Searcharxiv⌕ Search

arXiv subjects

Fei Liu

Publications and source records attributed to Fei Liu.

At least 181 records · Page 10Linked to original sources
arXiv2024

Can Large Language Models do Analytical Reasoning?

This paper explores the cutting-edge Large Language Model with analytical reasoning on sports. Our analytical reasoning embodies the tasks of letting large language models count how many points each team scores in a quarter in the NBA and NFL games. Our major discoveries are in two folds. Firstly, we find among all the models we employed, GPT-4 stands out in effectiveness, followed by Claude-2.1, with GPT-3.5, Gemini-Pro, and Llama-2-70b lagging behind. Specifically, we compare three different prompting techniques and a divide-and-conquer approach, we find that the latter was the most effective. Our divide-and-conquer approach breaks down play-by-play data into smaller, more manageable segments, solves each piece individually, and then aggregates them together. Besides the divide-and-conquer approach, we also explore the Chain of Thought (CoT) strategy, which markedly improves outcomes for certain models, notably GPT-4 and Claude-2.1, with their accuracy rates increasing significantly. However, the CoT strategy has negligible or even detrimental effects on the performance of other models like GPT-3.5 and Gemini-Pro. Secondly, to our surprise, we observe that most models, including GPT-4, struggle to accurately count the total scores for NBA quarters despite showing strong performance in counting NFL quarter scores. This leads us to further investigate the factors that impact the complexity of analytical reasoning tasks with extensive experiments, through which we conclude that task complexity depends on the length of context, the information density, and the presence of related information. Our research provides valuable insights into the complexity of analytical reasoning tasks and potential directions for developing future large language models.

cs.CL↗
arXiv2024

Purity and quasi-split torsors over Prüfer bases

We establish an analogue of the Zariski--Nagata purity theorem for finite étale covers on smooth schemes over Prüfer rings by demonstrating Auslander's flatness criterion in this non-Noetherian context. We derive an Auslander--Buchsbaum formula for general local rings, which provides a useful tool for studying the algebraic structures involved in our work. Through analysis of reflexive sheaves, we prove various purity theorems for torsors under certain group algebraic spaces, such as the reductive ones. Specifically, using results from EGAIV4 on parafactoriality on smooth schemes over normal bases, we prove the purity for cohomology groups of multiplicative type groups at this level of generality. Subsequently, we leverage the aforementioned purity results to resolve the Grothendieck--Serre conjecture for torsors under a quasi-split reductive group scheme over schemes smooth over Prüfer rings. Along the way, we also prove a version of the Nisnevich purity conjecture for quasi-split reductive group schemes in our Prüferian context, inspired by the recent work of Cesnavicius.

math.AG↗
arXiv2024

Simulated Data Generation Through Algorithmic Force Coefficient Estimation for AI-Based Robotic Projectile Launch Modeling

Modeling of non-rigid object launching and manipulation is complex considering the wide range of dynamics affecting trajectory, many of which may be unknown. Using physics models can be inaccurate because they cannot account for unknown factors and the effects of the deformation of the object as it is launched; moreover, deriving force coefficients for these models is not possible without extensive experimental testing. Recently, advancements in data-powered artificial intelligence methods have allowed learnable models and systems to emerge. It is desirable to train a model for launch prediction on a robot, as deep neural networks can account for immeasurable dynamics. However, the inability to collect large amounts of experimental data decreases performance of deep neural networks. Through estimating force coefficients, the accepted physics models can be leveraged to produce adequate supplemental data to artificially increase the size of the training set, yielding improved neural networks. In this paper, we introduce a new framework for algorithmic estimation of force coefficients for non-rigid object launching, which can be generalized to other domains, in order to generate large datasets. We implement a novel training algorithm and objective for our deep neural network to accurately model launch trajectory of non-rigid objects and predict whether they will hit a series of targets. Our experimental results demonstrate the effectiveness of using simulated data from force coefficient estimation and shows the importance of simulated data for training an effective neural network.

cs.RO↗
arXiv2024

Computing in the Era of Large Generative Models: From Cloud-Native to AI-Native

In this paper, we investigate the intersection of large generative AI models and cloud-native computing architectures. Recent large models such as ChatGPT, while revolutionary in their capabilities, face challenges like escalating costs and demand for high-end GPUs. Drawing analogies between large-model-as-a-service (LMaaS) and cloud database-as-a-service (DBaaS), we describe an AI-native computing paradigm that harnesses the power of both cloud-native technologies (e.g., multi-tenancy and serverless computing) and advanced machine learning runtime (e.g., batched LoRA inference). These joint efforts aim to optimize costs-of-goods-sold (COGS) and improve resource accessibility. The journey of merging these two domains is just at the beginning and we hope to stimulate future research and development in this area.

