Search

Self-play, characterized by agents' interactions with copies or past versions of itself, has recently gained prominence in reinforcement learning. This paper first clarifies the preliminaries of self-play, including the multi-agent reinforcement learning framework and basic game theory concepts. Then it provides a unified framework and classifies existing self-play algorithms within this framework. Moreover, the paper bridges the gap between the algorithms and their practical implications by illustrating the role of self-play in different scenarios. Finally, the survey highlights open challenges and future research directions in self-play. This paper is an essential guide map for understanding the multifaceted landscape of self-play in RL.

Despite the remarkable ability of large vision-language models (LVLMs) in image comprehension, these models frequently generate plausible yet factually incorrect responses, a phenomenon known as hallucination.Recently, in large language models (LLMs), augmenting LLMs by retrieving information from external knowledge resources has been proven as a promising solution to mitigate hallucinations.However, the retrieval augmentation in LVLM significantly lags behind the widespread applications of LVLM. Moreover, when transferred to augmenting LVLMs, sometimes the hallucination degree of the model is even exacerbated.Motivated by the research gap and counter-intuitive phenomenon, we introduce a novel framework, the Active Retrieval-Augmented large vision-language model (ARA), specifically designed to address hallucinations by incorporating three critical dimensions: (i) dissecting the retrieval targets based on the inherent hierarchical structures of images. (ii) pinpointing the most effective retrieval methods and filtering out the reliable retrieval results. (iii) timing the retrieval process to coincide with episodes of low certainty, while circumventing unnecessary retrieval during periods of high certainty. To assess the capability of our proposed ARA model in reducing hallucination, we employ three widely used LVLM models (LLaVA-1.5, Qwen-VL, and mPLUG-Owl2) across four benchmarks. Our empirical observations suggest that by utilizing fitting retrieval mechanisms and timing the retrieval judiciously, we can effectively mitigate the hallucination problem. We hope that this study can provide deeper insights into how to adapt the retrieval augmentation to LVLMs for reducing hallucinations with more effective retrieval and minimal retrieval occurrences.

While Large Vision-Language Models (LVLMs) have exhibited remarkable capabilities across a wide range of tasks, they suffer from hallucination problems, where models generate plausible yet incorrect answers given the input image-query pair. This hallucination phenomenon is even more severe when querying the image in non-English languages, while existing methods for mitigating hallucinations in LVLMs only consider the English scenarios. In this paper, we make the first attempt to mitigate this important multilingual hallucination in LVLMs. With thorough experiment analysis, we found that multilingual hallucination in LVLMs is a systemic problem that could arise from deficiencies in multilingual capabilities or inadequate multimodal abilities. To this end, we propose a two-stage Multilingual Hallucination Removal (MHR) framework for LVLMs, aiming to improve resistance to hallucination for both high-resource and low-resource languages. Instead of relying on the intricate manual annotations of multilingual resources, we fully leverage the inherent capabilities of the LVLM and propose a novel cross-lingual alignment method, which generates multiple responses for each image-query input and then identifies the hallucination-aware pairs for each language. These data pairs are finally used for direct preference optimization to prompt the LVLMs to favor non-hallucinating responses. Experimental results show that our MHR achieves a substantial reduction in hallucination generation for LVLMs. Notably, on our extended multilingual POPE benchmark, our framework delivers an average increase of 19.0% in accuracy across 13 different languages. Our code and model weights are available at https://github.com/ssmisya/MHR

In this work, we introduce Gemma 2, a new addition to the Gemma family of lightweight, state-of-the-art open models, ranging in scale from 2 billion to 27 billion parameters. In this new version, we apply several known technical modifications to the Transformer architecture, such as interleaving local-global attentions (Beltagy et al., 2020a) and group-query attention (Ainslie et al., 2023). We also train the 2B and 9B models with knowledge distillation (Hinton et al., 2015) instead of next token prediction. The resulting models deliver the best performance for their size, and even offer competitive alternatives to models that are 2-3 times bigger. We release all our models to the community.

This paper solves a recursive optimal stopping problem with Poisson stopping constraints using the penalized backward stochastic differential equation (PBSDE) with jumps. Stopping in this problem is only allowed at Poisson random intervention times, and jumps play a significant role not only through the stopping times but also in the recursive objective functional and model coefficients. To solve the problem, we propose a decomposition method based on Jacod-Pham that allows us to separate the problem into a series of sub-problems between each pair of consecutive Poisson stopping times. To represent the value function of the recursive optimal stopping problem when the initial time falls between two consecutive Poisson stopping times and the generator is concave/convex, we leverage the comparison theorem of BSDEs with jumps. We then apply the representation result to American option pricing in a nonlinear market with Poisson stopping constraints., Comment: 27 pages

Using first-principles simulations combined with many-body calculations, we show that two-dimensional free-standing quintuple-layer Bi2Se2Te is an inversion symmetric monolayer expected to achieve spatially indirect exciton with large exciton radius, small exciton effective mass and long exciton lifetime. Such system is theoretically predicted to be a promising platform for realizing excitonic Bose-Einstein condensation and superfluid due to its high phase transition temperatures of ~257 K and ~64.25 K for the BEC and excitonic superfluid, respectively. The importance of spin-orbit coupling is revealed, and the angular momentum selection rules for photon absorption are discussed. This finding suggests the potential of QL Bi2Se2Te monolayer with exotic bosonic bound states provides as a tantalizing high-temperature platform to probe excitonic physics.

