Search

In this paper, we propose a novel framework for enhancing visual comprehension in autonomous driving systems by integrating visual language models (VLMs) with additional visual perception module specialised in object detection. We extend the Llama-Adapter architecture by incorporating a YOLOS-based detection network alongside the CLIP perception network, addressing limitations in object detection and localisation. Our approach introduces camera ID-separators to improve multi-view processing, crucial for comprehensive environmental awareness. Experiments on the DriveLM visual question answering challenge demonstrate significant improvements over baseline models, with enhanced performance in ChatGPT scores, BLEU scores, and CIDEr metrics, indicating closeness of model answer to ground truth. Our method represents a promising step towards more capable and interpretable autonomous driving systems. Possible safety enhancement enabled by detection modality is also discussed., Comment: accepted by SafeGenAI workshop of NeurIPS 2024

Infrared and visible image fusion aim to integrate modality strengths for visually enhanced, informative images. Visible imaging in real-world scenarios is susceptible to dynamic environmental brightness fluctuations, leading to texture degradation. Existing fusion methods lack robustness against such brightness perturbations, significantly compromising the visual fidelity of the fused imagery. To address this challenge, we propose the Brightness Adaptive multimodal dynamic fusion framework (BA-Fusion), which achieves robust image fusion despite dynamic brightness fluctuations. Specifically, we introduce a Brightness Adaptive Gate (BAG) module, which is designed to dynamically select features from brightness-related channels for normalization, while preserving brightness-independent structural information within the source images. Furthermore, we propose a brightness consistency loss function to optimize the BAG module. The entire framework is tuned via alternating training strategies. Extensive experiments validate that our method surpasses state-of-the-art methods in preserving multi-modal image information and visual fidelity, while exhibiting remarkable robustness across varying brightness levels. Our code is available: https://github.com/SunYM2020/BA-Fusion., Comment: Accepted by IJCAI 2024

Visual object tracking aims to locate a targeted object in a video sequence based on an initial bounding box. Recently, Vision-Language~(VL) trackers have proposed to utilize additional natural language descriptions to enhance versatility in various applications. However, VL trackers are still inferior to State-of-The-Art (SoTA) visual trackers in terms of tracking performance. We found that this inferiority primarily results from their heavy reliance on manual textual annotations, which include the frequent provision of ambiguous language descriptions. In this paper, we propose ChatTracker to leverage the wealth of world knowledge in the Multimodal Large Language Model (MLLM) to generate high-quality language descriptions and enhance tracking performance. To this end, we propose a novel reflection-based prompt optimization module to iteratively refine the ambiguous and inaccurate descriptions of the target with tracking feedback. To further utilize semantic information produced by MLLM, a simple yet effective VL tracking framework is proposed and can be easily integrated as a plug-and-play module to boost the performance of both VL and visual trackers. Experimental results show that our proposed ChatTracker achieves a performance comparable to existing methods.

Understanding uncertainty plays a critical role in achieving common ground (Clark et al.,1983). This is especially important for multimodal AI systems that collaborate with users to solve a problem or guide the user through a challenging concept. In this work, for the first time, we present a dataset annotated in collaboration with developmental and cognitive psychologists for the purpose of studying nonverbal cues of uncertainty. We then present an analysis of the data, studying different roles of uncertainty and its relationship with task difficulty and performance. Lastly, we present a multimodal machine learning model that can predict uncertainty given a real-time video clip of a participant, which we find improves upon a baseline multimodal transformer model. This work informs research on cognitive coordination between human-human and human-AI and has broad implications for gesture understanding and generation. The anonymized version of our data and code will be publicly available upon the completion of the required consent forms and data sheets., Comment: SIGDIAL 2023

We have developed a photonic filter featuring dual independently tunable passbands. Employing the reconstruction equivalent-chirp technique, we designed linearly chirped sampled Bragg gratings with two equivalent phase shifts positioned at 1/3 and 2/3 of the cavity, thus introducing two passbands in the +1st channel. Leveraging the significant thermo-optic effect of silicon, dual-band tuning is achieved via micro-heaters integrated on the chip surface. By tuning the injection currents ranging from 0 to 35 mA into the micro-heaters, the filter exhibits a wide range of dual-wavelength filtering performance, with the frequency interval between the two passbands adjustable from 37.2 GHz to 186.1 GHz., Comment: 5 pages, 5 figures. arXiv admin note: substantial text overlap with arXiv:2410.07788