cs.DC↗
arXiv2024

Neural Combinatorial Optimization with Heavy Decoder: Toward Large Scale Generalization

Neural combinatorial optimization (NCO) is a promising learning-based approach for solving challenging combinatorial optimization problems without specialized algorithm design by experts. However, most constructive NCO methods cannot solve problems with large-scale instance sizes, which significantly diminishes their usefulness for real-world applications. In this work, we propose a novel Light Encoder and Heavy Decoder (LEHD) model with a strong generalization ability to address this critical issue. The LEHD model can learn to dynamically capture the relationships between all available nodes of varying sizes, which is beneficial for model generalization to problems of various scales. Moreover, we develop a data-efficient training scheme and a flexible solution construction mechanism for the proposed LEHD model. By training on small-scale problem instances, the LEHD model can generate nearly optimal solutions for the Travelling Salesman Problem (TSP) and the Capacitated Vehicle Routing Problem (CVRP) with up to 1000 nodes, and also generalizes well to solve real-world TSPLib and CVRPLib problems. These results confirm our proposed LEHD model can significantly improve the state-of-the-art performance for constructive NCO. The code is available at https://github.com/CIAM-Group/NCO_code/tree/main/single_objective/LEHD.

cs.LG↗
arXiv2024

InFoBench: Evaluating Instruction Following Ability in Large Language Models

This paper introduces the Decomposed Requirements Following Ratio (DRFR), a new metric for evaluating Large Language Models' (LLMs) ability to follow instructions. Addressing a gap in current methodologies, DRFR breaks down complex instructions into simpler criteria, facilitating a detailed analysis of LLMs' compliance with various aspects of tasks. Alongside this metric, we present InFoBench, a benchmark comprising 500 diverse instructions and 2,250 decomposed questions across multiple constraint categories. Our experiments compare DRFR with traditional scoring methods and explore annotation sources, including human experts, crowd-sourced workers, and GPT-4. The findings demonstrate DRFR's higher reliability and the effectiveness of using GPT-4 as a cost-efficient annotator. The evaluation of several advanced LLMs using this framework reveals their strengths and areas needing improvement, particularly in complex instruction-following. This study contributes a novel metric and benchmark, offering insights for future LLM development and evaluation.

cs.CL↗
arXiv2023

A newly developed 10kA-level HTS conductor: innovative tenon-mortise-based modularized conductor (TMMC) based on China ancient architecture

We propose a new type of high temperature superconducting (HTS) conductor concept: modularized conductors (MC) connected by Chinese traditional tenon mortise (TM) connection structure, reffered as TMMC. The conductor consists of multiple concentric round sub conductors with slots for stacking REBCO tapes. Innovatively, the REBCO stacks in the adjacent sub conductors are arranged with the fully misaligned configuration to enhance the critical current' s isotropy with respect to magnetic field and reduce ac loss. For example, the angle between the adjacent stacks in the two adjacent sub conductors is 45 degree if each subconductor contains 4 REBCO stacks. In order to construct the fully misaligned configuration, the sub conductors are designed with two open half circular formers and connected by tenonmortise structure which makes the conductor modulrized and simply to assembly and disassembly. Based on the design concept, a prototype conductor containing 160 REBCO tapes distributed in the four concentric sub conductors is fabricated. The conductor measured critical current is 13.69 kA at 77 K and sefl field, which is consistent to the simulaiton result. In order to further improve the TMMC' s engineering critical current density (Jce) and bending performance, we propose two enhancement approaches which are reducing the former' s thickness and rearrange stacks in the outer sub conductors. With the enhancements, both TMMC' s radius and Jce are comparable to the existing slotted core conductor. The study shows the TMMC' s advantages of nontwisted structures, easy assembly, high current carrying and low ac losses, which makes it promising for constructing large scale scientific devices.

cond-mat.supr-con↗
arXiv2023

Semi-Markov Processes in Open Quantum Systems. II. Counting Statistics with Resetting

A semi-Markov process method for obtaining general counting statistics for open quantum systems is extended to the scenario of resetting. The simultaneous presence of random resets and wave function collapses means that the quantum jump trajectories are no longer semi-Markov. However, focusing on trajectories and using simple probability formulas, general counting statistics can still be constructed from reset-free statistics. An exact tilted matrix equation is also obtained. The inputs of these methods are the survival distributions and waiting-time density distributions instead of quantum operators. In addition, a continuous-time cloning algorithm is introduced to simulate the large-deviation properties of open quantum systems. Several quantum optics systems are used to demonstrate these results.

