Clinicians compare breast DCE-MRI after neoadjuvant chemotherapy (NAC) with pre-treatment scans to evaluate the response to NAC. Clinical evidence supports that accurate longitudinal deformable registration without deforming treated tumor regions is key to quantifying tumor changes. We propose a conditional pyramid registration network based on unsupervised keypoint detection and selective volume-preserving to quantify changes over time. In this approach, we extract the structural and the abnormal keypoints from DCE-MRI, apply the structural keypoints for the registration algorithm to restrict large deformation, and employ volume-preserving loss based on abnormal keypoints to keep the volume of the tumor unchanged after registration. We use a clinical dataset with 1630 MRI scans from 314 patients treated with NAC. The results demonstrate that our method registers with better performance and better volume preservation of the tumors. Furthermore, a local-global-combining biomarker based on the proposed method achieves high accuracy in pathological complete response (pCR) prediction, indicating that predictive information exists outside tumor regions. The biomarkers could potentially be used to avoid unnecessary surgeries for certain patients. It may be valuable for clinicians and/or computer systems to conduct follow-up tumor segmentation and response prediction on images registered by our method. Our code is available on \url{https://github.com/fiy2W/Treatment-aware-Longitudinal-Registration}.
An important development direction in the Single-Image Super-Resolution (SISR) algorithms is to improve the efficiency of the algorithms. Recently, efficient Super-Resolution (SR) research focuses on reducing model complexity and improving efficiency through improved deep small kernel convolution, leading to a small receptive field. The large receptive field obtained by large kernel convolution can significantly improve image quality, but the computational cost is too high. To improve the reconstruction details of efficient super-resolution reconstruction, we propose a Symmetric Visual Attention Network (SVAN) by applying large receptive fields. The SVAN decomposes a large kernel convolution into three different combinations of convolution operations and combines them with an attention mechanism to form a Symmetric Large Kernel Attention Block (SLKAB), which forms a symmetric attention block with a bottleneck structure by the size of the receptive field in the convolution combination to extract depth features effectively as the basic component of the SVAN. Our network gets a large receptive field while minimizing the number of parameters and improving the perceptual ability of the model. The experimental results show that the proposed SVAN can obtain high-quality super-resolution reconstruction results using only about 30% of the parameters of existing SOTA methods.
In this technical report, we present TeleChat, a collection of large language models (LLMs) with parameters of 3 billion, 7 billion and 12 billion. It includes pretrained language models as well as fine-tuned chat models that is aligned with human preferences. TeleChat is initially pretrained on an extensive corpus containing a diverse collection of texts from both English and Chinese languages, including trillions of tokens. Subsequently, the model undergoes fine-tuning to align with human preferences, following a detailed methodology that we describe. We evaluate the performance of TeleChat on various tasks, including language understanding, mathematics, reasoning, code generation, and knowledge-based question answering. Our findings indicate that TeleChat achieves comparable performance to other open-source models of similar size across a wide range of public benchmarks. To support future research and applications utilizing LLMs, we release the fine-tuned model checkpoints of TeleChat's 7B and 12B variant, along with code and a portion of our pretraining data, to the public community.
Equipped with sensing, networking, and computing capabilities, Internet of Things (IoT) such as smartphones, wearables, smart speakers, and household robots have been seamlessly weaved into our daily lives. Recent advancements in Generative AI exemplified by GPT, LLaMA, DALL-E, and Stable Difussion hold immense promise to push IoT to the next level. In this article, we share our vision and views on the benefits that Generative AI brings to IoT, and discuss some of the most important applications of Generative AI in IoT-related domains. Fully harnessing Generative AI in IoT is a complex challenge. We identify some of the most critical challenges including high resource demands of the Generative AI models, prompt engineering, on-device inference, offloading, on-device fine-tuning, federated learning, security, as well as development tools and benchmarks, and discuss current gaps as well as promising opportunities on enabling Generative AI for IoT. We hope this article can inspire new research on IoT in the era of Generative AI.
This article presents a general Bayesian learning framework for multi-modal groupwise registration on medical images. The method builds on probabilistic modelling of the image generative process, where the underlying common anatomy and geometric variations of the observed images are explicitly disentangled as latent variables. Thus, groupwise registration is achieved through the solution to Bayesian inference. We propose a novel hierarchical variational auto-encoding architecture to realize the inference procedure of the latent variables, where the registration parameters can be calculated in a mathematically interpretable fashion. Remarkably, this new paradigm can learn groupwise registration in an unsupervised closed-loop self-reconstruction process, sparing the burden of designing complex intensity-based similarity measures. The computationally efficient disentangled architecture is also inherently scalable and flexible, allowing for groupwise registration on large-scale image groups with variable sizes. Furthermore, the inferred structural representations from disentanglement learning are capable of capturing the latent anatomy of the observations with visual semantics. Extensive experiments were conducted to validate the proposed framework, including four datasets from cardiac, brain and abdominal medical images. The results have demonstrated the superiority of our method over conventional similarity-based approaches in terms of accuracy, efficiency, scalability and interpretability.
