Recent advances in Large Reasoning Models (LRMs), particularly those leveraging Chain-of-Thought reasoning (CoT), have opened brand new possibility for Machine Translation (MT). This position paper argues that LRMs substantially transformed traditional neural MT as well as LLMs-based MT paradigms by reframing translation as a dynamic reasoning task that requires contextual, cultural, and linguistic understanding and reasoning. We identify three foundational shifts: 1) contextual coherence, where LRMs resolve ambiguities and preserve discourse structure through explicit reasoning over cross-sentence and complex context or even lack of context; 2) cultural intentionality, enabling models to adapt outputs by inferring speaker intent, audience expectations, and socio-linguistic norms; 3) self-reflection, LRMs can perform self-reflection during the inference time to correct the potential errors in translation especially extremely noisy cases, showing better robustness compared to simply mapping X->Y translation. We explore various scenarios in translation including stylized translation, document-level translation and multimodal translation by showcasing empirical examples that demonstrate the superiority of LRMs in translation. We also identify several interesting phenomenons for LRMs for MT including auto-pivot translation as well as the critical challenges such as over-localisation in translation and inference efficiency. In conclusion, we think that LRMs redefine translation systems not merely as text converters but as multilingual cognitive agents capable of reasoning about meaning beyond the text. This paradigm shift reminds us to think of problems in translation beyond traditional translation scenarios in a much broader context with LRMs - what we can achieve on top of it.

Bo Zeng, Chenyang Lyu, Sinuo Liu, Mingyan Zeng, Minghao Wu, Xuanfan Ni, Tianqi Shi, Yu Zhao, Yefeng Liu, Chenyu Zhu, Ruizhe Li, Jiahui Geng, Qing Li, Yu Tong, Longyue Wang, Weihua Luo, Kaifu Zhang. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Cryo-electron tomography (cryo-ET) is an important technique used to explore the structure and position of macromolecular complexes in a cellular environment. However, it is extremely difficult to extract sufficient information due to missing-wedge effects, low signal-to-noise ratio (SNR), and the compactness of the particles. Currently, unsupervised cryoET analysis methods struggle to achieve the desired accuracy, while supervised methods require a large amount of labeled data, which costs a lot of manpower, material resources, and financial resources. Even so, Cryo-ET simulation is beneficial as it provides an effective solution to assist supervised analysis methods by providing a large amount of labeled data to train, test, and optimize the models. However, most simulation methods only focus on a single structure, which can only provide limited help. Few methods simulate macromolecular crowding, but they either difficult to achieve a sufficient crowding level or cannot avoid overlap. Therefore, we proposed a new cryo-ET simulation method that packs macromolecules based on molecular dynamics to generate realistic and compact macromolecular crowding without overlap. We also simplified each macromolecule into a small ball to accelerate the simulation process. Our mechanics-based model computes the non-specific interaction, electrostatic interaction, and an external force to obtain the packed macromolecule crowding. From there, the obtained simulated cryo-ET is more realistic according to the imaging principle based on the coordinates of macromolecules under an equilibrium state. In conclusion, our experiments show that our method is able to pack the structures more tightly without overlap, and the simulated cryo-ET is more biologically realistic. Our simulation data can be used to expand the real data set and test methods such as particle picking, protein classification, and protein segmentation. The experimental results show that using the simulation method in this paper, the accuracy of training with all real data can be achieved when only 30% of the real data is used. This simulation method solves the scarcity, expense, and difficult-to-label problems of cryo-ET data, and provides a large amount of simulation data for researchers in the field of computational biology.

