Search

Recent large language models (LLMs) have demonstrated exceptional performance on general-purpose text embedding tasks. While dense embeddings have dominated related research, we introduce the first Lexicon-based EmbeddiNgS (LENS) leveraging LLMs that achieve competitive performance on these tasks. Regarding the inherent tokenization redundancy issue and unidirectional attention limitations in traditional causal LLMs, LENS consolidates the vocabulary space through token embedding clustering, and investigates bidirectional attention and various pooling strategies. Specifically, LENS simplifies lexicon matching by assigning each dimension to a specific token cluster, where semantically similar tokens are grouped together, and unlocking the full potential of LLMs through bidirectional attention. Extensive experiments demonstrate that LENS outperforms dense embeddings on the Massive Text Embedding Benchmark (MTEB), delivering compact feature representations that match the sizes of dense counterparts. Notably, combining LENSE with dense embeddings achieves state-of-the-art performance on the retrieval subset of MTEB (i.e. BEIR).

ABACUS (Atomic-orbital Based Ab-initio Computation at USTC) is an open-source software for first-principles electronic structure calculations and molecular dynamics simulations. It mainly features density functional theory (DFT) and is compatible with both plane-wave basis sets and numerical atomic orbital basis sets. ABACUS serves as a platform that facilitates the integration of various electronic structure methods, such as Kohn-Sham DFT, stochastic DFT, orbital-free DFT, and real-time time-dependent DFT, etc. In addition, with the aid of high-performance computing, ABACUS is designed to perform efficiently and provide massive amounts of first-principles data for generating general-purpose machine learning potentials, such as DPA models. Furthermore, ABACUS serves as an electronic structure platform that interfaces with several AI-assisted algorithms and packages, such as DeePKS-kit, DeePMD, DP-GEN, DeepH, DeePTB, etc.

Investigations show that a time-varying $\delta-\delta'$ mirror gives rise to asymmetrical vacuum radiation on its two sides, enabling one to extract propelling forces from the vacuum fluctuation. In this work, we propose a design of Casimir device to gain propulsions out of vacuum with conventional $\delta$ mirrors. We call this device a ``vacuum propellion'', which is experimentally feasible. It consists of a cavity made up of a perfectly reflective left mirror and a right mirror with time dependent transparency. All particles generated from this propellion are preferentially right-moving, so the cavity obtains a left-pointing propelling force., Comment: 15 pages,3 figures

1. An understanding of how biodiversity confers ecosystem stability is crucial in managing ecosystems under major environmental changes. Multiple biodiversity drivers can stabilize ecosystem functions over time. However, we know little about how local environmental conditions can influence these biodiversity drivers, and consequently how they indirectly shape the ecological stability of ecosystems. 2. We hypothesized that environmental factors can have opposite influences (i.e., not necessarily either positive or negative) on the temporal stability of communities in different environmental ranges depending on the biodiversity drivers involved. We tested this novel hypothesis by using data from a 4-year-long field study of submerged macrophyte across a water depth gradient in 8 heterogeneous bays of Erhai lake (with total sample size of 30,071 quadrats), a large lentic system in China. 3. Results indicate that a unimodal pattern of stability in temporal biomass measurements occurred along the water-depth gradient, and that multiple biodiversity drivers (the asynchrony in species dynamics, and the stability of dominant species) generally increased the temporal stability of aquatic primary producers. However, the effect of water depth either increased or decreased the stability of biomass according to the environmental conditions associated with sites along the water depth gradient. 4. Synthesis. These results reveal the influence of local environmental conditions on the biodiversity drivers of stability may help predict the functional consequences of biodiversity change across different scenarios of environmental change.

