Search

The da Vinci Research Kit (dVRK, also known as dVRK Classic) is an open-source teleoperated surgical robotic system whose hardware is obtained from the first generation da Vinci Surgical System (Intuitive, Sunnyvale, CA, USA). The dVRK has greatly facilitated research in robot-assisted surgery over the past decade and helped researchers address multiple major challenges in this domain. Recently, the dVRK-Si system, a new version of the dVRK which uses mechanical components from the da Vinci Si Surgical System, became available to the community. The major difference between the first generation da Vinci and the da Vinci Si is in the structural upgrade of the Patient Side Manipulator (PSM). Because of this upgrade, the gravity of the dVRK-Si PSM can no longer be ignored as in the dVRK Classic. The high gravity offset may lead to relatively low control accuracy and longer response time. In addition, although substantial progress has been made in addressing the dynamic model identification problem for the dVRK Classic, further research is required on model-based control for the dVRK-Si, due to differences in mechanical components and the demand for enhanced control performance. To address these problems, in this work, we present (1) a novel full kinematic model of the dVRK-Si PSM, and (2) a gravity compensation approach based on the dynamic model identification.

Language model pretraining with next token prediction has proved effective for scaling compute but is limited to the amount of available training data. Scaling reinforcement learning (RL) unlocks a new axis for the continued improvement of artificial intelligence, with the promise that large language models (LLMs) can scale their training data by learning to explore with rewards. However, prior published work has not produced competitive results. In light of this, we report on the training practice of Kimi k1.5, our latest multi-modal LLM trained with RL, including its RL training techniques, multi-modal data recipes, and infrastructure optimization. Long context scaling and improved policy optimization methods are key ingredients of our approach, which establishes a simplistic, effective RL framework without relying on more complex techniques such as Monte Carlo tree search, value functions, and process reward models. Notably, our system achieves state-of-the-art reasoning performance across multiple benchmarks and modalities -- e.g., 77.5 on AIME, 96.2 on MATH 500, 94-th percentile on Codeforces, 74.9 on MathVista -- matching OpenAI's o1. Moreover, we present effective long2short methods that use long-CoT techniques to improve short-CoT models, yielding state-of-the-art short-CoT reasoning results -- e.g., 60.8 on AIME, 94.6 on MATH500, 47.3 on LiveCodeBench -- outperforming existing short-CoT models such as GPT-4o and Claude Sonnet 3.5 by a large margin (up to +550%)., Comment: 25 pages

With the rapid growth of generative AI in numerous applications, explainable AI (XAI) plays a crucial role in ensuring the responsible development and deployment of generative AI technologies. XAI has undergone notable advancements and widespread adoption in recent years, reflecting a concerted push to enhance the transparency, interpretability, and credibility of AI systems. Recent research emphasizes that a proficient XAI method should adhere to a set of criteria, primarily focusing on two key areas. Firstly, it should ensure the quality and fluidity of explanations, encompassing aspects like faithfulness, plausibility, completeness, and tailoring to individual needs. Secondly, the design principle of the XAI system or mechanism should cover the following factors such as reliability, resilience, the verifiability of its outputs, and the transparency of its algorithm. However, research in XAI for generative models remains relatively scarce, with little exploration into how such methods can effectively meet these criteria in that domain. In this work, we propose PXGen, a post-hoc explainable method for generative models. Given a model that needs to be explained, PXGen prepares two materials for the explanation, the Anchor set and intrinsic & extrinsic criteria. Those materials are customizable by users according to their purpose and requirements. Via the calculation of each criterion, each anchor has a set of feature values and PXGen provides examplebased explanation methods according to the feature values among all the anchors and illustrated and visualized to the users via tractable algorithms such as k-dispersion or k-center.

State-of-the-art supervised stereo matching methods have achieved amazing results on various benchmarks. However, these data-driven methods suffer from generalization to real-world scenarios due to the lack of real-world annotated data. In this paper, we propose StereoGen, a novel pipeline for high-quality stereo image generation. This pipeline utilizes arbitrary single images as left images and pseudo disparities generated by a monocular depth estimation model to synthesize high-quality corresponding right images. Unlike previous methods that fill the occluded area in warped right images using random backgrounds or using convolutions to take nearby pixels selectively, we fine-tune a diffusion inpainting model to recover the background. Images generated by our model possess better details and undamaged semantic structures. Besides, we propose Training-free Confidence Generation and Adaptive Disparity Selection. The former suppresses the negative effect of harmful pseudo ground truth during stereo training, while the latter helps generate a wider disparity distribution and better synthetic images. Experiments show that models trained under our pipeline achieve state-of-the-art zero-shot generalization results among all published methods. The code will be available upon publication of the paper.

Recent advancements have highlighted the efficacy of self-supervised learning (SSL) features in various speech-related tasks, providing lightweight and versatile multi-view speech representations. However, our study reveals that while SSL features expedite model convergence, they conflict with traditional spectral features like FBanks in terms of update directions. In response, we propose a novel generalized feature fusion framework grounded in conditional computation, featuring a gradient-sensitive gating network and a multi-stage dropout strategy. This framework mitigates feature conflicts and bolsters model robustness to multi-view input features. By integrating SSL and spectral features, our approach accelerates convergence and maintains performance on par with spectral models across multiple speech translation tasks on the MUSTC dataset., Comment: ICASSP 2025

