Ye Yuan

Ye Yuan, Jiaming Song, Umar Iqbal et al. · cmu

Denoising diffusion models hold great promise for generating diverse and realistic human motions. However, existing motion diffusion models largely disregard the laws of physics in the diffusion process and often generate physically-implausible motions with pronounced artifacts such as floating, foot sliding, and ground penetration. This seriously impacts the quality of generated motions and limits their real-world application. To address this issue, we present a novel physics-guided motion diffusion model (PhysDiff), which incorporates physical constraints into the diffusion process. Specifically, we propose a physics-based motion projection module that uses motion imitation in a physics simulator to project the denoised motion of a diffusion step to a physically-plausible motion. The projected motion is further used in the next diffusion step to guide the denoising diffusion process. Intuitively, the use of physics in our model iteratively pulls the motion toward a physically-plausible space, which cannot be achieved by simple post-processing. Experiments on large-scale human motion datasets show that our approach achieves state-of-the-art motion quality and improves physical plausibility drastically (>78% for all datasets).

Bohan Li, Ye Yuan, Dingkang Liang et al.

Recently, most handwritten mathematical expression recognition (HMER) methods adopt the encoder-decoder networks, which directly predict the markup sequences from formula images with the attention mechanism. However, such methods may fail to accurately read formulas with complicated structure or generate long markup sequences, as the attention results are often inaccurate due to the large variance of writing styles or spatial layouts. To alleviate this problem, we propose an unconventional network for HMER named Counting-Aware Network (CAN), which jointly optimizes two tasks: HMER and symbol counting. Specifically, we design a weakly-supervised counting module that can predict the number of each symbol class without the symbol-level position annotations, and then plug it into a typical attention-based encoder-decoder model for HMER. Experiments on the benchmark datasets for HMER validate that both joint optimization and counting results are beneficial for correcting the prediction errors of encoder-decoder models, and CAN consistently outperforms the state-of-the-art methods. In particular, compared with an encoder-decoder model for HMER, the extra time cost caused by the proposed counting module is marginal. The source code is available at https://github.com/LBH1024/CAN.

Zhengyi Luo, Shun Iwase, Ye Yuan et al. · cmu

We propose embodied scene-aware human pose estimation where we estimate 3D poses based on a simulated agent's proprioception and scene awareness, along with external third-person observations. Unlike prior methods that often resort to multistage optimization, non-causal inference, and complex contact modeling to estimate human pose and human scene interactions, our method is one-stage, causal, and recovers global 3D human poses in a simulated environment. Since 2D third-person observations are coupled with the camera pose, we propose to disentangle the camera pose and use a multi-step projection gradient defined in the global coordinate frame as the movement cue for our embodied agent. Leveraging a physics simulation and prescanned scenes (e.g., 3D mesh), we simulate our agent in everyday environments (library, office, bedroom, etc.) and equip our agent with environmental sensors to intelligently navigate and interact with the geometries of the scene. Our method also relies only on 2D keypoints and can be trained on synthetic datasets derived from popular human motion databases. To evaluate, we use the popular H36M and PROX datasets and achieve high quality pose estimation on the challenging PROX dataset without ever using PROX motion sequences for training. Code and videos are available on the project page.

Jianhao Shen, Chenguang Wang, Ye Yuan et al.

This paper presents a parameter-lite transfer learning approach of pretrained language models (LM) for knowledge graph (KG) completion. Instead of finetuning, which modifies all LM parameters, we only tune a few new parameters while keeping the original LM parameters fixed. We establish this via reformulating KG completion as a "fill-in-the-blank" task, and introducing a parameter-lite encoder on top of the original LMs. We show that, by tuning far fewer parameters than finetuning, LMs transfer non-trivially to most tasks and reach competitiveness with prior state-of-the-art approaches. For instance, we outperform the fully finetuning approaches on a KG completion benchmark by tuning only 1% of the parameters. The code and datasets are available at \url{https://github.com/yuanyehome/PALT}.

Ye Yuan, Xiao Liu, Wondimu Dikubab et al.

Handwritten mathematical expression recognition (HMER) is a challenging task that has many potential applications. Recent methods for HMER have achieved outstanding performance with an encoder-decoder architecture. However, these methods adhere to the paradigm that the prediction is made "from one character to another", which inevitably yields prediction errors due to the complicated structures of mathematical expressions or crabbed handwritings. In this paper, we propose a simple and efficient method for HMER, which is the first to incorporate syntax information into an encoder-decoder network. Specifically, we present a set of grammar rules for converting the LaTeX markup sequence of each expression into a parsing tree; then, we model the markup sequence prediction as a tree traverse process with a deep neural network. In this way, the proposed method can effectively describe the syntax context of expressions, alleviating the structure prediction errors of HMER. Experiments on three benchmark datasets demonstrate that our method achieves better recognition performance than prior arts. To further validate the effectiveness of our method, we create a large-scale dataset consisting of 100k handwritten mathematical expression images acquired from ten thousand writers. The source code, new dataset, and pre-trained models of this work will be publicly available.

