Search

Recently, deep generative models have greatly advanced the progress of face video coding towards promising rate-distortion performance and diverse application functionalities. Beyond traditional hybrid video coding paradigms, Generative Face Video Compression (GFVC) relying on the strong capabilities of deep generative models and the philosophy of early Model-Based Coding (MBC) can facilitate the compact representation and realistic reconstruction of visual face signal, thus achieving ultra-low bitrate face video communication. However, these GFVC algorithms are sometimes faced with unstable reconstruction quality and limited bitrate ranges. To address these problems, this paper proposes a novel Progressive Face Video Compression framework, namely PFVC, that utilizes adaptive visual tokens to realize exceptional trade-offs between reconstruction robustness and bandwidth intelligence. In particular, the encoder of the proposed PFVC projects the high-dimensional face signal into adaptive visual tokens in a progressive manner, whilst the decoder can further reconstruct these adaptive visual tokens for motion estimation and signal synthesis with different granularity levels. Experimental results demonstrate that the proposed PFVC framework can achieve better coding flexibility and superior rate-distortion performance in comparison with the latest Versatile Video Coding (VVC) codec and the state-of-the-art GFVC algorithms. The project page can be found at https://github.com/Berlin0610/PFVC.

Anti-Money Laundering (AML) involves the identification of money laundering crimes in financial activities, such as cryptocurrency transactions. Recent studies advanced AML through the lens of graph-based machine learning, modeling the web of financial transactions as a graph and developing graph methods to identify suspicious activities. For instance, a recent effort on opensourcing datasets and benchmarks, Elliptic2, treats a set of Bitcoin addresses, considered to be controlled by the same entity, as a graph node and transactions among entities as graph edges. This modeling reveals the "shape" of a money laundering scheme - a subgraph on the blockchain. Despite the attractive subgraph classification results benchmarked by the paper, competitive methods remain expensive to apply due to the massive size of the graph; moreover, existing methods require candidate subgraphs as inputs which may not be available in practice. In this work, we introduce RevTrack, a graph-based framework that enables large-scale AML analysis with a lower cost and a higher accuracy. The key idea is to track the initial senders and the final receivers of funds; these entities offer a strong indication of the nature (licit vs. suspicious) of their respective subgraph. Based on this framework, we propose RevClassify, which is a neural network model for subgraph classification. Additionally, we address the practical problem where subgraph candidates are not given, by proposing RevFilter. This method identifies new suspicious subgraphs by iteratively filtering licit transactions, using RevClassify. Benchmarking these methods on Elliptic2, a new standard for AML, we show that RevClassify outperforms state-of-the-art subgraph classification techniques in both cost and accuracy. Furthermore, we demonstrate the effectiveness of RevFilter in discovering new suspicious subgraphs, confirming its utility for practical AML., Comment: ICAIF 2024. Code is available at https://github.com/MITIBMxGraph/RevTrack

Social media is recognized as an important source for deriving insights into public opinion dynamics and social impacts due to the vast textual data generated daily and the 'unconstrained' behavior of people interacting on these platforms. However, such analyses prove challenging due to the semantic shift phenomenon, where word meanings evolve over time. This paper proposes an unsupervised dynamic word embedding method to capture longitudinal semantic shifts in social media data without predefined anchor words. The method leverages word co-occurrence statistics and dynamic updating to adapt embeddings over time, addressing the challenges of data sparseness, imbalanced distributions, and synergistic semantic effects. Evaluated on a large COVID-19 Twitter dataset, the method reveals semantic evolution patterns of vaccine- and symptom-related entities across different pandemic stages, and their potential correlations with real-world statistics. Our key contributions include the dynamic embedding technique, empirical analysis of COVID-19 semantic shifts, and discussions on enhancing semantic shift modeling for computational social science research. This study enables capturing longitudinal semantic dynamics on social media to understand public discourse and collective phenomena.

Multimodal learning has gained increasing importance across various fields, offering the ability to integrate data from diverse sources such as images, text, and personalized records, which are frequently observed in medical domains. However, in scenarios where some modalities are missing, many existing frameworks struggle to accommodate arbitrary modality combinations, often relying heavily on a single modality or complete data. This oversight of potential modality combinations limits their applicability in real-world situations. To address this challenge, we propose Flex-MoE (Flexible Mixture-of-Experts), a new framework designed to flexibly incorporate arbitrary modality combinations while maintaining robustness to missing data. The core idea of Flex-MoE is to first address missing modalities using a new missing modality bank that integrates observed modality combinations with the corresponding missing ones. This is followed by a uniquely designed Sparse MoE framework. Specifically, Flex-MoE first trains experts using samples with all modalities to inject generalized knowledge through the generalized router ($\mathcal{G}$-Router). The $\mathcal{S}$-Router then specializes in handling fewer modality combinations by assigning the top-1 gate to the expert corresponding to the observed modality combination. We evaluate Flex-MoE on the ADNI dataset, which encompasses four modalities in the Alzheimer's Disease domain, as well as on the MIMIC-IV dataset. The results demonstrate the effectiveness of Flex-MoE highlighting its ability to model arbitrary modality combinations in diverse missing modality scenarios. Code is available at https://github.com/UNITES-Lab/flex-moe., Comment: NeurIPS 2024 Spotlight

In this paper, we propose a new framework for zero-shot object navigation. Existing zero-shot object navigation methods prompt LLM with the text of spatially closed objects, which lacks enough scene context for in-depth reasoning. To better preserve the information of environment and fully exploit the reasoning ability of LLM, we propose to represent the observed scene with 3D scene graph. The scene graph encodes the relationships between objects, groups and rooms with a LLM-friendly structure, for which we design a hierarchical chain-of-thought prompt to help LLM reason the goal location according to scene context by traversing the nodes and edges. Moreover, benefit from the scene graph representation, we further design a re-perception mechanism to empower the object navigation framework with the ability to correct perception error. We conduct extensive experiments on MP3D, HM3D and RoboTHOR environments, where SG-Nav surpasses previous state-of-the-art zero-shot methods by more than 10% SR on all benchmarks, while the decision process is explainable. To the best of our knowledge, SG-Nav is the first zero-shot method that achieves even higher performance than supervised object navigation methods on the challenging MP3D benchmark., Comment: Accepted to NeurIPS 2024. Project page: https://bagh2178.github.io/SG-Nav/

Large language models (LLMs) have achieved reasonable quality improvements in machine translation (MT). However, most current research on MT-LLMs still faces significant challenges in maintaining translation consistency and accuracy when processing entire documents. In this paper, we introduce DelTA, a Document-levEL Translation Agent designed to overcome these limitations. DelTA features a multi-level memory structure that stores information across various granularities and spans, including Proper Noun Records, Bilingual Summary, Long-Term Memory, and Short-Term Memory, which are continuously retrieved and updated by auxiliary LLM-based components. Experimental results indicate that DelTA significantly outperforms strong baselines in terms of translation consistency and quality across four open/closed-source LLMs and two representative document translation datasets, achieving an increase in consistency scores by up to 4.58 percentage points and in COMET scores by up to 3.16 points on average. DelTA employs a sentence-by-sentence translation strategy, ensuring no sentence omissions and offering a memory-efficient solution compared to the mainstream method. Furthermore, DelTA improves pronoun translation accuracy, and the summary component of the agent also shows promise as a tool for query-based summarization tasks. We release our code and data at https://github.com/YutongWang1216/DocMTAgent.

