arXiv subjects

Bing Liu

Publications and source records attributed to Bing Liu.

At least 91 records · Page 5Linked to original sources

arXiv2024

Constraining the low-energy cosmic ray flux in the central molecular zone from MeV nuclear deexcitation line observations

Low-energy cosmic rays (LECRs) dominate the ionization in dense regions of molecular clouds in which other ionizers such as UV or X-ray photons are effectively shielded. Thus it was argued that the high ionization rate at the central molecular zone (CMZ) of our Galaxy is mainly caused by LECRs. However, the required LECR flux is orders of magnitude higher than the extrapolation of GeV cosmic ray (CR) flux derived from GeV gamma-ray observations. In this paper, we considered two types of additional LECR components and found that only very soft anomalous CR components can explain such a high ionization rate. This LECR component will inevitably produce MeV nuclear deexcitation lines due to their inelastic scattering with the ambient gas. We calculated the MeV line emission and discussed the detectability of next-generation MeV instruments. We found that future MeV observations can be used to pin down the origin of the high ionization rate in the CMZ.

astro-ph.HE↗

arXiv2024

Replay-and-Forget-Free Graph Class-Incremental Learning: A Task Profiling and Prompting Approach

Class-incremental learning (CIL) aims to continually learn a sequence of tasks, with each task consisting of a set of unique classes. Graph CIL (GCIL) follows the same setting but needs to deal with graph tasks (e.g., node classification in a graph). The key characteristic of CIL lies in the absence of task identifiers (IDs) during inference, which causes a significant challenge in separating classes from different tasks (i.e., inter-task class separation). Being able to accurately predict the task IDs can help address this issue, but it is a challenging problem. In this paper, we show theoretically that accurate task ID prediction on graph data can be achieved by a Laplacian smoothing-based graph task profiling approach, in which each graph task is modeled by a task prototype based on Laplacian smoothing over the graph. It guarantees that the task prototypes of the same graph task are nearly the same with a large smoothing step, while those of different tasks are distinct due to differences in graph structure and node attributes. Further, to avoid the catastrophic forgetting of the knowledge learned in previous graph tasks, we propose a novel graph prompting approach for GCIL which learns a small discriminative graph prompt for each task, essentially resulting in a separate classification model for each task. The prompt learning requires the training of a single graph neural network (GNN) only once on the first task, and no data replay is required thereafter, thereby obtaining a GCIL model being both replay-free and forget-free. Extensive experiments on four GCIL benchmarks show that i) our task prototype-based method can achieve 100% task ID prediction accuracy on all four datasets, ii) our GCIL model significantly outperforms state-of-the-art competing methods by at least 18% in average CIL accuracy, and iii) our model is fully free of forgetting on the four datasets.

cs.LG↗

arXiv2024

Open-World Continual Learning: Unifying Novelty Detection and Continual Learning

As AI agents are increasingly used in the real open world with unknowns or novelties, they need the ability to (1) recognize objects that (a) they have learned before and (b) detect items that they have never seen or learned, and (2) learn the new items incrementally to become more and more knowledgeable and powerful. (1) is called novelty detection or out-of-distribution (OOD) detection and (2) is called class incremental learning (CIL), which is a setting of continual learning (CL). In existing research, OOD detection and CIL are regarded as two completely different problems. This paper first provides a theoretical proof that good OOD detection for each task within the set of learned tasks (called closed-world OOD detection) is necessary for successful CIL. We show this by decomposing CIL into two sub-problems: within-task prediction (WP) and task-id prediction (TP), and proving that TP is correlated with closed-world OOD detection. The key theoretical result is that regardless of whether WP and OOD detection (or TP) are defined explicitly or implicitly by a CIL algorithm, good WP and good closed-world OOD detection are necessary and sufficient conditions for good CIL, which unifies novelty or OOD detection and continual learning (CIL, in particular). We call this traditional CIL the closed-world CIL as it does not detect future OOD data in the open world. The paper then proves that the theory can be generalized or extended to open-world CIL, which is the proposed open-world continual learning, that can perform CIL in the open world and detect future or open-world OOD data. Based on the theoretical results, new CIL methods are also designed, which outperform strong baselines in CIL accuracy and in continual OOD detection by a large margin.

cs.LG↗

arXiv2024

Boosting LLM Translation Skills without General Ability Loss via Rationale Distillation