Hanjie Li, Changsheng Li, Kaituo Feng et al.

Graph structured data often possess dynamic characters in nature. Recent years have witnessed the increasing attentions paid to dynamic graph neural networks for modelling graph data. However, almost all existing approaches operate under the assumption that, upon the establishment of a new link, the embeddings of the neighboring nodes should undergo updates to learn temporal dynamics. Nevertheless, these approaches face the following limitation: If the node introduced by a new connection contains noisy information, propagating its knowledge to other nodes becomes unreliable and may even lead to the collapse of the model. In this paper, we propose Ada-DyGNN: a robust knowledge Adaptation framework via reinforcement learning for Dynamic Graph Neural Networks. In contrast to previous approaches, which update the embeddings of the neighbor nodes immediately after adding a new link, Ada-DyGNN adaptively determines which nodes should be updated. Considering that the decision to update the embedding of one neighbor node can significantly impact other neighbor nodes, we conceptualize the node update selection as a sequence decision problem and employ reinforcement learning to address it effectively. By this means, we can adaptively propagate knowledge to other nodes for learning robust node embedding representations. To the best of our knowledge, our approach constitutes the first attempt to explore robust knowledge adaptation via reinforcement learning specifically tailored for dynamic graph neural networks. Extensive experiments on three benchmark datasets demonstrate that Ada-DyGNN achieves the state-of-the-art performance. In addition, we conduct experiments by introducing different degrees of noise into the dataset, quantitatively and qualitatively illustrating the robustness of Ada-DyGNN.

Shiye Wang, Changsheng Li, Yanming Li et al.

In this paper, we explore the problem of deep multi-view subspace clustering framework from an information-theoretic point of view. We extend the traditional information bottleneck principle to learn common information among different views in a self-supervised manner, and accordingly establish a new framework called Self-supervised Information Bottleneck based Multi-view Subspace Clustering (SIB-MSC). Inheriting the advantages from information bottleneck, SIB-MSC can learn a latent space for each view to capture common information among the latent representations of different views by removing superfluous information from the view itself while retaining sufficient information for the latent representations of other views. Actually, the latent representation of each view provides a kind of self-supervised signal for training the latent representations of other views. Moreover, SIB-MSC attempts to learn the other latent space for each view to capture the view-specific information by introducing mutual information based regularization terms, so as to further improve the performance of multi-view subspace clustering. To the best of our knowledge, this is the first work to explore information bottleneck for multi-view subspace clustering. Extensive experiments on real-world multi-view data demonstrate that our method achieves superior performance over the related state-of-the-art methods.

Zhenggang Tang, Balakumar Sundaralingam, Jonathan Tremblay et al.

We present a system for collision-free control of a robot manipulator that uses only RGB views of the world. Perceptual input of a tabletop scene is provided by multiple images of an RGB camera (without depth) that is either handheld or mounted on the robot end effector. A NeRF-like process is used to reconstruct the 3D geometry of the scene, from which the Euclidean full signed distance function (ESDF) is computed. A model predictive control algorithm is then used to control the manipulator to reach a desired pose while avoiding obstacles in the ESDF. We show results on a real dataset collected and annotated in our lab.

Chengwu Liu, Jianhao Shen, Huajian Xin et al.

We present FIMO, an innovative dataset comprising formal mathematical problem statements sourced from the International Mathematical Olympiad (IMO) Shortlisted Problems. Designed to facilitate advanced automated theorem proving at the IMO level, FIMO is currently tailored for the Lean formal language. It comprises 149 formal problem statements, accompanied by both informal problem descriptions and their corresponding LaTeX-based informal proofs. Through initial experiments involving GPT-4, our findings underscore the existing limitations in current methodologies, indicating a substantial journey ahead before achieving satisfactory IMO-level automated theorem proving outcomes.

Jiachen Li, Ye Yuan, Hong-Bin Shen

Symbolic Regression (SR) is a type of regression analysis to automatically find the mathematical expression that best fits the data. Currently, SR still basically relies on various searching strategies so that a sample-specific model is required to be optimized for every expression, which significantly limits the model's generalization and efficiency. Inspired by the fact that human beings can infer a mathematical expression based on the curve of it, we propose Symbolic Expression Transformer (SET), a sample-agnostic model from the perspective of computer vision for SR. Specifically, the collected data is represented as images and an image caption model is employed for translating images to symbolic expressions. A large-scale dataset without overlap between training and testing sets in the image domain is released. Our results demonstrate the effectiveness of SET and suggest the promising direction of image-based model for solving the challenging SR problem.