On-device large language models (LLMs), referring to running LLMs on edge devices, have raised considerable interest owing to their superior privacy, reduced latency, and bandwidth saving. Nonetheless, the capabilities of on-device LLMs are intrinsically constrained by the limited capacity of edge devices compared to the much more powerful cloud centers. To bridge the gap between cloud-based and on-device AI, mobile edge intelligence (MEI) presents a viable solution to this problem by provisioning AI capabilities within the edge of mobile networks with improved privacy and latency relative to cloud computing. MEI sits between on-device AI and cloud-based AI, featuring wireless communications and more powerful computing resources than end devices. This article provides a contemporary survey on harnessing MEI for LLMs. We first cover the preliminaries of LLMs, starting with LLMs and MEI, followed by resource-efficient LLM techniques. We then illustrate several killer applications to demonstrate the need for deploying LLMs at the network edge and present an architectural overview of MEI for LLMs (MEI4LLM). Subsequently, we delve into various aspects of MEI4LLM, extensively covering edge LLM caching and delivery, edge LLM training, and edge LLM inference. Finally, we identify future research opportunities. We aim to inspire researchers in the field to leverage mobile edge computing to facilitate LLM deployment in close proximity to users, thereby unleashing the potential of LLMs across various privacy- and delay-sensitive applications., Comment: 37 pages, 13 figures

Novel collinear magnet, the altermagnet (AM) with spin-splitting energy band and zero net magnetization have attracted great interest due to its potential spintronic applications. Here, we demonstrate AM-like phases in a microscopic Kondo lattice model, widely used for heavy fermion compounds. With the framework of fermionic parton mean-field theory, we find the $d$-wave AM state can coexist with the intrinsic Kondo screening effect in such itinerant-local electron system if an alternating next-nearest-neighbor-hopping (NNNH) is included. Such alternating NNNH take nonmagnetic atoms, neglected in usual antiferromagnetism study, into account when encountering real-life candidate AM materials. The AM-like states are characterized by their spin-splitting quasiparticle bands, Fermi surface, spin-resolved distribution function and conductivity. It is suggested that the magnetic quantum oscillation and charge transport measurement can detect those AM-like phases. We hope the present work may be useful for exploring AM-like phases in $f$-electron compounds., Comment: 14 pages, 12 figures

Analog compute-in-memory (CIM) in static random-access memory (SRAM) is promising for accelerating deep learning inference by circumventing the memory wall and exploiting ultra-efficient analog low-precision arithmetic. Latest analog CIM designs attempt bit-parallel schemes for multi-bit analog Matrix-Vector Multiplication (MVM), aiming at higher energy efficiency, throughput, and training simplicity and robustness over conventional bit-serial methods that digitally shift-and-add multiple partial analog computing results. However, bit-parallel operations require more complex analog computations and become more sensitive to well-known analog CIM challenges, including large cell areas, inefficient and inaccurate multi-bit analog operations, and vulnerability to PVT variations. This paper presents PICO-RAM, a PVT-insensitive and compact CIM SRAM macro with charge-domain bit-parallel computation. It adopts a multi-bit thin-cell Multiply-Accumulate (MAC) unit that shares the same transistor layout as the most compact 6T SRAM cell. All analog computing modules, including digital-to-analog converters (DACs), MAC units, analog shift-and-add, and analog-to-digital converters (ADCs) reuse one set of local capacitors inside the array, performing in-situ computation to save area and enhance accuracy. A compact 8.5-bit dual-threshold time-domain ADC power gates the main path most of the time, leading to a significant energy reduction. Our 65-nm prototype achieves the highest weight storage density of 559 Kb/mm${^2}$ and exceptional robustness to temperature and voltage variations (-40 to 105 $^{\circ}$C and 0.65 to 1.2 V) among SRAM-based analog CIM designs., Comment: This manuscript has been accepted to IEEE Journal of Solid-State Circuits (JSSC)

The conceptualization and categorization of natural objects in the human mind have long intrigued cognitive scientists and neuroscientists, offering crucial insights into human perception and cognition. Recently, the rapid development of Large Language Models (LLMs) has raised the attractive question of whether these models can also develop human-like object representations through exposure to vast amounts of linguistic and multimodal data. In this study, we combined behavioral and neuroimaging analysis methods to uncover how the object concept representations in LLMs correlate with those of humans. By collecting large-scale datasets of 4.7 million triplet judgments from LLM and Multimodal LLM (MLLM), we were able to derive low-dimensional embeddings that capture the underlying similarity structure of 1,854 natural objects. The resulting 66-dimensional embeddings were found to be highly stable and predictive, and exhibited semantic clustering akin to human mental representations. Interestingly, the interpretability of the dimensions underlying these embeddings suggests that LLM and MLLM have developed human-like conceptual representations of natural objects. Further analysis demonstrated strong alignment between the identified model embeddings and neural activity patterns in many functionally defined brain ROIs (e.g., EBA, PPA, RSC and FFA). This provides compelling evidence that the object representations in LLMs, while not identical to those in the human, share fundamental commonalities that reflect key schemas of human conceptual knowledge. This study advances our understanding of machine intelligence and informs the development of more human-like artificial cognitive systems.

