Fei Gao

Siheng Li, Kejiao Li, Zenan Xu et al.

The growing disparity between the exponential scaling of computational resources and the finite growth of high-quality text data now constrains conventional scaling approaches for large language models (LLMs). To address this challenge, we introduce Reinforcement Learning on Pre-Training data (RLPT), a new training-time scaling paradigm for optimizing LLMs. In contrast to prior approaches that scale training primarily through supervised learning, RLPT enables the policy to autonomously explore meaningful trajectories to learn from pre-training data and improve its capability through reinforcement learning (RL). While existing RL strategies such as reinforcement learning from human feedback (RLHF) and reinforcement learning with verifiable rewards (RLVR) rely on human annotation for reward construction, RLPT eliminates this dependency by deriving reward signals directly from pre-training data. Specifically, it adopts a next-segment reasoning objective, rewarding the policy for accurately predicting subsequent text segments conditioned on the preceding context. This formulation allows RL to be scaled on pre-training data, encouraging the exploration of richer trajectories across broader contexts and thereby fostering more generalizable reasoning skills. Extensive experiments on both general-domain and mathematical reasoning benchmarks across multiple models validate the effectiveness of RLPT. For example, when applied to Qwen3-4B-Base, RLPT yields absolute improvements of $3.0$, $5.1$, $8.1$, $6.0$, $6.6$, and $5.3$ on MMLU, MMLU-Pro, GPQA-Diamond, KOR-Bench, AIME24, and AIME25, respectively. The results further demonstrate favorable scaling behavior, suggesting strong potential for continued gains with more compute. In addition, RLPT provides a solid foundation, extending the reasoning boundaries of LLMs and enhancing RLVR performance.

Youshen Xiao, Sheng Liao, Xuanyang Tian et al.

Acoustic-Resolution Photoacoustic Microscopy (AR-PAM) is promising for subcutaneous vascular imaging, but its spatial resolution is constrained by the Point Spread Function (PSF). Traditional deconvolution methods like Richardson-Lucy and model-based deconvolution use the PSF to improve resolution. However, accurately measuring the PSF is difficult, leading to reliance on less accurate blind deconvolution techniques. Additionally, AR-PAM suffers from long scanning times, which can be reduced via down-sampling, but this necessitates effective image recovery from under-sampled data, a task where traditional interpolation methods fall short, particularly at high under-sampling rates. To address these challenges, we propose an approach based on Implicit Neural Representations (INR). This method learns a continuous mapping from spatial coordinates to initial acoustic pressure, overcoming the limitations of discrete imaging and enhancing AR-PAM's resolution. By treating the PSF as a learnable parameter within the INR framework, our technique mitigates inaccuracies associated with PSF estimation. We evaluated our method on simulated vascular data, showing significant improvements in Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) over conventional methods. Qualitative enhancements were also observed in leaf vein and in vivo mouse brain microvasculature images. When applied to a custom AR-PAM system, experiments with pencil lead demonstrated that our method delivers sharper, higher-resolution results, indicating its potential to advance photoacoustic microscopy.

Mengjie Guo, Hengrong Lan, Changchun Yang et al.

Photoacoustic (PA) imaging is a biomedical imaging modality capable of acquiring high-contrast images of optical absorption at depths much greater than traditional optical imaging techniques. However, practical instrumentation and geometry limit the number of available acoustic sensors surrounding the imaging target, which results in the sparsity of sensor data. Conventional PA image reconstruction methods give severe artifacts when they are applied directly to the sparse PA data. In this paper, we firstly propose to employ a novel signal processing method to make sparse PA raw data more suitable for the neural network, concurrently speeding up image reconstruction. Then we propose Attention Steered Network (AS-Net) for PA reconstruction with multi-feature fusion. AS-Net is validated on different datasets, including simulated photoacoustic data from fundus vasculature phantoms and experimental data from in vivo fish and mice. Notably, the method is also able to eliminate some artifacts present in the ground truth for in vivo data. Results demonstrated that our method provides superior reconstructions at a faster speed.