Does Your 3D Encoder Really Work? When Pretrain-SFT from 2D VLMs Meets 3D VLMs

Remarkable progress in 2D Vision-Language Models (VLMs) has spurred interest in extending them to 3D settings for tasks like 3D Question Answering, Dense Captioning, and Visual Grounding. Unlike 2D VLMs that typically process images through an image encoder, 3D scenes, with their intricate spatial structures, allow for diverse model architectures. Based on their encoder design, this paper categorizes recent 3D VLMs into 3D object-centric, 2D image-based, and 3D scene-centric approaches. Despite the architectural similarity of 3D scene-centric VLMs to their 2D counterparts, they have exhibited comparatively lower performance compared with the latest 3D object-centric and 2D image-based approaches. To understand this gap, we conduct an in-depth analysis, revealing that 3D scene-centric VLMs show limited reliance on the 3D scene encoder, and the pre-train stage appears less effective than in 2D VLMs. Furthermore, we observe that data scaling benefits are less pronounced on larger datasets. Our investigation suggests that while these models possess cross-modal alignment capabilities, they tend to over-rely on linguistic cues and overfit to frequent answer distributions, thereby diminishing the effective utilization of the 3D encoder. To address these limitations and encourage genuine 3D scene understanding, we introduce a novel 3D Relevance Discrimination QA dataset designed to disrupt shortcut learning and improve 3D understanding. Our findings highlight the need for advanced evaluation and improved strategies for better 3D understanding in 3D VLMs.

MolLangBench: A Comprehensive Benchmark for Language-Prompted Molecular Structure Recognition, Editing, and Generation

Precise recognition, editing, and generation of molecules are essential prerequisites for both chemists and AI systems tackling various chemical tasks. We present MolLangBench, a comprehensive benchmark designed to evaluate fundamental molecule-language interface tasks: language-prompted molecular structure recognition, editing, and generation. To ensure high-quality, unambiguous, and deterministic outputs, we construct the recognition tasks using automated cheminformatics tools, and curate editing and generation tasks through rigorous expert annotation and validation. MolLangBench supports the evaluation of models that interface language with different molecular representations, including linear strings, molecular images, and molecular graphs. Evaluations of state-of-the-art models reveal significant limitations: the strongest model (o3) achieves $79.2\%$ and $78.5\%$ accuracy on recognition and editing tasks, which are intuitively simple for humans, and performs even worse on the generation task, reaching only $29.0\%$ accuracy. These results highlight the shortcomings of current AI systems in handling even preliminary molecular recognition and manipulation tasks. We hope MolLangBench will catalyze further research toward more effective and reliable AI systems for chemical applications.

Integral regularization PINNs for evolution equations

Evolution equations, including both ordinary differential equations (ODEs) and partial differential equations (PDEs), play a pivotal role in modeling dynamic systems. However, achieving accurate long-time integration for these equations remains a significant challenge. While physics-informed neural networks (PINNs) provide a mesh-free framework for solving PDEs, they often suffer from temporal error accumulation, which limits their effectiveness in capturing long-time behaviors. To alleviate this issue, we propose integral regularization PINNs (IR-PINNs), a novel approach that enhances temporal accuracy by incorporating an integral-based residual term into the loss function. This method divides the entire time interval into smaller sub-intervals and enforces constraints over these sub-intervals, thereby improving the resolution and correlation of temporal dynamics. Furthermore, IR-PINNs leverage adaptive sampling to dynamically refine the distribution of collocation points based on the evolving solution, ensuring higher accuracy in regions with sharp gradients or rapid variations. Numerical experiments on benchmark problems demonstrate that IR-PINNs outperform original PINNs and other state-of-the-art methods in capturing long-time behaviors, offering a robust and accurate solution for evolution equations.