We study the structure of scattering amplitudes of massive Kaluza-Klein (KK) states in the compactified 5-dimensional warped gauge and gravity theories. We present systematic formulations of the gauge theory equivalence theorem (GAET) and the gravitational equivalence theorem (GRET) for warped KK theories in $R_\xi^{}$ gauge, where the GAET connects the scattering amplitudes of longitudinal KK gauge bosons to that of the corresponding KK Goldstone bosons and the GRET connects the scattering amplitudes of KK gravitons of helicity-zero (helicity-one) to that of the corresponding gravitational KK Goldstone bosons. We analyze the structure of 3-point and 4-point scattering amplitudes of massive KK gauge bosons and of massive KK gravitons as well as their corresponding Goldstone bosons. We first prove the GAET and GRET explicitly for the fundamental 3-point KK gauge/gravity scattering amplitudes. We then demonstrate that the validity of the GAET and GRET for 4-point gauge/gravity scattering amplitudes can be reduced to the validity of GAET and GRET for 3-point gauge/gravity scattering amplitudes at tree level. With these, we study the double-copy construction of KK scattering amplitudes in the warped gauge/gravity theories. We newly realize the double-copy for massive 3-point full gauge/gravity amplitudes at tree level under proper correspondences of color-kinematics and of gauge/gravity couplings, whereas we can construct the double-copy for 4-point KK gauge/gravity amplitudes to the leading order (LO) of high energy expansion. We further demonstrate that this LO double-copy construction can be extended to $N$-point KK scattering amplitudes with $N\geqslant 4$., Comment: 91 pages. Improved version, references added

Over-the-air (OTA) firmware updates are essential for updating and maintaining IoT devices, especially those batteryless devices reliant on energy harvesting power sources. Flash memory, favored for its low cost and high density, is extensively used for data storage in many IoT devices. However, due to its high energy demands for update operations, there is often insufficient energy for code updates. This paper proposes an incremental flash-based OTA update approach tailored for energy harvesting IoT devices, tackling the challenges brought by limited memory resources and fluctuating energy availability. Our approach is composed of three techniques: segmentbased update packet design, deferred flash segment writes, and checkpoint-free update resumption. Segment-based update packet design segments firmware updates into smaller packets, each tailored for specific memory segments, thereby minimizing unnecessary flash operations and conserving energy. Deferred flash segment writes accumulate packets in Static Random-Access Memory (SRAM) for collective processing, reducing the frequency of energy-intensive operations. Crucially, our checkpointfree update resumption ensures efficient recovery from power interruptions without significant energy cost on data backup. Through thorough experimental evaluation, we have observed that our approach significantly reduces the total energy consumed during OTA updates, and decreases the average total update time in energy harvesting environments., Comment: 6 pages

The rise of online multi-modal sharing platforms like TikTok and YouTube has enabled personalized recommender systems to incorporate multiple modalities (such as visual, textual, and acoustic) into user representations. However, addressing the challenge of data sparsity in these systems remains a key issue. To address this limitation, recent research has introduced self-supervised learning techniques to enhance recommender systems. However, these methods often rely on simplistic random augmentation or intuitive cross-view information, which can introduce irrelevant noise and fail to accurately align the multi-modal context with user-item interaction modeling. To fill this research gap, we propose a novel multi-modal graph diffusion model for recommendation called DiffMM. Our framework integrates a modality-aware graph diffusion model with a cross-modal contrastive learning paradigm to improve modality-aware user representation learning. This integration facilitates better alignment between multi-modal feature information and collaborative relation modeling. Our approach leverages diffusion models' generative capabilities to automatically generate a user-item graph that is aware of different modalities, facilitating the incorporation of useful multi-modal knowledge in modeling user-item interactions. We conduct extensive experiments on three public datasets, consistently demonstrating the superiority of our DiffMM over various competitive baselines. For open-sourced model implementation details, you can access the source codes of our proposed framework at: https://github.com/HKUDS/DiffMM .

Efficient fine-tuning of large language models for task-specific applications is imperative, yet the vast number of parameters in these models makes their training increasingly challenging. Despite numerous proposals for effective methods, a substantial memory overhead remains for gradient computations during updates. \thm{Can we fine-tune a series of task-specific small models and transfer their knowledge directly to a much larger model without additional training?} In this paper, we explore weak-to-strong specialization using logit arithmetic, facilitating a direct answer to this question. Existing weak-to-strong methods often employ a static knowledge transfer ratio and a single small model for transferring complex knowledge, which leads to suboptimal performance. % To address this, To surmount these limitations, we propose a dynamic logit fusion approach that works with a series of task-specific small models, each specialized in a different task. This method adaptively allocates weights among these models at each decoding step, learning the weights through Kullback-Leibler divergence constrained optimization problems. We conduct extensive experiments across various benchmarks in both single-task and multi-task settings, achieving leading results. By transferring expertise from the 7B model to the 13B model, our method closes the performance gap by 96.4\% in single-task scenarios and by 86.3\% in multi-task scenarios compared to full fine-tuning of the 13B model. Notably, we achieve surpassing performance on unseen tasks. Moreover, we further demonstrate that our method can effortlessly integrate in-context learning for single tasks and task arithmetic for multi-task scenarios. (Our implementation is available in https://github.com/Facico/Dynamic-Logit-Fusion.), Comment: submit under review

In the era of large language models, model merging is a promising way to combine multiple task-specific models into a single multitask model without extra training. However, two challenges remain: (a) interference between different models and (b) heterogeneous data during testing. Traditional model merging methods often show significant performance gaps compared to fine-tuned models due to these issues. Additionally, a one-size-fits-all model lacks flexibility for diverse test data, leading to performance degradation. We show that both shared and exclusive task-specific knowledge are crucial for merging performance, but directly merging exclusive knowledge hinders overall performance. In view of this, we propose Twin-Merging, a method that encompasses two principal stages: (1) modularizing knowledge into shared and exclusive components, with compression to reduce redundancy and enhance efficiency; (2) dynamically merging shared and task-specific knowledge based on the input. This approach narrows the performance gap between merged and fine-tuned models and improves adaptability to heterogeneous data. Extensive experiments on $12$ datasets for both discriminative and generative tasks demonstrate the effectiveness of our method, showing an average improvement of $28.34\%$ in absolute normalized score for discriminative tasks and even surpassing the fine-tuned upper bound on the generative tasks. (Our implementation is available in https://github.com/LZY-the-boys/Twin-Mergin.), Comment: submit in review

