Search

Advancements in LLMs have recently unveiled challenges tied to computational efficiency and continual scalability due to their requirements of huge parameters, making the applications and evolution of these models on devices with limited computation resources and scenarios requiring various abilities increasingly cumbersome. Inspired by modularity within the human brain, there is a growing tendency to decompose LLMs into numerous functional modules, allowing for inference with part of modules and dynamic assembly of modules to tackle complex tasks, such as mixture-of-experts. To highlight the inherent efficiency and composability of the modular approach, we coin the term brick to represent each functional module, designating the modularized structure as configurable foundation models. In this paper, we offer a comprehensive overview and investigation of the construction, utilization, and limitation of configurable foundation models. We first formalize modules into emergent bricks - functional neuron partitions that emerge during the pre-training phase, and customized bricks - bricks constructed via additional post-training to improve the capabilities and knowledge of LLMs. Based on diverse functional bricks, we further present four brick-oriented operations: retrieval and routing, merging, updating, and growing. These operations allow for dynamic configuration of LLMs based on instructions to handle complex tasks. To verify our perspective, we conduct an empirical analysis on widely-used LLMs. We find that the FFN layers follow modular patterns with functional specialization of neurons and functional neuron partitions. Finally, we highlight several open issues and directions for future research. Overall, this paper aims to offer a fresh modular perspective on existing LLM research and inspire the future creation of more efficient and scalable foundational models.

Video quality assessment (VQA) is a crucial task in the development of video compression standards, as it directly impacts the viewer experience. This paper presents the results of the Compressed Video Quality Assessment challenge, held in conjunction with the Advances in Image Manipulation (AIM) workshop at ECCV 2024. The challenge aimed to evaluate the performance of VQA methods on a diverse dataset of 459 videos, encoded with 14 codecs of various compression standards (AVC/H.264, HEVC/H.265, AV1, and VVC/H.266) and containing a comprehensive collection of compression artifacts. To measure the methods performance, we employed traditional correlation coefficients between their predictions and subjective scores, which were collected via large-scale crowdsourced pairwise human comparisons. For training purposes, participants were provided with the Compressed Video Quality Assessment Dataset (CVQAD), a previously developed dataset of 1022 videos. Up to 30 participating teams registered for the challenge, while we report the results of 6 teams, which submitted valid final solutions and code for reproducing the results. Moreover, we calculated and present the performance of state-of-the-art VQA methods on the developed dataset, providing a comprehensive benchmark for future research. The dataset, results, and online leaderboard are publicly available at https://challenges.videoprocessing.ai/challenges/compressedvideo-quality-assessment.html.

The interplay of symmetry and topology in crystal solids has given rise to various elementary excitations as quasiparticles. Among these, those with significant Berry-phase-related transport responses are of particular interest. Here, we predict a new type of quasiparticle called topological charge quadruple (TCQ), which is analogous to a charge quadrupole but consists of two closely-packed pairs of Weyl points in momentum space, specifically in a half-Heusler antiferromagnet NdBiPt. Interestingly, the TCQ is protected by the spin-orbit $U(1)$ quasi-symmetry, rather than any exact crystallographic symmetries. This quasi-symmetry restricts the energy splitting induced by symmetry-lowering perturbations to a second-order effect. Furthermore, the closely located Berry curvature sources and sinks in the TCQ lead to a large Berry curvature dipole, resulting in a significant nonlinear Hall effect. Our work opens an avenue for designing novel quasiparticles using quasi-symmetries and developing materials with enhanced nonlinear responses., Comment: 4 figures

