Searcharxiv⌕ Search

arXiv subjects

Liwei Chen

Publications and source records attributed to Liwei Chen.

36 records · Page 2Linked to original sources
arXiv2023

A Step Closer to Comprehensive Answers: Constrained Multi-Stage Question Decomposition with Large Language Models

While large language models exhibit remarkable performance in the Question Answering task, they are susceptible to hallucinations. Challenges arise when these models grapple with understanding multi-hop relations in complex questions or lack the necessary knowledge for a comprehensive response. To address this issue, we introduce the "Decompose-and-Query" framework (D&Q). This framework guides the model to think and utilize external knowledge similar to ReAct, while also restricting its thinking to reliable information, effectively mitigating the risk of hallucinations. Experiments confirm the effectiveness of D&Q: On our ChitChatQA dataset, D&Q does not lose to ChatGPT in 67% of cases; on the HotPotQA question-only setting, D&Q achieved an F1 score of 59.6%. Our code is available at https://github.com/alkaidpku/DQ-ToolQA.

cs.CL↗
arXiv2023

Hardy spaces and Szegő projection on quotient domains

The Hardy spaces are defined on the quotient domain of a bounded complete Reinhardt domain by a finite subgroup of $U(n)$. The Szegő projection on the quotient domain can be studied by lifting to the covering space. This setting builds on the solution of a boundary value problem for holomorphic functions. In particular, when the covering space is either the polydisc or the unit ball in $\mathbb{C}^n$, the boundary value problem can be solved. Applying this theory in $\mathbb{C}^2$, we further obtain sharp results on the $L^p$ regularity of the Szegő projection on the symmetrized bidisc, generalized Thullen domains, and the minimal ball.

math.CV↗
arXiv2023

Stein's theorem on infinite type domains

The disc property is formulated for domains in $\mathbb{C}^n$. Holomorphic Lipschitz functions enjoy a gain in the order of Lipschitz regularity along the complex tangential direction on domains with disc property. Disc property is studied on various domains of infinite type. As applications, the local version of Stein's theorem is obtained on these domains, including the worm domains.

math.CV↗
arXiv2023

Bergman projection on the symmetrized bidisk

We apply the Bekollé-Bonami estimate for the (positive) Bergman projection on the weighted $L^p$ spaces on the unit disk. As the consequences, we obtain the boundedness of the Bergman projection on the weighted Sobolev space on the symmetrized bidisk. We also improve the boundedness result of the Bergman projection on the unweighted $L^p$ space on the symmetrized bidisk in \cite{CKY}.

math.CV↗
arXiv2023

In-situ monitoring additive manufacturing process with AI edge computing

In-situ monitoring system can be used to monitor the quality of additive manufacturing (AM) processes. In the case of digital image correlation (DIC) based in-situ monitoring systems, high-speed cameras were used to capture images of high resolutions. This paper proposed a novel in-situ monitoring system to accelerate the process of digital images using artificial intelligence (AI) edge computing board. It built a visual transformer based video super resolution (ViTSR) network to reconstruct high resolution (HR) videos frames. Fully convolutional network (FCN) was used to simultaneously extract the geometric characteristics of molten pool and plasma arc during the AM processes. Compared with 6 state-of-the-art super resolution methods, ViTSR ranks first in terms of peak signal to noise ratio (PSNR). The PSNR of ViTSR for 4x super resolution reached 38.16 dB on test data with input size of 75 pixels x 75 pixels. Inference time of ViTSR and FCN was optimized to 50.97 ms and 67.86 ms on AI edge board after operator fusion and model pruning. The total inference time of the proposed system was 118.83 ms, which meets the requirement of real-time quality monitoring with low cost in-situ monitoring equipment during AM processes. The proposed system achieved an accuracy of 96.34% on the multi-objects extraction task and can be applied to different AM processes.

eess.IV↗
arXiv2021

Upcycling Low-Nickel Polycrystalline Cathodes from Retired Electric Vehicle Batteries into Single-Crystal Nickel-Rich Cathodes

The electrification revolution in automobile industry and others demands annual production capacity of batteries at least on the order of 102 gigawatts hours, which presents a twofold challenge to supply of key materials such as cobalt and nickel and to recycling when the batteries retire. Pyrometallurgical and hydrometallurgical recycling are currently used in industry but suffer from complexity, high costs, and secondary pollution. Here we report a direct-recycling method in molten salts (MSDR) that is environmentally benign and value-creating based on a techno-economic analysis using real-world data and price information. We also experimentally demonstrate the feasibility of MSDR by upcycling a low-nickel polycrystalline LiNi0.5Mn0.3Co0.2O2 (NMC) cathode material that is widely used in early-year electric vehicles into Ni-rich (Ni > 65%) single-crystal NMCs with increased energy-density (>10% increase) and outstanding electrochemical performance (>94% capacity retention after 500 cycles in pouch-type full cells). This work opens up new opportunities for closed-loop recycling of electric vehicle batteries and manufacturing of next-generation NMC cathode materials.

