Internal language model (ILM) subtraction has been widely applied to improve the performance of the RNN-Transducer with external language model (LM) fusion for speech recognition. In this work, we show that sequence discriminative training has a strong correlation with ILM subtraction from both theoretical and empirical points of view. Theoretically, we derive that the global optimum of maximum mutual information (MMI) training shares a similar formula as ILM subtraction. Empirically, we show that ILM subtraction and sequence discriminative training achieve similar performance across a wide range of experiments on Librispeech, including both MMI and minimum Bayes risk (MBR) criteria, as well as neural transducers and LMs of both full and limited context. The benefit of ILM subtraction also becomes much smaller after sequence discriminative training. We also provide an in-depth study to show that sequence discriminative training has a minimal effect on the commonly used zero-encoder ILM estimation, but a joint effect on both encoder and prediction + joint network for posterior probability reshaping including both ILM and blank suppression.

Modeling long-term context in videos is crucial for many fine-grained tasks including temporal action segmentation. An interesting question that is still open is how much long-term temporal context is needed for optimal performance. While transformers can model the long-term context of a video, this becomes computationally prohibitive for long videos. Recent works on temporal action segmentation thus combine temporal convolutional networks with self-attentions that are computed only for a local temporal window. While these approaches show good results, their performance is limited by their inability to capture the full context of a video. In this work, we try to answer how much long-term temporal context is required for temporal action segmentation by introducing a transformer-based model that leverages sparse attention to capture the full context of a video. We compare our model with the current state of the art on three datasets for temporal action segmentation, namely 50Salads, Breakfast, and Assembly101. Our experiments show that modeling the full context of a video is necessary to obtain the best performance for temporal action segmentation.

Multimodal reasoning is a critical component in the pursuit of artificial intelligence systems that exhibit human-like intelligence, especially when tackling complex tasks. While the chain-of-thought (CoT) technique has gained considerable attention, the existing ScienceQA dataset, which focuses on multimodal scientific questions and explanations from elementary and high school textbooks, lacks a comprehensive evaluation of diverse approaches. To address this gap, we present COCO Multi-Modal Reasoning(COCO-MMR) dataset, a novel dataset that encompasses an extensive collection of open-ended questions, rationales, and answers derived from the large object dataset COCO. Unlike previous datasets that rely on multiple-choice questions, our dataset pioneers the use of open-ended questions in the context of multimodal CoT, introducing a more challenging problem that effectively assesses the reasoning capability of CoT models. Through comprehensive evaluations and detailed analyses, we provide valuable insights and propose innovative techniques, including multi-hop cross-modal attention and sentence-level contrastive learning, to enhance the image and text encoders. Extensive experiments demonstrate the efficacy of the proposed dataset and techniques, offering novel perspectives for advancing multimodal reasoning. The data and code are available at \href{https://github.com/weijingxuan/COCO-MMR}{https://github.com/weijingxuan/COCO-MMR}.

We introduce Text2Cinemagraph, a fully automated method for creating cinemagraphs from text descriptions - an especially challenging task when prompts feature imaginary elements and artistic styles, given the complexity of interpreting the semantics and motions of these images. We focus on cinemagraphs of fluid elements, such as flowing rivers, and drifting clouds, which exhibit continuous motion and repetitive textures. Existing single-image animation methods fall short on artistic inputs, and recent text-based video methods frequently introduce temporal inconsistencies, struggling to keep certain regions static. To address these challenges, we propose an idea of synthesizing image twins from a single text prompt - a pair of an artistic image and its pixel-aligned corresponding natural-looking twin. While the artistic image depicts the style and appearance detailed in our text prompt, the realistic counterpart greatly simplifies layout and motion analysis. Leveraging existing natural image and video datasets, we can accurately segment the realistic image and predict plausible motion given the semantic information. The predicted motion can then be transferred to the artistic image to create the final cinemagraph. Our method outperforms existing approaches in creating cinemagraphs for natural landscapes as well as artistic and other-worldly scenes, as validated by automated metrics and user studies. Finally, we demonstrate two extensions: animating existing paintings and controlling motion directions using text.

Generic sentence embeddings provide a coarse-grained approximation of semantic textual similarity but ignore specific aspects that make texts similar. Conversely, aspect-based sentence embeddings provide similarities between texts based on certain predefined aspects. Thus, similarity predictions of texts are more targeted to specific requirements and more easily explainable. In this paper, we present AspectCSE, an approach for aspect-based contrastive learning of sentence embeddings. Results indicate that AspectCSE achieves an average improvement of 3.97% on information retrieval tasks across multiple aspects compared to the previous best results. We also propose using Wikidata knowledge graph properties to train models of multi-aspect sentence embeddings in which multiple specific aspects are simultaneously considered during similarity predictions. We demonstrate that multi-aspect embeddings outperform single-aspect embeddings on aspect-specific information retrieval tasks. Finally, we examine the aspect-based sentence embedding space and demonstrate that embeddings of semantically similar aspect labels are often close, even without explicit similarity training between different aspect labels.