The recent surge of Multimodal Large Language Models (MLLMs) has fundamentally reshaped the landscape of AI research and industry, shedding light on a promising path toward the next AI milestone. However, significant challenges remain preventing MLLMs from being practical in real-world applications. The most notable challenge comes from the huge cost of running an MLLM with a massive number of parameters and extensive computation. As a result, most MLLMs need to be deployed on high-performing cloud servers, which greatly limits their application scopes such as mobile, offline, energy-sensitive, and privacy-protective scenarios. In this work, we present MiniCPM-V, a series of efficient MLLMs deployable on end-side devices. By integrating the latest MLLM techniques in architecture, pretraining and alignment, the latest MiniCPM-Llama3-V 2.5 has several notable features: (1) Strong performance, outperforming GPT-4V-1106, Gemini Pro and Claude 3 on OpenCompass, a comprehensive evaluation over 11 popular benchmarks, (2) strong OCR capability and 1.8M pixel high-resolution image perception at any aspect ratio, (3) trustworthy behavior with low hallucination rates, (4) multilingual support for 30+ languages, and (5) efficient deployment on mobile phones. More importantly, MiniCPM-V can be viewed as a representative example of a promising trend: The model sizes for achieving usable (e.g., GPT-4V) level performance are rapidly decreasing, along with the fast growth of end-side computation capacity. This jointly shows that GPT-4V level MLLMs deployed on end devices are becoming increasingly possible, unlocking a wider spectrum of real-world AI applications in the near future., Comment: preprint

Artificial intelligence (AI) technology has demonstrated remarkable potential in drug dis-covery, where pharmacokinetics plays a crucial role in determining the dosage, safety, and efficacy of new drugs. A major challenge for AI-driven drug discovery (AIDD) is the scarcity of high-quality data, which often requires extensive wet-lab work. A typical example of this is pharmacokinetic experiments. In this work, we develop a physical formula enhanced mul-ti-task learning (PEMAL) method that predicts four key parameters of pharmacokinetics simultaneously. By incorporating physical formulas into the multi-task framework, PEMAL facilitates effective knowledge sharing and target alignment among the pharmacokinetic parameters, thereby enhancing the accuracy of prediction. Our experiments reveal that PEMAL significantly lowers the data demand, compared to typical Graph Neural Networks. Moreover, we demonstrate that PEMAL enhances the robustness to noise, an advantage that conventional Neural Networks do not possess. Another advantage of PEMAL is its high flexibility, which can be potentially applied to other multi-task machine learning scenarios. Overall, our work illustrates the benefits and potential of using PEMAL in AIDD and other scenarios with data scarcity and noise.

The goal of No-Reference Image Quality Assessment (NR-IQA) is to predict the perceptual quality of an image in line with its subjective evaluation. To put the NR-IQA models into practice, it is essential to study their potential loopholes for model refinement. This paper makes the first attempt to explore the black-box adversarial attacks on NR-IQA models. Specifically, we first formulate the attack problem as maximizing the deviation between the estimated quality scores of original and perturbed images, while restricting the perturbed image distortions for visual quality preservation. Under such formulation, we then design a Bi-directional loss function to mislead the estimated quality scores of adversarial examples towards an opposite direction with maximum deviation. On this basis, we finally develop an efficient and effective black-box attack method against NR-IQA models. Extensive experiments reveal that all the evaluated NR-IQA models are vulnerable to the proposed attack method. And the generated perturbations are not transferable, enabling them to serve the investigation of specialities of disparate IQA models.

In this paper, we first investigate the global existence of a solution for the stochastic fractional nonlinear Schr\"odinger equation with radially symmetric initial data in a suitable energy space $H^{\alpha}$. We then show that the stochastic fractional nonlinear Schr\"odinger equation in the Stratonovich sense forms an infinite-dimensional stochastic Hamiltonian system, with its phase flow preserving symplecticity. Finally, we develop a stochastic midpoint scheme for the stochastic fractional nonlinear Schr\"odinger equation from the perspective of symplectic geometry. It is proved that the stochastic midpoint scheme satisfies the corresponding symplectic law in the discrete sense. A numerical example is conducted to validate the efficiency of the theory.