Yonggan Fu, Ye Yuan, Shang Wu et al.

Transfer learning leverages feature representations of deep neural networks (DNNs) pretrained on source tasks with rich data to empower effective finetuning on downstream tasks. However, the pretrained models are often prohibitively large for delivering generalizable representations, which limits their deployment on edge devices with constrained resources. To close this gap, we propose a new transfer learning pipeline, which leverages our finding that robust tickets can transfer better, i.e., subnetworks drawn with properly induced adversarial robustness can win better transferability over vanilla lottery ticket subnetworks. Extensive experiments and ablation studies validate that our proposed transfer learning pipeline can achieve enhanced accuracy-sparsity trade-offs across both diverse downstream tasks and sparsity patterns, further enriching the lottery ticket hypothesis.

Ye Yuan, Xin Luo

A high-dimensional and incomplete (HDI) matrix frequently appears in various big-data-related applications, which demonstrates the inherently non-negative interactions among numerous nodes. A non-negative latent factor (NLF) model performs efficient representation learning to an HDI matrix, whose learning process mostly relies on a single latent factor-dependent, non-negative and multiplicative update (SLF-NMU) algorithm. However, an SLF-NMU algorithm updates a latent factor based on the current update increment only without appropriate considerations of past learning information, resulting in slow convergence. Inspired by the prominent success of a proportional-integral (PI) controller in various applications, this paper proposes a Proportional-Integral-incorporated Non-negative Latent Factor (PI-NLF) model with two-fold ideas: a) establishing an Increment Refinement (IR) mechanism via considering the past update increments following the principle of a PI controller; and b) designing an IR-based SLF-NMU (ISN) algorithm to accelerate the convergence rate of a resultant model. Empirical studies on four HDI datasets demonstrate that a PI-NLF model outperforms the state-of-the-art models in both computational efficiency and estimation accuracy for missing data of an HDI matrix. Hence, this study unveils the feasibility of boosting the performance of a non-negative learning algorithm through an error feedback controller.

Leilei Cao, Yibo Guo, Ye Yuan et al.

Few-shot Semantic Segmentation (FSS) was proposed to segment unseen classes in a query image, referring to only a few annotated examples named support images. One of the characteristics of FSS is spatial inconsistency between query and support targets, e.g., texture or appearance. This greatly challenges the generalization ability of methods for FSS, which requires to effectively exploit the dependency of the query image and the support examples. Most existing methods abstracted support features into prototype vectors and implemented the interaction with query features using cosine similarity or feature concatenation. However, this simple interaction may not capture spatial details in query features. To alleviate this limitation, a few methods utilized all pixel-wise support information via computing the pixel-wise correlations between paired query and support features implemented with the attention mechanism of Transformer. These approaches suffer from heavy computation on the dot-product attention between all pixels of support and query features. In this paper, we propose a simple yet effective framework built upon Transformer termed as ProtoFormer to fully capture spatial details in query features. It views the abstracted prototype of the target class in support features as Query and the query features as Key and Value embeddings, which are input to the Transformer decoder. In this way, the spatial details can be better captured and the semantic features of target class in the query image can be focused. The output of the Transformer-based module can be viewed as semantic-aware dynamic kernels to filter out the segmentation mask from the enriched query features. Extensive experiments on PASCAL-$5^{i}$ and COCO-$20^{i}$ show that our ProtoFormer significantly advances the state-of-the-art methods.

Jinli Li, Ye Yuan

High-dimensional and incomplete (HDI) data holds tremendous interactive information in various industrial applications. A latent factor (LF) model is remarkably effective in extracting valuable information from HDI data with stochastic gradient decent (SGD) algorithm. However, an SGD-based LFA model suffers from slow convergence since it only considers the current learning error. To address this critical issue, this paper proposes a Nonlinear PID-enhanced Adaptive Latent Factor (NPALF) model with two-fold ideas: 1) rebuilding the learning error via considering the past learning errors following the principle of a nonlinear PID controller; b) implementing all parameters adaptation effectively following the principle of a particle swarm optimization (PSO) algorithm. Experience results on four representative HDI datasets indicate that compared with five state-of-the-art LFA models, the NPALF model achieves better convergence rate and prediction accuracy for missing data of an HDI data.