In this paper, we propose a post-training quantization framework of large vision-language models (LVLMs) for efficient multi-modal inference. Conventional quantization methods sequentially search the layer-wise rounding functions by minimizing activation discretization errors, which fails to acquire optimal quantization strategy without considering cross-layer dependency. On the contrary, we mine the cross-layer dependency that significantly influences discretization errors of the entire vision-language model, and embed this dependency into optimal quantization strategy searching with low search cost. Specifically, we observe the strong correlation between the activation entropy and the cross-layer dependency concerning output discretization errors. Therefore, we employ the entropy as the proxy to partition blocks optimally, which aims to achieve satisfying trade-offs between discretization errors and the search cost. Moreover, we optimize the visual encoder to disentangle the cross-layer dependency for fine-grained decomposition of search space, so that the search cost is further reduced without harming the quantization accuracy. Experimental results demonstrate that our method compresses the memory by 2.78x and increase generate speed by 1.44x about 13B LLaVA model without performance degradation on diverse multi-modal reasoning tasks. Code is available at https://github.com/ChangyuanWang17/QVLM.

Resource competition problems are often modeled using Colonel Blotto games. However, Colonel Blotto games only simulate scenarios where players act simultaneously. In many real-life scenarios, competition is sequential, such as cybersecurity, cloud services, Web investments, and more. To model such sequential competition, we model the Lottery Colonel Blotto game as a Stackelberg game. We solve the Stackelberg equilibrium in the Lottery Colonel Blotto game in which the first mover's strategy is actually a solution to a bi-level optimization problem. We develop a constructive method that allows for a series of game reductions. This method enables us to compute the leader's optimal commitment strategy in a polynomial number of iterations. Furthermore, we identify the conditions under which the Stackelberg equilibrium aligns with the Nash equilibria. Finally, we show that by making the optimal first move, the leader can improve utility by an infinite factor compared to its utility in the Nash equilibria. We find that the player with a smaller budget has a greater incentive to become the leader in the game. Surprisingly, even when the leader adopts the optimal commitment strategy, the follower's utility may improve compared to that in Nash equilibria.

The Mpemba effect (MPE), named after a student who first observed the phenomenon, has intrigued scientists for decades by showing that hot liquid can freeze faster than cold under certain conditions. Recently, analogous effects have been identified in integrable quantum systems. However, a key distinction between the classical MPE and its quantum analog is that the latter relies predominantly on the of the properties of the initial states rather than the cooling rate. In this paper, we explore the quench dynamics of Sachdev-Ye-Kitaev (SYK) systems coupled to thermal baths. We investigate three scenarios--SYK systems coupled to SYK thermal baths, SYK systems coupled to two thermal baths at different temperatures, and dissipative SYKs modeled by the Lindblad equation. In the regimes where the system and the baths are strongly coupled, we observe effective temperature oscillations and Mpemba crossings (MPCs)--the effect of temperature crossings which are absent in quasi-equilibrium thermodynamic analysis--when the system is strongly coupled to SYK thermal baths. These effects are not observed in the Liouvillian formalism. The emergence of MPCs in quantum chaotic systems exhibits strong parallels with the classical MPE., Comment: 21 pages, 14 figures. Comments and feedback are welcome! v2:several typos and minor mistakes corrected

There has been a growing trend that activities relating to clinical trials take place at locations other than traditional trial sites (hence decentralized clinical trials or DCTs), some of which are at settings of real-world clinical practice. Although there are numerous benefits of DCTs, this also brings some implications on a number of issues relating to the design, conduct, and analysis of DCTs. The Real-World Evidence Scientific Working Group of the American Statistical Association Biopharmaceutical Section has been reviewing the field of DCTs and provides in this paper considerations for decentralized trials from a statistical perspective. This paper first discusses selected critical decentralized elements that may have statistical implications on the trial and then summarizes regulatory guidance, framework, and initiatives on DCTs. More discussions are presented by focusing on the design (including construction of estimand), implementation, statistical analysis plan (including missing data handling), and reporting of safety events. Some additional considerations (e.g., ethical considerations, technology infrastructure, study oversight, data security and privacy, and regulatory compliance) are also briefly discussed. This paper is intended to provide statistical considerations for decentralized trials of medical products to support regulatory decision-making.

Real-world data (RWD) and real-world evidence (RWE) have been increasingly used in medical product development and regulatory decision-making, especially for rare diseases. After outlining the challenges and possible strategies to address the challenges in rare disease drug development (see the accompanying paper), the Real-World Evidence (RWE) Scientific Working Group of the American Statistical Association Biopharmaceutical Section reviews the roles of RWD and RWE in clinical trials for drugs treating rare diseases. This paper summarizes relevant guidance documents and frameworks by selected regulatory agencies and the current practice on the use of RWD and RWE in natural history studies and the design, conduct, and analysis of rare disease clinical trials. A targeted learning roadmap for rare disease trials is described, followed by case studies on the use of RWD and RWE to support a natural history study and marketing applications in various settings.

Developing drugs for rare diseases presents unique challenges from a statistical perspective. These challenges may include slowly progressive diseases with unmet medical needs, poorly understood natural history, small population size, diversified phenotypes and geneotypes within a disorder, and lack of appropriate surrogate endpoints to measure clinical benefits. The Real-World Evidence (RWE) Scientific Working Group of the American Statistical Association Biopharmaceutical Section has assembled a research team to assess the landscape including challenges and possible strategies to address these challenges and the role of real-world data (RWD) and RWE in rare disease drug development. This paper first reviews the current regulations by regulatory agencies worldwide and then discusses in more details the challenges from a statistical perspective in the design, conduct, and analysis of rare disease clinical trials. After outlining an overall development pathway for rare disease drugs, corresponding strategies to address the aforementioned challenges are presented. Other considerations are also discussed for generating relevant evidence for regulatory decision-making on drugs for rare diseases. The accompanying paper discusses how RWD and RWE can be used to improve the efficiency of rare disease drug development.