We have developed an integrated dual-band photonic filter (PF) utilizing equivalent chirped four-phase-shifted sidewall-sampled Bragg gratings (4PS-SBG) on a silicon-on-insulator (SOI) platform. Using the reconstruction equivalent-chirp technique, we designed linearly chirped 4PS Bragg gratings with two {\pi}-phase shifts ({\pi}-PS) positioned at 1/3 and 2/3 of the grating cavity, introducing two passbands in the +1st order channel. Leveraging the significant thermo-optic effect of silicon, dual-band tuning is achieved through integrated micro-heaters (MHs) on the chip surface. By varying the injection currents from 0 to 85 mA into the MHs, the device demonstrates continuous and wide-range optical frequency division (OFD) performance, with the frequency interval between the two passbands adjustable from 52.1 GHz to 439.5 GHz. Four notable frequency division setups at 100 GHz, 200 GHz, 300 GHz, and 400 GHz were demonstrated using a 100 GHz, 1535 nm semiconductor passive mode-locked laser as the light source., Comment: 9 pages, 11 figures

A novel grating modulation technique for laser arrays is proposed and demonstrated. This method modifies the initial phase within each grating period, applying a total phase shift that increments in an arithmetic progression, ensuring equal channel spacing across the array. Despite the varying phase shifts, the device maintains coupling efficiency comparable to traditional uniform grating structures. Furthermore, the continuous phase modulation enhances the stability of the lasing wavelength of the primary mode, reducing sensitivity to fabrication errors. This improved tolerance to manufacturing inaccuracies represents a significant technological advancement, making this approach highly promising for applications requiring precise and stable wavelength control.

Knowledge sharing is crucial in healthcare, especially when leveraging data from multiple clinical sites to address data scarcity, reduce costs, and enable timely interventions. Transfer learning can facilitate cross-site knowledge transfer, but a major challenge is heterogeneity in clinical concepts across different sites. Large Language Models (LLMs) show significant potential of capturing the semantic meaning of clinical concepts and reducing heterogeneity. This study analyzed electronic health records from two large healthcare systems to assess the impact of semantic embeddings from LLMs on local, shared, and transfer learning models. Results indicate that domain-specific LLMs, such as Med-BERT, consistently outperform in local and direct transfer scenarios, while generic models like OpenAI embeddings require fine-tuning for optimal performance. However, excessive tuning of models with biomedical embeddings may reduce effectiveness, emphasizing the need for balance. This study highlights the importance of domain-specific embeddings and careful model tuning for effective knowledge transfer in healthcare.

This study proposes and experimentally demonstrates a distributed feedback (DFB) laser with a distributed phase shift (DPS) region at the center of the DFB cavity. By modeling the field intensity distribution in the cavity and the output spectrum, the DPS region length and phase shift values have been optimized. Experimental comparisons with lasers using traditional {\pi}-phase shifts confirm that DFB lasers with optimized DPS lengths and larger phase shifts (up to 15{\pi}) achieve stable single longitudinal mode operation over a broader current range, with lower threshold current, higher power slope efficiency, and a higher side mode suppression ratio (SMSR). Furthermore, the minimum optical linewidth is reduced significantly, from 1.3 MHz to 220 kHz., Comment: 5 pages, 5 figures

Free-form structural forms are widely used to design spatial structures for their irregular spatial morphology. Current free-form form-finding methods cannot adequately meet the material properties, structural requirements or construction conditions, which brings the deviation between the initial 3D geometric design model and the constructed free-form structure. Thus, the main focus of this paper is to improve the rationality of free-form morphology considering multiple objectives in line with the characteristics and constraints of material. In this paper, glued laminated timber is selected as a case. Firstly, machine learning is adopted based on the predictive capability. By selecting a free-form timber grid structure and following the principles of NURBS, the free-form structure is simplified into free-form curves. The transformer is selected to train and predict the curvatures of the curves considering the material characteristics. After predicting the curvatures, the curves are transformed into vectors consisting of control points, weights, and knot vectors. To ensure the constructability and robustness of the structure, minimising the mass of the structure, stress and strain energy are the optimisation objectives. Two parameters (weight and the z-coordinate of the control points) of the free-from morphology are extracted as the variables of the free-form morphology to conduct the optimisation. The evaluation algorithm was selected as the optimal tool due to its capability to optimise multiple parameters. While optimising the two variables, the mechanical performance evaluation indexes such as the maximum displacement in the z-direction are demonstrated in the 60th step. The optimisation results for structure mass, stress and strain energy after 60 steps show the tendency of oscillation convergence, which indicates the efficiency of the proposal multi-objective optimisation., Comment: 11 pages, 9 figures