Accurate understanding of muscle activation and muscle forces plays an essential role in neuro-rehabilitation and musculoskeletal disorder treatments. Computational musculoskeletal modeling has been widely used as a powerful non-invasive tool to estimate them through inverse dynamics using static optimization, but the inherent computational complexity results in time-consuming analysis. In this paper, we propose a knowledge-based deep learning framework for time-efficient inverse dynamic analysis, which can predict muscle activation and muscle forces from joint kinematic data directly while not requiring any label information during model training. The Bidirectional Gated Recurrent Unit (BiGRU) neural network is selected as the backbone of our model due to its proficient handling of time-series data. Prior physical knowledge from forward dynamics and pre-selected inverse dynamics based physiological criteria are integrated into the loss function to guide the training of neural networks. Experimental validations on two datasets, including one benchmark upper limb movement dataset and one self-collected lower limb movement dataset from six healthy subjects, are performed. The experimental results have shown that the selected BiGRU architecture outperforms other neural network models when trained using our specifically designed loss function, which illustrates the effectiveness and robustness of the proposed framework., Comment: 10 pages, 8 figures, Journal paper

With Large Language Models (LLMs) recently demonstrating impressive proficiency in code generation, it is promising to extend their abilities to Hardware Description Language (HDL). However, LLMs tend to generate single HDL code blocks rather than hierarchical structures for hardware designs, leading to hallucinations, particularly in complex designs like Domain-Specific Accelerators (DSAs). To address this, we propose HiVeGen, a hierarchical LLM-based Verilog generation framework that decomposes generation tasks into LLM-manageable hierarchical submodules. HiVeGen further harnesses the advantages of such hierarchical structures by integrating automatic Design Space Exploration (DSE) into hierarchy-aware prompt generation, introducing weight-based retrieval to enhance code reuse, and enabling real-time human-computer interaction to lower error-correction cost, significantly improving the quality of generated designs.

We revisit the long-standing question of whether water molecules dissociate on the Ru(0001) surface through nanosecond-scale path-integral molecular dynamics simulations on a sizable supercell. This is made possible through the development of an efficient and reliable machine-learning potential with near first-principles accuracy, overcoming the limitations of previous ab initio studies. We show that the quantum delocalization associated with nuclear quantum effects enables rapid and frequent proton transfers between water molecules, thereby facilitating the water dissociation on Ru(0001). This work provides the direct theoretical evidence of water dissociation on Ru(0001), resolving the enduring issue in surface sciences and offering crucial atomistic insights into water-metal interfaces., Comment: 21 pages, 12 figures (include Supplemental Material)

Recently, there has been growing interest in simulating time-dependent Hamiltonians using quantum algorithms, driven by diverse applications, such as quantum adiabatic computing. While techniques for simulating time-independent Hamiltonian dynamics are well-established, time-dependent Hamiltonian dynamics is less explored and it is unclear how to systematically organize existing methods and to find new methods. Sambe-Howland's continuous clock elegantly transforms time-dependent Hamiltonian dynamics into time-independent Hamiltonian dynamics, which means that by taking different discretizations, existing methods for time-independent Hamiltonian dynamics can be exploited for time-dependent dynamics. In this work, we systemically investigate how Sambe-Howland's clock can serve as a unifying framework for simulating time-dependent Hamiltonian dynamics. Firstly, we demonstrate the versatility of this approach by showcasing its compatibility with analog quantum computing and digital quantum computing. Secondly, for digital quantum computers, we illustrate how this framework, combined with time-independent methods (e.g., product formulas, multi-product formulas, qDrift, and LCU-Taylor), can facilitate the development of efficient algorithms for simulating time-dependent dynamics. This framework allows us to (a) resolve the problem of finding minimum-gate time-dependent product formulas; (b) establish a unified picture of both Suzuki's and Huyghebaert and De Raedt's approaches; (c) generalize Huyghebaert and De Raedt's first and second-order formula to arbitrary orders; (d) answer an unsolved question in establishing time-dependent multi-product formulas; (e) and recover continuous qDrift on the same footing as time-independent qDrift. Thirdly, we demonstrate the efficacy of our newly developed higher-order Huyghebaert and De Raedt's algorithm through digital adiabatic simulation.