Type-C quasi-periodic oscillations (QPOs) in black hole X-ray transients typically manifest in the low-hard and hard-intermediate states. This study presents a detailed spectral and temporal analysis of the black hole candidate Swift J1727.8-1613 using NICER observations from August and September 2023, with a focus on the first flare period. The time-averaged spectra, along with the rms and phase-lag spectra of the QPOs, were jointly fitted using the time-dependent Comptonization model \text{vkompthdk} to examine the geometry of the corona during this flare. The results provide a comprehensive view of the QPO, where we detected type-C QPOs with a centroid frequency increasing from 0.32 Hz to 2.63 Hz, while it elevated when it entered the flare state, and its energy spectral properties as they evolved during the first flare period. Correlations between spectral and temporal properties suggest that type-C QPOs are primarily modulated by Lense-Thirring precession. Based on simultaneous radio observations indicating discrete jet ejections, we propose, for the first time, a scenario where the temporarily extended corona contracts vertically from approximately 2714 km to less than 900 km, overlying the inner accretion disc, with a transient jet seemingly being launched. The corona then recovers to nearly 2000 km by the end of the first flare period of Swift J1727.8-1613, rather than undergoing horizontal changes. A phenomenological analysis of the corona scenario during this flare period was also conducted., Comment: 16 pages, 6 figures, 3 tables, Submitted to ApJ

The widespread deployment of large language models (LLMs) has led to impressive advancements, yet information about their training data, a critical factor in their performance, remains undisclosed. Membership inference attacks (MIAs) aim to determine whether a specific instance was part of a target model's training data. MIAs can offer insights into LLM outputs and help detect and address concerns such as data contamination and compliance with privacy and copyright standards. However, applying MIAs to LLMs presents unique challenges due to the massive scale of pre-training data and the ambiguous nature of membership. Additionally, creating appropriate benchmarks to evaluate MIA methods is not straightforward, as training and test data distributions are often unknown. In this paper, we introduce EM-MIA, a novel MIA method for LLMs that iteratively refines membership scores and prefix scores via an expectation-maximization algorithm, leveraging the duality that the estimates of these scores can be improved by each other. Membership scores and prefix scores assess how each instance is likely to be a member and discriminative as a prefix, respectively. Our method achieves state-of-the-art results on the WikiMIA dataset. To further evaluate EM-MIA, we present OLMoMIA, a benchmark built from OLMo resources, which allows us to control the difficulty of MIA tasks with varying degrees of overlap between training and test data distributions. We believe that EM-MIA serves as a robust MIA method for LLMs and that OLMoMIA provides a valuable resource for comprehensively evaluating MIA approaches, thereby driving future research in this critical area., Comment: 14 pages

The availability of performant pre-trained models has led to a proliferation of fine-tuned expert models that are specialized to particular domains. This has enabled the creation of powerful and adaptive routing-based "Model MoErging" methods with the goal of using expert modules to create an aggregate system with improved performance or generalization. However, existing MoErging methods often prioritize generalization to unseen tasks at the expense of performance on held-in tasks, which limits its practical applicability in real-world deployment scenarios. We observe that current token-level routing mechanisms neglect the global semantic context of the input task. This token-wise independence hinders effective expert selection for held-in tasks, as routing decisions fail to incorporate the semantic properties of the task. To address this, we propose, Global and Local Instruction Driven Expert Router (GLIDER) that integrates a multi-scale routing mechanism, encompassing a semantic global router and a learned local router. The global router leverages LLM's advanced reasoning capabilities for semantic-related contexts to enhance expert selection. Given the input query and LLM, the router generates semantic task instructions that guide the retrieval of the most relevant experts across all layers. This global guidance is complemented by a local router that facilitates token-level routing decisions within each module, enabling finer control and enhanced performance on unseen tasks. Our experiments using T5-based models for T0 and FLAN tasks demonstrate that GLIDER achieves substantially improved held-in performance while maintaining strong generalization on held-out tasks. We also perform ablations experiments to dive deeper into the components of GLIDER. Our experiments highlight the importance of our multi-scale routing that leverages LLM-driven semantic reasoning for MoErging methods., Comment: Our code is available at https://github.com/UNITES-Lab/glider

Large Language Models (LLMs) demonstrate impressive capabilities across various domains, including role-playing, creative writing, mathematical reasoning, and coding. Despite these advancements, LLMs still encounter challenges with length control, frequently failing to adhere to specific length constraints due to their token-level operations and insufficient training on data with strict length limitations. We identify this issue as stemming from a lack of positional awareness and propose novel approaches--PositionID Prompting and PositionID Fine-Tuning--to address it. These methods enhance the model's ability to continuously monitor and manage text length during generation. Additionally, we introduce PositionID CP Prompting to enable LLMs to perform copy and paste operations accurately. Furthermore, we develop two benchmarks for evaluating length control and copy-paste abilities. Our experiments demonstrate that our methods significantly improve the model's adherence to length constraints and copy-paste accuracy without compromising response quality., Comment: 39 pages. CP-Bench and LenCtrl-Bench are available in https://huggingface.co/datasets/ZenMoore/CP-Bench and https://huggingface.co/datasets/ZenMoore/LenCtrl-Bench

Engineering high-order nonlinearities while suppressing lower-order terms is crucial for quantum error correction and state control in bosonic systems, yet it remains an outstanding challenge. Here, we introduce a general framework of Nonlinearity-Engineered Multi-loop SQUID (NEMS) device, enabling the realization of arbitrary nonlinearities by tuning fluxes in multiple loops within superconducting circuits. We demonstrate specific examples of NEMS devices that selectively engineer pure cubic, quartic, and quintic interactions with suppressed parasitic couplings, showing great promise for realizing Kerr-cat bias-preserving {\scshape cnot} gates and stabilizing four-leg cat qubits. By opening new avenues for tailoring nonlinear Hamiltonians of superconducting devices, this work enables sophisticated and precise manipulation of bosonic modes, with potential applications in quantum computation, simulation, and sensing., Comment: 26 pages, 13 figures

Large recommendation models (LRMs) are fundamental to the multi-billion dollar online advertising industry, processing massive datasets of hundreds of billions of examples before transitioning to continuous online training to adapt to rapidly changing user behavior. The massive scale of data directly impacts both computational costs and the speed at which new methods can be evaluated (R&D velocity). This paper presents actionable principles and high-level frameworks to guide practitioners in optimizing training data requirements. These strategies have been successfully deployed in Google's largest Ads CTR prediction models and are broadly applicable beyond LRMs. We outline the concept of data convergence, describe methods to accelerate this convergence, and finally, detail how to optimally balance training data volume with model size.