Ying Wang, Ye Yuan, Xin Luo

An undirected weighted graph (UWG) is frequently adopted to describe the interactions among a solo set of nodes from real applications, such as the user contact frequency from a social network services system. A graph convolutional network (GCN) is widely adopted to perform representation learning to a UWG for subsequent pattern analysis tasks such as clustering or missing data estimation. However, existing GCNs mostly neglects the latent collaborative information hidden in its connected node pairs. To address this issue, this study proposes to model the node collaborations via a symmetric latent factor analysis model, and then regards it as a node-collaboration module for supplementing the collaboration loss in a GCN. Based on this idea, a Node-collaboration-informed Graph Convolutional Network (NGCN) is proposed with three-fold ideas: a) Learning latent collaborative information from the interaction of node pairs via a node-collaboration module; b) Building the residual connection and weighted representation propagation to obtain high representation capacity; and c) Implementing the model optimization in an end-to-end fashion to achieve precise representation to the target UWG. Empirical studies on UWGs emerging from real applications demonstrate that owing to its efficient incorporation of node-collaborations, the proposed NGCN significantly outperforms state-of-the-art GCNs in addressing the task of missing weight estimation. Meanwhile, its good scalability ensures its compatibility with more advanced GCN extensions, which will be further investigated in our future studies.

Jiufang Chen, Ye Yuan

Stochastic gradient descent (SGD) algorithm is an effective learning strategy to build a latent factor analysis (LFA) model on a high-dimensional and incomplete (HDI) matrix. A particle swarm optimization (PSO) algorithm is commonly adopted to make an SGD-based LFA model's hyper-parameters, i.e, learning rate and regularization coefficient, self-adaptation. However, a standard PSO algorithm may suffer from accuracy loss caused by premature convergence. To address this issue, this paper incorporates more historical information into each particle's evolutionary process for avoiding premature convergence following the principle of a generalized-momentum (GM) method, thereby innovatively achieving a novel GM-incorporated PSO (GM-PSO). With it, a GM-PSO-based LFA (GMPL) model is further achieved to implement efficient self-adaptation of hyper-parameters. The experimental results on three HDI matrices demonstrate that the GMPL model achieves a higher prediction accuracy for missing data estimation in industrial applications.

Zhuang Liu, Zhichao Zhao, Ye Yuan et al.

In this technical report, we briefly introduce the solution of our team ''summer'' for Atomospheric Turbulence Mitigation in UG$^2$+ Challenge in CVPR 2022. In this task, we propose a unified end-to-end framework to reconstruct a high quality image from distorted frames, which is mainly consists of a Restormer-based image reconstruction module and a NIMA-based image quality assessment module. Our framework is efficient and generic, which is adapted to both hot-air image and text pattern. Moreover, we elaborately synthesize more than 10 thousands of images to simulate atmospheric turbulence. And these images improve the robustness of the model. Finally, we achieve the average accuracy of 98.53\% on the reconstruction result of the text patterns, ranking 1st on the final leaderboard.

Alan Wu, Ye Yuan, Ming Zhang

Visually impaired people are a large group who can only use braille for reading and writing. However, the lack of special educational resources is the bottleneck for educating them. Educational equity is a reflection of the level of social civilization, cultural equality, and individual dignity. Facilitating and improving lifelong learning channels for the visually impaired is of great significance. Their written braille homework or exam papers cannot be understood by sighted teachers, because of the lack of a highly accurate braille translation system, especially in Chinese which has tone marks. braille writers often omit tone marks to save space, leading to confusion when braille with the same consonants and vowels is translated into Chinese. Previous algorithms were insufficient in extracting contextual information, resulting in low accuracy of braille translations into Chinese. This project informatively fine-tuned the mT5 model with an Encoder-decoder architecture for braille to Chinese character conversion. This research created a training set of braille and corresponding Chinese text from the Leipzig Corpora. This project significantly reduced the confusion in braille, achieving $62.4$ and $62.3$ BLEU scores in the validation and test sets, with a curriculum learning fine-tuning method. By incorporating the braille recognition algorithm, this project is the first publicly available braille translation system and can benefit lots of visually impaired students and families who are preparing for the Chinese College Test and help to propel their college dreams in the future. There is a demo on our homepage\footnote{\url{https://vision-braille.com/}}.

Xianghui Xie, Bowen Wen, Yan Chang et al.