Photo-Sharing Multi-modal dialogue generation requires a dialogue agent not only to generate text responses but also to share photos at the proper moment. Using image text caption as the bridge, a pipeline model integrates an image caption model, a text generation model, and an image generation model to handle this complex multi-modal task. However, representing the images with text captions may lose important visual details and information and cause error propagation in the complex dialogue system. Besides, the pipeline model isolates the three models separately because discrete image text captions hinder end-to-end gradient propagation. We propose the first end-to-end model for photo-sharing multi-modal dialogue generation, which integrates an image perceptron and an image generator with a large language model. The large language model employs the vision encoder to perceive visual images in the input end. For image generation in the output end, we propose a dynamic vocabulary transformation matrix and use straight-through and gumbel-softmax techniques to align the large language model and stable diffusion model and achieve end-to-end gradient propagation. We perform experiments on PhotoChat and DialogCC datasets to evaluate our end-to-end model. Compared with pipeline models, the end-to-end model gains state-of-the-art performances on various metrics of text and image generation.

Meshless simulation of elasticity is important for deformable simulation in computer graphics. While shape matching is a popular meshless solution, it is limited to a subset of elastic constitutive models, challenging the simulation of generic elastic constitutive models using meshless integration. In contrast, peridynamics offers a more versatile capacity and can describe various material behavior through non-local interactions between vertices. However, the size of each stencil Hessian matrix varies with the number of nearby integration points, leading to inefficiency and accuracy loss. To address these challenges, we present an efficient and robust solver for generic elastic models based on peridynamics. We propose an efficient first-order Hessian proxy derived from the positive-negative decomposition of the stress tensor. The proposed symmetric positive definite proxies ensure convergence within a reasonable number of iterations while also being easy to parallelize on GPU. To further enhance stability, particularly for hyperelastic models, we propose enforcing strain limiting between peridynamics bonds to prevent tensile instability in meshless integration. Our algorithm includes two iteration loops of strain limiting and elastic Jacobis, and the pipeline is well-suited for GPU implementation. We evaluated the performance of our approach with a wide range of elastic constitutive models in diverse testing scenarios against the alternative numerical solvers. Our method features superior efficiency and faster convergence compared to existing numerical solvers. These compelling results underscore the practicality and effectiveness of our method for simulating elasticity via meshless integration.

Physics-based fluid simulation has played an increasingly important role in the computer graphics community. Recent methods in this area have greatly improved the generation of complex visual effects and its computational efficiency. Novel techniques have emerged to deal with complex boundaries, multiphase fluids, gas–liquid interfaces, and fine details. The parallel use of machine learning, image processing, and fluid control technologies has brought many interesting and novel research perspectives. In this survey, we provide an introduction to theoretical concepts underpinning physics-based fluid simulation and their practical implementation, with the aim for it to serve as a guide for both newcomers and seasoned researchers to explore the field of physics-based fluid simulation, with a focus on developments in the last decade. Driven by the distribution of recent publications in the field, we structure our survey to cover physical background; discretization approaches; computational methods that address scalability; fluid interactions with other materials and interfaces; and methods for expressive aspects of surface detail and control. From a practical perspective, we give an overview of existing implementations available for the above methods.

Summary We proposed a novel target‐driven fluid simulation method based on the weighted control model derived from the spatial geometric features of the target shape. First, the spatial geometric characteristics of the target model are taken into account to set the color field weights of control particles. This enabled the full expression of geometric characteristics of the target model, and improve the shape accuracy of controlled fluid. Then, the fluid is controlled to form the target shape under driving constraints, wherein we proposed a new adaptive constraint mechanism that enables efficient target shape generation. Finally, a new density constraint between the control particles and the controlled fluid particles is proposed to ensure the incompressibility of fluid during control. Compared to the state‐of‐the‐art target‐driven fluid control methods, our method achieves higher precision fluid control with higher efficiency.