We conducted a systematic comparison of statistical methods used for the analysis of time-to-event outcomes under various proportional and nonproportional hazard (NPH) scenarios. Our study used data from recently published oncology trials to compare the Log-rank test, still by far the most widely used option, against some available alternatives, including the MaxCombo test, the Restricted Mean Survival Time Difference (dRMST) test, the Generalized Gamma Model (GGM) and the Generalized F Model (GFM). Power, type I error rate, and time-dependent bias with respect to the RMST difference, survival probability difference, and median survival time were used to evaluate and compare the performance of these methods. In addition to the real data, we simulated three hypothetical scenarios with crossing hazards chosen so that the early and late effects 'cancel out' and used them to evaluate the ability of the aforementioned methods to detect time-specific and overall treatment effects. We implemented novel metrics for assessing the time-dependent bias in treatment effect estimates to provide a more comprehensive evaluation in NPH scenarios. Recommendations under each NPH scenario are provided by examining the type I error rate, power, and time-dependent bias associated with each statistical approach.

Dataset condensation (DC) methods aim to learn a smaller synthesized dataset with informative data records to accelerate the training of machine learning models. Current distribution matching (DM) based DC methods learn a synthesized dataset by matching the mean of the latent embeddings between the synthetic and the real dataset. However two distributions with the same mean can still be vastly different. In this work we demonstrate the shortcomings of using Maximum Mean Discrepancy to match latent distributions i.e. the weak matching power and lack of outlier regularization. To alleviate these shortcomings we propose our new method: Latent Quantile Matching (LQM) which matches the quantiles of the latent embeddings to minimize the goodness of fit test statistic between two distributions. Empirical experiments on both image and graph-structured datasets show that LQM matches or outperforms previous state of the art in distribution matching based DC. Moreover we show that LQM improves the performance in continual graph learning (CGL) setting where memory efficiency and privacy can be important. Our work sheds light on the application of DM based DC for CGL., Comment: Accepted by CVPR Workshop 2024: 1st Workshop on Dataset Distillation for Computer Vision

Text classification is a crucial task encountered frequently in practical scenarios, yet it is still under-explored in the era of large language models (LLMs). This study shows that LLMs are vulnerable to changes in the number and arrangement of options in text classification. Our extensive empirical analyses reveal that the key bottleneck arises from ambiguous decision boundaries and inherent biases towards specific tokens and positions. To mitigate these issues, we make the first attempt and propose a novel two-stage classification framework for LLMs. Our approach is grounded in the empirical observation that pairwise comparisons can effectively alleviate boundary ambiguity and inherent bias. Specifically, we begin with a self-reduction technique to efficiently narrow down numerous options, which contributes to reduced decision space and a faster comparison process. Subsequently, pairwise contrastive comparisons are employed in a chain-of-thought manner to draw out nuances and distinguish confusable options, thus refining the ambiguous decision boundary. Extensive experiments on four datasets (Banking77, HWU64, LIU54, and Clinic150) verify the effectiveness of our framework. Furthermore, benefitting from our framework, various LLMs can achieve consistent improvements. Our code and data are available in \url{https://github.com/Chuge0335/PC-CoT}., Comment: ACL2024 findings

The High Energy Photon Source (HEPS) represents a fourth-generation light source. This facility has made unprecedented advancements in accelerator technology, necessitating the development of new detectors to satisfy physical requirements such as single-photon resolution, large dynamic range, and high frame rates. Since 2016, the Institute of High Energy Physics has introduced the first user-experimental hybrid pixel detector, progressing to the fourth-generation million-pixel detector designed for challenging conditions, with the dual-threshold single-photon detector HEPS-Beijing PIXel (HEPS-BPIX) set as the next-generation target. HEPS-BPIX will employ the entirely new Application-Specific Integrated Circuit (ASIC) BP40 for pixel information readout. Data flow will be managed and controlled through readout electronics based on a two-tier Field-Programmable Gate Array (FPGA) system: the Front-End Electronics (FEE) and the Input-Output Board (IOB) handle the fan-out for 12 ASICs, and the u4FCP is tasked with processing serial data on high-speed links, transferring pixel-level data to the back-end RTM and uTCA chassis, or independently outputting through a network port, enabling remote control of the entire detector. The new HEPS-BPIX firmware has undergone a comprehensive redesign and update to meet the electronic characteristics of the new chip and to improve the overall performance of the detector. We provide an overview of the core subunits of HEPS-BPIX, emphasizing the readout system, evaluating the new hardware and firmware, and highlighting some of its innovative features and characteristics.