Deep learning has emerged as a promising technology for achieving Android malware detection. To further unleash its detection potentials, software visualization can be integrated for analyzing the details of app behaviors clearly. However, facing increasingly sophisticated malware, existing visualization-based methods, analyzing from one or randomly-selected few views, can only detect limited attack types. We propose and implement LensDroid, a novel technique that detects Android malware by visualizing app behaviors from multiple complementary views. Our goal is to harness the power of combining deep learning and software visualization to automatically capture and aggregate high-level features that are not inherently linked, thereby revealing hidden maliciousness of Android app behaviors. To thoroughly comprehend the details of apps, we visualize app behaviors from three related but distinct views of behavioral sensitivities, operational contexts and supported environments. We then extract high-order semantics based on the views accordingly. To exploit semantic complementarity of the views, we design a deep neural network based model for fusing the visualized features from local to global based on their contributions to downstream tasks. A comprehensive comparison with five baseline techniques is performed on datasets of more than 51K apps in three real-world typical scenarios, including overall threats, app evolution and zero-day malware. The experimental results show that the overall performance of LensDroid is better than the baseline techniques. We also validate the complementarity of the views and demonstrate that the multi-view fusion in LensDroid enhances Android malware detection., Comment: Submitted to TIFS

To satisfy the increasing demands for transmission rates of wireless communications, it is necessary to use spatial resources of electromagnetic (EM) waves. In this context, EM information theory (EIT) has become a hot topic by integrating the theoretical framework of deterministic mathematics and stochastic statistics to explore the transmission mechanisms of continuous EM waves. However, the previous studies were primarily focused on frame analysis, with limited exploration of practical applications and a comprehensive understanding of its essential physical characteristics. In this paper, we present a three-dimensional (3-D) line-of-sight channel capacity formula that captures the vector EM physics and accommodates both near- and far-field scenes. Based on the rigorous mathematical equation and the physical mechanism of fast multipole expansion, a channel model is established, and the finite angular spectral bandwidth feature of scattered waves is revealed. To adapt to the feature of the channel, an optimization problem is formulated for determining the mode currents on the transmitter, aiming to obtain the optimal design of the precoder and combiner. We make comprehensive analyses to investigate the relationship among the spatial degree of freedom, noise, and transmitted power, thereby establishing a rigorous upper bound of channel capacity. A series of simulations are conducted to validate the theoretical model and numerical method. This work offers a novel perspective and methodology for understanding and leveraging EIT, and provides a theoretical foundation for the design and optimization of future wireless communications., Comment: 31pages, 8 figures

In recent years, the issue of radon emanation and diffusion has become a critical concern for rare decay experiments, such as JUNO and PandaX-4T. This paper introduces a detector design featuring a symmetric radon detector cavity for the quantitative assessment of membrane materials' radon blocking capabilities. The performance of this design is evaluated through the application of Fick's Law and the diffusion equation considering material solubility. Our detector has completed measurements of radon diffusion coefficients for four types of membrane materials currently used in experiments, which also confirms the rationality of this detector design. The findings are instrumental in guiding the selection and evaluation of optimal materials for radon shielding to reduce radon background, contributing to boost sensitivities of rare event research., Comment: 7 pages, 10 figures and 2 tables

As large language models (LLMs) become increasingly versatile, numerous large scale benchmarks have been developed to thoroughly assess their capabilities. These benchmarks typically consist of diverse datasets and prompts to evaluate different aspects of LLM performance. However, comprehensive evaluations on hundreds or thousands of prompts incur tremendous costs in terms of computation, money, and time. In this work, we investigate strategies to improve evaluation efficiency by selecting a subset of examples from each benchmark using a learned policy. Our approach models the dependencies across test examples, allowing accurate prediction of the evaluation outcomes for the remaining examples based on the outcomes of the selected ones. Consequently, we only need to acquire the actual evaluation outcomes for the selected subset. We rigorously explore various subset selection policies and introduce a novel RL-based policy that leverages the captured dependencies. Empirical results demonstrate that our approach significantly reduces the number of evaluation prompts required while maintaining accurate performance estimates compared to previous methods.

Several pulsars with unusually long periods were discovered recently, comprising a potential population of ultra long period pulsars (ULPPs). The origin of their long periodicity is not well understood, but may be related to magnatars spun down by surrounding fallback disks. While there are few systematic investigations on the fallback disk-assisted evolution of magnetars, the instability in the disk has received little attention, which determines the lifetime of the disk. In this work we simulate the evolution of the magnetic field, spin period, and magnetic inclination angle of magnetars with a supernova fallback disk. We find that thermal viscous instability in the disk could significantly affect the formation of ULPPs. Our simulation results also reveal that a large fraction of ULPPs seem to be nearly aligned and orthogonal rotators. This might help place ULPPs above the death line in the pulse period - period derivative plane. However, some extra mechanisms seem to be required to account for radio emission of ULPPs., Comment: 15 pages, 8 figures, accepted for publication in ApJ

As the fundamental tool in quantum information science, the uncertainty principle is essential for manifesting nonclassical properties of quantum systems. Plenty of efforts on the uncertainty principle with two observables have been achieved, making it an appealing challenge to extend the scenario to multiple observables. Here, based on an optical setup, we demonstrate the uncertainty relations in two-qubit systems involving three physical components with the tight constant $2/\sqrt{3}$, which signifies a more precise limit in the measurement of multiple quantum components and offers deeper insights into the trade-offs between observables. Furthermore, we reveal the correspondence of the maximal values of the uncertainty functions and the degree of entanglement, where the more uncertainty is proportional to the higher degree of entanglement. Our results provide a new insight into understanding the uncertainty relations with multiple observables and may motivate more innovative applications in quantum information science., Comment: 13 pages,16 figures

Despite a long history of Nernst effect in superconductors, a satisfactory theory on its amplitude in vortex liquid phase is still absent. The central quantity of vortex Nernst signals is the entropy $s_{\phi}$ carried by each vortex. Here we show a semiclassical treatment based on London equation and Pippard nonlocal generalization. The derived $s_{\phi}$ is a function of both temperatures and magnetic fields. Its magnitude $s_{\phi}^{amp}$ scales with normal-state conductivity ${\sigma}_n$. Estimations based on our formula show good consistency with experimentally determined values. In dirty limit, the relation is further simplified into a Wiedemann-Franz-like ratio $s_{\phi}^{amp}/{\sigma}_n \propto k_B \ln 2/{\sigma}_Q$ if taking parameter values deduced from Homes' law, where ${\sigma}_Q=4e^2/h$ is two-dimensional quantum conductivity. We also address related issues, including bounds to $s_{\phi}$, the Nernst signal and viscosity-entropy density ratio, which are all expressed in fundamental physical constants.