In this work, we investigate the semileptonic decays of $B_{(s)}$ meson to $D_{0}^{\ast}(2300)$, $D_{s0}^{\ast}(2317)$, $D_{s1}(2460)$, $D_{s1}(2536)$, $D_{1}(2420)$ and $D_{1}(2430)$ in the covariant light-front quark model (CLFQM). We combine the helicity amplitudes via the corresponding form factors to obtain the branching ratios of the semileptonic decays $B_{(s)} \to D^{**}_{(s)}\ell \nu_\ell$ with $D^{**}_{(s)}$ referring to a P-wave exicted charmed meson $D_{0}^{\ast}(2300)$, $D_{s0}^{\ast}(2317)$, $D_{s1}(2460)$, $D_{s1}(2536)$, $D_{1}(2420)$ or $D_{1}(2430)$ and $\ell=e, \mu, \tau$. Furthermore, we also take into account another two physical observables, namely the longitudinal polarization fraction $f_L$ and the forward-backward asymmetry $A_{FB}$. Most of our predictions are comparable to the results given by other theoretical approaches and the present available data. The branching ratios of the semileptonic decay channels $B_{s} \to D_{s1}(2460) \ell \nu_\ell$ and $B \to D_{1}(2420) \ell \nu_\ell$ are larger than those of the semileptonic decays $B_{s} \to D_{s1}(2536) \ell \nu_\ell$ and $B \to D_{1}(2430) \ell \nu_\ell$, respectively. We find that the long-standing '$1/2$ vs $3/2$ puzzle' in the decays $B^{+}\to \bar{D}_1^{(\prime)0} \ell^{\prime+}\nu_{\ell^\prime}$ $(\ell^\prime=e,\mu)$ can be solved by taking some negative mixing angle $\theta_s$ values within a range from $-30.3^\circ$ to $-24.9^\circ$, corresponding to $\theta$ of about $5^\circ\sim10.4^\circ$. While Belle collaboration updated their measurements for the decays $B^{0}\to D^{*-}_0 \ell^{\prime+}\nu_{\ell^\prime}$ with only a small upper limit $Br(B^{0}\to D^{*-}_0 \ell^{\prime+}\nu_{\ell^\prime})<0.44\times10^{-3}$ obtained, which is much larger than most theoretical predictions and causes a new puzzle., Comment: 25 pages, 6 figures. arXiv admin note: text overlap with arXiv:2405.00496

The field of artificial intelligence has witnessed significant advancements in natural language processing, largely attributed to the capabilities of Large Language Models (LLMs). These models form the backbone of Agents designed to address long-context dependencies, particularly in Document-level Machine Translation (DocMT). DocMT presents unique challenges, with quality, consistency, and fluency being the key metrics for evaluation. Existing approaches, such as Doc2Doc and Doc2Sent, either omit sentences or compromise fluency. This paper introduces Doc-Guided Sent2Sent++, an Agent that employs an incremental sentence-level forced decoding strategy \textbf{to ensure every sentence is translated while enhancing the fluency of adjacent sentences.} Our Agent leverages a Doc-Guided Memory, focusing solely on the summary and its translation, which we find to be an efficient approach to maintaining consistency. Through extensive testing across multiple languages and domains, we demonstrate that Sent2Sent++ outperforms other methods in terms of quality, consistency, and fluency. The results indicate that, our approach has achieved significant improvements in metrics such as s-COMET, d-COMET, LTCR-$1_f$, and document-level perplexity (d-ppl). The contributions of this paper include a detailed analysis of current DocMT research, the introduction of the Sent2Sent++ decoding method, the Doc-Guided Memory mechanism, and validation of its effectiveness across languages and domains.

The inaccurate translation of numbers can lead to significant security issues, ranging from financial setbacks to medical inaccuracies. While large language models (LLMs) have made significant advancements in machine translation, their capacity for translating numbers has not been thoroughly explored. This study focuses on evaluating the reliability of LLM-based machine translation systems when handling numerical data. In order to systematically test the numerical translation capabilities of currently open source LLMs, we have constructed a numerical translation dataset between Chinese and English based on real business data, encompassing ten types of numerical translation. Experiments on the dataset indicate that errors in numerical translation are a common issue, with most open-source LLMs faltering when faced with our test scenarios. Especially when it comes to numerical types involving large units like ``million", ``billion", and "yi", even the latest llama3.1 8b model can have error rates as high as 20%. Finally, we introduce three potential strategies to mitigate the numerical mistranslations for large units., Comment: Accepted by ICASSP 2025

Spoken named entity recognition (NER) aims to identify named entities from speech, playing an important role in speech processing. New named entities appear every day, however, annotating their Spoken NER data is costly. In this paper, we demonstrate that existing Spoken NER systems perform poorly when dealing with previously unseen named entities. To tackle this challenge, we propose a method for generating Spoken NER data based on a named entity dictionary (NED) to reduce costs. Specifically, we first use a large language model (LLM) to generate sentences from the sampled named entities and then use a text-to-speech (TTS) system to generate the speech. Furthermore, we introduce a noise metric to filter out noisy data. To evaluate our approach, we release a novel Spoken NER benchmark along with a corresponding NED containing 8,853 entities. Experiment results show that our method achieves state-of-the-art (SOTA) performance in the in-domain, zero-shot domain adaptation, and fully zero-shot settings. Our data will be available at https://github.com/DeepLearnXMU/HeardU., Comment: Accepted by ICASSP 2025

With the widespread application of Large Language Models (LLMs) in the field of Natural Language Processing (NLP), enhancing their performance has become a research hotspot. This paper presents a novel multi-prompt ensemble decoding approach designed to bolster the generation quality of LLMs by leveraging the aggregation of outcomes from multiple prompts. Given a unique input $X$, we submit $n$ variations of prompts with $X$ to LLMs in batch mode to decode and derive probability distributions. For each token prediction, we calculate the ensemble probability by averaging the $n$ probability distributions within the batch, utilizing this aggregated probability to generate the token. This technique is dubbed Inner-Batch Ensemble. To facilitate efficient batch inference, we implement a Left-Padding strategy to maintain uniform input lengths across the n prompts. Through extensive experimentation on diverse NLP tasks, including machine translation, code generation, and text simplification, we demonstrate the efficacy of our method in enhancing LLM performance. The results show substantial improvements in BLEU scores, pass@$k$ rates, and LENS metrics over conventional methods.