In recent years, the long-range attention mechanism of vision transformers has driven significant performance breakthroughs across various computer vision tasks. However, the traditional self-attention mechanism, which processes both informative and non-informative tokens, suffers from inefficiency and inaccuracies. While sparse attention mechanisms have been introduced to mitigate these issues by pruning tokens involved in attention, they often lack context-awareness and intelligence. These mechanisms frequently apply a uniform token selection strategy across different inputs for batch training or optimize efficiency only for the inference stage. To overcome these challenges, we propose a novel algorithm: Select and Pack Attention (SPA). SPA dynamically selects informative tokens using a low-cost gating layer supervised by selection labels and packs these tokens into new batches, enabling a variable number of tokens to be used in parallelized GPU batch training and inference. Extensive experiments across diverse datasets and computer vision tasks demonstrate that SPA delivers superior performance and efficiency, including a 0.6 mAP improvement in object detection and a 16.4% reduction in computational costs.

In point-line SLAM systems, the utilization of line structural information and the optimization of lines are two significant problems. The former is usually addressed through structural regularities, while the latter typically involves using minimal parameter representations of lines in optimization. However, separating these two steps leads to the loss of constraint information to each other. We anchor lines with similar directions to a principal axis and optimize them with $n+2$ parameters for $n$ lines, solving both problems together. Our method considers scene structural information, which can be easily extended to different world hypotheses while significantly reducing the number of line parameters to be optimized, enabling rapid and accurate mapping and tracking. To further enhance the system's robustness and avoid mismatch, we have modeled the line-axis probabilistic data association and provided the algorithm for axis creation, updating, and optimization. Additionally, considering that most real-world scenes conform to the Atlanta World hypothesis, we provide a structural line detection strategy based on vertical priors and vanishing points. Experimental results and ablation studies on various indoor and outdoor datasets demonstrate the effectiveness of our system., Comment: 8 pages, 4 figures

This paper reviews published research in the field of computer-aided colorization technology. We argue that the colorization task originates from computer graphics, prospers by introducing computer vision, and tends to the fusion of vision and graphics, so we put forward our taxonomy and organize the whole paper chronologically. We extend the existing reconstruction-based colorization evaluation techniques, considering that aesthetic assessment of colored images should be introduced to ensure that colorization satisfies human visual-related requirements and emotions more closely. We perform the colorization aesthetic assessment on seven representative unconditional colorization models and discuss the difference between our assessment and the existing reconstruction-based metrics. Finally, this paper identifies unresolved issues and proposes fruitful areas for future research and development. Access to the project associated with this survey can be obtained at https://github.com/DanielCho-HK/Colorization.

The recent experiment shows the superconducting transition temperature in the Ruddlesden-Popper bilayer La$_3$Ni$_2$O$_{7}$ decreases monotonically with increasing pressure above 14 GPa. In order to unravel the underlying mechanism for this unusual dependence, we performed theoretical investigations by combining the density functional theory (DFT) and the unbiased functional renormalization group (FRG). Our DFT calculations show that the Fermi pockets are essentially unchanged with increasing pressure (above 14 GPa), but the bandwidth is enlarged, and particularly the interlayer hopping integral between the nickel $3d_{3z^2-r^2}$ orbitals is enhanced. From the DFT band structure, we construct the bilayer tight-binding model in terms of the nickel $3d_{3z^2-r^2}$ and $3d_{x^2-y^2}$ orbitals. On this basis, we investigate the superconductivity induced by correlation effects by FRG calculations. We find consistently $s_\pm$-wave pairing triggered by spin fluctuations, but the latter are weakened by pressure and lead to a decreasing transition temperature versus pressure, in qualitatively agreement with the experiment. We emphasize that the itinerancy of the $d$-orbitals is important and captured naturally in our FRG calculations, and we argue that the unusual pressure dependence would be unnatural, if not impossible, in the otherwise local-moment picture of the nickel $d$-orbitals. This sheds lights on the pertinent microscopic description of, and more importantly the mechanism of superconductivity in La$_3$Ni$_2$O$_{7}$., Comment: 8 pages, 4 figures