As remote sensing imaging technology continues to advance and evolve, processing high-resolution and diversified satellite imagery to improve segmentation accuracy and enhance interpretation efficiency emerg as a pivotal area of investigation within the realm of remote sensing. Although segmentation algorithms based on CNNs and Transformers achieve significant progress in performance, balancing segmentation accuracy and computational complexity remains challenging, limiting their wide application in practical tasks. To address this, this paper introduces state space model (SSM) and proposes a novel hybrid semantic segmentation network based on vision Mamba (CVMH-UNet). This method designs a cross-scanning visual state space block (CVSSBlock) that uses cross 2D scanning (CS2D) to fully capture global information from multiple directions, while by incorporating convolutional neural network branches to overcome the constraints of Vision Mamba (VMamba) in acquiring local information, this approach facilitates a comprehensive analysis of both global and local features. Furthermore, to address the issue of limited discriminative power and the difficulty in achieving detailed fusion with direct skip connections, a multi-frequency multi-scale feature fusion block (MFMSBlock) is designed. This module introduces multi-frequency information through 2D discrete cosine transform (2D DCT) to enhance information utilization and provides additional scale local detail information through point-wise convolution branches. Finally, it aggregates multi-scale information along the channel dimension, achieving refined feature fusion. Findings from experiments conducted on renowned datasets of remote sensing imagery demonstrate that proposed CVMH-UNet achieves superior segmentation performance while maintaining low computational complexity, outperforming surpassing current leading-edge segmentation algorithms.

Finding Minimum Energy Configurations (MECs) is essential in fields such as physics, chemistry, and materials science, as they represent the most stable states of the systems. In particular, identifying such MECs in multi-component alloys considered candidate PFMs is key because it determines the most stable arrangement of atoms within the alloy, directly influencing its phase stability, structural integrity, and thermo-mechanical properties. However, since the search space grows exponentially with the number of atoms considered, obtaining such MECs using computationally expensive first-principles DFT calculations often results in a cumbersome task. To escape the above compromise between physical fidelity and computational efficiency, we have developed a novel physics-based data-driven approach that combines Monte Carlo sampling, first-principles DFT calculations, and Machine Learning to accelerate the discovery of MECs in multi-component alloys. More specifically, we have leveraged well-established Cluster Expansion (CE) techniques with Local Outlier Factor models to establish strategies that enhance the reliability of the CE method. In this work, we demonstrated the capabilities of the proposed approach for the particular case of a tungsten-based quaternary high-entropy alloy. However, the method is applicable to other types of alloys and enables a wide range of applications.

Reward Models (RMs) are crucial for aligning language models with human preferences. Currently, the evaluation of RMs depends on measuring accuracy against a validation set of manually annotated preference data. Although this method is straightforward and widely adopted, the relationship between RM accuracy and downstream policy performance remains under-explored. In this work, we conduct experiments in a synthetic setting to investigate how differences in RM measured by accuracy translate into gaps in optimized policy performance. Our findings reveal that while there is a weak positive correlation between accuracy and downstream performance, policies optimized towards RMs with similar accuracy can exhibit quite different performance. Moreover, we discover that the way of measuring accuracy significantly impacts its ability to predict the final policy performance. Through the lens of Regressional Goodhart's effect, we identify the existence of exogenous variables impacting the relationship between RM quality measured by accuracy and policy model capability. This underscores the inadequacy of relying solely on accuracy to reflect their impact on policy optimization.

Learning from observation (LfO) aims to imitate experts by learning from state-only demonstrations without requiring action labels. Existing adversarial imitation learning approaches learn a generator agent policy to produce state transitions that are indistinguishable to a discriminator that learns to classify agent and expert state transitions. Despite its simplicity in formulation, these methods are often sensitive to hyperparameters and brittle to train. Motivated by the recent success of diffusion models in generative modeling, we propose to integrate a diffusion model into the adversarial imitation learning from observation framework. Specifically, we employ a diffusion model to capture expert and agent transitions by generating the next state, given the current state. Then, we reformulate the learning objective to train the diffusion model as a binary classifier and use it to provide "realness" rewards for policy learning. Our proposed framework, Diffusion Imitation from Observation (DIFO), demonstrates superior performance in various continuous control domains, including navigation, locomotion, manipulation, and games. Project page: https://nturobotlearninglab.github.io/DIFO, Comment: NeurIPS 2024. Project page: https://nturobotlearninglab.github.io/DIFO

In this study, energy-energy correlator (EEC) distributions for the $\rm D^0$, $\rm B^0$-tagged, inclusive, and the PYTHIA generated pure quark jets are computed in pp, p+Pb, and Pb+Pb collisions at \sqrts =5.02 TeV for a same jet transverse momentum interval 15-30 GeV. We find the number of particles per jet determines the height of the EEC distribution in pp baseline. The averaged energy weight distribution resulted in a shift of the originally larger angular distributed particle distribution to a smaller RL, thereby obtaining an EEC distribution. The EEC distributions for all quark-tagged jets in A+A exhibit a noticeable shift towards larger RL region, suggesting that the jets will be more widely distributed compared to those in pp collisions. The jet quenching effect will cause the pair angular distribution to shift towards larger values and increase the number of particles per jet. This redistribution of energy within the jets suggests that the already reduced jet energy is redistributed among a larger number of particles, leading to a reduced energy weight per pair. The enhancement of the number of particles per jet and the reduced averaged energy weight interplay with each other to form the medium modification of EEC., Comment: 9 pages, 5 figures

Batched sparse (BATS) code is a class of batched network code that can achieve a close-to-optimal rate when an optimal degree distribution is provided. We observed that most probability masses in this optimal distribution are very small, i.e., the distribution "looks" sparse. In this paper, we investigate the sparsity optimization of degree distribution for BATS codes that produces sparse degree distributions. There are many advantages to use a sparse degree distribution, say, it is robust to precision errors when sampling the degree distribution during encoding and decoding in practice. We discuss a few heuristics and also a way to obtain an exact sparsity solution. These approaches give a trade-off between computational time and achievable rate, thus give us the flexibility to adopt BATS codes in various scenarios, e.g., device with limited computational power, stable channel condition, etc., Comment: Full version of the conference version in ITW'24

Despite enjoying desirable efficiency and reduced reliance on domain expertise, existing neural methods for vehicle routing problems (VRPs) suffer from severe robustness issues -- their performance significantly deteriorates on clean instances with crafted perturbations. To enhance robustness, we propose an ensemble-based Collaborative Neural Framework (CNF) w.r.t. the defense of neural VRP methods, which is crucial yet underexplored in the literature. Given a neural VRP method, we adversarially train multiple models in a collaborative manner to synergistically promote robustness against attacks, while boosting standard generalization on clean instances. A neural router is designed to adeptly distribute training instances among models, enhancing overall load balancing and collaborative efficacy. Extensive experiments verify the effectiveness and versatility of CNF in defending against various attacks across different neural VRP methods. Notably, our approach also achieves impressive out-of-distribution generalization on benchmark instances., Comment: Accepted at NeurIPS 2024