Accurate capture of human-object interaction from ubiquitous sensors like RGB cameras is important for applications in human understanding, gaming, and robot learning. However, inferring 4D interactions from a single RGB view is highly challenging due to the unknown object and human information, depth ambiguity, occlusion, and complex motion, which hinder consistent 3D and temporal reconstruction. Previous methods simplify the setup by assuming ground truth object template or constraining to a limited set of object categories. We present CARI4D, the first category-agnostic method that reconstructs spatially and temporarily consistent 4D human-object interaction at metric scale from monocular RGB videos. To this end, we propose a pose hypothesis selection algorithm that robustly integrates the individual predictions from foundation models, jointly refine them through a learned render-and-compare paradigm to ensure spatial, temporal and pixel alignment, and finally reasoning about intricate contacts for further refinement satisfying physical constraints. Experiments show that our method outperforms prior art by 38% on in-distribution dataset and 36% on unseen dataset in terms of reconstruction error. Our model generalizes beyond the training categories and thus can be applied zero-shot to in-the-wild internet videos. Our code and pretrained models will be publicly released.

Jun Liu, Ye Yuan

We prove that various stochastic gradient descent methods, including the stochastic gradient descent (SGD), stochastic heavy-ball (SHB), and stochastic Nesterov's accelerated gradient (SNAG) methods, almost surely avoid any strict saddle manifold. To the best of our knowledge, this is the first time such results are obtained for SHB and SNAG methods. Moreover, our analysis expands upon previous studies on SGD by removing the need for bounded gradients of the objective function and uniformly bounded noise. Instead, we introduce a more practical local boundedness assumption for the noisy gradient, which is naturally satisfied in empirical risk minimization problems typically seen in training of neural networks.

Dejia Xu, Ye Yuan, Morteza Mardani et al.

Given the growing need for automatic 3D content creation pipelines, various 3D representations have been studied to generate 3D objects from a single image. Due to its superior rendering efficiency, 3D Gaussian splatting-based models have recently excelled in both 3D reconstruction and generation. 3D Gaussian splatting approaches for image to 3D generation are often optimization-based, requiring many computationally expensive score-distillation steps. To overcome these challenges, we introduce an Amortized Generative 3D Gaussian framework (AGG) that instantly produces 3D Gaussians from a single image, eliminating the need for per-instance optimization. Utilizing an intermediate hybrid representation, AGG decomposes the generation of 3D Gaussian locations and other appearance attributes for joint optimization. Moreover, we propose a cascaded pipeline that first generates a coarse representation of the 3D data and later upsamples it with a 3D Gaussian super-resolution module. Our method is evaluated against existing optimization-based 3D Gaussian frameworks and sampling-based pipelines utilizing other 3D representations, where AGG showcases competitive generation abilities both qualitatively and quantitatively while being several orders of magnitude faster. Project page: https://ir1d.github.io/AGG/

Jingbo Wang, Zhengyi Luo, Ye Yuan et al.

We address the challenge of content diversity and controllability in pedestrian simulation for driving scenarios. Recent pedestrian animation frameworks have a significant limitation wherein they primarily focus on either following trajectory [46] or the content of the reference video [57], consequently overlooking the potential diversity of human motion within such scenarios. This limitation restricts the ability to generate pedestrian behaviors that exhibit a wider range of variations and realistic motions and therefore restricts its usage to provide rich motion content for other components in the driving simulation system, e.g., suddenly changed motion to which the autonomous vehicle should respond. In our approach, we strive to surpass the limitation by showcasing diverse human motions obtained from various sources, such as generated human motions, in addition to following the given trajectory. The fundamental contribution of our framework lies in combining the motion tracking task with trajectory following, which enables the tracking of specific motion parts (e.g., upper body) while simultaneously following the given trajectory by a single policy. This way, we significantly enhance both the diversity of simulated human motion within the given scenario and the controllability of the content, including language-based control. Our framework facilitates the generation of a wide range of human motions, contributing to greater realism and adaptability in pedestrian simulations for driving scenarios. More information is on our project page https://wangjingbo1219.github.io/papers/CVPR2024_PACER_PLUS/PACERPLUSPage.html .

Pengcheng Gao, Zicheng Gao, Ye Yuan

High quality spatiotemporal signal is vitally important for real application scenarios like energy management, traffic planning and cyber security. Due to the uncontrollable factors like abrupt sensors breakdown or communication fault, the spatiotemporal signal collected by sensors is always incomplete. A dynamic graph convolutional network (DGCN) is effective for processing spatiotemporal signal recovery. However, it adopts a static GCN and a sequence neural network to explore the spatial and temporal patterns, separately. Such a separated two-step processing is loose spatiotemporal, thereby failing to capture the complex inner spatiotemporal correlation. To address this issue, this paper proposes a Compact-Dynamic Graph Convolutional Network (CDGCN) for spatiotemporal signal recovery with the following two-fold ideas: a) leveraging the tensor M-product to build a unified tensor graph convolution framework, which considers both spatial and temporal patterns simultaneously; and b) constructing a differential smoothness-based objective function to reduce the noise interference in spatiotemporal signal, thereby further improve the recovery accuracy. Experiments on real-world spatiotemporal datasets demonstrate that the proposed CDGCN significantly outperforms the state-of-the-art models in terms of recovery accuracy.