Large Language Models (LLMs) have achieved impressive results across numerous NLP tasks but still encounter difficulties in machine translation. Traditional methods to improve translation have typically involved fine-tuning LLMs using parallel corpora. However, vanilla fine-tuning often leads to catastrophic forgetting of the instruction-following capabilities and alignment with human preferences, compromising their broad general abilities and introducing potential security risks. These abilities, which are developed using proprietary and unavailable training data, make existing continual instruction tuning methods ineffective. To overcome this issue, we propose a novel approach called RaDis (Rationale Distillation). RaDis harnesses the strong generative capabilities of LLMs to create rationales for training data, which are then "replayed" to prevent forgetting. These rationales encapsulate general knowledge and safety principles, acting as self-distillation targets to regulate the training process. By jointly training on both reference translations and self-generated rationales, the model can learn new translation skills while preserving its overall general abilities. Extensive experiments demonstrate that our method enhances machine translation performance while maintaining the broader capabilities of LLMs across other tasks. This work presents a pathway for creating more versatile LLMs that excel in specialized tasks without compromising generality and safety.

cs.CL↗

arXiv2024

Facial Action Unit Detection by Adaptively Constraining Self-Attention and Causally Deconfounding Sample

Facial action unit (AU) detection remains a challenging task, due to the subtlety, dynamics, and diversity of AUs. Recently, the prevailing techniques of self-attention and causal inference have been introduced to AU detection. However, most existing methods directly learn self-attention guided by AU detection, or employ common patterns for all AUs during causal intervention. The former often captures irrelevant information in a global range, and the latter ignores the specific causal characteristic of each AU. In this paper, we propose a novel AU detection framework called AC2D by adaptively constraining self-attention weight distribution and causally deconfounding the sample confounder. Specifically, we explore the mechanism of self-attention weight distribution, in which the self-attention weight distribution of each AU is regarded as spatial distribution and is adaptively learned under the constraint of location-predefined attention and the guidance of AU detection. Moreover, we propose a causal intervention module for each AU, in which the bias caused by training samples and the interference from irrelevant AUs are both suppressed. Extensive experiments show that our method achieves competitive performance compared to state-of-the-art AU detection approaches on challenging benchmarks, including BP4D, DISFA, GFT, and BP4D+ in constrained scenarios and Aff-Wild2 in unconstrained scenarios. The code is available at https://github.com/ZhiwenShao/AC2D.

cs.CV↗

arXiv2024

The Power of Combining Data and Knowledge: GPT-4o is an Effective Interpreter of Machine Learning Models in Predicting Lymph Node Metastasis of Lung Cancer

Lymph node metastasis (LNM) is a crucial factor in determining the initial treatment for patients with lung cancer, yet accurate preoperative diagnosis of LNM remains challenging. Recently, large language models (LLMs) have garnered significant attention due to their remarkable text generation capabilities. Leveraging the extensive medical knowledge learned from vast corpora, LLMs can estimate probabilities for clinical problems, though their performance has historically been inferior to data-driven machine learning models. In this paper, we propose a novel ensemble method that combines the medical knowledge acquired by LLMs with the latent patterns identified by machine learning models to enhance LNM prediction performance. Initially, we developed machine learning models using patient data. We then designed a prompt template to integrate the patient data with the predicted probability from the machine learning model. Subsequently, we instructed GPT-4o, the most advanced LLM developed by OpenAI, to estimate the likelihood of LNM based on patient data and then adjust the estimate using the machine learning output. Finally, we collected three outputs from the GPT-4o using the same prompt and ensembled these results as the final prediction. Using the proposed method, our models achieved an AUC value of 0.778 and an AP value of 0.426 for LNM prediction, significantly improving predictive performance compared to baseline machine learning models. The experimental results indicate that GPT-4o can effectively leverage its medical knowledge and the probabilities predicted by machine learning models to achieve more accurate LNM predictions. These findings demonstrate that LLMs can perform well in clinical risk prediction tasks, offering a new paradigm for integrating medical knowledge and patient data in clinical predictions.

cs.CL↗

arXiv2024

Predicting Lung Cancer Patient Prognosis with Large Language Models

Prognosis prediction is crucial for determining optimal treatment plans for lung cancer patients. Traditionally, such predictions relied on models developed from retrospective patient data. Recently, large language models (LLMs) have gained attention for their ability to process and generate text based on extensive learned knowledge. In this study, we evaluate the potential of GPT-4o mini and GPT-3.5 in predicting the prognosis of lung cancer patients. We collected two prognosis datasets, i.e., survival and post-operative complication datasets, and designed multiple tasks to assess the models' performance comprehensively. Logistic regression models were also developed as baselines for comparison. The experimental results demonstrate that LLMs can achieve competitive, and in some tasks superior, performance in lung cancer prognosis prediction compared to data-driven logistic regression models despite not using additional patient data. These findings suggest that LLMs can be effective tools for prognosis prediction in lung cancer, particularly when patient data is limited or unavailable.