The local thermodynamic stability from the charge susceptibility of a holographic superfluid model at finite superfluid velocity is studied in the probe limit. Previous studies show that beyond a finite value of the superfluid velocity, the superfluid phase transition in the grand canonical ensemble becomes first order. We further reveal that in the canonical ensemble, the superfluid phase transition is still second order, and the difference indicates a section with negative susceptibility which means local thermodynamic instability beyond this superfluid velocity. However, we also meet the ``cave of wind'' behavior at larger superfluid velocity which complicate the phase diagram. We further study the influence of the two nonlinear terms $\lambda|\psi|^4$ and $\tau|\psi|^6$ with parameters $\lambda$ and $\tau$ on the condensate curves, and set appropriate values of $\lambda$ and $\tau$ to remove the "cave of wind" region in the canonical ensemble to get a more elegant phase diagram and better represent the region with such instability, which is possible to be used to realize spontaneous formation of vortexes and quantum turbulence., Comment: 10 pages, 8 figures

With the expansion of the power grid and the increase of the proportion of new energy sources, the uncertainty and random factors of the power grid increase, endangering the safe operation of the system. It is particularly important to find out the critical links of vulnerability in the power grid to ensure the reliability of the power grid operation. Aiming at the problem that the identification speed of the traditional critical link of vulnerability identification methods is slow and difficult to meet the actual operation requirements of the power grid, the improved graph attention network (IGAT) based identification method of the critical link is proposed. First, the evaluation index set is established by combining the complex network theory and the actual operation data of power grid. Secondly, IGAT is used to dig out the mapping relationship between various indicators and critical links of vulnerability during the operation of the power grid, establish the identification model of critical links of vulnerability, and optimize the original graph attention network considering the training accuracy and efficiency. Thirdly, the original data set is obtained through simulation, and the identification model is trained, verified and tested. Finally, the model is applied to the improved IEEE 30-node system and the actual power grid, and the results show that the proposed method is feasible, and the accuracy and speed are better than that of traditional methods. It has certain engineering utilization value., Comment: in Chinese language

Text-to-image generation models have achieved remarkable advancements in recent years, aiming to produce realistic images from textual descriptions. However, these models often struggle with generating anatomically accurate representations of human hands. The resulting images frequently exhibit issues such as incorrect numbers of fingers, unnatural twisting or interlacing of fingers, or blurred and indistinct hands. These issues stem from the inherent complexity of hand structures and the difficulty in aligning textual descriptions with precise visual depictions of hands. To address these challenges, we propose a novel approach named Hand1000 that enables the generation of realistic hand images with target gesture using only 1,000 training samples. The training of Hand1000 is divided into three stages with the first stage aiming to enhance the model's understanding of hand anatomy by using a pre-trained hand gesture recognition model to extract gesture representation. The second stage further optimizes text embedding by incorporating the extracted hand gesture representation, to improve alignment between the textual descriptions and the generated hand images. The third stage utilizes the optimized embedding to fine-tune the Stable Diffusion model to generate realistic hand images. In addition, we construct the first publicly available dataset specifically designed for text-to-hand image generation. Based on the existing hand gesture recognition dataset, we adopt advanced image captioning models and LLaMA3 to generate high-quality textual descriptions enriched with detailed gesture information. Extensive experiments demonstrate that Hand1000 significantly outperforms existing models in producing anatomically correct hand images while faithfully representing other details in the text, such as faces, clothing, and colors., Comment: Accepted by AAAI 2025. Project page https://haozhuo-zhang.github.io/Hand1000-project-page/

We design and demonstrate selective injection GaN heterojunction bipolar transistors that utilize a patterned base for selective injection of electrons from the emitter. The design maneuvers minority carrier injection through a thin p-GaN base region, while the majority carrier holes for base current are injected from thick p-GaN regions adjacent to the thin p-GaN base. The design is realized using a regrowth emitter approach with SiO$_2$ as a spacer between the emitter layer and the thick p-GaN base contact regions. The fabricated device demonstrated state-of-art output current density (I$_{C, max}$) ~275 kA/cm$^2$ with a current gain ($\beta$) of 9, and 17 for the planar HBT design (I$_{C, max}$ =150 kA/cm$^2$). The reported results highlight the potential of the selective injection design to overcome the persistent GaN HBT design tradeoff between base resistance and current gain, paving the way for next-generation radio frequency and mm-Wave applications.