To promote speech processing and recognition research in driving scenarios, we build on the success of the Intelligent Cockpit Speech Recognition Challenge (ICSRC) held at ISCSLP 2022 and launch the ICASSP 2024 In-Car Multi-Channel Automatic Speech Recognition (ICMC-ASR) Challenge. This challenge collects over 100 hours of multi-channel speech data recorded inside a new energy vehicle and 40 hours of noise for data augmentation. Two tracks, including automatic speech recognition (ASR) and automatic speech diarization and recognition (ASDR) are set up, using character error rate (CER) and concatenated minimum permutation character error rate (cpCER) as evaluation metrics, respectively. Overall, the ICMC-ASR Challenge attracts 98 participating teams and receives 53 valid results in both tracks. In the end, first-place team USTCiflytek achieves a CER of 13.16% in the ASR track and a cpCER of 21.48% in the ASDR track, showing an absolute improvement of 13.08% and 51.4% compared to our challenge baseline, respectively., Comment: Accepted at ICASSP 2024

This study presents a novel approach to addressing the challenge of missing data in multivariate time series, with a particular focus on the complexities of healthcare data. Our Conditional Self-Attention Imputation (CSAI) model, grounded in a transformer-based framework, introduces a conditional hidden state initialization tailored to the intricacies of medical time series data. This methodology diverges from traditional imputation techniques by specifically targeting the imbalance in missing data distribution, a crucial aspect often overlooked in healthcare datasets. By integrating advanced knowledge embedding and a non-uniform masking strategy, CSAI adeptly adjusts to the distinct patterns of missing data in Electronic Health Records (EHRs).

Open-vocabulary keyword spotting (KWS), which allows users to customize keywords, has attracted increasingly more interest. However, existing methods based on acoustic models and post-processing train the acoustic model with ASR training criteria to model all phonemes, making the acoustic model under-optimized for the KWS task. To solve this problem, we propose a novel unified two-pass open-vocabulary KWS (U2-KWS) framework inspired by the two-pass ASR model U2. Specifically, we employ the CTC branch as the first stage model to detect potential keyword candidates and the decoder branch as the second stage model to validate candidates. In order to enhance any customized keywords, we redesign the U2 training procedure for U2-KWS and add keyword information by audio and text cross-attention into both branches. We perform experiments on our internal dataset and Aishell-1. The results show that U2-KWS can achieve a significant relative wake-up rate improvement of 41% compared to the traditional customized KWS systems when the false alarm rate is fixed to 0.5 times per hour., Comment: Accepted by ASRU2023

In solid state systems, group representation theory is powerful in characterizing the behavior of quasiparticles, notably the energy degeneracy. While conventional group theory is effective in answering yes-or-no questions related to symmetry breaking, its application to determining the magnitude of energy splitting resulting from symmetry lowering is limited. Here, we propose a theory on quasisymmetry and near degeneracy, thereby expanding the applicability of group theory to address questions regarding large-or-small energy splitting. Defined within the degenerate subspace of an unperturbed Hamiltonian, quasisymmetries form an enlarged symmetry group eliminating the first-order splitting. This framework ensures that the magnitude of splitting arises as a second-order effect of symmetry-lowering perturbations, such as external fields and spin-orbit coupling. We systematically tabulate the quasisymmetry groups within 32 crystallographic point groups and find all the possible unitary quasisymmetry group structures regarding double degeneracy. Applying our theory to the realistic material AgLa, we predict a "quasi-Dirac semimetal" phase characterized by two tiny-gap band anticrossings., Comment: 7 pages, 3 figures

The development of large language models (LLMs) has greatly advanced the field of multimodal understanding, leading to the emergence of large multimodal models (LMMs). In order to enhance the level of visual comprehension, recent studies have equipped LMMs with region-level understanding capabilities by representing object bounding box coordinates as a series of text sequences (pix2seq). In this paper, we introduce a novel paradigm for object location modeling called pix2emb method, where we ask the LMM to output the location embeddings and then decode them with different decoders. This paradigm allows us to use different location formats (such as bounding boxes and masks) in multimodal conversations. Leveraging the proposed pix2emb method, we train an LMM named NExT-Chat and demonstrate its capability of handling multiple tasks like visual grounding, region captioning, and grounded reasoning. Comprehensive experiments show the effectiveness of our NExT-Chat on various tasks, e.g., NExT-Chat (87.7) vs. Shikra (86.9) on POPE-Random, NExT-Chat (68.9) vs. LISA (67.9) on referring expression segmentation task, and NExT-Chat (79.6) vs. Kosmos-2 (62.3) on region caption task. The code and model are released at https://github.com/NExT-ChatV/NExT-Chat., Comment: Technical Report (https://next-chatv.github.io/)