We develop a first-principles approach to compute infrared (IR) vibrational absorption and Raman scattering spectra with excitonic effects included. Our method is based on a perturbative expansion of electron-phonon and electron-light couplings in the time-dependent adiabatic GW (TD-aGW) theory. We show that excitonic effects in the IR absorption spectrum can be included by replacing the free electron-hole propagators in the perturbative expression for independent particles with their interacting counterparts, which are readily available from standard GW-Bethe-Salpeter equation calculations. For Raman spectrum, our derived expression agrees with the single and double resonance terms from a diagrammatic approach. We show significant excitonic enhancement in both the IR and resonance Raman scattering intensity for monolayer MoS2, WS2, and WSe2. Moreover, the exciton-phonon coupling strength and exciton energy landscape can be accessed by analyzing resonance Raman spectrum of these materials., Comment: 17 pages, 4 figures

Unsupervised anomaly detection in brain imaging is challenging. In this paper, we propose a self-supervised masked mesh learning for unsupervised anomaly detection in 3D cortical surfaces. Our framework leverages the intrinsic geometry of the cortical surface to learn a self-supervised representation that captures the underlying structure of the brain. We introduce a masked mesh convolutional neural network (MMN) that learns to predict masked regions of the cortical surface. By training the MMN on a large dataset of healthy subjects, we learn a representation that captures the normal variation in the cortical surface. We then use this representation to detect anomalies in unseen individuals by calculating anomaly scores based on the reconstruction error of the MMN. We evaluate our framework by training on population-scale dataset UKB and HCP-Aging and testing on two datasets of Alzheimer's disease patients ADNI and OASIS3. Our results show that our framework can detect anomalies in cortical thickness, cortical volume, and cortical sulcus features, which are known to be sensitive biomarkers for Alzheimer's disease. Our proposed framework provides a promising approach for unsupervised anomaly detection based on normative variation of cortical features.

Understanding exciton thermalization is critical for optimizing optoelectronic and photocatalytic processes in many materials. However, it is hard to access the dynamics of such processes experimentally, especially on systems such as monolayer transition metal dichalcogenides, where various low-energy excitations pathways can compete for exciton thermalization. Here, we study exciton dynamics due to exciton-phonon scattering in monolayer MoS2 from a first-principles, interacting Green's function approach, to obtain the relaxation and thermalization of low-energy excitons following different initial excitations at different temperatures. We find that the thermalization occurs on a picosecond timescale at 300 K but can increase by an order of magnitude at 100 K. The long total thermalization time, owing to the nature of its excitonic band structure, is dominated by slow spin-flip scattering processes in monolayer MoS2. In contrast, thermalization of excitons in individual spin-aligned and spin-anti-aligned channels can be achieved within a few hundred fs when exciting higher-energy excitons. We further simulate the intensity spectrum of time-resolved angle-resolved photoemission spectroscopy (TR-ARPES) experiments and anticipate that such calculations may serve as a map to correlate spectroscopic signatures with microscopic exciton dynamics., Comment: 19 pages, 8 figures

Chain-of-Thought prompting has significantly enhanced the reasoning capabilities of large language models, with numerous studies exploring factors influencing its performance. However, the underlying mechanisms remain poorly understood. To further demystify the operational principles, this work examines three key aspects: decoding, projection, and activation, aiming to elucidate the changes that occur within models when employing Chainof-Thought. Our findings reveal that LLMs effectively imitate exemplar formats while integrating them with their understanding of the question, exhibiting fluctuations in token logits during generation but ultimately producing a more concentrated logits distribution, and activating a broader set of neurons in the final layers, indicating more extensive knowledge retrieval compared to standard prompts. Our code and data will be publicly avialable when the paper is accepted.

The increasing complexity of computer systems necessitates innovative approaches to fault and error management, going beyond traditional manual log analysis. While existing solutions using large language models (LLMs) show promise, they are limited by a gap between natural and domain-specific languages, which restricts their effectiveness in real-world applications. Our approach addresses these limitations by integrating interpretable domain knowledge into open-source LLMs through continual pre-training (CPT), enhancing performance on log tasks while retaining natural language processing capabilities. We created a comprehensive dataset, NLPLog, with over 250,000 question-answer pairs to facilitate this integration. Our model, SuperLog, trained with this dataset, achieves the best performance across four log analysis tasks, surpassing the second-best model by an average of 12.01%. Our contributions include a novel CPT paradigm that significantly improves model performance, the development of SuperLog with state-of-the-art results, and the release of a large-scale dataset to support further research in this domain.

As a fine-grained task, multimodal aspect-based sentiment analysis (MABSA) mainly focuses on identifying aspect-level sentiment information in the text-image pair. However, we observe that it is difficult to recognize the sentiment of aspects in low-quality samples, such as those with low-resolution images that tend to contain noise. And in the real world, the quality of data usually varies for different samples, such noise is called data uncertainty. But previous works for the MABSA task treat different quality samples with the same importance and ignored the influence of data uncertainty. In this paper, we propose a novel data uncertainty-aware multimodal aspect-based sentiment analysis approach, UA-MABSA, which weighted the loss of different samples by the data quality and difficulty. UA-MABSA adopts a novel quality assessment strategy that takes into account both the image quality and the aspect-based cross-modal relevance, thus enabling the model to pay more attention to high-quality and challenging samples. Extensive experiments show that our method achieves state-of-the-art (SOTA) performance on the Twitter-2015 dataset. Further analysis demonstrates the effectiveness of the quality assessment strategy.

The contribution of a time-independent toroidally-symmetric radial electric field $E_r$ is implemented in VisualStart [Comp. Phys. Comm. 275 (2022) 108305; arXiv:2111.08224], a code whose purposes include the construction of guiding center (GC) drift orbit databases for the study of plasma instabilities in tokamaks. $E_r$ is important for the thermal part of the velocity distribution and for fast particle resonances in the kHz frequency range. KSTAR, JT-60U and ITER tokamak cases are used as working examples to test our methods and discuss practical issues connected with $E_r$. Two points are worth noting: First, the GC orbit space is sampled in the magnetic midplane as before, and we find that in the presence of $E_r$, midplane-based coordinates are not only equivalent but superior to conventional constants of motion, allowing to attain high numerical accuracy and efficiency with a relatively simple mesh. Second, the periodic parallel acceleration and deceleration of GCs via the mirror force is modulated by $E_r$. Although this parallel electric acceleration averages to zero during a poloidal transit (or bounce) period, it has important consequences, one being the known shift of the trapped-passing boundary. Another consequence is that electric frequency shifts depend on the chosen reference point, so that some care is required when evaluating the $E_r$-dependence of transit frequencies for resonance analyses., Comment: 42 pages, 23 figures, submitted to Computer Physics Communications