cond-mat.stat-mech↗
arXiv2023

Asymptotic Large Deviations of Counting Statistics in Open Quantum Systems

We use a semi-Markov process method to calculate large deviations of counting statistics for three open quantum systems, including a resonant two-level system and resonant three-level systems in the $Λ$- and $V$-configurations. In the first two systems, radical solutions to the scaled cumulant generating functions are obtained. Although this is impossible in the third system, since a general sixth-degree polynomial equation is present, we still obtain asymptotically large deviations of the complex system. Our results show that, in these open quantum systems, the large deviation rate functions at zero current are equal to two times the largest nonzero real parts of the eigenvalues of operator $-{\rm i}\hat H$, where $\hat H$ is a non-Hermitian Hamiltonian, while at a large current, these functions possess a unified formula.

cond-mat.stat-mech↗
arXiv2023

Algorithm Evolution Using Large Language Model

Optimization can be found in many real-life applications. Designing an effective algorithm for a specific optimization problem typically requires a tedious amount of effort from human experts with domain knowledge and algorithm design skills. In this paper, we propose a novel approach called Algorithm Evolution using Large Language Model (AEL). It utilizes a large language model (LLM) to automatically generate optimization algorithms via an evolutionary framework. AEL does algorithm-level evolution without model training. Human effort and requirements for domain knowledge can be significantly reduced. We take constructive methods for the salesman traveling problem as a test example, we show that the constructive algorithm obtained by AEL outperforms simple hand-crafted and LLM-generated heuristics. Compared with other domain deep learning model-based algorithms, these methods exhibit excellent scalability across different problem sizes. AEL is also very different from previous attempts that utilize LLMs as search operators in algorithms.

cs.NE↗
arXiv2023

DecipherPref: Analyzing Influential Factors in Human Preference Judgments via GPT-4

Human preference judgments are pivotal in guiding large language models (LLMs) to produce outputs that align with human values. Human evaluations are also used in summarization tasks to compare outputs from various systems, complementing existing automatic metrics. Despite their significance, however, there has been limited research probing these pairwise or $k$-wise comparisons. The collective impact and relative importance of factors such as output length, informativeness, fluency, and factual consistency are still not well understood. It is also unclear if there are other hidden factors influencing human judgments. In this paper, we conduct an in-depth examination of a collection of pairwise human judgments released by OpenAI. Utilizing the Bradley-Terry-Luce (BTL) model, we reveal the inherent preferences embedded in these human judgments. We find that the most favored factors vary across tasks and genres, whereas the least favored factors tend to be consistent, e.g., outputs are too brief, contain excessive off-focus content or hallucinated facts. Our findings have implications on the construction of balanced datasets in human preference evaluations, which is a crucial step in shaping the behaviors of future LLMs.

cs.CL↗
arXiv2023

Magnetic properties of the quasi-one-dimensional S = 1 spin chain antiferromagnet BaNiTe2O7

We report a quasi-one-dimensional S = 1 spin chain compound BaNiTe2O7. This magnetic system has been investigated by magnetic susceptibility, specific heat, and neutron powder diffraction. These results indicate that BaNiTe2O7 develops a short-range magnetic correlation around T ~ 22 K. With further cooling, an antiferromagnetic phase transition is observed at TN ~ 5.4 K. Neutron powder diffraction revealed antiferromagnetic noncollinear order with a commensurate propagation vector k = (1/2, 1, 0). The refined magnetic moment size of Ni2+ at 1.5 K is 1.84μB, and its noncollinear spin texture is confirmed by first-principles calculations. Inelastic neutron-scattering results and density functional theory calculations confirmed the quasi-one-dimensional nature of the spin systems.

cond-mat.str-el↗
arXiv2023

Score Mismatching for Generative Modeling

We propose a new score-based model with one-step sampling. Previously, score-based models were burdened with heavy computations due to iterative sampling. For substituting the iterative process, we train a standalone generator to compress all the time steps with the gradient backpropagated from the score network. In order to produce meaningful gradients for the generator, the score network is trained to simultaneously match the real data distribution and mismatch the fake data distribution. This model has the following advantages: 1) For sampling, it generates a fake image with only one step forward. 2) For training, it only needs 10 diffusion steps.3) Compared with consistency model, it is free of the ill-posed problem caused by consistency loss. On the popular CIFAR-10 dataset, our model outperforms Consistency Model and Denoising Score Matching, which demonstrates the potential of the framework. We further provide more examples on the MINIST and LSUN datasets. The code is available on GitHub.

cs.CV↗
arXiv2023

Achieving Autonomous Cloth Manipulation with Optimal Control via Differentiable Physics-Aware Regularization and Safety Constraints

