arXiv subjects

Yifei Li

Publications and source records attributed to Yifei Li.

At least 109 records · Page 6Linked to original sources

arXiv2024

NeuralFluid: Neural Fluidic System Design and Control with Differentiable Simulation

We present a novel framework to explore neural control and design of complex fluidic systems with dynamic solid boundaries. Our system features a fast differentiable Navier-Stokes solver with solid-fluid interface handling, a low-dimensional differentiable parametric geometry representation, a control-shape co-design algorithm, and gym-like simulation environments to facilitate various fluidic control design applications. Additionally, we present a benchmark of design, control, and learning tasks on high-fidelity, high-resolution dynamic fluid environments that pose challenges for existing differentiable fluid simulators. These tasks include designing the control of artificial hearts, identifying robotic end-effector shapes, and controlling a fluid gate. By seamlessly incorporating our differentiable fluid simulator into a learning framework, we demonstrate successful design, control, and learning results that surpass gradient-free solutions in these benchmark tasks.

physics.flu-dyn↗

arXiv2024

Few-shot Open Relation Extraction with Gaussian Prototype and Adaptive Margin

Few-shot relation extraction with none-of-the-above (FsRE with NOTA) aims at predicting labels in few-shot scenarios with unknown classes. FsRE with NOTA is more challenging than the conventional few-shot relation extraction task, since the boundaries of unknown classes are complex and difficult to learn. Meta-learning based methods, especially prototype-based methods, are the mainstream solutions to this task. They obtain the classification boundary by learning the sample distribution of each class. However, their performance is limited because few-shot overfitting and NOTA boundary confusion lead to misclassification between known and unknown classes. To this end, we propose a novel framework based on Gaussian prototype and adaptive margin named GPAM for FsRE with NOTA, which includes three modules, semi-factual representation, GMM-prototype metric learning and decision boundary learning. The first two modules obtain better representations to solve the few-shot problem through debiased information enhancement and Gaussian space distance measurement. The third module learns more accurate classification boundaries and prototypes through adaptive margin and negative sampling. In the training procedure of GPAM, we use contrastive learning loss to comprehensively consider the effects of range and margin on the classification of known and unknown classes to ensure the model's stability and robustness. Sufficient experiments and ablations on the FewRel dataset show that GPAM surpasses previous prototype methods and achieves state-of-the-art performance.

cs.CV↗

arXiv2024

A structure-preserving parametric finite element method for solid-state dewetting on curved substrates

We consider a two-dimensional sharp-interface model for solid-state dewetting of thin films with anisotropic surface energies on curved substrates, where the film/vapor interface and substrate surface are represented by an evolving and a static curve, respectively. The model is governed by the anisotropic surface diffusion for the evolving curve, with appropriate boundary conditions at the contact points where the two curves meet. The continuum model obeys an energy decay law and preserves the enclosed area between the two curves. We introduce an arclength parameterization for the substrate curve, which plays a crucial role in a structure-preserving approximation as it straightens the curved substrate and tracks length changes between contact points. Based on this insight, we introduce a symmetrized weak formulation which leads to an unconditional energy stable parametric approximation in terms of the discrete energy. We also provide an error estimate of the enclosed area, which depends on the substrate profile and can be zero in the case of a flat substrate. Furthermore, we introduce a correction to the discrete normals to enable an exact area preservation for general curved substrates. The resulting nonlinear system is efficiently solved using a hybrid iterative algorithm which combines both Picard and Newton's methods. Numerical results are presented to show the robustness and good properties of the introduced method for simulating solid-state dewetting on various curved substrates.

math.NA↗

arXiv2024

A unified structure-preserving parametric finite element method for anisotropic surface diffusion