Accurate segmentation of blood vessels is essential for various clinical assessments and postoperative analyses. However, the inherent challenges of vascular imaging, such as sparsity, fine granularity, low contrast, data distribution variability, and the critical need for preserving topological structure, making generalized vessel segmentation particularly complex. While specialized segmentation methods have been developed for specific anatomical regions, their over-reliance on tailored models hinders broader applicability and generalization. General-purpose segmentation models introduced in medical imaging often fail to address critical vascular characteristics, including the connectivity of segmentation results. To overcome these limitations, we propose an optimized vessel segmentation framework: a structure-agnostic approach incorporating small vessel enhancement and morphological correction for multi-modality vessel segmentation. To train and validate this framework, we compiled a comprehensive multi-modality dataset spanning 17 datasets and benchmarked our model against six SAM-based methods and 17 expert models. The results demonstrate that our approach achieves superior segmentation accuracy, generalization, and a 34.6% improvement in connectivity, underscoring its clinical potential. An ablation study further validates the effectiveness of the proposed improvements. We will release the code and dataset at github following the publication of this work., Comment: 12 pages, 7 figurres, submitted to TIP

Text-to-speech (TTS) models have been widely adopted to enhance automatic speech recognition (ASR) systems using text-only corpora, thereby reducing the cost of labeling real speech data. Existing research primarily utilizes additional text data and predefined speech styles supported by TTS models. In this paper, we propose Hard-Synth, a novel ASR data augmentation method that leverages large language models (LLMs) and advanced zero-shot TTS. Our approach employs LLMs to generate diverse in-domain text through rewriting, without relying on additional text data. Rather than using predefined speech styles, we introduce a hard prompt selection method with zero-shot TTS to clone speech styles that the ASR model finds challenging to recognize. Experiments demonstrate that Hard-Synth significantly enhances the Conformer model, achieving relative word error rate (WER) reductions of 6.5\%/4.4\% on LibriSpeech dev/test-other subsets. Additionally, we show that Hard-Synth is data-efficient and capable of reducing bias in ASR.

Snapshot Compressive Imaging (SCI) offers a possibility for capturing information in high-speed dynamic scenes, requiring efficient reconstruction method to recover scene information. Despite promising results, current deep learning-based and NeRF-based reconstruction methods face challenges: 1) deep learning-based reconstruction methods struggle to maintain 3D structural consistency within scenes, and 2) NeRF-based reconstruction methods still face limitations in handling dynamic scenes. To address these challenges, we propose SCIGS, a variant of 3DGS, and develop a primitive-level transformation network that utilizes camera pose stamps and Gaussian primitive coordinates as embedding vectors. This approach resolves the necessity of camera pose in vanilla 3DGS and enhances multi-view 3D structural consistency in dynamic scenes by utilizing transformed primitives. Additionally, a high-frequency filter is introduced to eliminate the artifacts generated during the transformation. The proposed SCIGS is the first to reconstruct a 3D explicit scene from a single compressed image, extending its application to dynamic 3D scenes. Experiments on both static and dynamic scenes demonstrate that SCIGS not only enhances SCI decoding but also outperforms current state-of-the-art methods in reconstructing dynamic 3D scenes from a single compressed image. The code will be made available upon publication.

Ultrasound (US) image stitching can expand the field-of-view (FOV) by combining multiple US images from varied probe positions. However, registering US images with only partially overlapping anatomical contents is a challenging task. In this work, we introduce SynStitch, a self-supervised framework designed for 2DUS stitching. SynStitch consists of a synthetic stitching pair generation module (SSPGM) and an image stitching module (ISM). SSPGM utilizes a patch-conditioned ControlNet to generate realistic 2DUS stitching pairs with known affine matrix from a single input image. ISM then utilizes this synthetic paired data to learn 2DUS stitching in a supervised manner. Our framework was evaluated against multiple leading methods on a kidney ultrasound dataset, demonstrating superior 2DUS stitching performance through both qualitative and quantitative analyses. The code will be made public upon acceptance of the paper.

Diffusion models have risen to prominence in time series forecasting, showcasing their robust capability to model complex data distributions. However, their effectiveness in deterministic predictions is often constrained by instability arising from their inherent stochasticity. In this paper, we revisit time series diffusion models and present a comprehensive framework that encompasses most existing diffusion-based methods. Building on this theoretical foundation, we propose a novel diffusion-based time series forecasting model, the Series-to-Series Diffusion Bridge Model ($\mathrm{S^2DBM}$), which leverages the Brownian Bridge process to reduce randomness in reverse estimations and improves accuracy by incorporating informative priors and conditions derived from historical time series data. Experimental results demonstrate that $\mathrm{S^2DBM}$ delivers superior performance in point-to-point forecasting and competes effectively with other diffusion-based models in probabilistic forecasting.

Large Multimodal Models (LMMs) have demonstrated the ability to interact with humans under real-world conditions by combining Large Language Models (LLMs) and modality encoders to align multimodal information (visual and auditory) with text. However, such models raise new safety challenges of whether models that are safety-aligned on text also exhibit consistent safeguards for multimodal inputs. Despite recent safety-alignment research on vision LMMs, the safety of audio LMMs remains under-explored. In this work, we comprehensively red team the safety of five advanced audio LMMs under three settings: (i) harmful questions in both audio and text formats, (ii) harmful questions in text format accompanied by distracting non-speech audio, and (iii) speech-specific jailbreaks. Our results under these settings demonstrate that open-source audio LMMs suffer an average attack success rate of 69.14% on harmful audio questions, and exhibit safety vulnerabilities when distracted with non-speech audio noise. Our speech-specific jailbreaks on Gemini-1.5-Pro achieve an attack success rate of 70.67% on the harmful query benchmark. We provide insights on what could cause these reported safety-misalignments. Warning: this paper contains offensive examples.

We have investigated the structures and electronic properties of ultra-thin Bi(110) films grown on an s-wave superconductor substrate using low-temperature scanning tunneling microscopy and spectroscopy. Remarkably, our experimental results validate the theoretical predictions that the manipulation of Bi(110) surface atom buckling can control the topological phase transition. Notably, we have observed robust unreconstructed edge states at the edges of both 3-bilayer (BL) and 4-BL Bi(110) films, with the 4-BL film displaying stronger edge state intensity and a smaller degree of atomic buckling. First-principle calculations further substantiate these findings, demonstrating a gradual reduction in buckling as the film thickness increases, with average height differences between two Bi atoms of approximately 0.19 {\AA}, 0.10 {\AA}, 0.05 {\AA}, and 0.00 {\AA} for the 1-BL, 2-BL, 3-BL, and 4-BL Bi(110) films, respectively. When Bi films are larger than 2 layers, the system changes from a trivial to a non-trivial phase. This research sets the stage for the controlled realization of topological superconductors through the superconducting proximity effect, providing a significant platform for investigating Majorana zero modes and fabricating quantum devices.