Recent advances in topological one-dimensional photonic crystal concepts have enabled the development of robust light-emitting devices by incorporating a topological interface state (TIS) at the cavity center. In this study, we theoretically and experimentally demonstrate a one-dimensional TIS-extended photonic crystal (1D-TISE-PC) structure. By integrating a linearly dispersive zero-index one-dimensional photonic crystal structure with a four-phase shift sampled grating, photons propagate along the cavity without phase differences, enhancing the robustness to material variations and extending the TIS. Our findings indicate that extending the TIS promotes a more uniform photon distribution along the laser cavity and mitigates the spatial hole burning (SHB) effect. We fabricated and characterized a 1550 nm sidewall 1D-TISE-PC semiconductor laser, achieving stable single-mode operation across a wide current range from 60 to 420 mA, with a side-mode suppression ratio of 50 dB. The 1D-TISE-PC structure exhibited a linewidth narrowing effect to approximately 150 kHz Lorentzian linewidth. Utilizing reconstruction equivalent-chirp technology for the 4PS sampled grating enabled precise wavelength control in 1D-TISE-PC laser arrays, achieving a wavelength spacing of 0.796 nm +- 0.003 nm. We show that the TIS still exists in the TISE cavity and topological protection is preserved. Its mode extension characteristics mitigate the SHB so narrows the linewidth. We argue that the design simplicity and improvement of the fabrication tolerance make this architecture suitable for high-power and narrow-linewidth semiconductor lasers development.

Active learning (AL) for multiple target models aims to reduce labeled data querying while effectively training multiple models concurrently. Existing AL algorithms often rely on iterative model training, which can be computationally expensive, particularly for deep models. In this paper, we propose a one-shot AL method to address this challenge, which performs all label queries without repeated model training. Specifically, we extract different representations of the same dataset using distinct network backbones, and actively learn the linear prediction layer on each representation via an $\ell_p$-regression formulation. The regression problems are solved approximately by sampling and reweighting the unlabeled instances based on their maximum Lewis weights across the representations. An upper bound on the number of samples needed is provided with a rigorous analysis for $p\in [1, +\infty)$. Experimental results on 11 benchmarks show that our one-shot approach achieves competitive performances with the state-of-the-art AL methods for multiple target models., Comment: The proof of Lemma 3.11 is fixed

Rapid progress in multimodal large language models (MLLMs) highlights the need to introduce challenging yet realistic benchmarks to the academic community, while existing benchmarks primarily focus on understanding simple natural images and short context. In this paper, we present MULTI as a cutting-edge benchmark for evaluating MLLMs on understanding complex tables and images, and reasoning with long context. MULTI provides multimodal inputs and requires responses that are either precise or open-ended, reflecting real-life examination styles. MULTI includes over 18,000 questions and challenges MLLMs with a variety of tasks, ranging from formula derivation to image detail analysis and cross-modality reasoning. We also introduce MULTI-Elite, a 500-question selected hard subset, and MULTI-Extend, with more than 4,500 external knowledge context pieces. Our evaluation indicates significant potential for MLLM advancement, with GPT-4V achieving a 63.7% accuracy rate on MULTI, in contrast to other MLLMs scoring between 28.5% and 55.3%. MULTI serves not only as a robust evaluation platform but also paves the way for the development of expert-level AI., Comment: 16 pages, 9 figures, 10 tables. Details and access are available at: https://OpenDFM.github.io/MULTI-Benchmark/

Transfer learning has become a pivotal technique in machine learning and has proven to be effective in various real-world applications. However, utilizing this technique for classification tasks with sequential data often faces challenges, primarily attributed to the scarcity of class labels. To address this challenge, we introduce Multi-Source Adaptive Weighting (MSAW), an online multi-source transfer learning method. MSAW integrates a dynamic weighting mechanism into an ensemble framework, enabling automatic adjustment of weights based on the relevance and contribution of each source (representing historical knowledge) and target model (learning from newly acquired data). We demonstrate the effectiveness of MSAW by applying it to detect Respiratory Syncytial Virus cases within Emergency Department visits, utilizing multiple years of electronic health records from the University of Pittsburgh Medical Center. Our method demonstrates performance improvements over many baselines, including refining pre-trained models with online learning as well as three static weighting approaches, showing MSAW's capacity to integrate historical knowledge with progressively accumulated new data. This study indicates the potential of online transfer learning in healthcare, particularly for developing machine learning models that dynamically adapt to evolving situations where new data is incrementally accumulated., Comment: 10 pages, 2 figures

