While pre-trained models, such as large language models, can achieve high performance with minimal fine-tuning, the source datasets used for pre-training often contain irrelevant or blackundant data, which can degrade performance on target tasks. Domain Adaptation Information Gain (DAIG)-based source data selection improves performance by pre-training on source data selected based on rough prior knowledge obtained from target data in advance. However, DAIG’s key component, the transition matrix, lacks flexibility and is limited to handling only single-label classification tasks. To address this limitation, we propose the Generalized DAIG (GDAIG)-guided selection process, a novel framework that extends DAIG to support multi-label classification. GDAIG introduces a soft transition matrix to capture inter-label dependencies and employs binary cross-entropy loss to enable adaptation to multi-label data. By leveraging “rough prior knowledge” from initial training on target data, GDAIG actively selects informative and task-relevant source data for pre-training. Experiments on medical image and general object classification datasets demonstrate that GDAIG consistently outperforms baseline approaches, with particularly significant improvements in scenarios involving label mismatch between source and target domains (partial or no label overlap), where conventional transfer learning methods suffer from noise caused by irrelevant source labels. These results highlight GDAIG’s ability to enhance the effectiveness of pre-trained models through strategic source data selection, thereby optimizing performance for specific target tasks. Our framework goes beyond existing approaches that rely solely on pre-trained models, emphasizing the direct utilization of task-relevant source data. Furthermore, GDAIG provides a practical and effective solution for domains with scarce labeled data, such as medical image analysis. • A GDAIG-guided data selection strategy for multi-label classification is proposed. • GDAIG improves target model performance through task-relevant multi-label data selection. • A probabilistic transition matrix captures inter-label dependencies. • “Rough prior” from target data effectively guides source data pre-training. • GDAIG outperforms conventional baselines across diverse multi-label scenarios.

Zero-shot domain-specific image classification is challenging in classifying real images without ground-truth in-domain training examples. Recent research involved knowledge from texts with a text-to-image model to generate in-domain training images in zero-shot scenarios. However, existing methods heavily rely on simple prompt strategies, limiting the diversity of synthetic training images, thus leading to inferior performance compared to real images. In this paper, we propose AttrSyn, which leverages large language models to generate attributed prompts. These prompts allow for the generation of more diverse attributed synthetic images. Experiments for zero-shot domain-specific image classification on two fine-grained datasets show that training with synthetic images generated by AttrSyn significantly outperforms CLIP’s zero-shot classification under most situations and consistently surpasses simple prompt strategies.

Recent research on explainable recommendation generally frames the task as a standard text generation problem, and evaluates models simply based on the textual similarity between the predicted and ground-truth explanations. However, this approach fails to consider one crucial aspect of the systems: whether their outputs accurately reflect the users' (post-purchase) sentiments, i.e., whether and why they would like and/or dislike the recommended items. To shed light on this issue, we introduce new datasets and evaluation methods that focus on the users' sentiments. Specifically, we construct the datasets by explicitly extracting users' positive and negative opinions from their post-purchase reviews using an LLM, and propose to evaluate systems based on whether the generated explanations 1) align well with the users' sentiments, and 2) accurately identify both positive and negative opinions of users on the target items. We benchmark several recent models on our datasets and demonstrate that achieving strong performance on existing metrics does not ensure that the generated explanations align well with the users' sentiments. Lastly, we find that existing models can provide more sentiment-aware explanations when the users' (predicted) ratings for the target items are directly fed into the models as input. The datasets and benchmark implementation are available at: https://github.com/jchanxtarov/sent_xrec.

LiDAR point cloud plays an important role in various real-world areas. It is usually generated as sequences by LiDAR on moving vehicles. Regarding the large data size of LiDAR point clouds, Dynamic Point Cloud Compression (DPCC) methods are developed to reduce transmission and storage data costs. However, most existing DPCC methods neglect the intrinsic misalignment in LiDAR point cloud sequences, limiting the rate–distortion (RD) performance. This paper proposes a Misalignment-aware Dynamic LiDAR Point Cloud Compression method (MDLPCC), which alleviates the misalignment problem in both macroscope and microscope. MDLPCC exploits a global transformation (GlobTrans) method to eliminate the macroscopic misalignment problem, which is the obvious gap between two continuous point cloud frames. MDLPCC also uses a spatial–temporal mixed structure to alleviate the microscopic misalignment, which still exists in the detailed parts of two point clouds after GlobTrans. The experiments on our MDLPCC show superior performance over existing point cloud compression methods.