Image dehazing has drawn a significant attention in recent years. Learning-based methods usually require paired hazy and corresponding ground truth (haze-free) images for training. However, it is difficult to collect real-world image pairs, which prevents developments of existing methods. Although several works partially alleviate this issue by using synthetic datasets or small-scale real datasets. The haze intensity distribution bias and scene homogeneity in existing datasets limit the generalization ability of these methods, particularly when encountering images with previously unseen haze intensities. In this work, we present LMHaze, a large-scale, high-quality real-world dataset. LMHaze comprises paired hazy and haze-free images captured in diverse indoor and outdoor environments, spanning multiple scenarios and haze intensities. It contains over 5K high-resolution image pairs, surpassing the size of the biggest existing real-world dehazing dataset by over 25 times. Meanwhile, to better handle images with different haze intensities, we propose a mixture-of-experts model based on Mamba (MoE-Mamba) for dehazing, which dynamically adjusts the model parameters according to the haze intensity. Moreover, with our proposed dataset, we conduct a new large multimodal model (LMM)-based benchmark study to simulate human perception for evaluating dehazed images. Experiments demonstrate that LMHaze dataset improves the dehazing performance in real scenarios and our dehazing method provides better results compared to state-of-the-art methods.

We explored the Patrol Security Game (PSG), a robotic patrolling problem modeled as an extensive-form Stackelberg game, where the attacker determines the timing, location, and duration of their attack. Our objective is to devise a patrolling schedule with an infinite time horizon that minimizes the attacker's payoff. We demonstrated that PSG can be transformed into a combinatorial minimax problem with a closed-form objective function. By constraining the defender's strategy to a time-homogeneous first-order Markov chain (i.e., the patroller's next move depends solely on their current location), we proved that the optimal solution in cases of zero penalty involves either minimizing the expected hitting time or return time, depending on the attacker model, and that these solutions can be computed efficiently. Additionally, we observed that increasing the randomness in the patrol schedule reduces the attacker's expected payoff in high-penalty cases. However, the minimax problem becomes non-convex in other scenarios. To address this, we formulated a bi-criteria optimization problem incorporating two objectives: expected maximum reward and entropy. We proposed three graph-based algorithms and one deep reinforcement learning model, designed to efficiently balance the trade-off between these two objectives. Notably, the third algorithm can identify the optimal deterministic patrol schedule, though its runtime grows exponentially with the number of patrol spots. Experimental results validate the effectiveness and scalability of our solutions, demonstrating that our approaches outperform state-of-the-art baselines on both synthetic and real-world crime datasets., Comment: Under review of TCPS

Large language models (LLMs) have exhibited outstanding performance in engaging with humans and addressing complex questions by leveraging their vast implicit knowledge and robust reasoning capabilities. However, such models are vulnerable to jailbreak attacks, leading to the generation of harmful responses. Despite recent research on single-turn jailbreak strategies to facilitate the development of defence mechanisms, the challenge of revealing vulnerabilities under multi-turn setting remains relatively under-explored. In this work, we propose Jigsaw Puzzles (JSP), a straightforward yet effective multi-turn jailbreak strategy against the advanced LLMs. JSP splits questions into harmless fractions as the input of each turn, and requests LLMs to reconstruct and respond to questions under multi-turn interaction. Our experimental results demonstrate that the proposed JSP jailbreak bypasses original safeguards against explicitly harmful content, achieving an average attack success rate of 93.76% on 189 harmful queries across 5 advanced LLMs (Gemini-1.5-Pro, Llama-3.1-70B, GPT-4, GPT-4o, GPT-4o-mini). Moreover, JSP achieves a state-of-the-art attack success rate of 92% on GPT-4 on the harmful query benchmark, and exhibits strong resistant to defence strategies. Warning: this paper contains offensive examples.

The semileptonic and nonleptonic decays of the b-flavor vector mesons $B^{*}_{u,d,s}$ and $B_{c}^{*}$ are investigated within the covariant light-front quark model (CLFQM). By calculating the form factors of the transitions $B_{u, d, s, c}^{*}\to P$ under the CLFQM, with $P$ denoting a pseudoscalar meson, i.e., $\pi, K, \eta_c(1S,2S), D_{(s)}, B_{(s)}$, we predict and discuss several physical observables, including the branching ratios, polarization fractions $f_{L}, f_{\|}$, and forward-backward asymmetries $A_{FB}$. The total widths of the single-photon radiative decay channels for these b-flavor vector mesons are estimated using their partial widths. In these considered decays, one can find that the semileptonic decays $B_{s}^{*0}\to D_{s}^{-}\ell^{\prime+}{\nu}_{\ell^\prime}$ and $B_{c}^{*+}\to B_{s}^{0}\ell^{\prime+}{\nu}_{\ell^\prime}, \eta_{c}\ell^{\prime+}{\nu}_{\ell^\prime}$, with $\ell^\prime$ being $e$ or $\tau$, and the nonleptonic channels $B_{c}^{*+}\to B^0_{s} \pi^{+}, B^0_{s} \rho^{+}$ have the largest branching ratios, which can reach up to the $10^{-7}$ order, and are most likely to be accessible at the future high-luminosity LHCb and Belle-II experiments., Comment: 30 pages, 4 figures,accepted for publication in Chin. Phys. C

Automatic log analysis is essential for the efficient Operation and Maintenance (O&M) of software systems, providing critical insights into system behaviors. However, existing approaches mostly treat log analysis as training a model to perform an isolated task ( e.g., anomaly detection, log parsing, etc.) using task-specific log-label pairs. These task-based approaches are inflexible in generalizing to complex scenarios, depend on task-specific training data, and cost significantly when deploying multiple models. In this paper, we propose an instruction-based training approach that transforms log-label pairs from multiple tasks and domains into a unified format of instruction-response pairs. Our trained model, LogLM, can follow complex user instructions and generalize better across different tasks, thereby increasing flexibility and reducing the dependence on task-specific training data. By integrating major log analysis tasks into a single model, our approach also relieves model deployment burden. Experimentally, LogLM outperforms existing approaches across five log analysis capabilities, and exhibits strong generalization abilities on complex instructions and unseen tasks., Comment: Accepted by ICSE 2025 (SEIP Track)

