Large Language Models (LLMs) have achieved remarkable success in natural language tasks, yet understanding their reasoning processes remains a significant challenge. We address this by introducing XplainLLM, a dataset accompanying an explanation framework designed to enhance LLM transparency and reliability. Our dataset comprises 24,204 instances where each instance interprets the LLM's reasoning behavior using knowledge graphs (KGs) and graph attention networks (GAT), and includes explanations of LLMs such as the decoder-only Llama-3 and the encoder-only RoBERTa. XplainLLM also features a framework for generating grounded explanations and the debugger-scores for multidimensional quality analysis. Our explanations include why-choose and why-not-choose components, reason-elements, and debugger-scores that collectively illuminate the LLM's reasoning behavior. Our evaluations demonstrate XplainLLM's potential to reduce hallucinations and improve grounded explanation generation in LLMs. XplainLLM is a resource for researchers and practitioners to build trust and verify the reliability of LLM outputs.
In low-bitrate speech coding, end-to-end speech coding networks aim to learn compact yet expressive features and a powerful decoder in a single network. A challenging problem as such results in unwelcome complexity increase and inferior speech quality. In this paper, we propose to separate the representation learning and information reconstruction tasks. We leverage an end-to-end codec for learning low-dimensional discrete tokens and employ a latent diffusion model to de-quantize coded features into a high-dimensional continuous space, relieving the decoder's burden of de-quantizing and upsampling. To mitigate the issue of over-smooth generation, we introduce midway-infilling with less noise reduction and stronger conditioning. In ablation studies, we investigate the hyperparameters for midway-infilling and latent diffusion space with different dimensions. Subjective listening tests show that our model outperforms the state-of-the-art at two low bitrates, 1.5 and 3 kbps. Codes and samples of this work are available on our webpage.
Grammatical error correction (GEC) is an important NLP task that is currently usually solved with autoregressive sequence-to-sequence models. However, approaches of this class are inherently slow due to one-by-one token generation, so non-autoregressive alternatives are needed. In this work, we propose a novel non-autoregressive approach to GEC that decouples the architecture into a permutation network that outputs a self-attention weight matrix that can be used in beam search to find the best permutation of input tokens (with auxiliary {ins} tokens) and a decoder network based on a step-unrolled denoising autoencoder that fills in specific tokens. This allows us to find the token permutation after only one forward pass of the permutation network, avoiding autoregressive constructions. We show that the resulting network improves over previously known non-autoregressive methods for GEC and reaches the level of autoregressive methods that do not use language-specific synthetic data generation methods. Our results are supported by a comprehensive experimental validation on the ConLL-2014 and Write&Improve+LOCNESS datasets and an extensive ablation study that supports our architectural and algorithmic choices.
In this paper, we propose a novel joint source-channel coding (JSCC) approach for channel-adaptive digital semantic communications. In semantic communication systems with digital modulation and demodulation, robust design of JSCC encoder and decoder becomes challenging not only due to the unpredictable dynamics of channel conditions but also due to diverse modulation orders. To address this challenge, we first develop a new demodulation method which assesses the uncertainty of the demodulation output to improve the robustness of the digital semantic communication system. We then devise a robust training strategy which enhances the robustness and flexibility of the JSCC encoder and decoder against diverse channel conditions and modulation orders. To this end, we model the relationship between the encoder's output and decoder's input using binary symmetric erasure channels and then sample the parameters of these channels from diverse distributions. We also develop a channel-adaptive modulation technique for an inference phase, in order to reduce the communication latency while maintaining task performance. In this technique, we adaptively determine modulation orders for the latent variables based on channel conditions. Using simulations, we demonstrate the superior performance of the proposed JSCC approach for image classification, reconstruction, and retrieval tasks compared to existing JSCC approaches.