We propose and analyze a unified structure-preserving parametric finite element method (SP-PFEM) for the anisotropic surface diffusion of curves in two dimensions $(d=2)$ and surfaces in three dimensions $(d=3)$ with an arbitrary anisotropic surface energy density $γ(\boldsymbol{n})$, where $\boldsymbol{n}\in \mathbb{S}^{d-1}$ represents the outward unit vector. By introducing a novel unified surface energy matrix $\boldsymbol{G}_k(\boldsymbol{n})$ depending on $γ(\boldsymbol{n})$, the Cahn--Hoffman $\boldsymbolξ$-vector and a stabilizing function $k(\boldsymbol{n}):\ \mathbb{S}^{d-1}\to {\mathbb R}$, we obtain a unified and conservative variational formulation for the anisotropic surface diffusion via different surface differential operators including the surface gradient operator, the surface divergence operator and the surface Laplace--Beltrami operator. A SP-PFEM discretization is presented for the variational problem. In order to establish the unconditional energy stability of the proposed SP-PFEM under a very mild condition on $γ(\boldsymbol{n})$, we propose a new framework via {\sl local energy estimate} for proving energy stability/structure-preserving properties of the parametric finite element method for the anisotropic surface diffusion. This framework sheds light on how to prove unconditional energy stability of other numerical methods for geometric partial differential equations. Extensive numerical results are reported to demonstrate the efficiency and accuracy as well as structure-preserving properties of the proposed SP-PFEM for the anisotropic surface diffusion with arbitrary anisotropic surface energy density $γ(\boldsymbol{n})$ arising from different applications.

math.NA↗

arXiv2024

Enhancing Human-Robot Collaborative Assembly in Manufacturing Systems Using Large Language Models

The development of human-robot collaboration has the ability to improve manufacturing system performance by leveraging the unique strengths of both humans and robots. On the shop floor, human operators contribute with their adaptability and flexibility in dynamic situations, while robots provide precision and the ability to perform repetitive tasks. However, the communication gap between human operators and robots limits the collaboration and coordination of human-robot teams in manufacturing systems. Our research presents a human-robot collaborative assembly framework that utilizes a large language model for enhancing communication in manufacturing environments. The framework facilitates human-robot communication by integrating voice commands through natural language for task management. A case study for an assembly task demonstrates the framework's ability to process natural language inputs and address real-time assembly challenges, emphasizing adaptability to language variation and efficiency in error resolution. The results suggest that large language models have the potential to improve human-robot interaction for collaborative manufacturing assembly applications.

cs.RO↗

arXiv2024

Learning Physical Simulation with Message Passing Transformer

Machine learning methods for physical simulation have achieved significant success in recent years. We propose a new universal architecture based on Graph Neural Network, the Message Passing Transformer, which incorporates a Message Passing framework, employs an Encoder-Processor-Decoder structure, and applies Graph Fourier Loss as loss function for model optimization. To take advantage of the past message passing state information, we propose Hadamard-Product Attention to update the node attribute in the Processor, Hadamard-Product Attention is a variant of Dot-Product Attention that focuses on more fine-grained semantics and emphasizes on assigning attention weights over each feature dimension rather than each position in the sequence relative to others. We further introduce Graph Fourier Loss (GFL) to balance high-energy and low-energy components. To improve time performance, we precompute the graph's Laplacian eigenvectors before the training process. Our architecture achieves significant accuracy improvements in long-term rollouts for both Lagrangian and Eulerian dynamical systems over current methods.

cs.LG↗

arXiv2024

An Autonomous Driving Model Integrated with BEV-V2X Perception, Fusion Prediction of Motion and Occupancy, and Driving Planning, in Complex Traffic Intersections

The comprehensiveness of vehicle-to-everything (V2X) recognition enriches and holistically shapes the global Birds-Eye-View (BEV) perception, incorporating rich semantics and integrating driving scene information, thereby serving features of vehicle state prediction, decision-making and driving planning. Utilizing V2X message sets to form BEV map proves to be an effective perception method for connected and automated vehicles (CAVs). Specifically, Map Msg. (MAP), Signal Phase And Timing (SPAT) and Roadside Information (RSI) contributes to the achievement of road connectivity, synchronized traffic signal navigation and obstacle warning. Moreover, harnessing time-sequential Basic Safety Msg. (BSM) data from multiple vehicles allows for the real-time perception and future state prediction. Therefore, this paper develops a comprehensive autonomous driving model that relies on BEV-V2X perception, Interacting Multiple model Unscented Kalman Filter (IMM-UKF)-based fusion prediction, and deep reinforcement learning (DRL)-based decision making and planning. We integrated them into a DRL environment to develop an optimal set of unified driving behaviors that encompass obstacle avoidance, lane changes, overtaking, turning maneuver, and synchronized traffic signal navigation. Consequently, a complex traffic intersection scenario was simulated, and the well-trained model was applied for driving planning. The observed driving behavior closely resembled that of an experienced driver, exhibiting anticipatory actions and revealing notable operational highlights of driving policy.