MOTIVATION: Cryo-Electron Tomography (cryo-ET) is a 3D imaging technology that enables the visualization of subcellular structures in situ at near-atomic resolution. Cellular cryo-ET images help in resolving the structures of macromolecules and determining their spatial relationship in a single cell, which has broad significance in cell and structural biology. Subtomogram classification and recognition constitute a primary step in the systematic recovery of these macromolecular structures. Supervised deep learning methods have been proven to be highly accurate and efficient for subtomogram classification, but suffer from limited applicability due to scarcity of annotated data. While generating simulated data for training supervised models is a potential solution, a sizeable difference in the image intensity distribution in generated data as compared with real experimental data will cause the trained models to perform poorly in predicting classes on real subtomograms. RESULTS: In this work, we present Cryo-Shift, a fully unsupervised domain adaptation and randomization framework for deep learning-based cross-domain subtomogram classification. We use unsupervised multi-adversarial domain adaption to reduce the domain shift between features of simulated and experimental data. We develop a network-driven domain randomization procedure with 'warp' modules to alter the simulated data and help the classifier generalize better on experimental data. We do not use any labeled experimental data to train our model, whereas some of the existing alternative approaches require labeled experimental samples for cross-domain classification. Nevertheless, Cryo-Shift outperforms the existing alternative approaches in cross-domain subtomogram classification in extensive evaluation studies demonstrated herein using both simulated and experimental data. AVAILABILITYAND IMPLEMENTATION: https://github.com/xulabs/aitom. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

We propose a novel weakly supervised approach for 3D semantic segmentation on volumetric images. Unlike most existing methods that require voxel-wise densely labeled training data, our weakly-supervised CIVA-Net is the first model that only needs image-level class labels as guidance to learn accurate volumetric segmentation. Our model learns from cross-image co-occurrence for integral region generation, and explores inter-voxel affinity relations to predict segmentation with accurate boundaries. We empirically validate our model on both simulated and real cryo-ET datasets. Our experiments show that CIVA-Net achieves comparable performance to the state-of-the-art models trained with stronger supervision.

Abstract A major issue in smoothed particle hydrodynamics (SPH) approaches is the numerical dissipation during the projection process, especially under coarse discretizations. High‐frequency details, such as turbulence and vortices, are smoothed out, leading to unrealistic results. To address this issue, we introduce a vorticity refinement (VR) solver for SPH fluids with negligible computational overhead. In this method, the numerical dissipation of the vorticity field is recovered by the difference between the theoretical and the actual vorticity, so as to enhance turbulence details. Instead of solving the Biot‐Savart integrals, a stream function, which is easier and more efficient to solve, is used to relate the vorticity field to the velocity field. We obtain turbulence effects of different intensity levels by changing an adjustable parameter. Since the vorticity field is enhanced according to the curl field, our method can not only amplify existing vortices, but also capture additional turbulence. Our VR solver is straightforward to implement and can be easily integrated into existing SPH methods.

We propose an efficient method for simulating a cryo-Electron Tomography (cryo-ET) image of a target macromolecule with several neighbor macromolecules packed to achieve a realistic crowded cytoplasm content. The simulated results are subtomograms with corresponding noise-free 3D density maps and pre-specified labels (PDB ID, center locations, and orientations) to assist bioimage analysis. They can serve as benchmark datasets for testing developing cryo-ET analysis algorithms and as training datasets with readily available ground truth labels for learning neural network models. The COVID-19 pandemic has sparked a global health crisis that severely impacting lives worldwide. As an important application, we simulated the scene of SARS-CoV-2 interacting with the host cell. The simulated cryo-ET images clearly showed the binding domain of the virus and the host cell to facilitate the research of SARS-CoV-2' infection. We also trained two different classification models to demonstrate that our simulated cryo-ET data is able to assist the cryo-ET analysis task and to validate the performance between different methods.

Trapped air in liquid is an important factor which affect the realism of fluid simulation. However, due to the complex physical properties, simulating the interaction and transformation between air and Liquid is extremely challenging and time-consuming. In this paper, we propose a multi-scale simulation method under particle-based framework to achieve the realistic and efficient simulation of air-liquid fluid. A unified generation rule is proposed according to the kinetic energy and the velocity difference between fluid particles. Two velocity-based dynamic models are then established for different size of air materials respectively. The Brownian motion of small scale air materials is achieved by Schilk random function. The interaction and air transfer between large scale air materials is achieved by inverse diffusion equation and a new high-order kernel function. Experimental results show that the proposed method can improve the fidelity and richness of the fluid simulation. The post-processing scheme makes it able to be integrated with existing particle method easily.