Graph neural networks (GNNs) are becoming increasingly popular for EEG-based depression detection. However, previous GNN-based methods fail to sufficiently consider the characteristics of depression, thus limiting their performance. Firstly, studies in neuroscience indicate that depression patients exhibit both common and individualized brain abnormal patterns. Previous GNN-based approaches typically focus either on fixed graph connections to capture common abnormal brain patterns or on adaptive connections to capture individualized patterns, which is inadequate for depression detection. Secondly, brain network exhibits a hierarchical structure, which includes the arrangement from channel-level graph to region-level graph. This hierarchical structure varies among individuals and contains significant information relevant to detecting depression. Nonetheless, previous GNN-based methods overlook these individualized hierarchical information. To address these issues, we propose a Hybrid GNN (HGNN) that merges a Common Graph Neural Network (CGNN) branch utilizing fixed connection and an Individualized Graph Neural Network (IGNN) branch employing adaptive connections. The two branches capture common and individualized depression patterns respectively, complementing each other. Furthermore, we enhance the IGNN branch with a Graph Pooling and Unpooling Module (GPUM) to extract individualized hierarchical information. Extensive experiments on two public datasets show that our model achieves state-of-the-art performance.

The rapid development of large language models (LLMs) has significantly transformed the field of artificial intelligence, demonstrating remarkable capabilities in natural language processing and moving towards multi-modal functionality. These models are increasingly integrated into diverse applications, impacting both research and industry. However, their development and deployment present substantial challenges, including the need for extensive computational resources, high energy consumption, and complex software optimizations. Unlike traditional deep learning systems, LLMs require unique optimization strategies for training and inference, focusing on system-level efficiency. This paper surveys hardware and software co-design approaches specifically tailored to address the unique characteristics and constraints of large language models. This survey analyzes the challenges and impacts of LLMs on hardware and algorithm research, exploring algorithm optimization, hardware design, and system-level innovations. It aims to provide a comprehensive understanding of the trade-offs and considerations in LLM-centric computing systems, guiding future advancements in AI. Finally, we summarize the existing efforts in this space and outline future directions toward realizing production-grade co-design methodologies for the next generation of large language models and AI systems., Comment: Accepted by IEEE Circuits and Systems Magazine

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

Haptic feedback to the surgeon during robotic surgery would enable safer and more immersive surgeries but estimating tissue interaction forces at the tips of robotically controlled surgical instruments has proven challenging. Few existing surgical robots can measure interaction forces directly and the additional sensor may limit the life of instruments. We present a hybrid model and learning-based framework for force estimation for the Patient Side Manipulators (PSM) of a da Vinci Research Kit (dVRK). The model-based component identifies the dynamic parameters of the robot and estimates free-space joint torque, while the learning-based component compensates for environmental factors, such as the additional torque caused by trocar interaction between the PSM instrument and the patient's body wall. We evaluate our method in an abdominal phantom and achieve an error in force estimation of under 10% normalized root-mean-squared error. We show that by using a model-based method to perform dynamics identification, we reduce reliance on the training data covering the entire workspace. Although originally developed for the dVRK, the proposed method is a generalizable framework for other compliant surgical robots. The code is available at https://github.com/vu-maple-lab/dvrk_force_estimation., Comment: Accepted by IROS 2024

This paper describes the submissions of Huawei Translation Services Center(HW-TSC) to WMT24 chat translation shared task on English$\leftrightarrow$Germany (en-de) bidirection. The experiments involved fine-tuning models using chat data and exploring various strategies, including Minimum Bayesian Risk (MBR) decoding and self-training. The results show significant performance improvements in certain directions, with the MBR self-training method achieving the best results. The Large Language Model also discusses the challenges and potential avenues for further research in the field of chat translation., Comment: 7 pages, 6 Tables, WMT24

This article introduces the submission status of the Translation into Low-Resource Languages of Spain task at (WMT 2024) by Huawei Translation Service Center (HW-TSC). We participated in three translation tasks: spanish to aragonese (es-arg), spanish to aranese (es-arn), and spanish to asturian (es-ast). For these three translation tasks, we use training strategies such as multilingual transfer, regularized dropout, forward translation and back translation, labse denoising, transduction ensemble learning and other strategies to neural machine translation (NMT) model based on training deep transformer-big architecture. By using these enhancement strategies, our submission achieved a competitive result in the final evaluation., Comment: 6 pages,wmt24. arXiv admin note: substantial text overlap with arXiv:2409.14842; text overlap with arXiv:2409.14800

This paper introduces the submission by Huawei Translation Center (HW-TSC) to the WMT24 Indian Languages Machine Translation (MT) Shared Task. To develop a reliable machine translation system for low-resource Indian languages, we employed two distinct knowledge transfer strategies, taking into account the characteristics of the language scripts and the support available from existing open-source models for Indian languages. For Assamese(as) and Manipuri(mn), we fine-tuned the existing IndicTrans2 open-source model to enable bidirectional translation between English and these languages. For Khasi (kh) and Mizo (mz), We trained a multilingual model as a baseline using bilingual data from these four language pairs, along with an additional about 8kw English-Bengali bilingual data, all of which share certain linguistic features. This was followed by fine-tuning to achieve bidirectional translation between English and Khasi, as well as English and Mizo. Our transfer learning experiments produced impressive results: 23.5 BLEU for en-as, 31.8 BLEU for en-mn, 36.2 BLEU for as-en, and 47.9 BLEU for mn-en on their respective test sets. Similarly, the multilingual model transfer learning experiments yielded impressive outcomes, achieving 19.7 BLEU for en-kh, 32.8 BLEU for en-mz, 16.1 BLEU for kh-en, and 33.9 BLEU for mz-en on their respective test sets. These results not only highlight the effectiveness of transfer learning techniques for low-resource languages but also contribute to advancing machine translation capabilities for low-resource Indian languages., Comment: 6 pages, wmt24. arXiv admin note: substantial text overlap with arXiv:2409.14800