Atrophic gastritis is a significant risk factor for developing gastric cancer. The incorporation of machine learning algorithms can efficiently elevate the possibility of accurately detecting atrophic gastritis. Nevertheless, when the trained model is applied in real-life circumstances, its output is often not consistently reliable. In this paper, we propose Adaptify, an adaptation scheme in which the model assimilates knowledge from its own classification decisions. Our proposed approach includes keeping the primary model constant, while simultaneously running and updating the auxiliary model. By integrating the knowledge gleaned by the auxiliary model into the primary model and merging their outputs, we have observed a notable improvement in output stability and consistency compared to relying solely on either the main model or the auxiliary model., Comment: ISBI 2024 Proceeding

In the field of Few-Shot Image Generation (FSIG) using Deep Generative Models (DGMs), accurately estimating the distribution of target domain with minimal samples poses a significant challenge. This requires a method that can both capture the broad diversity and the true characteristics of the target domain distribution. We present Conditional Relaxing Diffusion Inversion (CRDI), an innovative `training-free' approach designed to enhance distribution diversity in synthetic image generation. Distinct from conventional methods, CRDI does not rely on fine-tuning based on only a few samples. Instead, it focuses on reconstructing each target image instance and expanding diversity through few-shot learning. The approach initiates by identifying a Sample-wise Guidance Embedding (SGE) for the diffusion model, which serves a purpose analogous to the explicit latent codes in certain Generative Adversarial Network (GAN) models. Subsequently, the method involves a scheduler that progressively introduces perturbations to the SGE, thereby augmenting diversity. Comprehensive experiments demonstrates that our method surpasses GAN-based reconstruction techniques and equals state-of-the-art (SOTA) FSIG methods in performance. Additionally, it effectively mitigates overfitting and catastrophic forgetting, common drawbacks of fine-tuning approaches.

We report experimentally achieving first-ever electric field periodic poling of single crystal barium titanate (BTO, or BaTiO3) thin film on insulator. Owing to the outstanding optical nonlinearities of BTO, this result is a key step towards achieving quasi-phase-matching in BTO. We first grow the BTO thin film on a dysprosium scandate substrate using pulsed laser deposition with a thin layer of strontium ruthenate later serving as the bottom electrode for poling. We present characterization of the BTO thin film using x-ray diffraction and piezo-response force microscopy to clearly demonstrate single crystal, single domain growth of the film which enables the desired periodic poling. To investigate the poling quality, we apply both non-destructive piezo force response microscopy and destructive etching-assisted scanning electron microscopy and we show that high quality, uniform and intransient poling with 50 % duty cycle and periods ranging from 2 {\mu}m to 10 {\mu}m is achieved. The successful realization of periodic poling in BTO thin film unlocks the potential for highly efficient nonlinear processes under quasi-phase-matching that seemed far-fetched with prior polycrystalline BTO thin films which predominantly relied on efficiency-limited random or non-phase matching conditions and is a key step towards integration of BTO photonic devices.

Many evidences appear in the past decades and show that the negativity of Casimir energy is responsible for exotic mechanical and gravitational effects. We study in this work the Lorentz boost of a Casimir cavity, on which little attention is paid to its momentum in historical works. We find that the vacuum energy and momentum carried by the cavity transform differently from those of point particles due to the cavity's extension feature. However, the mass-shell condition of the two are identical as long as the cavity is finite along the moving direction only., Comment: A mistake is found in the calculation