Large Language Models (LLMs) have become pervasive due to their knowledge absorption and text-generation capabilities. Concurrently, the copyright issue for pretraining datasets has been a pressing concern, particularly when generation includes specific styles. Previous methods either focus on the defense of identical copyrighted outputs or find interpretability by individual tokens with computational burdens. However, the gap between them exists, where direct assessments of how dataset contributions impact LLM outputs are missing. Once the model providers ensure copyright protection for data holders, a more mature LLM community can be established. To address these limitations, we introduce CopyLens, a new framework to analyze how copyrighted datasets may influence LLM responses. Specifically, a two-stage approach is employed: First, based on the uniqueness of pretraining data in the embedding space, token representations are initially fused for potential copyrighted texts, followed by a lightweight LSTM-based network to analyze dataset contributions. With such a prior, a contrastive-learning-based non-copyright OOD detector is designed. Our framework can dynamically face different situations and bridge the gap between current copyright detection methods. Experiments show that CopyLens improves efficiency and accuracy by 15.2% over our proposed baseline, 58.7% over prompt engineering methods, and 0.21 AUC over OOD detection baselines.

We report the detection of an extended very-high-energy (VHE) gamma-ray source coincident with the locations of middle-aged (62.4~\rm kyr) pulsar PSR J0248+6021, by using the LHAASO-WCDA data of live 796 days and LHAASO-KM2A data of live 1216 days. A significant excess of \gray induced showers is observed both by WCDA in energy bands of 1-25~\rm TeV and KM2A in energy bands of $>$ 25~\rm TeV with 7.3 $\sigma$ and 13.5 $\sigma$, respectively. The best-fit position derived through WCDA data is R.A. = 42.06$^\circ \pm$ 0.12$^\circ$ and Dec. = 60.24$^\circ \pm $ 0.13$^\circ$ with an extension of 0.69$^\circ\pm$0.15$^\circ$ and that of the KM2A data is R.A.= 42.29$^\circ \pm $ 0.13$^\circ$ and Dec. = 60.38$^\circ \pm$ 0.07$^\circ$ with an extension of 0.37$^\circ\pm$0.07$^\circ$. No clear extended multiwavelength counterpart of this LHAASO source has been found from the radio band to the GeV band. The most plausible explanation of the VHE \gray emission is the inverse Compton process of highly relativistic electrons and positrons injected by the pulsar. These electrons/positrons are hypothesized to be either confined within the pulsar wind nebula or to have already escaped into the interstellar medium, forming a pulsar halo., Comment: 12 pages, 10 figures, Accepted by Sci. China-Phys. Mech. Astron

Consider a network of agents that all want to guess the correct value of some ground truth state. In a sequential order, each agent makes its decision using a single private signal which has a constant probability of error, as well as observations of actions from its network neighbors earlier in the order. We are interested in enabling \emph{network-wide asymptotic truth learning} -- that in a network of $n$ agents, almost all agents make a correct prediction with probability approaching one as $n$ goes to infinity. In this paper we study both random orderings and carefully crafted decision orders with respect to the graph topology as well as sufficient or necessary conditions for a graph to support such a good ordering. We first show that on a sparse graph of average constant degree with a random ordering asymptotic truth learning does not happen. We then show a rather modest sufficient condition to enable asymptotic truth learning. With the help of this condition we characterize graphs generated from the Erd\"os R\'enyi model and preferential attachment model. In an Erd\"os R\'enyi graph, unless the graph is super sparse (with $O(n)$ edges) or super dense (nearly a complete graph), there exists a decision ordering that supports asymptotic truth learning. Similarly, any preferential attachment network with a constant number of edges per node can achieve asymptotic truth learning under a carefully designed ordering but not under either a random ordering nor the arrival order. We also evaluated a variant of the decision ordering on different network topologies and demonstrated clear effectiveness in improving truth learning over random orderings., Comment: Accepted at the 20th Conference on Web and Internet Economics (WINE'24)

We present a generative method called CQG for constructing cloze questions from a given article using neural networks and WordNet, with an emphasis on generating multigram distractors. Built on sense disambiguation, text-to-text transformation, WordNet's synset taxonomies and lexical labels, CQG selects an answer key for a given sentence, segments it into a sequence of instances, generates instance-level distractor candidates (IDCs) using a transformer and sibling synsets.It then removes inappropriate IDCs, ranks the remaining IDCs based on contextual embedding similarities, as well as synset and lexical relatedness, forms distractor candidates by combinatorially replacing instances with the corresponding top-ranked IDCs, and checks if they are legitimate phrases. Finally, it selects top-ranked distractor candidates based on contextual semantic similarities to the answer key. Experiments show that this method significantly outperforms SOTA results. Human judges also confirm the high qualities of the generated distractors., Comment: 8 pages, 5 figures,5 tables, 2023 International Joint Conference on Neural Networks (IJCNN)

While large language models (LLMs) have integrated images, adapting them to graphs remains challenging, limiting their applications in materials and drug design. This difficulty stems from the need for coherent autoregressive generation across texts and graphs. To address this, we introduce Llamole, the first multimodal LLM capable of interleaved text and graph generation, enabling molecular inverse design with retrosynthetic planning. Llamole integrates a base LLM with the Graph Diffusion Transformer and Graph Neural Networks for multi-conditional molecular generation and reaction inference within texts, while the LLM, with enhanced molecular understanding, flexibly controls activation among the different graph modules. Additionally, Llamole integrates A* search with LLM-based cost functions for efficient retrosynthetic planning. We create benchmarking datasets and conduct extensive experiments to evaluate Llamole against in-context learning and supervised fine-tuning. Llamole significantly outperforms 14 adapted LLMs across 12 metrics for controllable molecular design and retrosynthetic planning., Comment: 27 pages, 11 figures, 4 tables

In recent decades, there has been substantial advances in time series models and benchmarks across various individual tasks, such as time series forecasting, classification, and anomaly detection. Meanwhile, compositional reasoning in time series is prevalent in real-world applications (e.g., decision-making and compositional question answering) and is in great demand. Unlike simple tasks that primarily focus on predictive accuracy, compositional reasoning emphasizes the synthesis of diverse information from both time series data and various domain knowledge, making it distinct and extremely more challenging. In this paper, we introduce Compositional Time Series Reasoning, a new task of handling intricate multistep reasoning tasks from time series data. Specifically, this new task focuses on various question instances requiring structural and compositional reasoning abilities on time series data, such as decision-making and compositional question answering. As an initial attempt to tackle this novel task, we developed TS-Reasoner, a program-aided approach that utilizes large language model (LLM) to decompose a complex task into steps of programs that leverage existing time series models and numerical subroutines. Unlike existing reasoning work which only calls off-the-shelf modules, TS-Reasoner allows for the creation of custom modules and provides greater flexibility to incorporate domain knowledge as well as user-specified constraints. We demonstrate the effectiveness of our method through a comprehensive set of experiments. These promising results indicate potential opportunities in the new task of time series reasoning and highlight the need for further research.