Ye Yuan

Understanding and modeling human behavior is fundamental to almost any computer vision and robotics applications that involve humans. In this thesis, we take a holistic approach to human behavior modeling and tackle its three essential aspects -- simulation, perception, and generation. Throughout the thesis, we show how the three aspects are deeply connected and how utilizing and improving one aspect can greatly benefit the other aspects. We also discuss the lessons learned and our vision for what is next for human behavior modeling.

Ye Yuan, Youyuan Zhang, Can Chen et al.

Offline model-based optimization (MBO) aims to maximize a black-box objective function using only an offline dataset of designs and scores. These tasks span various domains, such as robotics, material design, and protein and molecular engineering. A common approach involves training a surrogate model using existing designs and their corresponding scores, and then generating new designs through gradient-based updates with respect to the surrogate model. This method suffers from the out-of-distribution issue, where the surrogate model may erroneously predict high scores for unseen designs. To address this challenge, we introduce a novel method, Design Editing for Offline Model-based Optimization (DEMO), which leverages a diffusion prior to calibrate overly optimized designs. DEMO first generates pseudo design candidates by performing gradient ascent with respect to a surrogate model. While these pseudo design candidates contain information beyond the offline dataset, they might be invalid or have erroneously high predicted scores. Therefore, to address this challenge while utilizing the information provided by pseudo design candidates, we propose an editing process to refine these pseudo design candidates. We introduce noise to the pseudo design candidates and subsequently denoise them with a diffusion prior trained on the offline dataset, ensuring they align with the distribution of valid designs. Empirical evaluations on seven offline MBO tasks show that, with properly tuned hyperparameters, DEMOs score is competitive with the best previously reported scores in the literature.

Chengwu Liu, Ye Yuan, Yichun Yin et al.

Chain-of-Thought (CoT) prompting has become the de facto method to elicit reasoning capabilities from large language models (LLMs). However, to mitigate hallucinations in CoT that are notoriously difficult to detect, current methods such as process reward models (PRMs) or self-consistency operate as opaque boxes and do not provide checkable evidence for their judgments, possibly limiting their effectiveness. To address this issue, we draw inspiration from the idea that "the gold standard for supporting a mathematical claim is to provide a proof". We propose a retrospective, step-aware formal verification framework $Safe$. Rather than assigning arbitrary scores, we strive to articulate mathematical claims in formal mathematical language Lean 4 at each reasoning step and provide formal proofs to identify hallucinations. We evaluate our framework $Safe$ across multiple language models and various mathematical datasets, demonstrating a significant performance improvement while offering interpretable and verifiable evidence. We also propose $FormalStep$ as a benchmark for step correctness theorem proving with $30,809$ formal statements. To the best of our knowledge, our work represents the first endeavor to utilize formal mathematical language Lean 4 for verifying natural language content generated by LLMs, aligning with the reason why formal mathematical languages were created in the first place: to provide a robust foundation for hallucination-prone human-written proofs.

Jiefeng Li, Jinkun Cao, Haotian Zhang et al.

Human motion modeling traditionally separates motion generation and estimation into distinct tasks with specialized models. Motion generation models focus on creating diverse, realistic motions from inputs like text, audio, or keyframes, while motion estimation models aim to reconstruct accurate motion trajectories from observations like videos. Despite sharing underlying representations of temporal dynamics and kinematics, this separation limits knowledge transfer between tasks and requires maintaining separate models. We present GENMO, a unified Generalist Model for Human Motion that bridges motion estimation and generation in a single framework. Our key insight is to reformulate motion estimation as constrained motion generation, where the output motion must precisely satisfy observed conditioning signals. Leveraging the synergy between regression and diffusion, GENMO achieves accurate global motion estimation while enabling diverse motion generation. We also introduce an estimation-guided training objective that exploits in-the-wild videos with 2D annotations and text descriptions to enhance generative diversity. Furthermore, our novel architecture handles variable-length motions and mixed multimodal conditions (text, audio, video) at different time intervals, offering flexible control. This unified approach creates synergistic benefits: generative priors improve estimated motions under challenging conditions like occlusions, while diverse video data enhances generation capabilities. Extensive experiments demonstrate GENMO's effectiveness as a generalist framework that successfully handles multiple human motion tasks within a single model.

Zhengyi Luo, Chen Tessler, Toru Lin et al.