The core of the dialogue system is to generate relevant, informative, and human-like responses based on extensive dialogue history. Recently, dialogue generation domain has seen mainstream adoption of large language models (LLMs), due to its powerful capability in generating utterances. However, there is a natural deficiency for such models, that is, inherent position bias, which may lead them to pay more attention to the nearby utterances instead of causally relevant ones, resulting in generating irrelevant and generic responses in long-term dialogue. To alleviate such problem, in this paper, we propose a novel method, named Causal Perception long-term Dialogue framework (CPD), which employs perturbation-based causal variable discovery method to extract casually relevant utterances from the dialogue history and enhances model causal perception during fine-tuning. Specifically, a local-position awareness method is proposed in CPD for inter-sentence position correlation elimination, which helps models extract causally relevant utterances based on perturbations. Then, a casual-perception fine-tuning strategy is also proposed, to enhance the capability of discovering the causal invariant factors, by differently perturbing causally relevant and non-casually relevant ones for response generation. Experimental results on two datasets prove that our proposed method can effectively alleviate the position bias for multiple LLMs and achieve significant progress compared with existing baselines., Comment: Accepted to IJCAI 2024

Recently, the topic-grounded dialogue (TGD) system has become increasingly popular as its powerful capability to actively guide users to accomplish specific tasks through topic-guided conversations. Most existing works utilize side information (\eg topics or personas) in isolation to enhance the topic selection ability. However, due to disregarding the noise within these auxiliary information sources and their mutual influence, current models tend to predict user-uninteresting and contextually irrelevant topics. To build user-engaging and coherent dialogue agent, we propose a \textbf{P}ersonalized topic s\textbf{E}lection model for \textbf{T}opic-grounded \textbf{D}ialogue, named \textbf{PETD}, which takes account of the interaction of side information to selectively aggregate such information for more accurately predicting subsequent topics. Specifically, we evaluate the correlation between global topics and personas and selectively incorporate the global topics aligned with user personas. Furthermore, we propose a contrastive learning based persona selector to filter out irrelevant personas under the constraint of lacking pertinent persona annotations. Throughout the selection and generation, diverse relevant side information is considered. Extensive experiments demonstrate that our proposed method can generate engaging and diverse responses, outperforming state-of-the-art baselines across various evaluation metrics., Comment: Accepted to ACL 2024 Findings

Cross-lingual named entity recognition (NER) aims to train an NER model for the target language leveraging only labeled source language data and unlabeled target language data. Prior approaches either perform label projection on translated source language data or employ a source model to assign pseudo labels for target language data and train a target model on these pseudo-labeled data to generalize to the target language. However, these automatic labeling procedures inevitably introduce noisy labels, thus leading to a performance drop. In this paper, we propose a Global-Local Denoising framework (GLoDe) for cross-lingual NER. Specifically, GLoDe introduces a progressive denoising strategy to rectify incorrect pseudo labels by leveraging both global and local distribution information in the semantic space. The refined pseudo-labeled target language data significantly improves the model's generalization ability. Moreover, previous methods only consider improving the model with language-agnostic features, however, we argue that target language-specific features are also important and should never be ignored. To this end, we employ a simple auxiliary task to achieve this goal. Experimental results on two benchmark datasets with six target languages demonstrate that our proposed GLoDe significantly outperforms current state-of-the-art methods., Comment: Accepted by IJCAI 2024

This paper introduces Fortune Analytics Language Model (FALM). FALM empowers users with direct access to comprehensive business analysis, including market trends, company performance metrics, and expert insights. Unlike generic LLMs, FALM leverages a curated knowledge base built from professional journalism, enabling it to deliver precise and in-depth answers to intricate business questions. Users can further leverage natural language queries to directly visualize financial data, generating insightful charts and graphs to understand trends across diverse business sectors clearly. FALM fosters user trust and ensures output accuracy through three novel methods: 1) Time-aware reasoning guarantees accurate event registration and prioritizes recent updates. 2) Thematic trend analysis explicitly examines topic evolution over time, providing insights into emerging business landscapes. 3) Content referencing and task decomposition enhance answer fidelity and data visualization accuracy. We conduct both automated and human evaluations, demonstrating FALM's significant performance improvements over baseline methods while prioritizing responsible AI practices. These benchmarks establish FALM as a cutting-edge LLM in the business and media domains, with exceptional accuracy and trustworthiness.

Incorporating Knowledge Graphs into Recommendation has attracted growing attention in industry, due to the great potential of KG in providing abundant supplementary information and interpretability for the underlying models. However, simply integrating KG into recommendation usually brings in negative feedback in industry, due to the ignorance of the following two factors: i) users' multiple intents, which involve diverse nodes in KG. For example, in e-commerce scenarios, users may exhibit preferences for specific styles, brands, or colors. ii) knowledge noise, which is a prevalent issue in Knowledge Enhanced Recommendation (KGR) and even more severe in industry scenarios. The irrelevant knowledge properties of items may result in inferior model performance compared to approaches that do not incorporate knowledge. To tackle these challenges, we propose a novel approach named Knowledge Enhanced Multi-intent Transformer Network for Recommendation (KGTN), comprising two primary modules: Global Intents Modeling with Graph Transformer, and Knowledge Contrastive Denoising under Intents. Specifically, Global Intents with Graph Transformer focuses on capturing learnable user intents, by incorporating global signals from user-item-relation-entity interactions with a graph transformer, meanwhile learning intent-aware user/item representations. Knowledge Contrastive Denoising under Intents is dedicated to learning precise and robust representations. It leverages intent-aware representations to sample relevant knowledge, and proposes a local-global contrastive mechanism to enhance noise-irrelevant representation learning. Extensive experiments conducted on benchmark datasets show the superior performance of our proposed method over the state-of-the-arts. And online A/B testing results on Alibaba large-scale industrial recommendation platform also indicate the real-scenario effectiveness of KGTN., Comment: Accept By The Web Conf 2024 (WWW 2024) Industry Track. arXiv admin note: text overlap with arXiv:2204.08807

The recent 1/2-equation model of turbulence is a simplification of the standard Kolmogorov-Prandtl 1-equation URANS model. Surprisingly, initial numerical tests indicated that the 1/2-equation model produces comparable velocity statistics at reduced cost. It is also a test problem and first step for developing numerical analysis to address a full 1-equation model. This report begins the numerical analysis of the 1/2 equation model. Stability, convergence and error estimates are proven for a semi-discrete and fully discrete approximation. Finally, numerical tests are conducted to validate our convergence theory.

