from human interactions as reference guidance to improve exploration and reduce dependence on costly supervised fine-tuning. AI-generated…
…achieves strong performance with minimal supervised fine-tuning data by combining supervised signals, on-policy learning, and weighted training to prevent overfitting. AI-generated summary Reinforcement Learning with Verifiable Rewards (RLVR) has…
…Jingye Chen , Abstract Synthetic layered image data improves graphic design decomposition by enabling scalable training and better layer distribution control compared to traditional methods. AI-generated summary Recent advances in image generation…
…working effectively across all poison ratios without clustering or training-specific modifications. AI-generated summary Fine-tuning Large Language Models with untrusted data exposes models to backdoor attacks , where poisoned samples cause…
…Consequently, the model loses effective training signals for these questions, wasting the training data and computational budget. While simply increasing the sampling budget for these questions is a common remedy, the static…
…hand motion generation challenges through data-efficient post-training that eliminates need for paired preference data while using hand-aware local optimization for improved quality. AI-generated summary Human image animation has…
…Building on this dataset, we develop a unified training framework that combines a structured GRPO-based reward with a batch-ranking objective , achieving coherent global ordering without explicit pairwise labels. Experiments across…
…sufficient early-stage training to build a solid foundation, followed by moderate late-stage training to mitigate overfitting and achieve better final performance. The code and data are publicly available at https…
…pyrag consistently outperforms strong baselines under both training-free and RL-trained settings, with especially large gains on compositional multi-hop datasets. Our code, data and models are publicly available at https…