This work introduces advanced computational techniques for modeling the time evolution of compact binary systems using machine learning. The dynamics of compact binary systems, such as black holes and neutron stars, present significant nonlinear challenges due to the strong gravitational interactions and the requirement for precise numerical simulations. Traditional methods, like the post-Newtonian approximation, often require significant computational resources and face challenges in accuracy and efficiency. Here, we employed machine learning algorithms, including deep learning models like Long Short-Term Memory (LSTM) and Temporal Convolutional Network (TCN), to predict the future evolution of these systems based on extensive simulation data. Our results demonstrate that employing both LSTM and TCN even as black-box predictors for sequence prediction can also significantly improve the prediction accuracy without PINNs as PDE solvers with prior knowledge or inductive bias. By employing LSTM and TCN, we obtained $R^2$ values of 99.74\% and 99.19\% for the evolutionary orbits of compact binaries dataset, respectively. Our models demonstrate the ability to effectively capture the dynamics of the binaries, achieving high prediction performance with significantly reduced computational overhead by a factor of 40, compared to conventional numerical methods. This study paves the way for more effective and computationally scalable approaches to the understanding of gravitational phenomena and predictive modeling in gravitational-wave astronomy., Comment: pages, 6 figures, 7 tables, 1 algorithm

Various imaging modalities are used in patient diagnosis, each offering unique advantages and valuable insights into anatomy and pathology. Computed Tomography (CT) is crucial in diagnostics, providing high-resolution images for precise internal organ visualization. CT's ability to detect subtle tissue variations is vital for diagnosing diseases like lung cancer, enabling early detection and accurate tumor assessment. However, variations in CT scanner models and acquisition protocols introduce significant variability in the extracted radiomic features, even when imaging the same patient. This variability poses considerable challenges for downstream research and clinical analysis, which depend on consistent and reliable feature extraction. Current methods for medical image feature extraction, often based on supervised learning approaches, including GAN-based models, face limitations in generalizing across different imaging environments. In response to these challenges, we propose LTDiff++, a multiscale latent diffusion model designed to enhance feature extraction in medical imaging. The model addresses variability by standardizing non-uniform distributions in the latent space, improving feature consistency. LTDiff++ utilizes a UNet++ encoder-decoder architecture coupled with a conditional Denoising Diffusion Probabilistic Model (DDPM) at the latent bottleneck to achieve robust feature extraction and standardization. Extensive empirical evaluations on both patient and phantom CT datasets demonstrate significant improvements in image standardization, with higher Concordance Correlation Coefficients (CCC) across multiple radiomic feature categories. Through these advancements, LTDiff++ represents a promising solution for overcoming the inherent variability in medical imaging data, offering improved reliability and accuracy in feature extraction processes.

Large Language Models (LLMs) have shown impressive capabilities in code generation for popular programming languages. However, their performance on Low-Resource Programming Languages (LRPLs) and Domain-Specific Languages (DSLs) remains a significant challenge, affecting millions of developers-3.5 million users in Rust alone-who cannot fully utilize LLM capabilities. LRPLs and DSLs encounter unique obstacles, including data scarcity and, for DSLs, specialized syntax that is poorly represented in general-purpose datasets. Addressing these challenges is crucial, as LRPLs and DSLs enhance development efficiency in specialized domains, such as finance and science. While several surveys discuss LLMs in software engineering, none focus specifically on the challenges and opportunities associated with LRPLs and DSLs. Our survey fills this gap by systematically reviewing the current state, methodologies, and challenges in leveraging LLMs for code generation in these languages. We filtered 111 papers from over 27,000 published studies between 2020 and 2024 to evaluate the capabilities and limitations of LLMs in LRPLs and DSLs. We report the LLMs used, benchmarks, and metrics for evaluation, strategies for enhancing performance, and methods for dataset collection and curation. We identified four main evaluation techniques and several metrics for assessing code generation in LRPLs and DSLs. Our analysis categorizes improvement methods into six groups and summarizes novel architectures proposed by researchers. Despite various techniques and metrics, a standard approach and benchmark dataset for evaluating code generation in LRPLs and DSLs are lacking. This survey serves as a resource for researchers and practitioners at the intersection of LLMs, software engineering, and specialized programming languages, laying the groundwork for future advancements in code generation for LRPLs and DSLs.

In this paper, we study the thermodynamics of Schwarzschild-anti-de Sitter black holes within the framework of non-commutative geometry. By solving the Einstein's equations, we derive the corrected Schwarzschild-AdS black hole with Lorentzian distribution and analyze the thermodynamics. Our results confirm that if the energy-momentum tensor outside the event horizon is related to the mass of the black hole, the conventional first law of thermodynamics will be violated. The study of criticality reveals that the black hole undergoes a small black hole-large black hole phase transition similar to that of the Van der Waals system, with a critical point and a critical ratio slightly smaller than that of the Van der Waals fluid. As the non-commutative parameter increases, the phase transition process shortens, leading to a critical point, and ultimately to the disappearance of the phase transition. The violation of the conventional first law results in a discontinuity of the Gibbs free energy during the phase transition, indicating the occurrence of zeroth-order phase transition. Moreover, we investigate the Joule-Thomson expansion, obtaining the minimum inversion temperature and the minimum inversion mass., Comment: 37pages, 11figures

As large language models (LLMs) increasingly integrate into every aspect of our work and daily lives, there are growing concerns about user privacy, which push the trend toward local deployment of these models. There are a number of lightweight LLMs (e.g., Gemini Nano, LLAMA2 7B) that can run locally on smartphones, providing users with greater control over their personal data. As a rapidly emerging application, we are concerned about their performance on commercial-off-the-shelf mobile devices. To fully understand the current landscape of LLM deployment on mobile platforms, we conduct a comprehensive measurement study on mobile devices. We evaluate both metrics that affect user experience, including token throughput, latency, and battery consumption, as well as factors critical to developers, such as resource utilization, DVFS strategies, and inference engines. In addition, we provide a detailed analysis of how these hardware capabilities and system dynamics affect on-device LLM performance, which may help developers identify and address bottlenecks for mobile LLM applications. We also provide comprehensive comparisons across the mobile system-on-chips (SoCs) from major vendors, highlighting their performance differences in handling LLM workloads. We hope that this study can provide insights for both the development of on-device LLMs and the design for future mobile system architecture.