We explore the bound neutrons decay into invisible particles (e.g., $n\rightarrow 3 \nu$ or $nn \rightarrow 2 \nu$) in the JUNO liquid scintillator detector. The invisible decay includes two decay modes: $ n \rightarrow { inv} $ and $ nn \rightarrow { inv} $. The invisible decays of $s$-shell neutrons in $^{12}{\rm C}$ will leave a highly excited residual nucleus. Subsequently, some de-excitation modes of the excited residual nuclei can produce a time- and space-correlated triple coincidence signal in the JUNO detector. Based on a full Monte Carlo simulation informed with the latest available data, we estimate all backgrounds, including inverse beta decay events of the reactor antineutrino $\bar{\nu}_e$, natural radioactivity, cosmogenic isotopes and neutral current interactions of atmospheric neutrinos. Pulse shape discrimination and multivariate analysis techniques are employed to further suppress backgrounds. With two years of exposure, JUNO is expected to give an order of magnitude improvement compared to the current best limits. After 10 years of data taking, the JUNO expected sensitivities at a 90% confidence level are $\tau/B( n \rightarrow { inv} ) > 5.0 \times 10^{31} \, {\rm yr}$ and $\tau/B( nn \rightarrow { inv} ) > 1.4 \times 10^{32} \, {\rm yr}$., Comment: 28 pages, 7 figures, 4 tables

Temporal Knowledge Graph Reasoning (TKGR) is the process of utilizing temporal information to capture complex relations within a Temporal Knowledge Graph (TKG) to infer new knowledge. Conventional methods in TKGR typically depend on deep learning algorithms or temporal logical rules. However, deep learning-based TKGRs often lack interpretability, whereas rule-based TKGRs struggle to effectively learn temporal rules that capture temporal patterns. Recently, Large Language Models (LLMs) have demonstrated extensive knowledge and remarkable proficiency in temporal reasoning. Consequently, the employment of LLMs for Temporal Knowledge Graph Reasoning (TKGR) has sparked increasing interest among researchers. Nonetheless, LLMs are known to function as black boxes, making it challenging to comprehend their reasoning process. Additionally, due to the resource-intensive nature of fine-tuning, promptly updating LLMs to integrate evolving knowledge within TKGs for reasoning is impractical. To address these challenges, in this paper, we propose a Large Language Models-guided Dynamic Adaptation (LLM-DA) method for reasoning on TKGs. Specifically, LLM-DA harnesses the capabilities of LLMs to analyze historical data and extract temporal logical rules. These rules unveil temporal patterns and facilitate interpretable reasoning. To account for the evolving nature of TKGs, a dynamic adaptation strategy is proposed to update the LLM-generated rules with the latest events. This ensures that the extracted rules always incorporate the most recent knowledge and better generalize to the predictions on future events. Experimental results show that without the need of fine-tuning, LLM-DA significantly improves the accuracy of reasoning over several common datasets, providing a robust framework for TKGR tasks.

We establish the global $C^2$-estimates for the modified $\sigma_2$ curvature equation with prescribed boundary mean curvature, and particularly, the local boundary $C^2$ estimates on three-manifolds., Comment: Comments welcome

We propose a deep learning algorithm for high dimensional optimal stopping problems. Our method is inspired by the penalty method for solving free boundary PDEs. Within our approach, the penalized PDE is approximated using the Deep BSDE framework proposed by \cite{weinan2017deep}, which leads us to coin the term "Deep Penalty Method (DPM)" to refer to our algorithm. We show that the error of the DPM can be bounded by the loss function and $O(\frac{1}{\lambda})+O(\lambda h) +O(\sqrt{h})$, where $h$ is the step size in time and $\lambda$ is the penalty parameter. This finding emphasizes the need for careful consideration when selecting the penalization parameter and suggests that the discretization error converges at a rate of order $\frac{1}{2}$. We validate the efficacy of the DPM through numerical tests conducted on a high-dimensional optimal stopping model in the area of American option pricing. The numerical tests confirm both the accuracy and the computational efficiency of our proposed algorithm.

Multivariate time series forecasting (MTSF) is crucial for decision-making to precisely forecast the future values/trends, based on the complex relationships identified from historical observations of multiple sequences. Recently, Spatial-Temporal Graph Neural Networks (STGNNs) have gradually become the theme of MTSF model as their powerful capability in mining spatial-temporal dependencies, but almost of them heavily rely on the assumption of historical data integrity. In reality, due to factors such as data collector failures and time-consuming repairment, it is extremely challenging to collect the whole historical observations without missing any variable. In this case, STGNNs can only utilize a subset of normal variables and easily suffer from the incorrect spatial-temporal dependency modeling issue, resulting in the degradation of their forecasting performance. To address the problem, in this paper, we propose a novel Graph Interpolation Attention Recursive Network (named GinAR) to precisely model the spatial-temporal dependencies over the limited collected data for forecasting. In GinAR, it consists of two key components, that is, interpolation attention and adaptive graph convolution to take place of the fully connected layer of simple recursive units, and thus are capable of recovering all missing variables and reconstructing the correct spatial-temporal dependencies for recursively modeling of multivariate time series data, respectively. Extensive experiments conducted on five real-world datasets demonstrate that GinAR outperforms 11 SOTA baselines, and even when 90% of variables are missing, it can still accurately predict the future values of all variables., Comment: Accepted by KDD 2024 (Research track)

