分享

This paper introduces the Pandemic PACT Advanced Categorisation Engine (PPACE) along with its associated dataset. PPACE is a fine-tuned model developed to automatically classify research abstracts from funded biomedical projects according to WHO-aligned research priorities. This task is crucial for monitoring research trends and identifying gaps in global health preparedness and response. Our approach builds on human-annotated projects, which are allocated one or more categories from a predefined list. A large language model is then used to generate `rationales' explaining the reasoning behind these annotations. This augmented data, comprising expert annotations and rationales, is subsequently used to fine-tune a smaller, more efficient model. Developed as part of the Pandemic PACT project, which aims to track and analyse research funding and clinical evidence for a wide range of diseases with outbreak potential, PPACE supports informed decision-making by research funders, policymakers, and independent researchers. We introduce and release both the trained model and the instruction-based dataset used for its training. Our evaluation shows that PPACE significantly outperforms its baselines. The release of PPACE and its associated dataset offers valuable resources for researchers in multilabel biomedical document classification and supports advancements in aligning biomedical research with key global health priorities.

Traditional language model-based theorem proving assumes that by training on a sufficient amount of formal proof data, a model will learn to prove theorems. Our key observation is that a wealth of informal information that is not present in formal proofs can be useful for learning to prove theorems. For instance, humans think through steps of a proof, but this thought process is not visible in the resulting code. We present Lean-STaR, a framework for training language models to produce informal thoughts prior to each step of a proof, thereby boosting the model's theorem-proving capabilities. Lean-STaR uses retrospective ground-truth tactics to generate synthetic thoughts for training the language model. At inference time, the trained model directly generates the thoughts prior to the prediction of the tactics in each proof step. Building on the self-taught reasoner framework, we then apply expert iteration to further fine-tune the model on the correct proofs it samples and verifies using the Lean solver. Lean-STaR achieves state-of-the-art results on the miniF2F-test benchmark within the Lean theorem proving environment, significantly outperforming base models ($\boldsymbol{43.4\% \rightarrow 46.3\%,}$ Pass@64). We also analyze the impact of the augmented thoughts on various aspects of the theorem proving process, providing insights into their effectiveness.

The Visual-Dialog Based Emotion Explanation Generation Challenge focuses on generating emotion explanations through visual-dialog interactions in art discussions. Our approach combines state-of-the-art multi-modal models, including Language Model (LM) and Large Vision Language Model (LVLM), to achieve superior performance. By leveraging these models, we outperform existing benchmarks, securing the top rank in the ICCV23 Visual-Dialog Based Emotion Explanation Generation Challenge, which is part of the 5th Workshop On Closing The Loop Between Vision And Language (CLCV) with significant scores in F1 and BLEU metrics. Our method demonstrates exceptional ability in generating accurate emotion explanations, advancing our understanding of emotional impacts in art.

The current gold standard for the study of human movement is the marker-based motion capture system that offers high precision but constrained by costs and controlled environments. Markerless pose estimation systems emerge as ecological alternatives, allowing unobtrusive data acquisition in natural settings. This study compares the performance of two popular markerless systems, OpenPose (OP) and DeepLabCut (DLC), in assessing locomotion. Forty healthy subjects walked along a 5 meters walkway equipped with four force platforms and a camera. Gait parameters were obtained using OP BODY 25 Pre-Trained model (OPPT), DLC Model Zoo full human Pre-Trained model (DLCPT) and DLC Custom-Trained model (DLCCT), then compared with those acquired from the force platforms as reference system. Our results demonstrated that DLCCT outperformed DLCPT and OPPT, highlighting the importance of leveraging DeepLabCut transfer learning to enhance the pose estimation performance with a custom-trained neural networks. Moreover, DLCCT, with the implementation of the DLC refinement function, offers the most promising markerless pose estimation solution for evaluating locomotion. Therefore, our data provide insights into the DLC training and refinement processes required to achieve optimal performance. This study offers perspectives for clinicians and practitioners seeking accurate low-cost methods for movement assessment beyond laboratory settings.