cs.RO↗

arXiv2024

A Mobile Additive Manufacturing Robot Framework for Smart Manufacturing Systems

Recent technological innovations in the areas of additive manufacturing and collaborative robotics have paved the way toward realizing the concept of on-demand, personalized production on the shop floor. Additive manufacturing process can provide the capability of printing highly customized parts based on various customer requirements. Autonomous, mobile systems provide the flexibility to move custom parts around the shop floor to various manufacturing operations, as needed by product requirements. In this work, we proposed a mobile additive manufacturing robot framework for merging an additive manufacturing process system with an autonomous mobile base. Two case studies showcase the potential benefits of the proposed mobile additive manufacturing framework. The first case study overviews the effect that a mobile system can have on a fused deposition modeling process. The second case study showcases how integrating a mobile additive manufacturing machine can improve the throughput of the manufacturing system. The major findings of this study are that the proposed mobile robotic AM has increased throughput by taking advantage of the travel time between operations/processing sites. It is particularly suited to perform intermittent operations (e.g., preparing feedstock) during the travel time of the robotic AM. One major implication of this study is its application in manufacturing structural components (e.g., concrete construction, and feedstock preparation during reconnaissance missions) in remote or extreme terrains with on-site or on-demand feedstocks.

cs.RO↗

arXiv2024

TableLlama: Towards Open Large Generalist Models for Tables

Semi-structured tables are ubiquitous. There has been a variety of tasks that aim to automatically interpret, augment, and query tables. Current methods often require pretraining on tables or special model architecture design, are restricted to specific table types, or have simplifying assumptions about tables and tasks. This paper makes the first step towards developing open-source large language models (LLMs) as generalists for a diversity of table-based tasks. Towards that end, we construct TableInstruct, a new dataset with a variety of realistic tables and tasks, for instruction tuning and evaluating LLMs. We further develop the first open-source generalist model for tables, TableLlama, by fine-tuning Llama 2 (7B) with LongLoRA to address the long context challenge. We experiment under both in-domain setting and out-of-domain setting. On 7 out of 8 in-domain tasks, TableLlama achieves comparable or better performance than the SOTA for each task, despite the latter often has task-specific design. On 6 out-of-domain datasets, it achieves 5-44 absolute point gains compared with the base model, showing that training on TableInstruct enhances the model's generalizability. We open-source our dataset and trained model to boost future work on developing open generalist models for tables.

cs.CL↗

arXiv2024

A Stabilized Parametric Finite Element Method for Surface Diffusion with an Arbitrary Surface Energy

We proposed a structure-preserving stabilized parametric finite element method (SPFEM) for the evolution of closed curves under anisotropic surface diffusion with an arbitrary surface energy $\hatγ(θ)$. By introducing a non-negative stabilizing function $k(θ)$ depending on $\hatγ(θ)$, we obtained a novel stabilized conservative weak formulation for the anisotropic surface diffusion. A SPFEM is presented for the discretization of this weak formulation. We construct a comprehensive framework to analyze and prove the unconditional energy stability of the SPFEM under a very mild condition on $\hatγ(θ)$. This method can be applied to simulate solid-state dewetting of thin films with arbitrary surface energies, which are characterized by anisotropic surface diffusion and contact line migration. Extensive numerical results are reported to demonstrate the efficiency, accuracy and structure-preserving properties of the proposed SPFEM with anisotropic surface energies $\hatγ(θ)$ arising from different applications.

math.NA↗

arXiv2024

DiffAvatar: Simulation-Ready Garment Optimization with Differentiable Simulation

The realism of digital avatars is crucial in enabling telepresence applications with self-expression and customization. While physical simulations can produce realistic motions for clothed humans, they require high-quality garment assets with associated physical parameters for cloth simulations. However, manually creating these assets and calibrating their parameters is labor-intensive and requires specialized expertise. Current methods focus on reconstructing geometry, but don't generate complete assets for physics-based applications. To address this gap, we propose \papername,~a novel approach that performs body and garment co-optimization using differentiable simulation. By integrating physical simulation into the optimization loop and accounting for the complex nonlinear behavior of cloth and its intricate interaction with the body, our framework recovers body and garment geometry and extracts important material parameters in a physically plausible way. Our experiments demonstrate that our approach generates realistic clothing and body shape suitable for downstream applications. We provide additional insights and results on our webpage: https://people.csail.mit.edu/liyifei/publication/diffavatar/

cs.CV↗

arXiv2024

UniFaaS: Programming across Distributed Cyberinfrastructure with Federated Function Serving