UniGS: Unified Language-Image-3D Pretraining with Gaussian Splatting

Recent advancements in multi-modal 3D pre-training methods have shown promising efficacy in learning joint representations of text, images, and point clouds. However, adopting point clouds as 3D representation fails to fully capture the intricacies of the 3D world and exhibits a noticeable gap between the discrete points and the dense 2D pixels of images. To tackle this issue, we propose UniGS, integrating 3D Gaussian Splatting (3DGS) into multi-modal pre-training to enhance the 3D representation. We first rely on the 3DGS representation to model the 3D world as a collection of 3D Gaussians with color and opacity, incorporating all the information of the 3D scene while establishing a strong connection with 2D images. Then, to achieve Language-Image-3D pertaining, UniGS starts with a pre-trained vision-language model to establish a shared visual and textual space through extensive real-world image-text pairs. Subsequently, UniGS employs a 3D encoder to align the optimized 3DGS with the Language-Image representations to learn unified multi-modal representations. To facilitate the extraction of global explicit 3D features by the 3D encoder and achieve better cross-modal alignment, we additionally introduce a novel Gaussian-Aware Guidance module that guides the learning of fine-grained representations of the 3D domain. Through extensive experiments across the Objaverse, ABO, MVImgNet and SUN RGBD datasets with zero-shot classification, text-driven retrieval and open-world understanding tasks, we demonstrate the effectiveness of UniGS in learning a more general and stronger aligned multi-modal representation. Specifically, UniGS achieves leading results across different 3D tasks with remarkable improvements over previous SOTA, Uni3D, including on zero-shot classification (+9.36%), text-driven retrieval (+4.3%) and open-world understanding (+7.92%).

Foundation Models for Anomaly Detection: Vision and Challenges

As data continues to grow in volume and complexity across domains such as finance, manufacturing, and healthcare, effective anomaly detection is essential for identifying irregular patterns that may signal critical issues. Recently, foundation models (FMs) have emerged as a powerful tool for advancing anomaly detection. They have demonstrated unprecedented capabilities in enhancing anomaly identification, generating detailed data descriptions, and providing visual explanations. This survey presents the first comprehensive review of recent advancements in FM-based anomaly detection. We propose a novel taxonomy that classifies FMs into three categories based on their roles in anomaly detection tasks, i.e., as encoders, detectors, or interpreters. We provide a systematic analysis of state-of-the-art methods and discuss key challenges in leveraging FMs for improved anomaly detection. We also outline future research directions in this rapidly evolving field.

Automatic Annotation Augmentation Boosts Translation between Molecules and Natural Language

Recent advancements in AI for biological research focus on integrating molecular data with natural language to accelerate drug discovery. However, the scarcity of high-quality annotations limits progress in this area. This paper introduces LA$^3$, a Language-based Automatic Annotation Augmentation framework that leverages large language models to augment existing datasets, thereby improving AI training. We demonstrate the effectiveness of LA$^3$ by creating an enhanced dataset, LaChEBI-20, where we systematically rewrite the annotations of molecules from an established dataset. These rewritten annotations preserve essential molecular information while providing more varied sentence structures and vocabulary. Using LaChEBI-20, we train LaMolT5 based on a benchmark architecture to learn the mapping between molecular representations and augmented annotations. Experimental results on text-based *de novo* molecule generation and molecule captioning demonstrate that LaMolT5 outperforms state-of-the-art models. Notably, incorporating LA$^3$ leads to improvements of up to 301% over the benchmark architecture. Furthermore, we validate the effectiveness of LA$^3$ notable applications in *image*, *text* and *graph* tasks, affirming its versatility and utility.

Dual-Branch Graph Transformer Network for 3D Human Mesh Reconstruction from Video

Human Mesh Reconstruction (HMR) from monocular video plays an important role in human-robot interaction and collaboration. However, existing video-based human mesh reconstruction methods face a trade-off between accurate reconstruction and smooth motion. These methods design networks based on either RNNs or attention mechanisms to extract local temporal correlations or global temporal dependencies, but the lack of complementary long-term information and local details limits their performance. To address this problem, we propose a \textbf{D}ual-branch \textbf{G}raph \textbf{T}ransformer network for 3D human mesh \textbf{R}econstruction from video, named DGTR. DGTR employs a dual-branch network including a Global Motion Attention (GMA) branch and a Local Details Refine (LDR) branch to parallelly extract long-term dependencies and local crucial information, helping model global human motion and local human details (e.g., local motion, tiny movement). Specifically, GMA utilizes a global transformer to model long-term human motion. LDR combines modulated graph convolutional networks and the transformer framework to aggregate local information in adjacent frames and extract crucial information of human details. Experiments demonstrate that our DGTR outperforms state-of-the-art video-based methods in reconstruction accuracy and maintains competitive motion smoothness. Moreover, DGTR utilizes fewer parameters and FLOPs, which validate the effectiveness and efficiency of the proposed DGTR. Code is publicly available at \href{https://github.com/TangTao-PKU/DGTR}{\textcolor{myBlue}{https://github.com/TangTao-PKU/DGTR}}.