Human behavior is fundamentally shaped by visual perception -- our ability to interact with the world depends on actively gathering relevant information and adapting our movements accordingly. Behaviors like searching for objects, reaching, and hand-eye coordination naturally emerge from the structure of our sensory system. Inspired by these principles, we introduce Perceptive Dexterous Control (PDC), a framework for vision-driven dexterous whole-body control with simulated humanoids. PDC operates solely on egocentric vision for task specification, enabling object search, target placement, and skill selection through visual cues, without relying on privileged state information (e.g., 3D object positions and geometries). This perception-as-interface paradigm enables learning a single policy to perform multiple household tasks, including reaching, grasping, placing, and articulated object manipulation. We also show that training from scratch with reinforcement learning can produce emergent behaviors such as active search. These results demonstrate how vision-driven control and complex tasks induce human-like behaviors and can serve as the key ingredients in closing the perception-action loop for animation, robotics, and embodied AI.

Xingxing Hong, Yungong Wang, Dexin Jin et al.

Benchmarks are crucial for assessing multi-agent reinforcement learning (MARL) algorithms. While StarCraft II-related environments have driven significant advances in MARL, existing benchmarks like SMAC focus primarily on micromanagement, limiting comprehensive evaluation of high-level strategic intelligence. To address this, we introduce HLSMAC, a new cooperative MARL benchmark with 12 carefully designed StarCraft II scenarios based on classical stratagems from the Thirty-Six Stratagems. Each scenario corresponds to a specific stratagem and is designed to challenge agents with diverse strategic elements, including tactical maneuvering, timing coordination, and deception, thereby opening up avenues for evaluating high-level strategic decision-making capabilities. We also propose novel metrics across multiple dimensions beyond conventional win rate, such as ability utilization and advancement efficiency, to assess agents' overall performance within the HLSMAC environment. We integrate state-of-the-art MARL algorithms and LLM-based agents with our benchmark and conduct comprehensive experiments. The results demonstrate that HLSMAC serves as a robust testbed for advancing multi-agent strategic decision-making.

Marcel C. Bühler, Ye Yuan, Xueting Li et al.

We introduce Dream, Lift, Animate (DLA), a novel framework that reconstructs animatable 3D human avatars from a single image. This is achieved by leveraging multi-view generation, 3D Gaussian lifting, and pose-aware UV-space mapping of 3D Gaussians. Given an image, we first dream plausible multi-views using a video diffusion model, capturing rich geometric and appearance details. These views are then lifted into unstructured 3D Gaussians. To enable animation, we propose a transformer-based encoder that models global spatial relationships and projects these Gaussians into a structured latent representation aligned with the UV space of a parametric body model. This latent code is decoded into UV-space Gaussians that can be animated via body-driven deformation and rendered conditioned on pose and viewpoint. By anchoring Gaussians to the UV manifold, our method ensures consistency during animation while preserving fine visual details. DLA enables real-time rendering and intuitive editing without requiring post-processing. Our method outperforms state-of-the-art approaches on the ActorsHQ and 4D-Dress datasets in both perceptual quality and photometric accuracy. By combining the generative strengths of video diffusion models with a pose-aware UV-space Gaussian mapping, DLA bridges the gap between unstructured 3D representations and high-fidelity, animation-ready avatars.

Ye Yuan, Guangxiao Yuan, Renfang Wang et al.

High-Dimensional and Incomplete (HDI) data are frequently found in various industrial applications with complex interactions among numerous nodes, which are commonly non-negative for representing the inherent non-negativity of node interactions. A Non-negative Latent Factor (NLF) model is able to extract intrinsic features from such data efficiently. However, existing NLF models all adopt a static divergence metric like Euclidean distance or α-\b{eta} divergence to build its learning objective, which greatly restricts its scalability of accurately representing HDI data from different domains. Aiming at addressing this issue, this study presents an Adaptive Divergence-based Non-negative Latent Factor (ADNLF) model with three-fold ideas: a) generalizing the objective function with the α-\b{eta}-divergence to expand its potential of representing various HDI data; b) adopting a non-negative bridging function to connect the optimization variables with output latent factors for fulfilling the non-negativity constraints constantly; and c) making the divergence parameters adaptive through particle swarm optimization, thereby facilitating adaptive divergence in the learning objective to achieve high scalability. Empirical studies are conducted on four HDI datasets from real applications, whose results demonstrate that in comparison with state-of-the-art NLF models, an ADNLF model achieves significantly higher estimation accuracy for missing data of an HDI dataset with high computational efficiency.