cs.CL↗

arXiv2024

Efficient Quantum Circuit Simulation by Tensor Network Methods on Modern GPUs

Efficient simulation of quantum circuits has become indispensable with the rapid development of quantum hardware. The primary simulation methods are based on state vectors and tensor networks. As the number of qubits and quantum gates grows larger in current quantum devices, traditional state-vector based quantum circuit simulation methods prove inadequate due to the overwhelming size of the Hilbert space and extensive entanglement. Consequently, brutal force tensor network simulation algorithms become the only viable solution in such scenarios. The two main challenges faced in tensor network simulation algorithms are optimal contraction path finding and efficient execution on modern computing devices, with the latter determines the actual efficiency. In this study, we investigate the optimization of such tensor network simulations on modern GPUs and propose general optimization strategies from two aspects: computational efficiency and accuracy. Firstly, we propose to transform critical Einstein summation operations into GEMM operations, leveraging the specific features of tensor network simulations to amplify the efficiency of GPUs. Secondly, by analyzing the data characteristics of quantum circuits, we employ extended precision to ensure the accuracy of simulation results and mixed precision to fully exploit the potential of GPUs, resulting in faster and more precise simulations. Our numerical experiments demonstrate that our approach can achieve a 3.96x reduction in verification time for random quantum circuit samples in the 18-cycle case of Sycamore, with sustained performance exceeding 21 TFLOPS on one A100. This method can be easily extended to the 20-cycle case, maintaining the same performance, accelerating by 12.5x compared to the state-of-the-art CPU-based results and 4.48-6.78x compared to the state-of-the-art GPU-based results reported in the literature.

quant-ph↗

arXiv2024

SciConNav: Knowledge navigation through contextual learning of extensive scientific research trajectories

New knowledge builds upon existing foundations, which means an interdependent relationship exists between knowledge, manifested in the historical development of the scientific system for hundreds of years. By leveraging natural language processing techniques, this study introduces the Scientific Concept Navigator (SciConNav), an embedding-based navigation model to infer the "knowledge pathway" from the research trajectories of millions of scholars. We validate that the learned representations effectively delineate disciplinary boundaries and capture the intricate relationships between diverse concepts. The utility of the inferred navigation space is showcased through multiple applications. Firstly, we demonstrated the multi-step analogy inferences within the knowledge space and the interconnectivity between concepts in different disciplines. Secondly, we formulated the attribute dimensions of knowledge across domains, observing the distributional shifts in the arrangement of 19 disciplines along these conceptual dimensions, including "Theoretical" to "Applied", and "Chemical" to "Biomedical', highlighting the evolution of functional attributes within knowledge domains. Lastly, by analyzing the high-dimensional knowledge network structure, we found that knowledge connects with shorter global pathways, and interdisciplinary knowledge plays a critical role in the accessibility of the global knowledge network. Our framework offers a novel approach to mining knowledge inheritance pathways in extensive scientific literature, which is of great significance for understanding scientific progression patterns, tailoring scientific learning trajectories, and accelerating scientific progress.

cs.IR↗

arXiv2024

Talk With Human-like Agents: Empathetic Dialogue Through Perceptible Acoustic Reception and Reaction

Large Language Model (LLM)-enhanced agents become increasingly prevalent in Human-AI communication, offering vast potential from entertainment to professional domains. However, current multi-modal dialogue systems overlook the acoustic information present in speech, which is crucial for understanding human communication nuances. This oversight can lead to misinterpretations of speakers' intentions, resulting in inconsistent or even contradictory responses within dialogues. To bridge this gap, in this paper, we propose PerceptiveAgent, an empathetic multi-modal dialogue system designed to discern deeper or more subtle meanings beyond the literal interpretations of words through the integration of speech modality perception. Employing LLMs as a cognitive core, PerceptiveAgent perceives acoustic information from input speech and generates empathetic responses based on speaking styles described in natural language. Experimental results indicate that PerceptiveAgent excels in contextual understanding by accurately discerning the speakers' true intentions in scenarios where the linguistic meaning is either contrary to or inconsistent with the speaker's true feelings, producing more nuanced and expressive spoken dialogues. Code is publicly available at: \url{https://github.com/Haoqiu-Yan/PerceptiveAgent}.