The application of transfer learning, leveraging knowledge from source domains to enhance model performance in a target domain, has significantly grown, supporting diverse real-world applications. Its success often relies on shared knowledge between domains, typically required in these methodologies. Commonly, methods assume identical feature and label spaces in both domains, known as homogeneous transfer learning. However, this is often impractical as source and target domains usually differ in these spaces, making precise data matching challenging and costly. Consequently, heterogeneous transfer learning (HTL), which addresses these disparities, has become a vital strategy in various tasks. In this paper, we offer an extensive review of over 60 HTL methods, covering both data-based and model-based approaches. We describe the key assumptions and algorithms of these methods and systematically categorize them into instance-based, feature representation-based, parameter regularization, and parameter tuning techniques. Additionally, we explore applications in natural language processing, computer vision, multimodal learning, and biomedicine, aiming to deepen understanding and stimulate further research in these areas. Our paper includes recent advancements in HTL, such as the introduction of transformer-based models and multimodal learning techniques, ensuring the review captures the latest developments in the field. We identify key limitations in current HTL studies and offer systematic guidance for future research, highlighting areas needing further exploration and suggesting potential directions for advancing the field., Comment: 23 pages, 7 figures

The coronavirus disease 2019 (COVID-19) has led to a global pandemic of significant severity. In addition to its high level of contagiousness, COVID-19 can have a heterogeneous clinical course, ranging from asymptomatic carriers to severe and potentially life-threatening health complications. Many patients have to revisit the emergency room (ER) within a short time after discharge, which significantly increases the workload for medical staff. Early identification of such patients is crucial for helping physicians focus on treating life-threatening cases. In this study, we obtained Electronic Health Records (EHRs) of 3,210 encounters from 13 affiliated ERs within the University of Pittsburgh Medical Center between March 2020 and January 2021. We leveraged a Natural Language Processing technique, ScispaCy, to extract clinical concepts and used the 1001 most frequent concepts to develop 7-day revisit models for COVID-19 patients in ERs. The research data we collected from 13 ERs may have distributional differences that could affect the model development. To address this issue, we employed a classic deep transfer learning method called the Domain Adversarial Neural Network (DANN) and evaluated different modeling strategies, including the Multi-DANN algorithm, the Single-DANN algorithm, and three baseline methods. Results showed that the Multi-DANN models outperformed the Single-DANN models and baseline models in predicting revisits of COVID-19 patients to the ER within 7 days after discharge. Notably, the Multi-DANN strategy effectively addressed the heterogeneity among multiple source domains and improved the adaptation of source data to the target domain. Moreover, the high performance of Multi-DANN models indicates that EHRs are informative for developing a prediction model to identify COVID-19 patients who are very likely to revisit an ER within 7 days after discharge., Comment: to appear at ICHI 2023

We consider the problem of identifying the provenance of free/open source software (FOSS) and specifically the need of identifying where reused source code has been copied from. We propose a lightweight approach to solve the problem based on software identifiers-such as the names of variables, classes, and functions chosen by programmers. The proposed approach is able to efficiently narrow down to a small set of candidate origin products, to be further analyzed with more expensive techniques to make a final provenance determination.By analyzing the PyPI (Python Packaging Index) open source ecosystem we find that globally defined identifiers are very distinct. Across PyPI's 244 K packages we found 11.2 M different global identifiers (classes and method/function names-with only 0.6% of identifiers shared among the two types of entities); 76% of identifiers were used only in one package, and 93% in at most 3. Randomly selecting 3 non-frequent global identifiers from an input product is enough to narrow down its origins to a maximum of 3 products within 89% of the cases.We validate the proposed approach by mapping Debian source packages implemented in Python to the corresponding PyPI packages; this approach uses at most five trials, where each trial uses three randomly chosen global identifiers from a randomly chosen python file of the subject software package, then ranks results using a popularity index and requires to inspect only the top result. In our experiments, this method is effective at finding the true origin of a project with a recall of 0.9 and precision of 0.77.

Infrared and visible image fusion aims to integrate comprehensive information from multiple sources to achieve superior performances on various practical tasks, such as detection, over that of a single modality. However, most existing methods directly combined the texture details and object contrast of different modalities, ignoring the dynamic changes in reality, which diminishes the visible texture in good lighting conditions and the infrared contrast in low lighting conditions. To fill this gap, we propose a dynamic image fusion framework with a multi-modal gated mixture of local-to-global experts, termed MoE-Fusion, to dynamically extract effective and comprehensive information from the respective modalities. Our model consists of a Mixture of Local Experts (MoLE) and a Mixture of Global Experts (MoGE) guided by a multi-modal gate. The MoLE performs specialized learning of multi-modal local features, prompting the fused images to retain the local information in a sample-adaptive manner, while the MoGE focuses on the global information that complements the fused image with overall texture detail and contrast. Extensive experiments show that our MoE-Fusion outperforms state-of-the-art methods in preserving multi-modal image texture and contrast through the local-to-global dynamic learning paradigm, and also achieves superior performance on detection tasks. Our code will be available: https://github.com/SunYM2020/MoE-Fusion.