Sampling invariant distributions from an Ito diffusion process presents a significant challenge in stochastic simulation. Traditional numerical solvers for stochastic differential equations require both a fine step size and a lengthy simulation period, resulting in both biased and correlated samples. Current deep learning-based method solves the stationary Fokker--Planck equation to determine the invariant probability density function in form of deep neural networks, but they generally do not directly address the problem of sampling from the computed density function. In this work, we introduce a framework that employs a weak generative sampler (WGS) to directly generate independent and identically distributed (iid) samples induced by a transformation map derived from the stationary Fokker--Planck equation. Our proposed loss function is based on the weak form of the Fokker--Planck equation, integrating normalizing flows to characterize the invariant distribution and facilitate sample generation from the base distribution. Our randomized test function circumvents the need for mini-max optimization in the traditional weak formulation. Distinct from conventional generative models, our method neither necessitates the computationally intensive calculation of the Jacobian determinant nor the invertibility of the transformation map. A crucial component of our framework is the adaptively chosen family of test functions in the form of Gaussian kernel functions with centres selected from the generated data samples. Experimental results on several benchmark examples demonstrate the effectiveness of our method, which offers both low computational costs and excellent capability in exploring multiple metastable states., Comment: 24 pages,10 figures

Current facial expression recognition (FER) models are often designed in a supervised learning manner and thus are constrained by the lack of large-scale facial expression images with high-quality annotations. Consequently, these models often fail to generalize well, performing poorly on unseen images in inference. Vision-language-based zero-shot models demonstrate a promising potential for addressing such challenges. However, these models lack task-specific knowledge and therefore are not optimized for the nuances of recognizing facial expressions. To bridge this gap, this work proposes a novel method, Exp-CLIP, to enhance zero-shot FER by transferring the task knowledge from large language models (LLMs). Specifically, based on the pre-trained vision-language encoders, we incorporate a projection head designed to map the initial joint vision-language space into a space that captures representations of facial actions. To train this projection head for subsequent zero-shot predictions, we propose to align the projected visual representations with task-specific semantic meanings derived from the LLM encoder, and the text instruction-based strategy is employed to customize the LLM knowledge. Given unlabelled facial data and efficient training of the projection head, Exp-CLIP achieves superior zero-shot results to the CLIP models and several other large vision-language models (LVLMs) on seven in-the-wild FER datasets. The code and pre-trained models are available at https://github.com/zengqunzhao/Exp-CLIP., Comment: Accepted at WACV 2025 (Camera-Ready Version)

In ObjectNav, agents must locate specific objects within unseen environments, requiring effective perception, prediction, localization and planning capabilities. This study finds that state-of-the-art embodied AI agents compete for higher navigation quality, but often compromise the computational efficiency. To address this issue, we introduce "Skip-SCAR," an optimization framework that builds computationally and memory-efficient embodied AI agents to accomplish high-quality visual navigation tasks. Skip-SCAR opportunistically skips the redundant step computations during semantic segmentation and local re-planning without hurting the navigation quality. Skip-SCAR also adopts a novel hybrid sparse and dense network for object prediction, optimizing both the computation and memory footprint. Tested on the HM3D ObjectNav datasets and real-world physical hardware systems, Skip-SCAR not only minimizes hardware resources but also sets new performance benchmarks, demonstrating the benefits of optimizing both navigation quality and computational efficiency for robotics., Comment: 7 pages, 9 figures

As large language models (LLMs) continue to grow by scaling laws, reinforcement learning from human feedback (RLHF) has gained significant attention due to its outstanding performance. However, unlike pretraining or fine-tuning a single model, scaling reinforcement learning from human feedback (RLHF) for training large language models poses coordination challenges across four models. We present OpenRLHF, an open-source framework enabling efficient RLHF scaling. Unlike existing RLHF frameworks that co-locate four models on the same GPUs, OpenRLHF re-designs scheduling for the models beyond 70B parameters using Ray, vLLM, and DeepSpeed, leveraging improved resource utilization and diverse training approaches. Integrating seamlessly with Hugging Face, OpenRLHF provides an out-of-the-box solution with optimized algorithms and launch scripts, which ensures user-friendliness. OpenRLHF implements RLHF, DPO, rejection sampling, and other alignment techniques. Empowering state-of-the-art LLM development, OpenRLHF's code is available at \url{https://github.com/OpenRLHF/OpenRLHF}.