An exciting advancement in the field of multilingual models is the emergence of autoregressive models with zero- and few-shot capabilities, a phenomenon widely reported in large-scale language models. To further improve model adaptation to cross-lingual tasks, another trend is to further fine-tune the language models with either full fine-tuning or parameter-efficient tuning. However, the interaction between parameter-efficient fine-tuning (PEFT) and cross-lingual tasks in multilingual autoregressive models has yet to be studied. Specifically, we lack an understanding of the role of linguistic distributions in multilingual models in the effectiveness of token-based prompt tuning. To address this question, we conduct experiments comparing prompt tuning and fine-tuning on the decoder-based multilingual model, XGLM, with four cross-lingual tasks (XNLI, PAWS-X, POS, NER). According to our study, prompt tuning achieves on par or better performance over fine-tuning across all languages while updating at most 0.13\% of the model parameters. Moreover, we empirically show that prompt tuning is more effective in enhancing the performance of low-resource languages than fine-tuning. Our further analysis shows that the phenomenon is related to the tokenization scheme of the multilingual model.
Inspection of high-voltage power equipment is an effective way to ensure power supply reliability. Object recognition, one of the key technologies in automatic power equipment inspection, attracts attention of many researchers and engineers. Although quite a few existing models have some their own advantages, object relationship between equipment which is very important in this task is scarcely considered. This paper combining object relationship modeling and Transformer Model proposes a Relation Transformer Model. It has four parts -- backbone, encoder, decoder and prediction heads. With this structure, the proposed method shows in experiments a much better performance than other three commonly used models in object recognition in substation, largely promoting the development of automatic power equipment inspection.
Retinal vascular segmentation, a widely researched topic in biomedical image processing, aims to reduce the workload of ophthalmologists in treating and detecting retinal disorders. Segmenting retinal vessels presents unique challenges; previous techniques often failed to effectively segment branches and microvascular structures. Recent neural network approaches struggle to balance local and global properties and frequently miss tiny end vessels, hindering the achievement of desired results. To address these issues in retinal vessel segmentation, we propose a comprehensive micro-vessel extraction mechanism based on an encoder-decoder neural network architecture. This network includes residual, encoder booster, bottleneck enhancement, squeeze, and excitation building blocks. These components synergistically enhance feature extraction and improve the prediction accuracy of the segmentation map. Our solution has been evaluated using the DRIVE, CHASE-DB1, and STARE datasets, yielding competitive results compared to previous studies. The AUC and accuracy on the DRIVE dataset are 0.9884 and 0.9702, respectively. For the CHASE-DB1 dataset, these scores are 0.9903 and 0.9755, respectively, and for the STARE dataset, they are 0.9916 and 0.9750. Given its accurate and robust performance, the proposed approach is a solid candidate for being implemented in real-life diagnostic centers and aiding ophthalmologists.
Heterogeneous Information Networks (HINs), which consist of various types of nodes and edges, have recently demonstrated excellent performance in graph mining. However, most existing heterogeneous graph neural networks (HGNNs) ignore the problems of missing attributes, inaccurate attributes and scarce labels for nodes, which limits their expressiveness. In this paper, we propose a generative self-supervised model GraMI to address these issues simultaneously. Specifically, GraMI first initializes all the nodes in the graph with a low-dimensional representation matrix. After that, based on the variational graph autoencoder framework, GraMI learns both node-level and attribute-level embeddings in the encoder, which can provide fine-grained semantic information to construct node attributes. In the decoder, GraMI reconstructs both links and attributes. Instead of directly reconstructing raw features for attributed nodes, GraMI generates the initial low-dimensional representation matrix for all the nodes, based on which raw features of attributed nodes are further reconstructed to leverage accurate attributes. In this way, GraMI can not only complete informative features for non-attributed nodes, but rectify inaccurate ones for attributed nodes. Finally, we conduct extensive experiments to show the superiority of GraMI in tackling HINs with missing and inaccurate attributes.