• Domain adaptation information gain-based target-related data selection is proposed. • Proposed DAIG improves target model accuracy via target-related data selection. • DAIG effectively gathers relevant data from source to benefit target tasks. • DAIG extracts “rough prior” from target data for source data pre-training. • DAIG-guided selection outperforms baselines in multiple experimental settings. In recent years, due to the explosive popularity of large-scale pre-trained models such as large language models, pre-training approaches that use a massive amount of source data and can be applied to various target tasks are becoming more popular. Pre-trained models allow us to learn highly accurate target models by fine-tuning them with target data, even when their volume is insufficient. However, the source data used to train a pre-training model is generally a large and miscellaneous data set obtained in the wild without being aware of the target task, and it highly possibly contains much data that does not contribute to relearning the target task. This study defines a novel paradigm as “target-aware source data selection,” which uses the source data itself instead of a pre-training model and selects source data for pre-training and aims to increase its quality, effectiveness, and robustness. Our proposal fundamentally differs from the current studies addressing the lack of target data and conventional transfer learning approaches, improving source data quality using the novel Domain Adaptation Information Gain criteria. Specifically, the target model is pre-trained while actively selecting only informative data from the source data using the “rough-prior knowledge” obtained from the target data training before the pre-training. Finally, fine-tuning the model with the target data results in a highly accurate model for the target (downstream) task. The effectiveness of our proposed paradigm has been demonstrated through multifaceted experiments using multiple pairs of target data and source data with different strengths of their relevance.

In recent years, the task of learned point cloud compression has gained prominence. An important type of point cloud, LiDAR point cloud, is generated by spinning LiDAR on vehicles. This process results in numerous circular shapes and azimuthal angle invariance features within the point clouds. However, these two features have been largely overlooked by previous methodologies. In this paper, we introduce a model-agnostic method called Spherical-Coordinate-based learned Point cloud compression (SCP), designed to fully leverage the features of circular shapes and azimuthal angle invariance. Additionally, we propose a multi-level Octree for SCP to mitigate the reconstruction error for distant areas within the Spherical-coordinate-based Octree. SCP exhibits excellent universality, making it applicable to various learned point cloud compression techniques. Experimental results demonstrate that SCP surpasses previous state-of-the-art methods by up to 29.14% in point-to-point PSNR BD-Rate.

Researchers and practitioners have recently reframed powerful Large Language Models (LLMs) as *agents*, enabling them to automate complex tasks largely via the use of specialized functions. To facilitate the development of LLM agents, we present a novel paradigm of training LLM agents without modifying the LLM weights, which is particularly useful when the LLMs are difficult or inaccessible for modifications. Inspired by how humans continuously forge tools to adapt to real-world tasks, rather than change our biological structure to fit a static set of tools, we propose to progressively forge agent's functions to better solve the downstream tasks instead of modifying the LLM weights. By treating the functions as learnable `agent parameters' and leveraging the fundamental idea of model training in artificial intelligence, we develop AgentOptimizer that employs the LLM to update agents' functions and devise an *agent training* algorithm with two strategies, roll-back, and early-stop, to streamline the training process. With extensive experiments, we showcase that the agent training paradigm could significantly improve the performance of representative LLM agents in various downstream tasks. We also study the behavior of the agent training regarding aspects like the learning curve and domain transferability.

Programmatic Weak Supervision (PWS) has emerged as a widespread paradigm to synthesize training labels efficiently. The core component of PWS is the label model, which infers true labels by aggregating the outputs of multiple noisy supervision sources abstracted as labeling functions (LFs). Existing statistical label models typically rely only on the outputs of LF, ignoring the instance features when modeling the underlying generative process. In this paper, we attempt to incorporate the instance features into a statistical label model via the proposed FABLE. In particular, it is built on a mixture of Bayesian label models, each corresponding to a global pattern of correlation, and the coefficients of the mixture components are predicted by a Gaussian Process classifier based on instance features. We adopt an auxiliary variable-based variational inference algorithm to tackle the non-conjugate issue between the Gaussian Process and Bayesian label models. Extensive empirical comparison on eleven benchmark datasets sees FABLE achieving the highest averaged performance across nine baselines. Our implementation of FABLE can be found in https://github.com/JieyuZ2/wrench/blob/main/wrench/labelmodel/fable.py.