Reinforcement learning (RL) with tree search has demonstrated superior performance in traditional reasoning tasks.Compared to conventional independent chain sampling strategies with outcome supervision, tree search enables better exploration of the reasoning space and provides dense, on-policy process rewards during RL training but remains under-explored in On-Policy LLM RL.We propose TreeRL, a reinforcement learning framework that directly incorporates on-policy tree search for RL training.Our approach includes intermediate supervision and eliminates the need for separate reward model training.Existing approaches typically train a separate process reward model, which can suffer from distribution mismatch and reward hacking.We also introduce a cost-effective tree search approach that achieves higher search efficiency under the same generation token budget by strategically branching from high-uncertainty intermediate steps rather than using random branching.Experiments on challenging math and code reasoning benchmarks demonstrate that TreeRL achieves superior performance compared to traditional ChainRL, highlighting the potential of tree search for LLM.

The current watermark-removal neural networks (WRNNs) can effectively remove the watermarks from watermarked images without damaging their host images, which poses a significant threat to image copyright protection. As one of the most effective technologies of preventing watermarks from being removed, the watermark vaccine generally attacks the WRNNs by generating and adding the adversarial perturbations to watermarked images. However, the existing watermark vaccine schemes perturb all the pixels of watermarked images, which makes it difficult to find a good trade-off between attack efficiency and imperceptibility. To address the above issues, we propose a Dual-Population Watermark Vaccine (DPWV) scheme. In this scheme, we formulate the task of adding adversarial perturbation as a bi-objective optimization problem, and address it by decoupling the space of adversarial perturbation addition to the Intensity Population (IP)-based and Position Population (PP)-based subspaces to search for the optimal solution. The extensive experiments demonstrate that the proposed scheme significantly outperforms the state-of-the-arts in the aspects of attack efficiency and imperceptibility, simultaneously, with the improvements of 45%-55% attack efficiency and 30%-40% attack imperceptibility.

Visible watermarks are generally embedded into digital images to claim their ownership for copyright protection. Unfortunately, the watermark removal models based on Deep Neural Networks (DNNs) are able to remove the watermarks from watermarked images, posing a great threat to image copyright protection. To prevent the watermark from being removed, watermark vaccines, i.e., adversarial perturbations, are usually added to the watermarked images to attack the target models, making them unable to remove the watermarks. However, the existing approaches indiscriminately add the watermark vaccine to the whole image region, and have not considered the vaccine failure caused by image noises, thereby still suffering from the issues of low imperceptibility and robustness. To address the above issues, we propose an Attention-Guided Watermark Vaccine (AGWV) scheme. Specifically, we propose pixel-feature attention (PFA) to identify the proper region for adding watermark vaccine, so as to achieve high imperceptibility for the added watermark vaccine. Then, we adopt image noises to perturb the vaccinated images and further optimize the watermark vaccine to correct the attention bias caused by image noise, thereby enhancing the robustness of watermark vaccines. Moreover, we design a vaccine evaluation model to intuitively evaluate the protective performances of watermark vaccines. Extensive experiments demonstrate that the proposed AGWV outperforms the state-of-the-arts in the aspects of both imperceptibility and robustness for defending against watermark removal models. Supplementary Material is available at https://github.com/YujiangLi0v0/ICME25.git

Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks. However, existing approaches mainly rely on imitation learning and struggle to achieve effective test-time scaling. While reinforcement learning (RL) holds promise for enabling self-exploration, recent attempts yield modest improvements in complex reasoning. In this paper, we present T1 to scale RL by encouraging exploration and understand inference scaling. We first initialize the LLM using synthesized chain-of-thought data that integrates trial-and-error and self-verification. To scale RL training, we promote increased sampling diversity through over-sampling. We demonstrate that T1 with open LLMs as its base exhibits inference scaling behavior and achieves superior performance on challenging math reasoning benchmarks. More importantly, we present a simple strategy to examine inference scaling, where increased inference budgets directly lead to T1’s better performance without any additional verification. The model weights and training data are publicly available at https://github.com/THUDM/T1.

Despite huge progress in skeleton-based action recognition, its generalizability to different domains remains a challenging issue. In this paper, to solve the skeleton action generalization problem, we present a recover-and-resample augmentation framework based on a novel complete action prior. We observe that human daily actions are confronted with temporal mismatch across different datasets, as they are usually partial observations of their complete action sequences. By recovering complete actions and resampling from these full sequences, we can generate strong augmentations for unseen domains. At the same time, we discover the nature of general action completeness within large datasets, indicated by the per-frame diversity over time. This allows us to exploit two assets of transferable knowledge that can be shared across action samples and be helpful for action completion: boundary poses for determining the action start, and linear temporal transforms for capturing global action patterns. Therefore, we formulate the recovering stage as a two-step stochastic action completion with boundary pose-conditioned extrapolation followed by smooth linear transforms. Both the boundary poses and linear transforms can be efficiently learned from the whole dataset via clustering. We validate our approach on a cross-dataset setting with three skeleton action datasets, outperforming other domain generalization approaches by a considerable margin.

The smart ocean has aroused the interest of government, business, and academia because of the wealth of marine resources. It has been suggested to use underwater Internet of Things (IoT) frameworks to collect a variety of data from smart seas that can aid in the underwater green transport system, ecological sustainability, military intelligence gathering, and a variety of other operations. Because of the limited resources accessible to IoT devices regarding communication overhead, processing expenses, and battery capacity, security and privacy concerns in underwater green transport systems have lately been a critical source of worry. In this context, We presented a unique identity-based authentication mechanism for underwater green transport systems. Our suggested solution uses lightweight authentication mechanisms that prove secure communication between different elements of the green transport system.

Land is one of the most important natural resources. The assessment of the current land use pattern suitability can help people make good use of the natural resources. In this paper, the land-use suitability index (SI) is used to evaluate the suitability of the land use pattern in the hilly area of Shandong Peninsular of China. Land use data is derived from Landsat TM/ETM acquired in 1988 and 2000 using the multi-source information fusion method. The results indicate that, the land-use suitability is slightly improved from 1988 to 2000 and the corresponding SI - values changed from 0.77 to 0.80. The difference value of land-use suitability is only 0.03, not as large as people previously predicted.