Recently, instruction-following audio-language models have received broad attention for audio interaction with humans. However, the absence of pre-trained audio models capable of handling diverse audio types and tasks has hindered progress in this field. Consequently, most existing works have only been able to support a limited range of interaction capabilities. In this paper, we develop the Qwen-Audio model and address this limitation by scaling up audio-language pre-training to cover over 30 tasks and various audio types, such as human speech, natural sounds, music, and songs, to facilitate universal audio understanding abilities. However, directly co-training all tasks and datasets can lead to interference issues, as the textual labels associated with different datasets exhibit considerable variations due to differences in task focus, language, granularity of annotation, and text structure. To overcome the one-to-many interference, we carefully design a multi-task training framework by conditioning on a sequence of hierarchical tags to the decoder for encouraging knowledge sharing and avoiding interference through shared and specified tags respectively. Remarkably, Qwen-Audio achieves impressive performance across diverse benchmark tasks without requiring any task-specific fine-tuning, surpassing its counterparts. Building upon the capabilities of Qwen-Audio, we further develop Qwen-Audio-Chat, which allows for input from various audios and text inputs, enabling multi-turn dialogues and supporting various audio-central scenarios.
We propose a novel method for generating abstract art. First an autoencoder is trained to encode and decode the style representations of images, which are extracted from source images with a pretrained VGG network. Then, the decoder component of the autoencoder is extracted and used as a generator in a GAN. The generator works with an ensemble of discriminators. Each discriminator takes different style representations of the same images, and the generator is trained to create images that create convincing style representations in order to deceive all of the generators. The generator is also trained to maximize a diversity term. The resulting images had a surreal, geometric quality. We call our approach ARTEMIS (ARTistic Encoder- Multi- Discriminators Including Self-Attention), as it uses the self-attention layers and an encoder-decoder architecture.
Although chain-of-thought (CoT) prompting combined with language models has achieved encouraging results on complex reasoning tasks, the naive greedy decoding used in CoT prompting usually causes the repetitiveness and local optimality. To address this shortcoming, ensemble-optimization tries to obtain multiple reasoning paths to get the final answer assembly. However, current ensemble-optimization methods either simply employ rule-based post-processing such as \textit{self-consistency}, or train an additional model based on several task-related human annotations to select the best one among multiple reasoning paths, yet fail to generalize to realistic settings where the type of input questions is unknown or the answer format of reasoning paths is unknown. To avoid their limitations, we propose \textbf{Self-Agreement}, a generalizable ensemble-optimization method applying in almost all scenarios where the type of input questions and the answer format of reasoning paths may be known or unknown. Self-agreement firstly samples from language model's decoder to generate a \textit{diverse} set of reasoning paths, and subsequently prompts the language model \textit{one more time} to determine the optimal answer by selecting the most \textit{agreed} answer among the sampled reasoning paths. Self-agreement simultaneously achieves remarkable performance on six public reasoning benchmarks and superior generalization capabilities.
Optical flow estimation is very challenging in situations with transparent or occluded objects. In this work, we address these challenges at the task level by introducing Amodal Optical Flow, which integrates optical flow with amodal perception. Instead of only representing the visible regions, we define amodal optical flow as a multi-layered pixel-level motion field that encompasses both visible and occluded regions of the scene. To facilitate research on this new task, we extend the AmodalSynthDrive dataset to include pixel-level labels for amodal optical flow estimation. We present several strong baselines, along with the Amodal Flow Quality metric to quantify the performance in an interpretable manner. Furthermore, we propose the novel AmodalFlowNet as an initial step toward addressing this task. AmodalFlowNet consists of a transformer-based cost-volume encoder paired with a recurrent transformer decoder which facilitates recurrent hierarchical feature propagation and amodal semantic grounding. We demonstrate the tractability of amodal optical flow in extensive experiments and show its utility for downstream tasks such as panoptic tracking. We make the dataset, code, and trained models publicly available at http://amodal-flow.cs.uni-freiburg.de.