Cloth manipulation is a category of deformable object manipulation of great interest to the robotics community, from applications of automated laundry-folding and home organizing and cleaning to textiles and flexible manufacturing. Despite the desire for automated cloth manipulation, the thin-shell dynamics and under-actuation nature of cloth present significant challenges for robots to effectively interact with them. Many recent works omit explicit modeling in favor of learning-based methods that may yield control policies directly. However, these methods require large training sets that must be collected and curated. In this regard, we create a framework for differentiable modeling of cloth dynamics leveraging an Extended Position-based Dynamics (XPBD) algorithm. Together with the desired control objective, physics-aware regularization terms are designed for better results, including trajectory smoothness and elastic potential energy. In addition, safety constraints, such as avoiding obstacles, can be specified using signed distance functions (SDFs). We formulate the cloth manipulation task with safety constraints as a constrained optimization problem, which can be effectively solved by mainstream gradient-based optimizers thanks to the end-to-end differentiability of our framework. Finally, we assess the proposed framework for manipulation tasks with various safety thresholds and demonstrate the feasibility of result trajectories on a surgical robot. The effects of the regularization terms are analyzed in an additional ablation study.

cs.RO↗
arXiv2023

PaniniQA: Enhancing Patient Education Through Interactive Question Answering

Patient portal allows discharged patients to access their personalized discharge instructions in electronic health records (EHRs). However, many patients have difficulty understanding or memorizing their discharge instructions. In this paper, we present PaniniQA, a patient-centric interactive question answering system designed to help patients understand their discharge instructions. PaniniQA first identifies important clinical content from patients' discharge instructions and then formulates patient-specific educational questions. In addition, PaniniQA is also equipped with answer verification functionality to provide timely feedback to correct patients' misunderstandings. Our comprehensive automatic and human evaluation results demonstrate our PaniniQA is capable of improving patients' mastery of their medical instructions through effective interactions

cs.CL↗
arXiv2023

The Hopf-Tsuji-Sullivan Dichotomy on Visibility Manifolds Without Conjugate Points

In this article, we establish the Hopf-Tsuji-Sullivan dichotomy for geodesic flows on certain manifolds with no conjugate points: either the geodesic flow is conservative and ergodic, or it is completely dissipative and non-ergodic. We also show several equivalent conditions to the conservativity, such the Poincaré series diverges at the critical exponent, the conical limit set has full Patterson-Sullivan measure, etc.

math.DS↗
arXiv2023

MeetingBank: A Benchmark Dataset for Meeting Summarization

As the number of recorded meetings increases, it becomes increasingly important to utilize summarization technology to create useful summaries of these recordings. However, there is a crucial lack of annotated meeting corpora for developing this technology, as it can be hard to collect meetings, especially when the topics discussed are confidential. Furthermore, meeting summaries written by experienced writers are scarce, making it hard for abstractive summarizers to produce sensible output without a reliable reference. This lack of annotated corpora has hindered the development of meeting summarization technology. In this paper, we present MeetingBank, a new benchmark dataset of city council meetings over the past decade. MeetingBank is unique among other meeting corpora due to its divide-and-conquer approach, which involves dividing professionally written meeting minutes into shorter passages and aligning them with specific segments of the meeting. This breaks down the process of summarizing a lengthy meeting into smaller, more manageable tasks. The dataset provides a new testbed of various meeting summarization systems and also allows the public to gain insight into how council decisions are made. We make the collection, including meeting video links, transcripts, reference summaries, agenda, and other metadata, publicly available to facilitate the development of better meeting summarization techniques. Our dataset can be accessed at: https://meetingbank.github.io

cs.CL↗
arXiv2023

DAMP: Doubly Aligned Multilingual Parser for Task-Oriented Dialogue

Modern virtual assistants use internal semantic parsing engines to convert user utterances to actionable commands. However, prior work has demonstrated that semantic parsing is a difficult multilingual transfer task with low transfer efficiency compared to other tasks. In global markets such as India and Latin America, this is a critical issue as switching between languages is prevalent for bilingual users. In this work we dramatically improve the zero-shot performance of a multilingual and codeswitched semantic parsing system using two stages of multilingual alignment. First, we show that constrastive alignment pretraining improves both English performance and transfer efficiency. We then introduce a constrained optimization approach for hyperparameter-free adversarial alignment during finetuning. Our Doubly Aligned Multilingual Parser (DAMP) improves mBERT transfer performance by 3x, 6x, and 81x on the Spanglish, Hinglish and Multilingual Task Oriented Parsing benchmarks respectively and outperforms XLM-R and mT5-Large using 3.2x fewer parameters.

cs.CL↗