A recent experiment observes a series of quantum spin Hall effects in transition metal dichalcogenide moir\'e MoTe$_2$ [K. Kang, \textit{et. al}, Nature 628, 522-526 (2024)]. Among them, the filling $\nu=3$ state points to a time-reversal pair of edge states resembling those of the even-denominator fractional Chern insulators (FCIs). Inspired by this discovery, we investigate whether a robust incompressible quantum Hall liquid can be stabilized in the half-filled Chern band of twisted MoTe$_2$ bilayers. We use the continuum model with parameters relevant to twisted MoTe$_2$ bilayers and obtain three consecutive nearly flat Chern bands with the same Chern number. Crucially, when the second moir\'e miniband is half-filled, signatures of non-Abelian states are found via exact diagonalization calculations, including the stable six-fold ground state degeneracy which grows more robust for larger lattice sizes and is consistent with an even-denominator FCI state. We further perform flux insertion simulations to reveal a 1/2 quantized many-body Chern number as direct evidence of topological order. Furthermore, the ground state density structure factors show no sharp peak, indicating no charge density wave order. These evidences signal the potential of realizing the non-Abelian state at zero magnetic field in twisted bilayer MoTe$_2$ at the fractional hole filling 3/2., Comment: a complete undated version with errors corrected

Recommender systems play a crucial role in tackling the challenge of information overload by delivering personalized recommendations based on individual user preferences. Deep learning techniques, such as RNNs, GNNs, and Transformer architectures, have significantly propelled the advancement of recommender systems by enhancing their comprehension of user behaviors and preferences. However, supervised learning methods encounter challenges in real-life scenarios due to data sparsity, resulting in limitations in their ability to learn representations effectively. To address this, self-supervised learning (SSL) techniques have emerged as a solution, leveraging inherent data structures to generate supervision signals without relying solely on labeled data. By leveraging unlabeled data and extracting meaningful representations, recommender systems utilizing SSL can make accurate predictions and recommendations even when confronted with data sparsity. In this paper, we provide a comprehensive review of self-supervised learning frameworks designed for recommender systems, encompassing a thorough analysis of over 170 papers. We conduct an exploration of nine distinct scenarios, enabling a comprehensive understanding of SSL-enhanced recommenders in different contexts. For each domain, we elaborate on different self-supervised learning paradigms, namely contrastive learning, generative learning, and adversarial learning, so as to present technical details of how SSL enhances recommender systems in various contexts. We consistently maintain the related open-source materials at https://github.com/HKUDS/Awesome-SSLRec-Papers.

The Circular Electron Positron Collider (CEPC) has been proposed to enable more thorough and precise measurements of the properties of Higgs, W, and Z bosons, as well as to search for new physics. In response to the stringent performance requirements of the vertex detector for the CEPC, a baseline vertex detector prototype was tested and characterized for the first time using a 6 GeV electron beam at DESY II Test Beam Line 21. The baseline vertex detector prototype is designed with a cylindrical barrel structure that contains six double-sided detector modules (ladders). Each side of the ladder includes TaichuPix-3 sensors based on Monolithic Active Pixel Sensor (MAPS) technology, a flexible printed circuit, and a carbon fiber support structure. Additionally, the readout electronics and the Data Acquisition system were also examined during this beam test. The performance of the prototype was evaluated using an electron beam that passed through six ladders in a perpendicular direction. The offline data analysis indicates a spatial resolution of about 5 um, with detection efficiency exceeding 99 % and an impact parameter resolution of about 5.1 um. These promising results from this baseline vertex detector prototype mark a significant step toward realizing the optimal vertex detector for the CEPC.

We obtain the Liouville theorem for constant $k$-curvature $\sigma_{k}(A_{g})$ in $\mathbb{R}_{+}^{n}$ with constant $\mathcal{B}_{k}^{g}$ curvature on $\partial\mathbb{R}_{+}^{n}$, where $\mathcal{B}_{k}^{g}$ is derived from the variational functional for $\sigma_{k}(A_{g})$, and specially represents the boundary term in the Gauss-Bonnet-Chern formula for $k=n/2$., Comment: Comments Welcome

The integrated device of a perovskite solar cell with a Li-ion battery is an innovative solution for decentralized energy storage in smart electronic devices. In this study, we examine the stability of Li ions intercalated in a CsPbI$_3$ perovskite and their effect on the electronic structure of Li$_x$CsPbI$_3$ compounds using first-principles density functional theory. Our simulations demonstrate that the insertion of Li at concentrations up to $x$ = 1 into CsPbI$_3$ is energetically possible. Moreover, we identify that the distortion of the Pb-I octahedra has the strongest impact on the change in the electronic band gap. Specifically, an increase in the amount of intercalated Li causes larger structural distortions, which in turn lead to an increasing band gap as function of the Li content.