BACKGROUND: Cryo-electron tomography is an important and powerful technique to explore the structure, abundance, and location of ultrastructure in a near-native state. It contains detailed information of all macromolecular complexes in a sample cell. However, due to the compact and crowded status, the missing edge effect, and low signal to noise ratio (SNR), it is extremely challenging to recover such information with existing image processing methods. Cryo-electron tomogram simulation is an effective solution to test and optimize the performance of the above image processing methods. The simulated images could be regarded as the labeled data which covers a wide range of macromolecular complexes and ultrastructure. To approximate the crowded cellular environment, it is very important to pack these heterogeneous structures as tightly as possible. Besides, simulating non-deformable and deformable components under a unified framework also need to be achieved. RESULT: In this paper, we proposed a unified framework for simulating crowded cryo-electron tomogram images including non-deformable macromolecular complexes and deformable ultrastructures. A macromolecule was approximated using multiple balls with fixed relative positions to reduce the vacuum volume. A ultrastructure, such as membrane and filament, was approximated using multiple balls with flexible relative positions so that this structure could deform under force field. In the experiment, 400 macromolecules of 20 representative types were packed into simulated cytoplasm by our framework, and numerical verification proved that our method has a smaller volume and higher compression ratio than the baseline single-ball model. We also packed filaments, membranes and macromolecules together, to obtain a simulated cryo-electron tomogram image with deformable structures. The simulated results are closer to the real Cryo-ET, making the analysis more difficult. The DOG particle picking method and the image segmentation method are tested on our simulation data, and the experimental results show that these methods still have much room for improvement. CONCLUSION: The proposed multi-ball model can achieve more crowded packaging results and contains richer elements with different properties to obtain more realistic cryo-electron tomogram simulation. This enables users to simulate cryo-electron tomogram images with non-deformable macromolecular complexes and deformable ultrastructures under a unified framework. To illustrate the advantages of our framework in improving the compression ratio, we calculated the volume of simulated macromolecular under our multi-ball method and traditional single-ball method. We also performed the packing experiment of filaments and membranes to demonstrate the simulation ability of deformable structures. Our method can be used to do a benchmark by generating large labeled cryo-ET dataset and evaluating existing image processing methods. Since the content of the simulated cryo-ET is more complex and crowded compared with previous ones, it will pose a greater challenge to existing image processing methods.

A critical problem of Smooth Particle Hydrodynamics (SPH) methods is the numerical dissipation in viscosity computation. This leads to unrealistic results where high frequency details, like turbulence, are smoothed out. To address this issue, we introduce a viscosity-based vorticity correction scheme for SPH fluids, without complex time integration or limited time steps. In our method, the energy difference in viscosity computation is used to correct the vorticity field. Instead of solving Biot-Savart integrals, we adopt stream function, which is easier to solve and more efficient, to recover the velocity field from the vorticity difference. Our method can increase the existing vortex significantly and generate additional turbulence at potential position. Moreover, it is simple to implement and can be easily integrated with other SPH methods.

Under particle-based framework, level set is generally defined for fluid surfaces and is integrated with marching cubes algorithm to extract fluid surfaces. In these methods, anisotropic kernels method has proven successful for reconstructing fluid surfaces with high quality. It can perfectly represent smooth surfaces, thin stream and sharp features of fluids compare to other methods. In this paper, we propose a novel approach to extend it to the simulation of multiphase fluids simulation. In order to ensure fine effects for both fluid surface and multiphase interface, we modify the calculation of original anisotropic kernels and address a binary tree strategy for reconstruction. Our method can extract fluid surfaces simply and effectively for particle-based multiphase simulation. It solved the problem of overlaps and gaps at multiphase interface that exist in traditional methods. The experimental results demonstrate that our method keep a good fluid surface and interface effects.