Jun Liu, Ye Yuan

The vast majority of convergence rates analysis for stochastic gradient methods in the literature focus on convergence in expectation, whereas trajectory-wise almost sure convergence is clearly important to ensure that any instantiation of the stochastic algorithms would converge with probability one. Here we provide a unified almost sure convergence rates analysis for stochastic gradient descent (SGD), stochastic heavy-ball (SHB), and stochastic Nesterov's accelerated gradient (SNAG) methods. We show, for the first time, that the almost sure convergence rates obtained for these stochastic gradient methods on strongly convex functions, are arbitrarily close to their optimal convergence rates possible. For non-convex objective functions, we not only show that a weighted average of the squared gradient norms converges to zero almost surely, but also the last iterates of the algorithms. We further provide last-iterate almost sure convergence rates analysis for stochastic gradient methods on weakly convex smooth functions, in contrast with most existing results in the literature that only provide convergence in expectation for a weighted average of the iterates.

Kai Zheng, Yuanjiang Wang, Ye Yuan

While self-supervised representation learning (SSL) has proved to be effective in the large model, there is still a huge gap between the SSL and supervised method in the lightweight model when following the same solution. We delve into this problem and find that the lightweight model is prone to collapse in semantic space when simply performing instance-wise contrast. To address this issue, we propose a relation-wise contrastive paradigm with Relation Knowledge Distillation (ReKD). We introduce a heterogeneous teacher to explicitly mine the semantic information and transferring a novel relation knowledge to the student (lightweight model). The theoretical analysis supports our main concern about instance-wise contrast and verify the effectiveness of our relation-wise contrastive learning. Extensive experimental results also demonstrate that our method achieves significant improvements on multiple lightweight models. Particularly, the linear evaluation on AlexNet obviously improves the current state-of-art from 44.7% to 50.1%, which is the first work to get close to the supervised 50.5%. Code will be made available.

Handong Ma, Changsheng Li, Xinchu Shi et al.

Recently deep learning has been successfully applied to unsupervised active learning. However, current method attempts to learn a nonlinear transformation via an auto-encoder while ignoring the sample relation, leaving huge room to design more effective representation learning mechanisms for unsupervised active learning. In this paper, we propose a novel deep unsupervised Active Learning model via Learnable Graphs, named ALLG. ALLG benefits from learning optimal graph structures to acquire better sample representation and select representative samples. To make the learnt graph structure more stable and effective, we take into account $k$-nearest neighbor graph as a priori, and learn a relation propagation graph structure. We also incorporate shortcut connections among different layers, which can alleviate the well-known over-smoothing problem to some extent. To the best of our knowledge, this is the first attempt to leverage graph structure learning for unsupervised active learning. Extensive experiments performed on six datasets demonstrate the efficacy of our method.

Lei Gan, Huabin Huang, Banghuai Li et al.

Image segmentation in the urban scene has recently attracted much attention due to its success in autonomous driving systems. However, the poor performance of concerned foreground targets, e.g., traffic lights and poles, still limits its further practical applications. In urban scenes, foreground targets are always concealed in their surrounding stuff because of the special camera position and 3D perspective projection. What's worse, it exacerbates the unbalance between foreground and background classes in high-level features due to the continuous expansion of the reception field. We call it Feature Camouflage. In this paper, we present a novel add-on module, named Feature Balance Network (FBNet), to eliminate the feature camouflage in urban-scene segmentation. FBNet consists of two key components, i.e., Block-wise BCE(BwBCE) and Dual Feature Modulator(DFM). BwBCE serves as an auxiliary loss to ensure uniform gradients for foreground classes and their surroundings during backpropagation. At the same time, DFM intends to enhance the deep representation of foreground classes in high-level features adaptively under the supervision of BwBCE. These two modules facilitate each other as a whole to ease feature camouflage effectively. Our proposed method achieves a new state-of-the-art segmentation performance on two challenging urban-scene benchmarks, i.e., Cityscapes and BDD100K. Code will be released for reproduction.

Bowen Yu, Ye Yuan, Loren Terveen et al.

Artificial intelligence algorithms have been used to enhance a wide variety of products and services, including assisting human decision making in high-stakes contexts. However, these algorithms are complex and have trade-offs, notably between prediction accuracy and fairness to population subgroups. This makes it hard for designers to understand algorithms and design products or services in a way that respects users' goals, values, and needs. We proposed a method to help designers and users explore algorithms, visualize their trade-offs, and select algorithms with trade-offs consistent with their goals and needs. We evaluated our method on the problem of predicting criminal defendants' likelihood to re-offend through (i) a large-scale Amazon Mechanical Turk experiment, and (ii) in-depth interviews with domain experts. Our evaluations show that our method can help designers and users of these systems better understand and navigate algorithmic trade-offs. This paper contributes a new way of providing designers the ability to understand and control the outcomes of algorithmic systems they are creating.