Semantic communication is a promising technology to improve communication efficiency by transmitting only the semantic information of the source data. However, traditional semantic communication methods primarily focus on data reconstruction tasks, which may not be efficient for emerging generative tasks such as text-to-speech (TTS) synthesis. To address this limitation, this paper develops a novel generative semantic communication framework for TTS synthesis, leveraging generative artificial intelligence technologies. Firstly, we utilize a pre-trained large speech model called WavLM and the residual vector quantization method to construct two semantic knowledge bases (KBs) at the transmitter and receiver, respectively. The KB at the transmitter enables effective semantic extraction, while the KB at the receiver facilitates lifelike speech synthesis. Then, we employ a transformer encoder and a diffusion model to achieve efficient semantic coding without introducing significant communication overhead. Finally, numerical results demonstrate that our framework achieves much higher fidelity for the generated speech than four baselines, in both cases with additive white Gaussian noise channel and Rayleigh fading channel., Comment: The paper has been accepted by IEEE Globecom Workshop

Pre-trained Transformers inherently possess the characteristic of sparse activation, where only a small fraction of the neurons are activated for each token. While sparse activation has been explored through post-training methods, its potential in pre-training remains untapped. In this work, we first study how activation properties change during pre-training. Our examination reveals that Transformers exhibit sparse activation throughout the majority of the pre-training process while the activation correlation keeps evolving as training progresses. Leveraging this observation, we propose Switchable Sparse-Dense Learning (SSD). SSD adaptively switches between the Mixtures-of-Experts (MoE) based sparse training and the conventional dense training during the pre-training process, leveraging the efficiency of sparse training and avoiding the static activation correlation of sparse training. Compared to dense training, SSD achieves comparable performance with identical model size and reduces pre-training costs. Moreover, the models trained with SSD can be directly used as MoE models for sparse inference and achieve the same performance as dense models with up to $2\times$ faster inference speed. Codes are available at https://github.com/thunlp/moefication., Comment: ICML 2024

Large language models (LLMs) exhibit varying strengths and weaknesses across different tasks, prompting recent studies to explore the benefits of ensembling models to leverage their complementary advantages. However, existing LLM ensembling methods often overlook model compatibility and struggle with inefficient alignment of probabilities across the entire vocabulary. In this study, we empirically investigate the factors influencing ensemble performance, identifying model performance, vocabulary size, and response style as key determinants, revealing that compatibility among models is essential for effective ensembling. This analysis leads to the development of a simple yet effective model selection strategy that identifies compatible models. Additionally, we introduce the \textsc{Uni}on \textsc{T}op-$k$ \textsc{E}nsembling (\textsc{UniTE}), a novel approach that efficiently combines models by focusing on the union of the top-k tokens from each model, thereby avoiding the need for full vocabulary alignment and reducing computational overhead. Extensive evaluations across multiple benchmarks demonstrate that \textsc{UniTE} significantly enhances performance compared to existing methods, offering a more efficient framework for LLM ensembling.

Multi-task-learning(MTL) is a multi-target optimization task. Neural networks try to realize each target using a shared interpretative space within MTL. However, as the scale of datasets expands and the complexity of tasks increases, knowledge sharing becomes increasingly challenging. In this paper, we first re-examine previous cross-attention MTL methods from the perspective of noise. We theoretically analyze this issue and identify it as a flaw in the cross-attention mechanism. To address this issue, we propose an information bottleneck knowledge extraction module (KEM). This module aims to reduce inter-task interference by constraining the flow of information, thereby reducing computational complexity. Furthermore, we have employed neural collapse to stabilize the knowledge-selection process. That is, before input to KEM, we projected the features into ETF space. This mapping makes our method more robust. We implemented and conducted comparative experiments with this method on multiple datasets. The results demonstrate that our approach significantly outperforms existing methods in multi-task learning.

Scaling laws in language modeling traditionally quantify training loss as a function of dataset size and model parameters, providing compute-optimal estimates but often neglecting the impact of data quality on model generalization. In this paper, we extend the conventional understanding of scaling law by offering a microscopic view of data quality within the original formulation -- effective training tokens -- which we posit to be a critical determinant of performance for parameter-constrained language models. Specifically, we formulate the proposed term of effective training tokens to be a combination of two readily-computed indicators of text: (i) text diversity and (ii) syntheticity as measured by a teacher model. We pretrained over $200$ models of 25M to 1.5B parameters on a diverse set of sampled, synthetic data, and estimated the constants that relate text quality, model size, training tokens, and eight reasoning task accuracy scores. We demonstrated the estimated constants yield +0.83 Pearson correlation with true accuracies, and analyzed it in scenarios involving widely-used data techniques such as data sampling and synthesis which aim to improve data quality., Comment: Accepted to EMNLP 2024 Industry Track, 18 pages, 9 figures, 4 tables

We introduce the Overall Performance Index (OPI), an intrinsic metric to evaluate retrieval-augmented generation (RAG) mechanisms for applications involving deep-logic queries. OPI is computed as the harmonic mean of two key metrics: the Logical-Relation Correctness Ratio and the average of BERT embedding similarity scores between ground-truth and generated answers. We apply OPI to assess the performance of LangChain, a popular RAG tool, using a logical relations classifier fine-tuned from GPT-4o on the RAG-Dataset-12000 from Hugging Face. Our findings show a strong correlation between BERT embedding similarity scores and extrinsic evaluation scores. Among the commonly used retrievers, the cosine similarity retriever using BERT-based embeddings outperforms others, while the Euclidean distance-based retriever exhibits the weakest performance. Furthermore, we demonstrate that combining multiple retrievers, either algorithmically or by merging retrieved sentences, yields superior performance compared to using any single retriever alone.

In this article, we present a novel user-centric service provision for immersive communications (IC) in 6G to deal with the uncertainty of individual user behaviors while satisfying unique requirements on the quality of multi-sensory experience. To this end, we propose a data-oriented approach for network resource management, featuring personalized data management that can support network modeling tailored to different user demands. Our approach leverages the digital twin (DT) technique as a key enabler. Particularly, a DT is established for each user, and the data attributes in the DT are customized based on the characteristics of the user. The DT functions, corresponding to various data operations, are customized in the development, evaluation, and update of network models to meet unique user demands. A trace-driven case study demonstrates the effectiveness of our approach in achieving user-centric IC and the significance of personalized data management in 6G.