Temporal Sentence Grounding (TSG), which aims to localize moments from videos based on the given natural language queries, has attracted widespread attention. Existing works are mainly designed for short videos, failing to handle TSG in long videos, which poses two challenges: i) complicated contexts in long videos require temporal reasoning over longer moment sequences, and ii) multiple modalities including textual speech with rich information require special designs for content understanding in long videos. To tackle these challenges, in this work we propose a Grounding-Prompter method, which is capable of conducting TSG in long videos through prompting LLM with multimodal information. In detail, we first transform the TSG task and its multimodal inputs including speech and visual, into compressed task textualization. Furthermore, to enhance temporal reasoning under complicated contexts, a Boundary-Perceptive Prompting strategy is proposed, which contains three folds: i) we design a novel Multiscale Denoising Chain-of-Thought (CoT) to combine global and local semantics with noise filtering step by step, ii) we set up validity principles capable of constraining LLM to generate reasonable predictions following specific formats, and iii) we introduce one-shot In-Context-Learning (ICL) to boost reasoning through imitation, enhancing LLM in TSG task understanding. Experiments demonstrate the state-of-the-art performance of our Grounding-Prompter method, revealing the benefits of prompting LLM with multimodal information for TSG in long videos.
Recently, researchers have attempted to investigate the capability of LLMs in handling videos and proposed several video LLM models. However, the ability of LLMs to handle video grounding (VG), which is an important time-related video task requiring the model to precisely locate the start and end timestamps of temporal moments in videos that match the given textual queries, still remains unclear and unexplored in literature. To fill the gap, in this paper, we propose the LLM4VG benchmark, which systematically evaluates the performance of different LLMs on video grounding tasks. Based on our proposed LLM4VG, we design extensive experiments to examine two groups of video LLM models on video grounding: (i) the video LLMs trained on the text-video pairs (denoted as VidLLM), and (ii) the LLMs combined with pretrained visual description models such as the video/image captioning model. We propose prompt methods to integrate the instruction of VG and description from different kinds of generators, including caption-based generators for direct visual description and VQA-based generators for information enhancement. We also provide comprehensive comparisons of various VidLLMs and explore the influence of different choices of visual models, LLMs, prompt designs, etc, as well. Our experimental evaluations lead to two conclusions: (i) the existing VidLLMs are still far away from achieving satisfactory video grounding performance, and more time-related video tasks should be included to further fine-tune these models, and (ii) the combination of LLMs and visual models shows preliminary abilities for video grounding with considerable potential for improvement by resorting to more reliable models and further guidance of prompt instructions.
Multi-hop question answering (MQA) is one of the challenging tasks to evaluate machine's comprehension and reasoning abilities, where large language models (LLMs) have widely achieved the human-comparable performance. Due to the dynamics of knowledge facts in real world, knowledge editing has been explored to update model with the up-to-date facts while avoiding expensive re-training or fine-tuning. Starting from the edited fact, the updated model needs to provide cascading changes in the chain of MQA. The previous art simply adopts a mix-up prompt to instruct LLMs conducting multiple reasoning tasks sequentially, including question decomposition, answer generation, and conflict checking via comparing with edited facts. However, the coupling of these functionally-diverse reasoning tasks inhibits LLMs' advantages in comprehending and answering questions while disturbing them with the unskilled task of conflict checking. We thus propose a framework, Programmable knowledge editing for Multi-hop Question Answering (PokeMQA), to decouple the jobs. Specifically, we prompt LLMs to decompose knowledge-augmented multi-hop question, while interacting with a detached trainable scope detector to modulate LLMs behavior depending on external conflict signal. The experiments on three LLM backbones and two benchmark datasets validate our superiority in knowledge editing of MQA, outperforming all competitors by a large margin in almost all settings and consistently producing reliable reasoning process.
Large Language Models (LLMs) have demonstrated remarkable capabilities in important tasks such as natural language understanding, language generation, and complex reasoning and have the potential to make a substantial impact on our society. Such capabilities, however, come with the considerable resources they demand, highlighting the strong need to develop effective techniques for addressing their efficiency challenges. In this survey, we provide a systematic and comprehensive review of efficient LLMs research. We organize the literature in a taxonomy consisting of three main categories, covering distinct yet interconnected efficient LLMs topics from model-centric, data-centric, and framework-centric perspective, respectively. We have also created a GitHub repository where we compile the papers featured in this survey at https://github.com/AIoT-MLSys-Lab/EfficientLLMs, and will actively maintain this repository and incorporate new research as it emerges. We hope our survey can serve as a valuable resource to help researchers and practitioners gain a systematic understanding of the research developments in efficient LLMs and inspire them to contribute to this important and exciting field.