arXiv subjects

Lang Qin

Publications and source records attributed to Lang Qin.

25 records · Page 2Linked to original sources

arXiv2024

Listening to Patients: A Framework of Detecting and Mitigating Patient Misreport for Medical Dialogue Generation

Medical Dialogue Systems aim to provide automated healthcare support through patient-agent conversations. Previous efforts typically regard patients as ideal users -- one who accurately and consistently reports their health conditions. However, in reality, patients often misreport their symptoms, leading to discrepancies between their reports and actual health conditions. Overlooking patient misreport will affect the quality of healthcare consultations provided by MDS. To address this issue, we argue that MDS should ''listen to patients'' and tackle two key challenges: how to detect and mitigate patient misreport effectively. In this work, we propose PaMis, a framework of detecting and mitigating Patient Misreport for medical dialogue generation. PaMis first constructs dialogue entity graphs, then detects patient misreport based on graph entropy, and mitigates patient misreport by formulating clarifying questions. Experiments indicate that PaMis effectively enhances medical response generation, enabling models like GPT-4 to detect and mitigate patient misreports, and provide high-quality healthcare assistance.

cs.CL↗

arXiv2024

An improved Hamilton matrix estimates for the heat equation

In this paper, we remove the assumption on the gradient of the Ricci curvature in Hamilton's matrix Harnack estimate for the heat equation on all closed manifolds, answering a question which has been around since the 1990s. New ingredients include a recent sharp Li-Yau estimate, construction of a suitable vector field and various use of integral arguments, iteration and a little tensor algebra.

math.DG↗

arXiv2024

EAS-SNN: End-to-End Adaptive Sampling and Representation for Event-based Detection with Recurrent Spiking Neural Networks

Event cameras, with their high dynamic range and temporal resolution, are ideally suited for object detection, especially under scenarios with motion blur and challenging lighting conditions. However, while most existing approaches prioritize optimizing spatiotemporal representations with advanced detection backbones and early aggregation functions, the crucial issue of adaptive event sampling remains largely unaddressed. Spiking Neural Networks (SNNs), which operate on an event-driven paradigm through sparse spike communication, emerge as a natural fit for addressing this challenge. In this study, we discover that the neural dynamics of spiking neurons align closely with the behavior of an ideal temporal event sampler. Motivated by this insight, we propose a novel adaptive sampling module that leverages recurrent convolutional SNNs enhanced with temporal memory, facilitating a fully end-to-end learnable framework for event-based detection. Additionally, we introduce Residual Potential Dropout (RPD) and Spike-Aware Training (SAT) to regulate potential distribution and address performance degradation encountered in spike-based sampling modules. Empirical evaluation on neuromorphic detection datasets demonstrates that our approach outperforms existing state-of-the-art spike-based methods with significantly fewer parameters and time steps. For instance, our method yields a 4.4\% mAP improvement on the Gen1 dataset, while requiring 38\% fewer parameters and only three time steps. Moreover, the applicability and effectiveness of our adaptive sampling methodology extend beyond SNNs, as demonstrated through further validation on conventional non-spiking models. Code is available at https://github.com/Windere/EAS-SNN.

cs.CV↗

arXiv2024

GRSN: Gated Recurrent Spiking Neurons for POMDPs and MARL

Spiking neural networks (SNNs) are widely applied in various fields due to their energy-efficient and fast-inference capabilities. Applying SNNs to reinforcement learning (RL) can significantly reduce the computational resource requirements for agents and improve the algorithm's performance under resource-constrained conditions. However, in current spiking reinforcement learning (SRL) algorithms, the simulation results of multiple time steps can only correspond to a single-step decision in RL. This is quite different from the real temporal dynamics in the brain and also fails to fully exploit the capacity of SNNs to process temporal data. In order to address this temporal mismatch issue and further take advantage of the inherent temporal dynamics of spiking neurons, we propose a novel temporal alignment paradigm (TAP) that leverages the single-step update of spiking neurons to accumulate historical state information in RL and introduces gated units to enhance the memory capacity of spiking neurons. Experimental results show that our method can solve partially observable Markov decision processes (POMDPs) and multi-agent cooperation problems with similar performance as recurrent neural networks (RNNs) but with about 50% power consumption.

cs.NE↗

arXiv2024

A Low Latency Adaptive Coding Spiking Framework for Deep Reinforcement Learning

In recent years, spiking neural networks (SNNs) have been used in reinforcement learning (RL) due to their low power consumption and event-driven features. However, spiking reinforcement learning (SRL), which suffers from fixed coding methods, still faces the problems of high latency and poor versatility. In this paper, we use learnable matrix multiplication to encode and decode spikes, improving the flexibility of the coders and thus reducing latency. Meanwhile, we train the SNNs using the direct training method and use two different structures for online and offline RL algorithms, which gives our model a wider range of applications. Extensive experiments have revealed that our method achieves optimal performance with ultra-low latency (as low as 0.8% of other SRL methods) and excellent energy efficiency (up to 5X the DNNs) in different algorithms and different environments.

cs.LG↗

arXiv2023

Well Begun is Half Done: Generator-agnostic Knowledge Pre-Selection for Knowledge-Grounded Dialogue

Accurate knowledge selection is critical in knowledge-grounded dialogue systems. Towards a closer look at it, we offer a novel perspective to organize existing literature, i.e., knowledge selection coupled with, after, and before generation. We focus on the third under-explored category of study, which can not only select knowledge accurately in advance, but has the advantage to reduce the learning, adjustment, and interpretation burden of subsequent response generation models, especially LLMs. We propose GATE, a generator-agnostic knowledge selection method, to prepare knowledge for subsequent response generation models by selecting context-related knowledge among different knowledge structures and variable knowledge requirements. Experimental results demonstrate the superiority of GATE, and indicate that knowledge selection before generation is a lightweight yet effective way to facilitate LLMs (e.g., ChatGPT) to generate more informative responses.

cs.CL↗

arXiv2019

Near 100% CO Selectivity in Nanoscaled Iron-Based Oxygen Carriers for Chemical Looping Methane Partial Oxidation

Chemical looping methane partial oxidation provides an energy and cost effective route for methane utilization. However, there is considerable CO2 co-production in state-of-the-art chemical looping systems, rendering a decreased productivity in value-added fuels or chemicals. In this work, we show that the co-production of CO2 can be dramatically suppressed in methane partial oxidation reactions using iron oxide nanoparticles, with a size of 2~8 nm, as the oxygen carrier. To stabilize these nanoparticles at high temperatures, they are embedded in an ordered, gas-permeable mesoporous silica matrix. We experimentally obtained near 100% CO selectivity in a cyclic redox system at 750°C to 935°C, which is a significantly lower temperature range than in conventional oxygen carrier systems. Density functional theory calculations elucidate the origins for such selectivity and reveal that CH4 adsorption energies decrease with increasing nanoparticle size. These calculations also show that low-coordinated lattice oxygen atoms on the surface of nanoparticles significantly promote Fe-O bond cleavage and CO formation. We envision that embedded nanostructured oxygen carriers have the potential to serve as a general materials platform for achieving 100% selectivity in redox reactions at high temperatures.

physics.chem-ph↗