Semantic communication (SemCom) is an emerging technology that extracts useful meaning from data and sends only relevant semantic information. Thus, it has the great potential to improve the spectrum efficiency of conventional wireless systems with bit transmissions, especially in low signal-to-noise ratio (SNR) and small bandwidth regions. However, the existing works have mostly overlooked the constraints of mobile devices, which may not have sufficient capabilities to implement resource-demanding semantic encoder/decoder based on deep learning. To address this issue, we propose in this paper a new semantic relay (SemRelay), which is equipped with a semantic receiver to assist multiuser text transmissions. Specifically, the SemRelay decodes semantic information from a base station and forwards it to the users using conventional bit transmission, hence effectively improving text transmission efficiency. To study the multiuser resource allocation, we formulate an optimization problem to maximize the multiuser weighted sum-rate by jointly designing the SemRelay transmit power allocation and system bandwidth allocation. Although this problem is non-convex and hence challenging to solve, we propose an efficient algorithm to obtain its high-quality suboptimal solution by using the block coordinate descent method. Last, numerical results show the effectiveness of the proposed algorithm as well as superior performance of the proposed SemRelay over the conventional decode-and-forward (DF) relay, especially in small bandwidth region.
We present an integrated prediction-optimization (PredOpt) framework to efficiently solve sequential decision-making problems by predicting the values of binary decision variables in an optimal solution. We address the key issues of sequential dependence, infeasibility, and generalization in machine learning (ML) to make predictions for optimal solutions to combinatorial problems. The sequential nature of the combinatorial optimization problems considered is captured with recurrent neural networks and a sliding-attention window. We integrate an attention-based encoder-decoder neural network architecture with an infeasibility-elimination and generalization framework to learn high-quality feasible solutions to time-dependent optimization problems. In this framework, the required level of predictions is optimized to eliminate the infeasibility of the ML predictions. These predictions are then fixed in mixed-integer programming (MIP) problems to solve them quickly with the aid of a commercial solver. We demonstrate our approach to tackling the two well-known dynamic NP-Hard optimization problems: multi-item capacitated lot-sizing (MCLSP) and multi-dimensional knapsack (MSMK). Our results show that models trained on shorter and smaller-dimensional instances can be successfully used to predict longer and larger-dimensional problems. The solution time can be reduced by three orders of magnitude with an average optimality gap below 0.1%. We compare PredOpt with various specially designed heuristics and show that our framework outperforms them. PredOpt can be advantageous for solving dynamic MIP problems that need to be solved instantly and repetitively.
Automatic video description requires the generation of natural language statements about the actions, events, and objects in the video. An important human trait, when we describe a video, is that we are able to do this with variable levels of detail. Different from this, existing approaches for automatic video descriptions are mostly focused on single sentence generation at a fixed level of detail. Instead, here we address video description of manipulation actions where different levels of detail are required for being able to convey information about the hierarchical structure of these actions relevant also for modern approaches of robot learning. We propose one hybrid statistical and one end-to-end framework to address this problem. The hybrid method needs much less data for training, because it models statistically uncertainties within the video clips, while in the end-to-end method, which is more data-heavy, we are directly connecting the visual encoder to the language decoder without any intermediate (statistical) processing step. Both frameworks use LSTM stacks to allow for different levels of description granularity and videos can be described by simple single-sentences or complex multiple-sentence descriptions. In addition, quantitative results demonstrate that these methods produce more realistic descriptions than other competing approaches.
Deep learning for histopathology has been successfully used for disease classification, image segmentation and more. However, combining image and text modalities using current state-of-the-art methods has been a challenge due to the high resolution of histopathology images. Automatic report generation for histopathology images is one such challenge. In this work, we show that using an existing pre-trained Vision Transformer in a two-step process of first using it to encode 4096x4096 sized patches of the Whole Slide Image (WSI) and then using it as the encoder and an LSTM decoder for report generation, we can build a fairly performant and portable report generation mechanism that takes into account the whole of the high resolution image, instead of just the patches. We are also able to use representations from an existing powerful pre-trained hierarchical vision transformer and show its usefulness in not just zero shot classification but also for report generation.
