World models allow autonomous agents to plan and explore by predicting the visual outcomes of different actions. However, for robot manipulation, it is challenging to accurately model the fine-grained robot-object interaction within the visual space using existing methods which overlooks precise alignment between each action and the corresponding frame. In this paper, we present IRASim, a novel world model capable of generating videos with fine-grained robotobject interaction details, conditioned on historical observations and robot action trajectories. We train a diffusion transformer and introduce a novel frame-level actionconditioning module within each transformer block to explicitly model and strengthen the action-frame alignment. Extensive experiments show that: (1) the quality of the videos generated by our method surpasses all the baseline methods and scales effectively with increased model size and computation; (2) policy evaluations using IRASim exhibit a strong correlation with those using the ground-truth simulator, highlighting its potential to accelerate real-world policy evaluation; (3) testing-time scaling through model-based planning with IRASim significantly enhances policy performance, as evidenced by an improvement in the IoU metric on the Push-T benchmark from 0.637 to 0.961; (4) IRASim provides flexible action controllability, allowing virtual robotic arms in datasets to be controlled via a keyboard or VR controller. Video and code are available at https://gen-irasim.github.io/.

Existing pretrained models for 3D mesh generation often suffer from data biases and produce low-quality results, while global reinforcement learning (RL) methods rely on object-level rewards that struggle to capture local structure details. To address these challenges, we present $\textbf{Mesh-RFT}$, a novel fine-grained reinforcement fine-tuning framework that employs Masked Direct Preference Optimization (M-DPO) to enable localized refinement via quality-aware face masking. To facilitate efficient quality evaluation, we introduce an objective topology-aware scoring system to evaluate geometric integrity and topological regularity at both object and face levels through two metrics: Boundary Edge Ratio (BER) and Topology Score (TS). By integrating these metrics into a fine-grained RL strategy, Mesh-RFT becomes the first method to optimize mesh quality at the granularity of individual faces, resolving localized errors while preserving global coherence. Experiment results show that our M-DPO approach reduces Hausdorff Distance (HD) by 24.6\% and improves Topology Score (TS) by 3.8\% over pre-trained models, while outperforming global DPO methods with a 17.4\% HD reduction and 4.9\% TS gain. These results demonstrate Mesh-RFT’s ability to improve geometric integrity and topological regularity, achieving new state-of-the-art performance in production-ready mesh generation.

Script event prediction aims to predict the subsequent event given the context. This requires the capability to infer the correlations between events. Recent works have attempted to improve event correlation reasoning by using pretrained language models and incorporating external knowledge (e.g., discourse relations). Though promising results have been achieved, some challenges still remain. First, the pretrained language models adopted by current works ignore event-level knowledge, resulting in an inability to capture the correlations between events well. Second, modeling correlations between events with discourse relations is limited because it can only capture explicit correlations between events with discourse markers, and cannot capture many implicit correlations. To this end, we propose a novel generative approach for this task, in which a pretrained language model is fine-tuned with an event-centric pretraining objective and predicts the next event within a generative paradigm. Specifically, we first introduce a novel event-level blank infilling strategy as the learning objective to inject event-level knowledge into the pretrained language model, and then design a likelihood-based contrastive loss for fine-tuning the generative model. Instead of using an additional prediction layer, we perform prediction by using sequence likelihoods generated by the generative model. Our approach models correlations between events in a soft way without any external knowledge. The likelihood-based prediction eliminates the need to use additional networks to make predictions and is somewhat interpretable since it scores each word in the event. Experimental results on the multi-choice narrative cloze (MCNC) task demonstrate that our approach achieves better results than other state-of-the-art baselines. Our code will be available at https://github.com/zhufq00/mcnc.

Adverse drug-drug interactions (DDIs) can compromise the effectiveness of concurrent drug administration, posing a significant challenge in healthcare.As the development of new drugs continues, the potential for unknown adverse effects resulting from DDIs becomes a growing concern.Traditional computational methods for DDI prediction may fail to capture interactions for new drugs due to the lack of knowledge.In this paper, we introduce a new problem setup as zero-shot DDI prediction that deals with the case of new drugs.Leveraging textual information from online databases like DrugBank and PubChem, we propose an innovative approach TextDDI with a language model-based DDI predictor and a reinforcement learning (RL)-based information selector, enabling the selection of concise and pertinent text for accurate DDI prediction on new drugs.Empirical results show the benefits of the proposed approach on several settings including zero-shot and few-shot DDI prediction, and the selected texts are semantically relevant.Our code and data are available at https: //github.com/zhufq00/DDIs-Prediction.

The problem of multisensors fusion target trajectory tracking under the Bayesian variational inference (VI) is to find the jointly accurate posterior distribution. In this article, a joint optimization method, called VINFNet, combining inference modeling and data-driven is proposed. The proposed VINFNet incorporates the respective advantages of state-space latent inference models and deep generative network that can explicitly model the physical process of target motion and construct complex posterior distributions of target trajectory through a series of invertible mappings. Specifically, the joint probabilistic representation of the multisensors latent variable is generated by VI, with the optimization on the evidence lower bound (ELBO) to guarantee convergence. However, finding the approximate posterior distribution of targets in VI is a crucially intractable problem. Therefore, a normalized flow generation model under a multilayers perceptron strategy is proposed to recover the approximate posterior distribution of targets, overcoming the challenge of choosing the posterior distribution during VI. The proposed VINFNet neither requires the computation of complex Jacobi matrices as in model-based algorithms such as Kalman filter (KF) nor lacks interpretability as in data-driven neural networks. Simulations and ablation experiments evaluate that the VINFNet algorithm outperforms prevalent methods regarding convergence, accuracy, robustness, and effectiveness via fusing different data sources.

The parametrization of recurrent neural network (RNN) to solve the gradient vanishing and exploding problem is critical for sequential learning. The reason lies on eigenvalue of the gradient of loss function against the recurrent weight matrix in recurrent weight matrix. To control the eigenvalues, the orthogonal constraint is imposed on the recurrent weight matrix. In this article, we analyze the designing mechanism of decomposition methods of three orthogonal constrained RNNs (OCRNNs) and derive their corresponding training algorithms. We compare the performance of the four OCRNNs and the standard long short-term memory (LSTM) network on the synthetic baseline copying and adding tasks. We find out that the coordinate descent-based iteration of the two OCRNNs proposed by us can achieve comparative or better testing error and convergence speed than the rest model. The above two OCRNN models are more cost-effective in terms of total number of parameters, which save the storage of the model. Furthermore, we introduce the pseudospectrum to visualize and monitor the evolving of the orthogonality of the recurrent weight matrix and find that the orthogonality is a empirically useful condition but not rigorously theoretical guarantee for convergence speed. Finally, we deploy the three OCRNNs on the acoustic polyp detection problem based on the and formulate the detection problem as the sequential binary classification. We also demonstrate that our proposed two OCRNNs can achieve comparative accuracy with less total number of network parameters. The quick inference time demonstrates its ability for Internet of Things (IoT) application.