Modern scientific applications are increasingly decomposable into individual functions that may be deployed across distributed and diverse cyberinfrastructure such as supercomputers, clouds, and accelerators. Such applications call for new approaches to programming, distributed execution, and function-level management. We present UniFaaS, a parallel programming framework that relies on a federated function-as-a-service (FaaS) model to enable composition of distributed, scalable, and high-performance scientific workflows, and to support fine-grained function-level management. UniFaaS provides a unified programming interface to compose dynamic task graphs with transparent wide-area data management. UniFaaS exploits an observe-predict-decide approach to efficiently map workflow tasks to target heterogeneous and dynamic resources. We propose a dynamic heterogeneity-aware scheduling algorithm that employs a delay mechanism and a re-scheduling mechanism to accommodate dynamic resource capacity. Our experiments show that UniFaaS can efficiently execute workflows across computing resources with minimal scheduling overhead. We show that UniFaaS can improve the performance of a real-world drug screening workflow by as much as 22.99% when employing an additional 19.48% of resources and a montage workflow by 54.41% when employing an additional 47.83% of resources across multiple distributed clusters, in contrast to using a single cluster

cs.DC↗

arXiv2024

Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs

Empowering large language models to accurately express confidence in their answers is essential for trustworthy decision-making. Previous confidence elicitation methods, which primarily rely on white-box access to internal model information or model fine-tuning, have become less suitable for LLMs, especially closed-source commercial APIs. This leads to a growing need to explore the untapped area of black-box approaches for LLM uncertainty estimation. To better break down the problem, we define a systematic framework with three components: prompting strategies for eliciting verbalized confidence, sampling methods for generating multiple responses, and aggregation techniques for computing consistency. We then benchmark these methods on two key tasks-confidence calibration and failure prediction-across five types of datasets (e.g., commonsense and arithmetic reasoning) and five widely-used LLMs including GPT-4 and LLaMA 2 Chat. Our analysis uncovers several key insights: 1) LLMs, when verbalizing their confidence, tend to be overconfident, potentially imitating human patterns of expressing confidence. 2) As model capability scales up, both calibration and failure prediction performance improve. 3) Employing our proposed strategies, such as human-inspired prompts, consistency among multiple responses, and better aggregation strategies can help mitigate this overconfidence from various perspectives. 4) Comparisons with white-box methods indicate that while white-box methods perform better, the gap is narrow, e.g., 0.522 to 0.605 in AUROC. Despite these advancements, none of these techniques consistently outperform others, and all investigated methods struggle in challenging tasks, such as those requiring professional knowledge, indicating significant scope for improvement. We believe this study can serve as a strong baseline and provide insights for eliciting confidence in black-box LLMs.

cs.CL↗

arXiv2024

Resolution-Agnostic Neural Compression for High-Fidelity Portrait Video Conferencing via Implicit Radiance Fields

Video conferencing has caught much more attention recently. High fidelity and low bandwidth are two major objectives of video compression for video conferencing applications. Most pioneering methods rely on classic video compression codec without high-level feature embedding and thus can not reach the extremely low bandwidth. Recent works instead employ model-based neural compression to acquire ultra-low bitrates using sparse representations of each frame such as facial landmark information, while these approaches can not maintain high fidelity due to 2D image-based warping. In this paper, we propose a novel low bandwidth neural compression approach for high-fidelity portrait video conferencing using implicit radiance fields to achieve both major objectives. We leverage dynamic neural radiance fields to reconstruct high-fidelity talking head with expression features, which are represented as frame substitution for transmission. The overall system employs deep model to encode expression features at the sender and reconstruct portrait at the receiver with volume rendering as decoder for ultra-low bandwidth. In particular, with the characteristic of neural radiance fields based model, our compression approach is resolution-agnostic, which means that the low bandwidth achieved by our approach is independent of video resolution, while maintaining fidelity for higher resolution reconstruction. Experimental results demonstrate that our novel framework can (1) construct ultra-low bandwidth video conferencing, (2) maintain high fidelity portrait and (3) have better performance on high-resolution video compression than previous works.

cs.CV↗

arXiv2024

AttributionBench: How Hard is Automatic Attribution Evaluation?