physics.app-ph↗
arXiv2020

Zipper Stack: Shadow Stacks Without Shadow

Return-Oriented Programming (ROP) is a typical attack technique that exploits return addresses to abuse existing code repeatedly. Most of the current return address protecting mechanisms (also known as the Backward-Edge Control-Flow Integrity) work only in limited threat models. For example, the attacker cannot break memory isolation, or the attacker has no knowledge of a secret key or random values. This paper presents a novel, lightweight mechanism protecting return addresses, Zipper Stack, which authenticates all return addresses by a chain structure using cryptographic message authentication codes (MACs). This innovative design can defend against the most powerful attackers who have full control over the program's memory and even know the secret key of the MAC function. This threat model is stronger than the one used in related work. At the same time, it produces low-performance overhead. We implemented Zipper Stack by extending the RISC-V instruction set architecture, and the evaluation on FPGA shows that the performance overhead of Zipper Stack is only 1.86%. Thus, we think Zipper Stack is suitable for actual deployment.

cs.CR↗
arXiv2019

Product domains, Multi-Cauchy transforms, and the $\bar \partial$ equation

Solution operators for the equation $\bar \partial u=f$ are constructed on general product domains in $\mathbb{C}^n$. When the factors are one-dimensional, the operator is a simple integral operator: it involves specific derivatives of $f$ integrated against iterated Cauchy kernels. For higher dimensional factors, the solution is constructed by solving sub-$\bar \partial$ equations with modified data on the factors. Estimates of the operators in several norms are proved.

math.CV↗
arXiv2019

$L^p$ regularity of the Bergman Projection on domains covered by the polydisk

If a bounded domain can be covered by the polydisk through a rational proper holomorphic map, then the Bergman projection is $L^p$-bounded for $p$ in a certain range depending on the ramified rational covering. This result can be applied to the symmetrized polydisk and to the Hartogs triangle with exponent $γ$.

math.CV↗
arXiv2018

Encoding Implicit Relation Requirements for Relation Extraction: A Joint Inference Approach

Relation extraction is the task of identifying predefined relationship between entities, and plays an essential role in information extraction, knowledge base construction, question answering and so on. Most existing relation extractors make predictions for each entity pair locally and individually, while ignoring implicit global clues available across different entity pairs and in the knowledge base, which often leads to conflicts among local predictions from different entity pairs. This paper proposes a joint inference framework that employs such global clues to resolve disagreements among local predictions. We exploit two kinds of clues to generate constraints which can capture the implicit type and cardinality requirements of a relation. Those constraints can be examined in either hard style or soft style, both of which can be effectively explored in an integer linear program formulation. Experimental results on both English and Chinese datasets show that our proposed framework can effectively utilize those two categories of global clues and resolve the disagreements among local predictions, thus improve various relation extractors when such clues are applicable to the datasets. Our experiments also indicate that the clues learnt automatically from existing knowledge bases perform comparably to or better than those refined by human.

cs.CL↗
arXiv2018

A solution operator for $\bar\partial$ on the Hartogs triangle and $L^p$ estimates

An integral solution operator for $\bar\partial$ is constructed on product domains that include the punctured bidisc. This operator is shown to satisfy $L^p$ estimates for all $1\leq p <\infty$, though with non-standard -- relative to strongly pseudoconvex domains -- bounding term. These estimates imply $L^p$ estimates for $\bar\partial$ on the Hartogs triangle, with greater range of $p$ than the canonical solution satisfies.

math.CV↗
arXiv2018

Exploiting Rich Syntactic Information for Semantic Parsing with Graph-to-Sequence Model

Existing neural semantic parsers mainly utilize a sequence encoder, i.e., a sequential LSTM, to extract word order features while neglecting other valuable syntactic information such as dependency graph or constituent trees. In this paper, we first propose to use the \textit{syntactic graph} to represent three types of syntactic information, i.e., word order, dependency and constituency features. We further employ a graph-to-sequence model to encode the syntactic graph and decode a logical form. Experimental results on benchmark datasets show that our model is comparable to the state-of-the-art on Jobs640, ATIS and Geo880. Experimental results on adversarial examples demonstrate the robustness of the model is also improved by encoding more syntactic information.

cs.CL↗
arXiv2015

Weighted Bergman Projection on the Hartogs Triangle

We prove the $L^p$ regularity of the weighted Bergman projection on the Hartogs triangle, where the weights are powers of the distance to the singularity at the boundary. The restricted range of $p$ is proved to be sharp. By using a two-weight inequality on the upper half plane with Muckenhoupt weights, we can consider a slightly wider class of weights.

math.CV↗
arXiv2014

Contactless Probing of the Intrinsic Carrier Transport in Single-Walled Carbon Nanotubes

Intrinsic carrier transport properties of single-walled carbon nanotubes are probed by two parallel methods on the same individual tubes: the contactless dielectric force microscopy (DFM) technique and the conventional field-effect transistor (FET) method. The dielectric responses of SWNTs are strongly correlated with electronic transport of the corresponding FETs. The DC bias voltage in DFM plays a role analogous to the gate voltage in FET. A microscopic model based on the general continuity equation and numerical simulation is built to reveal the link between intrinsic properties such as carrier concentration and mobility and the macroscopic observable, i.e. dielectric responses, in DFM experiments. Local transport barriers in nanotubes, which influence the device transport behaviors, are also detected with nanometer scale resolution.

cond-mat.mes-hall↗