The attention-based deep contextual biasing method has been demonstrated to effectively improve the recognition performance of end-to-end automatic speech recognition (ASR) systems on given contextual phrases. However, unlike shallow fusion methods that directly bias the posterior of the ASR model, deep biasing methods implicitly integrate contextual information, making it challenging to control the degree of bias. In this study, we introduce a spike-triggered deep biasing method that simultaneously supports both explicit and implicit bias. Moreover, both bias approaches exhibit significant improvements and can be cascaded with shallow fusion methods for better results. Furthermore, we propose a context sampling enhancement strategy and improve the contextual phrase filtering algorithm. Experiments on the public WenetSpeech Mandarin biased-word dataset show a 32.0% relative CER reduction compared to the baseline model, with an impressively 68.6% relative CER reduction on contextual phrases., Comment: Accepted by ASRU2023

No-Reference Video Quality Assessment (NR-VQA) plays an essential role in improving the viewing experience of end-users. Driven by deep learning, recent NR-VQA models based on Convolutional Neural Networks (CNNs) and Transformers have achieved outstanding performance. To build a reliable and practical assessment system, it is of great necessity to evaluate their robustness. However, such issue has received little attention in the academic community. In this paper, we make the first attempt to evaluate the robustness of NR-VQA models against adversarial attacks, and propose a patch-based random search method for black-box attack. Specifically, considering both the attack effect on quality score and the visual quality of adversarial video, the attack problem is formulated as misleading the estimated quality score under the constraint of just-noticeable difference (JND). Built upon such formulation, a novel loss function called Score-Reversed Boundary Loss is designed to push the adversarial video's estimated quality score far away from its ground-truth score towards a specific boundary, and the JND constraint is modeled as a strict $L_2$ and $L_\infty$ norm restriction. By this means, both white-box and black-box attacks can be launched in an effective and imperceptible manner. The source code is available at https://github.com/GZHU-DVL/AttackVQA.

We establish the stochastic Strichartz estimate for the fractional Schr\"odinger equation with multiplicative noise. With the help of the deterministic Strichartz estimates, we prove the existence and uniqueness of a global solution to the stochastic fractional nonlinear Schr\"odinger equation in $L^2(\mathbb{R}^n)$. In addition, we also prove a general blow up result by deriving a localized virial estimate and the generalized Strauss inequality with a restricted class of initial data.

Those fundamental physical properties, such as phase transitions, Weyl fermions, and spin excitation, in all magnetic ordered materials, were ultimately believed to rely on the symmetry theory of magnetic space groups. Recently, it has come to light that a more comprehensive group, known as the spin space group (SSG), which combines separate spin and spatial operations, is necessary to fully characterize the geometry and underlying properties of magnetic ordered materials. However, the basic theory of SSG has seldom been developed. In this work, we present a systematic study of the enumeration and the representation theory of SSG. Starting from the 230 crystallographic space groups and finite translation groups with a maximum order of 8, we establish an extensive collection of over 100000 SSGs under a four-index nomenclature as well as the International notation. We then identify inequivalent SSGs specifically applicable to collinear, coplanar, and noncoplanar magnetic configurations. To facilitate the identification of SSG, we develop an online program (findspingroup.com) that can determine the SSG symmetries of any magnetic ordered crystals. Moreover, we derive the irreducible co-representations of the little group in momentum space within the SSG framework. Finally, we illustrate the SSG symmetries and physical effects beyond the framework of magnetic space groups through several representative material examples, including a well-known altermagnet RuO2, spiral spin polarization in the coplanar antiferromagnet CeAuAl3, and geometric Hall effect in the noncoplanar antiferromagnet CoNb3S6. Our work advances the field of group theory in describing magnetic ordered materials, opening up avenues for deeper comprehension and further exploration of emergent phenomena in magnetic materials., Comment: To appear in Phys. Rev. X. 158 pages, including the main text (41 pages including 3 tables and 7 figures) and appendix. There is another Supplementary table with the full list of spin space groups at https://liuqh.phy.sustech.edu.cn/wp-content/uploads/92-supp.pdf