The advent of deep reinforcement learning (DRL) has significantly advanced the field of robotics, particularly in the control and coordination of quadruped robots. However, the complexity of real-world tasks often necessitates the deployment of multi-robot systems capable of sophisticated interaction and collaboration. To address this need, we introduce the Multi-agent Quadruped Environment (MQE), a novel platform designed to facilitate the development and evaluation of multi-agent reinforcement learning (MARL) algorithms in realistic and dynamic scenarios. MQE emphasizes complex interactions between robots and objects, hierarchical policy structures, and challenging evaluation scenarios that reflect real-world applications. We present a series of collaborative and competitive tasks within MQE, ranging from simple coordination to complex adversarial interactions, and benchmark state-of-the-art MARL algorithms. Our findings indicate that hierarchical reinforcement learning can simplify task learning, but also highlight the need for advanced algorithms capable of handling the intricate dynamics of multi-agent interactions. MQE serves as a stepping stone towards bridging the gap between simulation and practical deployment, offering a rich environment for future research in multi-agent systems and robot learning. For open-sourced code and more details of MQE, please refer to https://ziyanx02.github.io/multiagent-quadruped-environment/ ., Comment: Open-source code is available at https://github.com/ziyanx02/multiagent-quadruped-environment

The increasing complexity of deep neural networks poses significant barriers to democratizing them to resource-limited edge devices. To address this challenge, split federated learning (SFL) has emerged as a promising solution by of floading the primary training workload to a server via model partitioning while enabling parallel training among edge devices. However, although system optimization substantially influences the performance of SFL under resource-constrained systems, the problem remains largely uncharted. In this paper, we provide a convergence analysis of SFL which quantifies the impact of model splitting (MS) and client-side model aggregation (MA) on the learning performance, serving as a theoretical foundation. Then, we propose AdaptSFL, a novel resource-adaptive SFL framework, to expedite SFL under resource-constrained edge computing systems. Specifically, AdaptSFL adaptively controls client-side MA and MS to balance communication-computing latency and training convergence. Extensive simulations across various datasets validate that our proposed AdaptSFL framework takes considerably less time to achieve a target accuracy than benchmarks, demonstrating the effectiveness of the proposed strategies., Comment: 15 pages, 10 figures

To meet the requirements of real-world applications, it is essential to control generations of large language models (LLMs). Prior research has tried to introduce reinforcement learning (RL) into controllable text generation while most existing methods suffer from overfitting issues (finetuning-based methods) or semantic collapse (post-processing methods). However, current RL methods are generally guided by coarse-grained (sentence/paragraph-level) feedback, which may lead to suboptimal performance owing to semantic twists or progressions within sentences. To tackle that, we propose a novel reinforcement learning algorithm named TOLE which formulates TOken-LEvel rewards for controllable text generation, and employs a "first-quantize-then-noise" paradigm to enhance the robustness of the RL algorithm.Furthermore, TOLE can be flexibly extended to multiple constraints with little computational expense. Experimental results show that our algorithm can achieve superior performance on both single-attribute and multi-attribute control tasks. We have released our codes at https://github.com/WindyLee0822/CTG, Comment: Accepted to NAACL 2024 Findings

In this paper, a novel cyber-insurance model design is proposed based on system risk evaluation with smart technology applications. The cyber insurance policy for power systems is tailored via cyber risk modeling, reliability impact analysis, and insurance premium calculation. A stochastic Epidemic Network Model is developed to evaluate the cyber risk by propagating cyberattacks among graphical vulnerabilities. Smart technologies deployed in risk modeling include smart monitoring and job thread assignment. Smart monitoring boosts the substation availability against cyberattacks with preventive and corrective measures. The job thread assignment solution reduces the execution failures by distributing the control and monitoring tasks to multiple threads. Reliability assessment is deployed to estimate load losses convertible to monetary losses. These monetary losses would be shared through a mutual insurance plan. To ensure a fair distribution of indemnity, a new Shapley mutual insurance principle is devised. Effectiveness of the proposed Shapley mutual insurance design is validated via case studies. The Shapley premium is compared with existent premium designs. It is shown that the Shapley premium has high indemnity levels closer to those of Tail Conditional Expectation premium. Meanwhile, the Shapley premium is nearly as affordable as the coalitional premium and keeps a relatively low insolvency probability., Comment: Power system reliability, cyber-insurance, power system security, cyber-physical systems, cyber risk modeling, actuarial design, tail risk

Halide perovskites are highly promising light-harvesting materials with strong ionic character, enabling in principle the combination of a solar cell and a Li-ion battery in one integrated photo-battery device. Here, we investigate Li ions inside crystals of CsPbI$_3$, as a prototype compound, by means of density-functional-theory calculations. Our findings demonstrate that the interstitial location and migration of Li ions depend strongly on the dynamic nature of the crystal structure of the perovskite compound. We consider two limiting cases for Li in CsPbI$_{3}$,(i) the cubic-symmetry structure as a model for the limit of fast ion motion and (ii) a distorted cubic structure as a model for the limit of slow ion motion. For both limiting cases we obtain moderate energy barriers for migrating Li ions, which highlight the potential of halide perovskites like CsPbI$_3$ for applications in photo-battery devices.

We demonstrate the existence of a topological chiral spin liquid in the frustrated Shastry-Sutherland Heisenberg model with an additional spin chirality interaction, using numerically unbiased exact diagonalization and density matrix renormalization group methods. We establish a quantum phase diagram where conventional phases, including dimer singlet, plaquette singlet, N{\' e}el and collinear phase, can be clearly identified by suitable local order parameters. Among them a $SU(2)_1$ chiral spin liquid emerges in the highly frustrated region, which is unambiguously identified by two topologically degenerate ground states, modular matrix, and characteristic level counting in entanglement spectrum, featuring the same topological order of $\nu=1/2$ bosonic Laughlin state. The phase boundaries among the different orders are determined by the energy level crossing analysis and wave function fidelity susceptibility., Comment: 8 pages, 7 figures