Symbolic regression (SR) is a powerful technique for discovering the underlying mathematical expressions from observed data. Inspired by the success of deep learning, recent efforts have focused on two categories for SR methods. One is using a neural network or genetic programming to search the expression tree directly. Although this has shown promising results, the large search space poses difficulties in learning constant factors and processing high-dimensional problems. Another approach is leveraging a transformer-based model training on synthetic data and offers advantages in inference speed. However, this method is limited to fixed small numbers of dimensions and may encounter inference problems when given data is out-of-distribution compared to the synthetic data. In this work, we propose DySymNet, a novel neural-guided Dynamic Symbolic Network for SR. Instead of searching for expressions within a large search space, we explore DySymNet with various structures and optimize them to identify expressions that better-fitting the data. With a topology structure like neural networks, DySymNet not only tackles the challenge of high-dimensional problems but also proves effective in optimizing constants. Based on extensive numerical experiments using low-dimensional public standard benchmarks and the well-known SRBench with more variables, our method achieves state-of-the-art performance in terms of fitting accuracy and robustness to noise.

Clinically, automated polyp segmentation techniques have the potential to significantly improve the efficiency and accuracy of medical diagnosis, thereby reducing the risk of colorectal cancer in patients. Unfortunately, existing methods suffer from two significant weaknesses that can impact the accuracy of segmentation. Firstly, features extracted by encoders are not adequately filtered and utilized. Secondly, semantic conflicts and information redundancy caused by feature fusion are not attended to. To overcome these limitations, we propose a novel approach for polyp segmentation, named MLFF-Net, which leverages multi-level feature fusion and attention mechanisms. Specifically, MLFF-Net comprises three modules: Multi-scale Attention Module (MAM), High-level Feature Enhancement Module (HFEM), and Global Attention Module (GAM). Among these, MAM is used to extract multi-scale information and polyp details from the shallow output of the encoder. In HFEM, the deep features of the encoders complement each other by aggregation. Meanwhile, the attention mechanism redistributes the weight of the aggregated features, weakening the conflicting redundant parts and highlighting the information useful to the task. GAM combines features from the encoder and decoder features, as well as computes global dependencies to prevent receptive field locality. Experimental results on five public datasets show that the proposed method not only can segment multiple types of polyps but also has advantages over current state-of-the-art methods in both accuracy and generalization ability.

While large language models (LLMs) have demonstrated remarkable capabilities across a range of downstream tasks, a significant concern revolves around their propensity to exhibit hallucinations: LLMs occasionally generate content that diverges from the user input, contradicts previously generated context, or misaligns with established world knowledge. This phenomenon poses a substantial challenge to the reliability of LLMs in real-world scenarios. In this paper, we survey recent efforts on the detection, explanation, and mitigation of hallucination, with an emphasis on the unique challenges posed by LLMs. We present taxonomies of the LLM hallucination phenomena and evaluation benchmarks, analyze existing approaches aiming at mitigating LLM hallucination, and discuss potential directions for future research.

Autonomous navigation in underwater environments presents challenges due to factors such as light absorption and water turbidity, limiting the effectiveness of optical sensors. Sonar systems are commonly used for perception in underwater operations as they are unaffected by these limitations. Traditional computer vision algorithms are less effective when applied to sonar-generated acoustic images, while convolutional neural networks (CNNs) typically require large amounts of labeled training data that are often unavailable or difficult to acquire. To this end, we propose a novel compact deep sonar descriptor pipeline that can generalize to real scenarios while being trained exclusively on synthetic data. Our architecture is based on a ResNet18 back-end and a properly parameterized random Gaussian projection layer, whereas input sonar data is enhanced with standard ad-hoc normalization/prefiltering techniques. A customized synthetic data generation procedure is also presented. The proposed method has been evaluated extensively using both synthetic and publicly available real data, demonstrating its effectiveness compared to state-of-the-art methods.

It has been called the new gold rush – a rush to catch up with China in producing and refining the materials needed in everything from computers to cars: but has it come too late to save Europe's car industry? Deep inside a former East German town lies the first fruits of the EU's grand plan to "de-risk" and wean itself off dependency on imports for the green revolution. In Bitterfeld-Wolfen, 140km south-west of Berlin, an Amsterdam-listed company is scrambling to complete construction of a vast factory that will be the first in Europe to deliver battery-grade lithium. There is now a race across Europe to both mine the silver-white soft metal and manufacture its refined form, lithium hydroxide – the key ingredient in the batteries that power electric cars, robot vacuum cleaners and mobile phones. "Everybody wants to get access to lithium. This is maybe why they call it the white gold, because it is like a gold rush," says Stefan Scherer, chief executive of AMG Lithium.