We introduce 3DEgo to address a novel problem of directly synthesizing photorealistic 3D scenes from monocular videos guided by textual prompts. Conventional methods construct a text-conditioned 3D scene through a three-stage process, involving pose estimation using Structure-from-Motion (SfM) libraries like COLMAP, initializing the 3D model with unedited images, and iteratively updating the dataset with edited images to achieve a 3D scene with text fidelity. Our framework streamlines the conventional multi-stage 3D editing process into a single-stage workflow by overcoming the reliance on COLMAP and eliminating the cost of model initialization. We apply a diffusion model to edit video frames prior to 3D scene creation by incorporating our designed noise blender module for enhancing multi-view editing consistency, a step that does not require additional training or fine-tuning of T2I diffusion models. 3DEgo utilizes 3D Gaussian Splatting to create 3D scenes from the multi-view consistent edited frames, capitalizing on the inherent temporal continuity and explicit point cloud data. 3DEgo demonstrates remarkable editing precision, speed, and adaptability across a variety of video sources, as validated by extensive evaluations on six datasets, including our own prepared GS25 dataset. Project Page: https://3dego.github.io/

The current methods of video-based 3D human pose estimation have achieved significant progress; however, they continue to confront the significant challenge of depth ambiguity. To address this limitation, this paper presents the spatio-temporal GraphFormer framework for 3D human pose estimation in video, which integrates body structure graph-based representations with spatio-temporal information. Specifically, we develop a spatio-temporal criss-cross graph (STG) attention mechanism. This approach is designed to learn the long-range dependencies in data across both time and space, integrating graph information directly into the respective attention layers. Furthermore, we introduce the dual-path modulated hop-wise regular GCN (MHR-GCN) module, which utilizes modulation to optimize parameter usage and employs spatio-temporal hop-wise skip connections to acquire higher-order information. Additionally, this module processes temporal and spatial dimensions independently to learn their respective features while avoiding mutual influence. Finally, we demonstrate that our method achieves state-of-the-art performance in 3D human pose estimation on the Human3.6M and MPI-INF-3DHP datasets.

The Vision Foundation Model has recently gained attention in medical image analysis. Its zero-shot learning capabilities accelerate AI deployment and enhance the generalizability of clinical applications. However, segmenting pathological images presents a special focus on the flexibility of segmentation targets. For instance, a single click on a Whole Slide Image (WSI) could signify a cell, a functional unit, or layers, adding layers of complexity to the segmentation tasks. Current models primarily predict potential outcomes but lack the flexibility needed for physician input. In this paper, we explore the potential of enhancing segmentation model flexibility by introducing various task prompts through a Large Language Model (LLM) alongside traditional task tokens. Our contribution is in four-fold: (1) we construct a computational-efficient pipeline that uses finetuned language prompts to guide flexible multi-class segmentation; (2) We compare segmentation performance with fixed prompts against free-text; (3) We design a multi-task kidney pathology segmentation dataset and the corresponding various free-text prompts; and (4) We evaluate our approach on the kidney pathology dataset, assessing its capacity to new cases during inference.

Range-View(RV)-based 3D point cloud segmentation is widely adopted due to its compact data form. However, RV-based methods fall short in providing robust segmentation for the occluded points and suffer from distortion of projected RGB images due to the sparse nature of 3D point clouds. To alleviate these problems, we propose a new LiDAR and Camera Range-view-based 3D point cloud semantic segmentation method (LaCRange). Specifically, a distortion-compensating knowledge distillation (DCKD) strategy is designed to remedy the adverse effect of RV projection of RGB images. Moreover, a context-based feature fusion module is introduced for robust and preservative sensor fusion. Finally, in order to address the limited resolution of RV and its insufficiency of 3D topology, a new point refinement scheme is devised for proper aggregation of features in 2D and augmentation of point features in 3D. We evaluated the proposed method on large-scale autonomous driving datasets \ie SemanticKITTI and nuScenes. In addition to being real-time, the proposed method achieves state-of-the-art results on nuScenes benchmark