Islamophobic language on online platforms fosters intolerance, making detection and elimination crucial for promoting harmony. Traditional hate speech detection models rely on NLP techniques like tokenization, part-of-speech tagging, and encoder-decoder models. However, Graph Neural Networks (GNNs), with their ability to utilize relationships between data points, offer more effective detection and greater explainability. In this work, we represent speeches as nodes and connect them with edges based on their context and similarity to develop the graph. This study introduces a novel paradigm using GNNs to identify and explain hate speech towards Islam. Our model leverages GNNs to understand the context and patterns of hate speech by connecting texts via pretrained NLP-generated word embeddings, achieving state-of-the-art performance and enhancing detection accuracy while providing valuable explanations. This highlights the potential of GNNs in combating online hate speech and fostering a safer, more inclusive online environment.
CNNs and Self attention have achieved great success in multimedia applications for dynamic association learning of self-attention and convolution in image restoration. However, CNNs have at least two shortcomings: 1) limited receptive field; 2) static weight of sliding window at inference, unable to cope with the content diversity.In view of the advantages and disadvantages of CNNs and Self attention, this paper proposes an association learning method to utilize the advantages and suppress their shortcomings, so as to achieve high-quality and efficient inpainting. We regard rain distribution reflects the degradation location and degree, in addition to the rain distribution prediction. Thus, we propose to refine background textures with the predicted degradation prior in an association learning manner. As a result, we accomplish image deraining by associating rain streak removal and background recovery, where an image deraining network and a background recovery network are designed for two subtasks. The key part of association learning is a novel multi-input attention module. It generates the degradation prior and produces the degradation mask according to the predicted rainy distribution. Benefited from the global correlation calculation of SA, MAM can extract the informative complementary components from the rainy input with the degradation mask, and then help accurate texture restoration. Meanwhile, SA tends to aggregate feature maps with self-attention importance, but convolution diversifies them to focus on the local textures. A hybrid fusion network involves one residual Transformer branch and one encoder-decoder branch. The former takes a few learnable tokens as input and stacks multi-head attention and feed-forward networks to encode global features of the image. The latter, conversely, leverages the multi-scale encoder-decoder to represent contexture knowledge.
Predicting human mobility holds significant practical value, with applications ranging from enhancing disaster risk planning to simulating epidemic spread. In this paper, we present the GeoFormer, a decoder-only transformer model adapted from the GPT architecture to forecast human mobility. Our proposed model is rigorously tested in the context of the HuMob Challenge 2023 -- a competition designed to evaluate the performance of prediction models on standardized datasets to predict human mobility. The challenge leverages two datasets encompassing urban-scale data of 25,000 and 100,000 individuals over a longitudinal period of 75 days. GeoFormer stands out as a top performer in the competition, securing a place in the top-3 ranking. Its success is underscored by performing well on both performance metrics chosen for the competition -- the GEO-BLEU and the Dynamic Time Warping (DTW) measures. The performance of the GeoFormer on the HuMob Challenge 2023 underscores its potential to make substantial contributions to the field of human mobility prediction, with far-reaching implications for disaster preparedness, epidemic control, and beyond.
While Connectionist Temporal Classification (CTC) models deliver state-of-the-art accuracy in automated speech recognition (ASR) pipelines, their performance has been limited by CPU-based beam search decoding. We introduce a GPU-accelerated Weighted Finite State Transducer (WFST) beam search decoder compatible with current CTC models. It increases pipeline throughput and decreases latency, supports streaming inference, and also supports advanced features like utterance-specific word boosting via on-the-fly composition. We provide pre-built DLPack-based python bindings for ease of use with Python-based machine learning frameworks at https://github.com/nvidia-riva/riva-asrlib-decoder. We evaluated our decoder for offline and online scenarios, demonstrating that it is the fastest beam search decoder for CTC models. In the offline scenario it achieves up to 7 times more throughput than the current state-of-the-art CPU decoder and in the online streaming scenario, it achieves nearly 8 times lower latency, with same or better word error rate.