cs.CL↗

arXiv2024

Lifelong and Continual Learning Dialogue Systems

Dialogue systems, commonly known as chatbots, have gained escalating popularity in recent times due to their wide-spread applications in carrying out chit-chat conversations with users and task-oriented dialogues to accomplish various user tasks. Existing chatbots are usually trained from pre-collected and manually-labeled data and/or written with handcrafted rules. Many also use manually-compiled knowledge bases (KBs). Their ability to understand natural language is still limited, and they tend to produce many errors resulting in poor user satisfaction. Typically, they need to be constantly improved by engineers with more labeled data and more manually compiled knowledge. This book introduces the new paradigm of lifelong learning dialogue systems to endow chatbots the ability to learn continually by themselves through their own self-initiated interactions with their users and working environments to improve themselves. As the systems chat more and more with users or learn more and more from external sources, they become more and more knowledgeable and better and better at conversing. The book presents the latest developments and techniques for building such continual learning dialogue systems that continuously learn new language expressions and lexical and factual knowledge during conversation from users and off conversation from external sources, acquire new training examples during conversation, and learn conversational skills. Apart from these general topics, existing works on continual learning of some specific aspects of dialogue systems are also surveyed. The book concludes with a discussion of open challenges for future research.

cs.CL↗

arXiv2024

Relational Learning in Pre-Trained Models: A Theory from Hypergraph Recovery Perspective

Foundation Models (FMs) have demonstrated remarkable insights into the relational dynamics of the world, leading to the crucial question: how do these models acquire an understanding of world hybrid relations? Traditional statistical learning, particularly for prediction problems, may overlook the rich and inherently structured information from the data, especially regarding the relationships between objects. We introduce a mathematical model that formalizes relational learning as hypergraph recovery to study pre-training of FMs. In our framework, the world is represented as a hypergraph, with data abstracted as random samples from hyperedges. We theoretically examine the feasibility of a Pre-Trained Model (PTM) to recover this hypergraph and analyze the data efficiency in a minimax near-optimal style. By integrating rich graph theories into the realm of PTMs, our mathematical framework offers powerful tools for an in-depth understanding of pre-training from a unique perspective and can be used under various scenarios. As an example, we extend the framework to entity alignment in multimodal learning.

cs.AI↗

arXiv2024

ENN's Roadmap for Proton-Boron Fusion Based on Spherical Torus

ENN Science and Technology Development Co., Ltd. (ENN) is committed to generating fusion energy in an environmentally friendly and cost-effective manner, which requires abundant aneutronic fuel. Proton-boron ( p-$^{11}$B or p-B) fusion is considered an ideal choice for this purpose. Recent studies have suggested that p-B fusion, although challenging, is feasible based on new cross-section data, provided that a hot ion mode and high wall reflection can be achieved to reduce electron radiation loss. The high beta and good confinement of the spherical torus (ST) make it an ideal candidate for p-B fusion. By utilizing the new spherical torus energy confinement scaling law, a reactor with a major radius $R_0=4$ m, central magnetic field $B_0=6$ T, central temperature $T_{i0}=150$ keV, plasma current $I_p=30$ MA, and hot ion mode $T_i/T_e=4$ can yield p-B fusion with $Q>10$. A roadmap for p-B fusion has been developed, with the next-generation device named EHL-2. EHL stands for ENN He-Long, which literally means ``peaceful Chinese Loong". The main target parameters include $R_0\simeq1.05$ m, $A\simeq1.85$, $B_0\simeq3$ T, $T_{i0}\simeq30$ keV, $I_p\simeq3$ MA, and $T_i/T_e\geq2$. The existing ST device EXL-50 was simultaneously upgraded to provide experimental support for the new roadmap, involving the installation and upgrading of the central solenoid, vacuum chamber, and magnetic systems. The construction of the upgraded ST fusion device, EXL-50U, was completed at the end of 2023, and it achieved its first plasma in January 2024. The construction of EHL-2 is estimated to be completed by 2026.

physics.plasm-ph↗

arXiv2024

Precise measurement of pion-bump structure using future MeV gamma-ray detectors

The pion-bump structure in the gamma-ray spectrum is a direct proof for the hadronic origin of the gamma rays, and thus the decisive evidence for the acceleration of hadronic cosmic rays in astrophysical objects. However, the identification of such a spectral feature is limited by the resolution and energy coverage of current gamma-ray instruments. Furthermore, there are unavoidable bremsstrahlung emissions from secondary and primary electrons, which may dominate the gamma-ray emission below the pion-bump. Thus, the study of this gamma-ray emission component can provide unique information on the acceleration and confinement of high-energy particles. In this paper, we studied the predicted gamma-ray spectrum assuming both hadronic or leptonic origin in mid-aged supernova remnants W44, we discuss the detection potential of future MeV missions on these emissions and possible implications.