By incorporating additional contextual information, deep biasing methods have emerged as a promising solution for speech recognition of personalized words. However, for real-world voice assistants, always biasing on such personalized words with high prediction scores can significantly degrade the performance of recognizing common words. To address this issue, we propose an adaptive contextual biasing method based on Context-Aware Transformer Transducer (CATT) that utilizes the biased encoder and predictor embeddings to perform streaming prediction of contextual phrase occurrences. Such prediction is then used to dynamically switch the bias list on and off, enabling the model to adapt to both personalized and common scenarios. Experiments on Librispeech and internal voice assistant datasets show that our approach can achieve up to 6.7% and 20.7% relative reduction in WER and CER compared to the baseline respectively, mitigating up to 96.7% and 84.9% of the relative WER and CER increase for common cases. Furthermore, our approach has a minimal performance impact in personalized scenarios while maintaining a streaming inference pipeline with negligible RTF increase.

Contextual information plays a crucial role in speech recognition technologies and incorporating it into the end-to-end speech recognition models has drawn immense interest recently. However, previous deep bias methods lacked explicit supervision for bias tasks. In this study, we introduce a contextual phrase prediction network for an attention-based deep bias method. This network predicts context phrases in utterances using contextual embeddings and calculates bias loss to assist in the training of the contextualized model. Our method achieved a significant word error rate (WER) reduction across various end-to-end speech recognition models. Experiments on the LibriSpeech corpus show that our proposed model obtains a 12.1% relative WER improvement over the baseline model, and the WER of the context phrases decreases relatively by 40.5%. Moreover, by applying a context phrase filtering strategy, we also effectively eliminate the WER degradation when using a larger biasing list., Comment: Accepted by interspeech2023

While developing a new multimodal LLM (MLLM) by pre-training on tremendous image-text pairs from scratch can be exceedingly resource-consuming, connecting an existing LLM with a comparatively lightweight visual prompt generator (VPG) becomes a feasible paradigm. However, further tuning the VPG part of the MLLM still suffers from indispensable computational costs, i.e., requiring thousands of GPU hours and millions of training data. One alternative solution is to transfer an existing VPG from any existing MLLMs for the target MLLM. In this work, we for the first time investigate the VPG transferability across LLMs, and explore a solution to reduce the cost of VPG transfer. We first study the VPG transfer across different LLM sizes (e.g., small-to-large), and across different LLM types, through which we diagnose the key factors to maximize the transfer efficiency. Based on our observation, we design a two-stage transfer framework named VPGTrans, which is simple yet highly effective. Through extensive experiments, we demonstrate that VPGTrans helps significantly speed up the transfer learning process without compromising performance. Remarkably, it helps achieve the VPG transfer from BLIP-2 OPT$_\text{2.7B}$ to BLIP-2 OPT$_\text{6.7B}$ with over 10 times speed-up and 10.7% training data compared with connecting a VPG to OPT$_\text{6.7B}$ from scratch. Further, a series of intriguing findings and potential rationales behind them are provided and discussed. Finally, we showcase the practical value of our VPGTrans approach, by customizing two novel MLLMs, including VL-LLaMA and VL-Vicuna, with recently released LLaMA and Vicuna LLMs., Comment: Project Website: https://vpgtrans.github.io Code: https://github.com/VPGTrans/VPGTrans NeurIPS 2023

This paper describes our NPU-ASLP system for the Audio-Visual Diarization and Recognition (AVDR) task in the Multi-modal Information based Speech Processing (MISP) 2022 Challenge. Specifically, the weighted prediction error (WPE) and guided source separation (GSS) techniques are used to reduce reverberation and generate clean signals for each single speaker first. Then, we explore the effectiveness of Branchformer and E-Branchformer based ASR systems. To better make use of the visual modality, a cross-attention based multi-modal fusion module is proposed, which explicitly learns the contextual relationship between different modalities. Experiments show that our system achieves a concatenated minimum-permutation character error rate (cpCER) of 28.13\% and 31.21\% on the Dev and Eval set, and obtains second place in the challenge., Comment: 2 pages, accepted by ICASSP 2023