Modern generative search engines enhance the reliability of large language model (LLM) responses by providing cited evidence. However, evaluating the answer's attribution, i.e., whether every claim within the generated responses is fully supported by its cited evidence, remains an open problem. This verification, traditionally dependent on costly human evaluation, underscores the urgent need for automatic attribution evaluation methods. To bridge the gap in the absence of standardized benchmarks for these methods, we present AttributionBench, a comprehensive benchmark compiled from various existing attribution datasets. Our extensive experiments on AttributionBench reveal the challenges of automatic attribution evaluation, even for state-of-the-art LLMs. Specifically, our findings show that even a fine-tuned GPT-3.5 only achieves around 80% macro-F1 under a binary classification formulation. A detailed analysis of more than 300 error cases indicates that a majority of failures stem from the model's inability to process nuanced information, and the discrepancy between the information the model has access to and that human annotators do.

cs.CL↗

arXiv2024

Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations

In this paper, we present an innovative process-oriented math process reward model called \textbf{Math-Shepherd}, which assigns a reward score to each step of math problem solutions. The training of Math-Shepherd is achieved using automatically constructed process-wise supervision data, breaking the bottleneck of heavy reliance on manual annotation in existing work. We explore the effectiveness of Math-Shepherd in two scenarios: 1) \textit{Verification}: Math-Shepherd is utilized for reranking multiple outputs generated by Large Language Models (LLMs); 2) \textit{Reinforcement Learning}: Math-Shepherd is employed to reinforce LLMs with step-by-step Proximal Policy Optimization (PPO). With Math-Shepherd, a series of open-source LLMs demonstrates exceptional performance. For instance, the step-by-step PPO with Math-Shepherd significantly improves the accuracy of Mistral-7B (77.9\%$\to$84.1\% on GSM8K and 28.6\%$\to$33.0\% on MATH). The accuracy can be further enhanced to 89.1\% and 43.5\% on GSM8K and MATH with the verification of Math-Shepherd, respectively. We believe that automatic process supervision holds significant potential for the future evolution of LLMs.

cs.AI↗

arXiv2024

Flows: Building Blocks of Reasoning and Collaborating AI

Recent advances in artificial intelligence (AI) have produced highly capable and controllable systems. This creates unprecedented opportunities for structured reasoning as well as collaboration among multiple AI systems and humans. To fully realize this potential, it is essential to develop a principled way of designing and studying such structured interactions. For this purpose, we introduce the conceptual framework Flows. Flows are self-contained building blocks of computation, with an isolated state, communicating through a standardized message-based interface. This modular design simplifies the process of creating Flows by allowing them to be recursively composed into arbitrarily nested interactions and is inherently concurrency-friendly. Crucially, any interaction can be implemented using this framework, including prior work on AI-AI and human-AI interactions, prompt engineering schemes, and tool augmentation. We demonstrate the potential of Flows on competitive coding, a challenging task on which even GPT-4 struggles. Our results suggest that structured reasoning and collaboration substantially improve generalization, with AI-only Flows adding +21 and human-AI Flows adding +54 absolute points in terms of solve rate. To support rapid and rigorous research, we introduce the aiFlows library embodying Flows. The aiFlows library is available at https://github.com/epfl-dlab/aiflows. Data and Flows for reproducing our experiments are available at https://github.com/epfl-dlab/cc_flows.

cs.AI↗

arXiv2024

An energy-stable parametric finite element method for the planar Willmore flow

We propose an energy-stable parametric finite element method (PFEM) for the planar Willmore flow and establish its unconditional energy stability of the full discretization scheme. The key lies in the introduction of two novel geometric identities to describe the planar Willmore flow: the first one involves the coupling of the outward unit normal vector $\boldsymbol{n}$ and the normal velocity $V$, and the second one concerns the time derivative of the mean curvature $κ$. Based on them, we derive a set of new geometric partial differential equations for the planar Willmore flow, leading to our new fully-discretized and unconditionally energy-stable PFEM. Our stability analysis is also based on the two new geometric identities. Extensive numerical experiments are provided to illustrate its efficiency and validate its unconditional energy stability.

math.NA↗