astro-ph.HE↗

arXiv2024

Detection of extended gamma-ray emission in the vicinity of Cl Danks 1 and 2

We report the detection of high-energy gamma-ray emission towards the G305 star-forming region. Using almost 15 years of observation data from {\sl Fermi} Large Area Telescope, we detected an extended gamma-ray source in this region with a significance of $\sim 13 σ$. The gamma-ray radiation reveals a clear pion-bump feature and can be fitted with the power law parent proton spectrum with an index of $-2.5$. The total cosmic ray (CR) proton energy in the gamma-ray production region is estimated to be the order of $10^{49}\ \rm erg$. We further derived the CR radial distribution from both the gamma-ray emission and gas distribution and found it roughly obeys the $1/r$ type profile, which is consistent with other similar systems and expected from the continuous injection of CRs by the central powerful young massive star cluster Danks 1 or Danks 2 in this region. Together with former detections of similar gamma-ray structures, such as Cygnus cocoon, Westerlund 1, Westerlund 2, NGC 3603, and W40, the detection supports the hypothesis that young massive star clusters are CR accelerators.

astro-ph.HE↗

arXiv2024

The current status of large language models in summarizing radiology report impressions

Large language models (LLMs) like ChatGPT show excellent capabilities in various natural language processing tasks, especially for text generation. The effectiveness of LLMs in summarizing radiology report impressions remains unclear. In this study, we explore the capability of eight LLMs on the radiology report impression summarization. Three types of radiology reports, i.e., CT, PET-CT, and Ultrasound reports, are collected from Peking University Cancer Hospital and Institute. We use the report findings to construct the zero-shot, one-shot, and three-shot prompts with complete example reports to generate the impressions. Besides the automatic quantitative evaluation metrics, we define five human evaluation metrics, i.e., completeness, correctness, conciseness, verisimilitude, and replaceability, to evaluate the semantics of the generated impressions. Two thoracic surgeons (ZSY and LB) and one radiologist (LQ) compare the generated impressions with the reference impressions and score each impression under the five human evaluation metrics. Experimental results show that there is a gap between the generated impressions and reference impressions. Although the LLMs achieve comparable performance in completeness and correctness, the conciseness and verisimilitude scores are not very high. Using few-shot prompts can improve the LLMs' performance in conciseness and verisimilitude, but the clinicians still think the LLMs can not replace the radiologists in summarizing the radiology impressions.

cs.CL↗

arXiv2024

Probing Language Models for Pre-training Data Detection

Large Language Models (LLMs) have shown their impressive capabilities, while also raising concerns about the data contamination problems due to privacy issues and leakage of benchmark datasets in the pre-training phase. Therefore, it is vital to detect the contamination by checking whether an LLM has been pre-trained on the target texts. Recent studies focus on the generated texts and compute perplexities, which are superficial features and not reliable. In this study, we propose to utilize the probing technique for pre-training data detection by examining the model's internal activations. Our method is simple and effective and leads to more trustworthy pre-training data detection. Additionally, we propose ArxivMIA, a new challenging benchmark comprising arxiv abstracts from Computer Science and Mathematics categories. Our experiments demonstrate that our method outperforms all baselines, and achieves state-of-the-art performance on both WikiMIA and ArxivMIA, with additional experiments confirming its efficacy (Our code and dataset are available at https://github.com/zhliu0106/probing-lm-data).

cs.CL↗

arXiv2024

Safety through Permissibility: Shield Construction for Fast and Safe Reinforcement Learning

Designing Reinforcement Learning (RL) solutions for real-life problems remains a significant challenge. A major area of concern is safety. "Shielding" is a popular technique to enforce safety in RL by turning user-defined safety specifications into safe agent behavior. However, these methods either suffer from extreme learning delays, demand extensive human effort in designing models and safe domains in the problem, or require pre-computation. In this paper, we propose a new permissibility-based framework to deal with safety and shield construction. Permissibility was originally designed for eliminating (non-permissible) actions that will not lead to an optimal solution to improve RL training efficiency. This paper shows that safety can be naturally incorporated into this framework, i.e. extending permissibility to include safety, and thereby we can achieve both safety and improved efficiency. Experimental evaluation using three standard RL applications shows the effectiveness of the approach.

cs.LG↗