With the strong representational power of large language models (LLMs), generative error correction (GER) for automatic speech recognition (ASR) aims to provide semantic and phonetic refinements to address ASR errors. This work explores how LLM-based GER can enhance and expand the capabilities of Japanese language processing, presenting the first GER benchmark for Japanese ASR with 0.9-2.6k text utterances. We also introduce a new multi-pass augmented generative error correction (MPA GER) by integrating multiple system hypotheses on the input side with corrections from multiple LLMs on the output side and then merging them. To the best of our knowledge, this is the first investigation of the use of LLMs for Japanese GER, which involves second-pass language modeling on the output transcriptions generated by the ASR system (e.g., N-best hypotheses). Our experiments demonstrated performance improvement in the proposed methods of ASR quality and generalization both in SPREDS-U1-ja and CSJ data.

Past ontology requirements engineering (ORE) has primarily relied on manual methods, such as interviews and collaborative forums, to gather user requirements from domain experts, especially in large projects. Current OntoChat offers a framework for ORE that utilises large language models (LLMs) to streamline the process through four key functions: user story creation, competency question (CQ) extraction, CQ filtration and analysis, and ontology testing support. In OntoChat, users are expected to prompt the chatbot to generate user stories. However, preliminary evaluations revealed that they struggle to do this effectively. To address this issue, we experimented with a research method called participatory prompting, which involves researcher-mediated interactions to help users without deep knowledge of LLMs use the chatbot more effectively. This participatory prompting user study produces pre-defined prompt templates based on user queries, focusing on creating and refining personas, goals, scenarios, sample data, and data resources for user stories. These refined user stories will subsequently be converted into CQs.

Recent methods using diffusion models have made significant progress in human image generation with various additional controls such as pose priors. However, existing approaches still struggle to generate high-quality images with consistent pose alignment, resulting in unsatisfactory outputs. In this paper, we propose a framework delving into the graph relations of pose priors to provide control information for human image generation. The main idea is to establish a graph topological structure between the pose priors and latent representation of diffusion models to capture the intrinsic associations between different pose parts. A Progressive Graph Integrator (PGI) is designed to learn the spatial relationships of the pose priors with the graph structure, adopting a hierarchical strategy within an Adapter to gradually propagate information across different pose parts. A pose perception loss is further introduced based on a pretrained pose estimation network to minimize the pose differences. Extensive qualitative and quantitative experiments conducted on the Human-Art and LAION-Human datasets demonstrate that our model achieves superior performance, with a 9.98% increase in pose average precision compared to the latest benchmark model. The code is released on *******.

This thesis provides methods and analysis of models which make progress on this goal. The techniques outlined are task agnostic, and should provide benefit when used with nearly any transformer LM. We introduce two new finetuning methods which add new capabilities to the models they are used on. The first adds a recurrence mechanism, which removes the fixed-window sized constraint and improves the efficiency of a transformer decoder. The second allows masked language models (MLMs) to be used for initialization of both the encoder and decoder of a non-autoregressive sequence-to-sequence transformer, opening up generative applications of models which were previously only used for natural language understanding tasks. We also introduce two new techniques for improving the quality of predictions of any transformer decoder without additional finetuning. One, hidden state optimization, can be applied to any transformer decoder to improve the quality of predictions at inference time, especially for few-shot classification. The other, conditional beam search, allows practitioners to search for natural language generation (NLG) model outputs with high likelihood while conditioning on the event that the output is not degenerate (e.g. empty, repetitive, etc.). Finally, we provide theoretical and empirical insights on the divergence of model-likelihood and output quality which has widely been observed in prior work. These insights apply to any model which represents a distribution over text, and apply to language models which are not transformers or even autoregressive. We argue that the NLP community has, to some extent, misunderstood the implications of these findings, and encourage a point of view which has more nuance.