ARTS: Semi-Analytical Regressor using Disentangled Skeletal Representations for Human Mesh Recovery from Videos

Although existing video-based 3D human mesh recovery methods have made significant progress, simultaneously estimating human pose and shape from low-resolution image features limits their performance. These image features lack sufficient spatial information about the human body and contain various noises (e.g., background, lighting, and clothing), which often results in inaccurate pose and inconsistent motion. Inspired by the rapid advance in human pose estimation, we discover that compared to image features, skeletons inherently contain accurate human pose and motion. Therefore, we propose a novel semiAnalytical Regressor using disenTangled Skeletal representations for human mesh recovery from videos, called ARTS. Specifically, a skeleton estimation and disentanglement module is proposed to estimate the 3D skeletons from a video and decouple them into disentangled skeletal representations (i.e., joint position, bone length, and human motion). Then, to fully utilize these representations, we introduce a semi-analytical regressor to estimate the parameters of the human mesh model. The regressor consists of three modules: Temporal Inverse Kinematics (TIK), Bone-guided Shape Fitting (BSF), and Motion-Centric Refinement (MCR). TIK utilizes joint position to estimate initial pose parameters and BSF leverages bone length to regress bone-aligned shape parameters. Finally, MCR combines human motion representation with image features to refine the initial human model parameters. Extensive experiments demonstrate that our ARTS surpasses existing state-of-the-art video-based methods in both per-frame accuracy and temporal consistency on popular benchmarks: 3DPW, MPI-INF-3DHP, and Human3.6M. Code is available at https://github.com/TangTao-PKU/ARTS.

LiDAR-GS:Real-time LiDAR Re-Simulation using Gaussian Splatting

LiDAR simulation plays a crucial role in closed-loop simulation for autonomous driving. Although recent advancements, such as the use of reconstructed mesh and Neural Radiance Fields (NeRF), have made progress in simulating the physical properties of LiDAR, these methods have struggled to achieve satisfactory frame rates and rendering quality. To address these limitations, we present LiDAR-GS, the first LiDAR Gaussian Splatting method, for real-time high-fidelity re-simulation of LiDAR sensor scans in public urban road scenes. The vanilla Gaussian Splatting, designed for camera models, cannot be directly applied to LiDAR re-simulation. To bridge the gap between passive camera and active LiDAR, our LiDAR-GS designs a differentiable laser beam splatting, grounded in the LiDAR range view model. This innovation allows for precise surface splatting by projecting lasers onto micro cross-sections, effectively eliminating artifacts associated with local affine approximations. Additionally, LiDAR-GS leverages Neural Gaussian Fields, which further integrate view-dependent clues, to represent key LiDAR properties that are influenced by the incident angle and external factors. Combining these practices with some essential adaptations, e.g., dynamic instances decomposition, our approach succeeds in simultaneously re-simulating depth, intensity, and ray-drop channels, achieving state-of-the-art results in both rendering frame rate and quality on publically available large scene datasets. Our source code will be made publicly available.

A hybrid FEM-PINN method for time-dependent partial differential equations

In this work, we present a hybrid numerical method for solving evolution partial differential equations (PDEs) by merging the time finite element method with deep neural networks. In contrast to the conventional deep learning-based formulation where the neural network is defined on a spatiotemporal domain, our methodology utilizes finite element basis functions in the time direction where the space-dependent coefficients are defined as the output of a neural network. We then apply the Galerkin or collocation projection in the time direction to obtain a system of PDEs for the space-dependent coefficients which is approximated in the framework of PINN. The advantages of such a hybrid formulation are twofold: statistical errors are avoided for the integral in the time direction, and the neural network's output can be regarded as a set of reduced spatial basis functions. To further alleviate the difficulties from high dimensionality and low regularity, we have developed an adaptive sampling strategy that refines the training set. More specifically, we use an explicit density model to approximate the distribution induced by the PDE residual and then augment the training set with new time-dependent random samples given by the learned density model. The effectiveness and efficiency of our proposed method have been demonstrated through a series of numerical experiments.