The performance of the keyword spotting (KWS) system based on audio modality, commonly measured in false alarms and false rejects, degrades significantly under the far field and noisy conditions. Therefore, audio-visual keyword spotting, which leverages complementary relationships over multiple modalities, has recently gained much attention. However, current studies mainly focus on combining the exclusively learned representations of different modalities, instead of exploring the modal relationships during each respective modeling. In this paper, we propose a novel visual modality enhanced end-to-end KWS framework (VE-KWS), which fuses audio and visual modalities from two aspects. The first one is utilizing the speaker location information obtained from the lip region in videos to assist the training of multi-channel audio beamformer. By involving the beamformer as an audio enhancement module, the acoustic distortions, caused by the far field or noisy environments, could be significantly suppressed. The other one is conducting cross-attention between different modalities to capture the inter-modal relationships and help the representation learning of each modality. Experiments on the MSIP challenge corpus show that our proposed model achieves 2.79% false rejection rate and 2.95% false alarm rate on the Eval set, resulting in a new SOTA performance compared with the top-ranking systems in the ICASSP2022 MISP challenge., Comment: 5 pages. Accepted at ICASSP2023

In a Dirac semimetal, the massless Dirac fermion has zero chirality, leading to surface states connected adiabatically to a topologically trivial surface state as well as vanishing anomalous Hall effect (AHE). Recently, it is predicted that in the nonrelativistic limit of certain collinear antiferromagnets, there exists a type of chiral Dirac-like fermion, whose dispersion manifests four-fold degenerate crossing points formed by spin-degenerate linear bands, with topologically protected Fermi arcs. Such unconventional chiral fermion, protected by a hidden SU(2) symmetry in the hierarchy of an enhanced crystallographic group, namely spin space group, is not experimentally verified yet. Here, by angle-resolved photoemission spectroscopy measurements, we reveal the surface origin of the electron pocket at the Fermi surface in collinear antiferromagnet CoNb3S6. Combining with neutron diffraction and first-principles calculations, we suggest a multidomain collinear AFM configuration, rendering the the existence of the Fermi-arc surface states induced by chiral Dirac-like fermions. Our work provides spectral evidence of the chiral Dirac-like fermion caused by particular spin symmetry in CoNb3S6, paving an avenue for exploring new emergent phenomena in antiferromagnets with unconventional quasiparticle excitations., Comment: 19 pages, 4 figures

Large-scale commonsense knowledge bases empower a broad range of AI applications, where the automatic extraction of commonsense knowledge (CKE) is a fundamental and challenging problem. CKE from text is known for suffering from the inherent sparsity and reporting bias of commonsense in text. Visual perception, on the other hand, contains rich commonsense knowledge about real-world entities, e.g., (person, can_hold, bottle), which can serve as promising sources for acquiring grounded commonsense knowledge. In this work, we present CLEVER, which formulates CKE as a distantly supervised multi-instance learning problem, where models learn to summarize commonsense relations from a bag of images about an entity pair without any human annotation on image instances. To address the problem, CLEVER leverages vision-language pre-training models for deep understanding of each image in the bag, and selects informative instances from the bag to summarize commonsense entity relations via a novel contrastive attention mechanism. Comprehensive experimental results in held-out and human evaluation show that CLEVER can extract commonsense knowledge in promising quality, outperforming pre-trained language model-based methods by 3.9 AUC and 6.4 mAUC points. The predicted commonsense scores show strong correlation with human judgment with a 0.78 Spearman coefficient. Moreover, the extracted commonsense can also be grounded into images with reasonable interpretability. The data and codes can be obtained at https://github.com/thunlp/CLEVER., Comment: Accepted by AAAI 2023

This paper summarizes the outcomes from the ISCSLP 2022 Intelligent Cockpit Speech Recognition Challenge (ICSRC). We first address the necessity of the challenge and then introduce the associated dataset collected from a new-energy vehicle (NEV) covering a variety of cockpit acoustic conditions and linguistic contents. We then describe the track arrangement and the baseline system. Specifically, we set up two tracks in terms of allowed model/system size to investigate resource-constrained and -unconstrained setups, targeting to vehicle embedded as well as cloud ASR systems respectively. Finally we summarize the challenge results and provide the major observations from the submitted systems., Comment: Accepted by ISCSLP2022