In real-world scenarios, images captured often suffer from blurring, noise, and other forms of image degradation, and due to sensor limitations, people usually can only obtain low dynamic range images. To achieve high-quality images, researchers have attempted various image restoration and enhancement operations on photographs, including denoising, deblurring, and high dynamic range imaging. However, merely performing a single type of image enhancement still cannot yield satisfactory images. In this paper, to deal with the challenge above, we propose the Composite Refinement Network (CRNet) to address this issue using multiple exposure images. By fully integrating information-rich multiple exposure inputs, CRNet can perform unified image restoration and enhancement. To improve the quality of image details, CRNet explicitly separates and strengthens high and low-frequency information through pooling layers, using specially designed Multi-Branch Blocks for effective fusion of these frequencies. To increase the receptive field and fully integrate input features, CRNet employs the High-Frequency Enhancement Module, which includes large kernel convolutions and an inverted bottleneck ConvFFN. Our model secured third place in the first track of the Bracketing Image Restoration and Enhancement Challenge, surpassing previous SOTA models in both testing metrics and visual quality., Comment: This paper is accepted by CVPR2024 Workshop, Code: https://github.com/CalvinYang0/CRNet

Federated learning (FL), aimed at leveraging vast distributed datasets, confronts a crucial challenge: the heterogeneity of data across different silos. While previous studies have explored discrete representations to enhance model generalization across minor distributional shifts, these approaches often struggle to adapt to new data silos with significantly divergent distributions. In response, we have identified that models derived from FL exhibit markedly increased uncertainty when applied to data silos with unfamiliar distributions. Consequently, we propose an innovative yet straightforward iterative framework, termed Uncertainty-Based Extensible-Codebook Federated Learning (UEFL). This framework dynamically maps latent features to trainable discrete vectors, assesses the uncertainty, and specifically extends the discretization dictionary or codebook for silos exhibiting high uncertainty. Our approach aims to simultaneously enhance accuracy and reduce uncertainty by explicitly addressing the diversity of data distributions, all while maintaining minimal computational overhead in environments characterized by heterogeneous data silos. Through experiments conducted on five datasets, our method has demonstrated its superiority, achieving significant improvements in accuracy (by 3%--22.1%) and uncertainty reduction (by 38.83%--96.24%), thereby outperforming contemporary state-of-the-art methods. The source code is available at https://github.com/destiny301/uefl.

We introduce a new unsupervised text embedding method, Meta-Task Prompting with Explicit One-Word Limitation (MetaEOL), for generating high-quality sentence embeddings from Large Language Models (LLMs) without the need for model fine-tuning. Leveraging meta-task prompting, MetaEOL guides LLMs to produce embeddings through a series of carefully designed prompts that address multiple representational aspects. Our comprehensive experiments demonstrate that embeddings averaged from various meta-tasks are versatile embeddings that yield competitive performance on Semantic Textual Similarity (STS) benchmarks and excel in downstream tasks, surpassing contrastive-trained models. Our findings suggest a new scaling law, offering a versatile and resource-efficient approach for embedding generation across diverse scenarios., Comment: ACL 2024

Recent studies demonstrate that query expansions generated by large language models (LLMs) can considerably enhance information retrieval systems by generating hypothetical documents that answer the queries as expansions. However, challenges arise from misalignments between the expansions and the retrieval corpus, resulting in issues like hallucinations and outdated information due to the limited intrinsic knowledge of LLMs. Inspired by Pseudo Relevance Feedback (PRF), we introduce Corpus-Steered Query Expansion (CSQE) to promote the incorporation of knowledge embedded within the corpus. CSQE utilizes the relevance assessing capability of LLMs to systematically identify pivotal sentences in the initially-retrieved documents. These corpus-originated texts are subsequently used to expand the query together with LLM-knowledge empowered expansions, improving the relevance prediction between the query and the target documents. Extensive experiments reveal that CSQE exhibits strong performance without necessitating any training, especially with queries for which LLMs lack knowledge., Comment: EACL 2024 (Short)