This report outlines our approach for the WMT24 Discourse-Level Literary Translation Task, focusing on the Chinese-English language pair in the Constrained Track. Translating literary texts poses significant challenges due to the nuanced meanings, idiomatic expressions, and intricate narrative structures inherent in such works. To address these challenges, we leveraged the Chinese-Llama2 model, specifically enhanced for this task through a combination of Continual Pre-training (CPT) and Supervised Fine-Tuning (SFT). Our methodology includes a novel Incremental Decoding framework, which ensures that each sentence is translated with consideration of its broader context, maintaining coherence and consistency throughout the text. This approach allows the model to capture long-range dependencies and stylistic elements, producing translations that faithfully preserve the original literary quality. Our experiments demonstrate significant improvements in both sentence-level and document-level BLEU scores, underscoring the effectiveness of our proposed framework in addressing the complexities of document-level literary translation., Comment: 7 pages, 2 figures, wmt24

This paper presents the submission of Huawei Translation Services Center (HW-TSC) to machine translation tasks of the 20th China Conference on Machine Translation (CCMT 2024). We participate in the bilingual machine translation task and multi-domain machine translation task. For these two translation tasks, we use training strategies such as regularized dropout, bidirectional training, data diversification, forward translation, back translation, alternated training, curriculum learning, and transductive ensemble learning to train neural machine translation (NMT) models based on the deep Transformer-big architecture. Furthermore, to explore whether large language model (LLM) can help improve the translation quality of NMT systems, we use supervised fine-tuning to train llama2-13b as an Automatic post-editing (APE) model to improve the translation results of the NMT model on the multi-domain machine translation task. By using these plyometric strategies, our submission achieves a competitive result in the final evaluation., Comment: 13 pages, 2 figures, 6 Tables, CCMT2024. arXiv admin note: substantial text overlap with arXiv:2409.14800

This paper presents the submission of Huawei Translate Services Center (HW-TSC) to the WMT24 general machine translation (MT) shared task, where we participate in the English to Chinese (en2zh) language pair. Similar to previous years' work, we use training strategies such as regularized dropout, bidirectional training, data diversification, forward translation, back translation, alternated training, curriculum learning, and transductive ensemble learning to train the neural machine translation (NMT) model based on the deep Transformer-big architecture. The difference is that we also use continue pre-training, supervised fine-tuning, and contrastive preference optimization to train the large language model (LLM) based MT model. By using Minimum Bayesian risk (MBR) decoding to select the final translation from multiple hypotheses for NMT and LLM-based MT models, our submission receives competitive results in the final evaluation., Comment: 10 pages, 4 figures, 2 Tables, EMNLP2024

Large language models can enhance automatic speech recognition systems through generative error correction. In this paper, we propose Pinyin-enhanced GEC, which leverages Pinyi, the phonetic representation of Mandarin Chinese, as supplementary information to improve Chinese ASR error correction. Our approach only utilizes synthetic errors for training and employs the one-best hypothesis during inference. Additionally, we introduce a multitask training approach involving conversion tasks between Pinyin and text to align their feature spaces. Experiments on the Aishell-1 and the Common Voice datasets demonstrate that our approach consistently outperforms GEC with text-only input. More importantly, we provide intuitive explanations for the effectiveness of PY-GEC and multitask training from two aspects: 1) increased attention weight on Pinyin features; and 2) aligned feature space between Pinyin and text hidden states.

Recent advancements in integrating speech information into large language models (LLMs) have significantly improved automatic speech recognition (ASR) accuracy. However, existing methods often constrained by the capabilities of the speech encoders under varied acoustic conditions, such as accents. To address this, we propose LA-RAG, a novel Retrieval-Augmented Generation (RAG) paradigm for LLM-based ASR. LA-RAG leverages fine-grained token-level speech datastores and a speech-to-speech retrieval mechanism to enhance ASR accuracy via LLM in-context learning (ICL) capabilities. Experiments on Mandarin and various Chinese dialect datasets demonstrate significant improvements in ASR accuracy compared to existing methods, validating the effectiveness of our approach, especially in handling accent variations., Comment: submitted to ICASSP 2025

Open-vocabulary detection (OVD) aims to detect objects beyond a predefined set of categories. As a pioneering model incorporating the YOLO series into OVD, YOLO-World is well-suited for scenarios prioritizing speed and efficiency. However, its performance is hindered by its neck feature fusion mechanism, which causes the quadratic complexity and the limited guided receptive fields. To address these limitations, we present Mamba-YOLO-World, a novel YOLO-based OVD model employing the proposed MambaFusion Path Aggregation Network (MambaFusion-PAN) as its neck architecture. Specifically, we introduce an innovative State Space Model-based feature fusion mechanism consisting of a Parallel-Guided Selective Scan algorithm and a Serial-Guided Selective Scan algorithm with linear complexity and globally guided receptive fields. It leverages multi-modal input sequences and mamba hidden states to guide the selective scanning process. Experiments demonstrate that our model outperforms the original YOLO-World on the COCO and LVIS benchmarks in both zero-shot and fine-tuning settings while maintaining comparable parameters and FLOPs. Additionally, it surpasses existing state-of-the-art OVD methods with fewer parameters and FLOPs.

Just like other heavy flavor mesons, the weak decays of $D^*_{(s)}$ mesons can also provide a platform to check the Standard Model (SM), explore new physics (NP) and understand the mechanisms of weak interactions. At present, the theoretical and experimental researches on $D^*_{(s)}$ mesons are relatively limited. In addition to the dominant electromagnetic decays, the $D^*_{(s)}$ weak decays should also be feasible to explore the $D^*_{(s)}$ mesons. In this paper, we use the covariant light-front quark model (CLFQM) to study the branching ratios of the semi-leptonic decays $D^*_{(s)}\to P\ell^{+}\nu_{\ell}$ and the non-leptonic decays $D^*_{(s)}\to PP, PV$ with $P=\pi, K, \eta^{(\prime)}, V=\rho, K^*, \phi$ and $\ell=e, \mu$, which are within the range $10^{-13}\sim 10^{-6}$. Among these decays, the channels $D_{s}^{*+}\to\eta \ell^{+}\nu_{\ell}$ and $D^{*+}_{s}\to \eta\rho^{+}$ possess the largest branching ratios, which can reach up to $10^{-6}$ order. These decays are most likely to be accessible at the future high-luminosity experiments. One can find that the branching ratios $\mathcal{B}r(D_{s}^{*+}\to\eta \ell^{+}\nu_{\ell})=1.46\times10^{-6}$ and $\mathcal{B}r(D_{s}^{*+}\to\eta \rho^{+})=1.04\times10^{-6}$ correspond to tens of thousands of events in the $e^+e^-$ collider experiments, such as the STCF, CEPC and FCC-ee, and tens of millions of events at the HL-LHC. In a word, it is feasible to study the $D^*_{(s)}$ meson weak decays in the future experiments. Furthermore, we also predict and discuss another two physical observations, that is, the longitudinal polarization fraction $f_{L}$ and the forward-backward asymmetry $A_{FB}$, for our considered decays., Comment: 23 pages, 4 figures. arXiv admin note: text overlap with arXiv:2311.04431