We report an AlGaInAs multiple quantum well integrated source of polarization controlled light consisting of a polarization mode converter PMC, differential phase shifter(DPS), and a side wall grating distributed-feedback DFB laser. We demonstrate an asymmetrical stepped-height ridge waveguide PMC to realize TE to TM polarization conversion and a symmetrical straight waveguide DPS to enable polarization rotation from approximately counterclockwise circular polarization to linear polarization. Based on the identical epitaxial layer scheme, all of the PMC, DPS, and DFB laser can be integrated monolithically using only a single step of metalorganic vapor phase epitaxy and two steps of III V material dry etching. For the DFB-PMC device, a high TE to TM polarization conversion efficiency 98% over a wide range of DFB injection currents is reported at 1555 nm wavelength. For the DFB-PMC-DPS device, a 60 degree rotation of the Stokes vector was obtained on the Poincar\'e sphere with a range of bias voltage from 0 V to -4.0 V at IDFB is 170 mA., Comment: arXiv admin note: text overlap with arXiv:2210.10519

Active regression considers a linear regression problem where the learner receives a large number of data points but can only observe a small number of labels. Since online algorithms can deal with incremental training data and take advantage of low computational cost, we consider an online extension of the active regression problem: the learner receives data points one by one and immediately decides whether it should collect the corresponding labels. The goal is to efficiently maintain the regression of received data points with a small budget of label queries. We propose novel algorithms for this problem under $\ell_p$ loss where $p\in[1,2]$. To achieve a $(1+\epsilon)$-approximate solution, our proposed algorithms only require $\tilde{\mathcal{O}}(\epsilon^{-1} d \log(n\kappa))$ queries of labels, where $n$ is the number of data points and $\kappa$ is a quantity, called the condition number, of the data points. The numerical results verify our theoretical results and show that our methods have comparable performance with offline active regression algorithms., Comment: A preliminary version appeared in the Proceedings of the 39th International Conference on Machine Learning (ICML 2022), PMLR 162, pp 3320--3335, 2022. v2: optimal dependence on $\epsilon$ in query complexity

In applications such as natural language processing or computer vision, one is given a large $n \times d$ matrix $A = (a_{i,j})$ and would like to compute a matrix decomposition, e.g., a low rank approximation, of a function $f(A) = (f(a_{i,j}))$ applied entrywise to $A$. A very important special case is the likelihood function $f\left( A \right ) = \log{\left( \left| a_{ij}\right| +1\right)}$. A natural way to do this would be to simply apply $f$ to each entry of $A$, and then compute the matrix decomposition, but this requires storing all of $A$ as well as multiple passes over its entries. Recent work of Liang et al.\ shows how to find a rank-$k$ factorization to $f(A)$ for an $n \times n$ matrix $A$ using only $n \cdot \operatorname{poly}(\epsilon^{-1}k\log n)$ words of memory, with overall error $10\|f(A)-[f(A)]_k\|_F^2 + \operatorname{poly}(\epsilon/k) \|f(A)\|_{1,2}^2$, where $[f(A)]_k$ is the best rank-$k$ approximation to $f(A)$ and $\|f(A)\|_{1,2}^2$ is the square of the sum of Euclidean lengths of rows of $f(A)$. Their algorithm uses three passes over the entries of $A$. The authors pose the open question of obtaining an algorithm with $n \cdot \operatorname{poly}(\epsilon^{-1}k\log n)$ words of memory using only a single pass over the entries of $A$. In this paper we resolve this open question, obtaining the first single-pass algorithm for this problem and for the same class of functions $f$ studied by Liang et al. Moreover, our error is $\|f(A)-[f(A)]_k\|_F^2 + \operatorname{poly}(\epsilon/k) \|f(A)\|_F^2$, where $\|f(A)\|_F^2$ is the sum of squares of Euclidean lengths of rows of $f(A)$. Thus our error is significantly smaller, as it removes the factor of $10$ and also $\|f(A)\|_F^2 \leq \|f(A)\|_{1,2}^2$. We also give an algorithm for regression, pointing out an error in previous work, and empirically validate our results., Comment: Accepted to ICML 2021