Previous studies on federated learning (FL) often encounter performance degradation due to data heterogeneity among different clients. In light of the recent advances in multimodal large language models (MLLMs), such as GPT-4v and LLaVA, which demonstrate their exceptional proficiency in multimodal tasks, such as image captioning and multimodal question answering. We introduce a novel federated learning framework, named Multimodal Large Language Model Assisted Federated Learning (MLLM-LLaVA-FL), which employs powerful MLLMs at the server end to address the heterogeneous and long-tailed challenges. Owing to the advanced cross-modality representation capabilities and the extensive open-vocabulary prior knowledge of MLLMs, our framework is adept at harnessing the extensive, yet previously underexploited, open-source data accessible from websites and powerful server-side computational resources. Hence, the MLLM-LLaVA-FL not only enhances the performance but also avoids increasing the risk of privacy leakage and the computational burden on local devices, distinguishing it from prior methodologies. Our framework has three key stages. Initially, we conduct global visual-text pretraining of the model. This pretraining is facilitated by utilizing the extensive open-source data available online, with the assistance of MLLMs. Subsequently, the pretrained model is distributed among various clients for local training. Finally, once the locally trained models are transmitted back to the server, a global alignment is carried out under the supervision of MLLMs to further enhance the performance. Experimental evaluations on established benchmarks, show that our framework delivers promising performance in the typical scenarios with data heterogeneity and long-tail distribution across different clients in FL., Comment: Accepted to WACV 2025

Swift J1858.6$-$0814 (hereafter J1858) is a transient neutron star low-mass X-ray binary (NS LMXB). There is controversy regarding its donor mass derived from observations and theoretical calculations. In this paper, we adopt seven magnetic braking (MB) prescriptions suggested in the literature and different metallicity $Z$ to simulate the evolution of the LMXB. Our results show that, employing the MB model proposed by \citet{2012ApJ...746...43R} ("rm12"), the Convection And Rotation Boosted ("carb") model \citep{2019ApJ...886L..31V}, as well as the Intermediate ("inter") and Convection-boosted ("cboost") models in \citet{2019MNRAS.483.5595V} can match (part of) the observational parameters of J1858 well. We then apply our method to other observed LMXBs and find that the "rm12" and "inter" MB laws are most promising in explaining transient LMXBs. In comparison, the simulations with the "cboost" and "carb" MB laws are more inclined to reproduce persistent LMXBs and ultra-compact X-ray binaries (UCXBs), respectively. Our results, though subject to computational and/or observational bias, show that it is challenging to find a unified MB law that applies to the NS LMXB sub-populations simultaneously, indicating our lack of understanding of the true MB law. In addition, we explore the influence of various MB laws on the magnitude of the bifurcation periods in LMXBs., Comment: 15 pages, 7 figures, 1 table and 1 appendix, accepted for publication in ApJ

There is a great need to accurately predict short-term precipitation, which has socioeconomic effects such as agriculture and disaster prevention. Recently, the forecasting models have employed multi-source data as the multi-modality input, thus improving the prediction accuracy. However, the prevailing methods usually suffer from the desynchronization of multi-source variables, the insufficient capability of capturing spatio-temporal dependency, and unsatisfactory performance in predicting extreme precipitation events. To fix these problems, we propose a short-term precipitation forecasting model based on spatio-temporal alignment attention, with SATA as the temporal alignment module and STAU as the spatio-temporal feature extractor to filter high-pass features from precipitation signals and capture multi-term temporal dependencies. Based on satellite and ERA5 data from the southwestern region of China, our model achieves improvements of 12.61\% in terms of RMSE, in comparison with the state-of-the-art methods.

In this paper, we provide a criterion on uniform large deviation principles (ULDP) for stochastic differential equations under locally weak monotone conditions and Lyapunov conditions, which can be applied to stochastic systems with coefficients of polynomial growth and possible degenerate driving noises, including the stochastic Hamiltonian systems. The weak convergence method plays an important role in obtaining the ULDP. This result extends the scope of applications of the main theorem in \cite{WYZZ}., Comment: arXiv admin note: substantial text overlap with arXiv:2402.16522

Domain Generalization (DG) has been recently explored to improve the generalizability of point cloud classification (PCC) models toward unseen domains. However, they often suffer from limited receptive fields or quadratic complexity due to using convolution neural networks or vision Transformers. In this paper, we present the first work that studies the generalizability of state space models (SSMs) in DG PCC and find that directly applying SSMs into DG PCC will encounter several challenges: the inherent topology of the point cloud tends to be disrupted and leads to noise accumulation during the serialization stage. Besides, the lack of designs in domain-agnostic feature learning and data scanning will introduce unanticipated domain-specific information into the 3D sequence data. To this end, we propose a novel framework, PointDGMamba, that excels in strong generalizability toward unseen domains and has the advantages of global receptive fields and efficient linear complexity. PointDGMamba consists of three innovative components: Masked Sequence Denoising (MSD), Sequence-wise Cross-domain Feature Aggregation (SCFA), and Dual-level Domain Scanning (DDS). In particular, MSD selectively masks out the noised point tokens of the point cloud sequences, SCFA introduces cross-domain but same-class point cloud features to encourage the model to learn how to extract more generalized features. DDS includes intra-domain scanning and cross-domain scanning to facilitate information exchange between features. In addition, we propose a new and more challenging benchmark PointDG-3to1 for multi-domain generalization. Extensive experiments demonstrate the effectiveness and state-of-the-art performance of PointDGMamba., Comment: Accepted to AAAI 2025