arXiv subjects

Liangzhi Li

Publications and source records attributed to Liangzhi Li.

At least 19 recordsLinked to original sources

arXiv2026

The Blending Ratio Is Not Where the Performance Is: Diagnosing Prototype Blending for Few-Shot Adaptation of Vision-Language Models

Many few-shot adaptation methods for vision-language models classify with a convex combination of the zero-shot text prototype and the mean of the K labelled image features, with a single blending ratio routinely tuned on held-out labels, often on the test set itself. We ask what the family's own bias-variance justification invites: what is the right ratio, can it be estimated without validation data, and is finding it where the performance is? First, the ratio minimising prototype mean-squared error has a closed form whose support-set plug-in is exactly a positive-part James-Stein coefficient shrinking towards the text prototype. Across 4,800 cells (ten datasets, five backbones including SigLIP, five shot counts, five seeds, four prompt tiers) this theoretically optimal ratio is a reliable estimate of the wrong quantity: on the 950 primary-tier cells where it is defined it trails a test-set-oracle ratio by 8.5 points. It saturates near 1, discarding the text prior for a nearest-class-mean classifier, because 78% of the text-image prototype distance it treats as bias is a class-independent offset that the arg max largely cancels. We prove the mechanism and bound its share of the damage at 26% by a counterfactual. Second, leave-one-out on the support set alone sets a ratio landing within 0.9 points of the oracle blend, so it is estimable without validation data. Third, validation-free linear probes beat even the oracle-tuned blend: CLAP by +1.9 points and LP++ by +1.5 on average, and at K >= 4 all four validation-free baselines sit above the oracle, the linear probes by margins excluding zero. These results locate the ceiling in the model class, not the hyperparameter: the ratio can be set near-optimally for free, and it is still not where the performance is. Code, cached features, per-cell records: https://huggingface.co/datasets/Liangzhi-Li/clipbench-blending

cs.CV↗

arXiv2025

Instructor-Worker Large Language Model System for Policy Recommendation: a Case Study on Air Quality Analysis of the January 2025 Los Angeles Wildfires

The Los Angeles wildfires of January 2025 caused more than 250 billion dollars in damage and lasted for nearly an entire month before containment. Following our previous work, the Digital Twin Building, we modify and leverage the multi-agent large language model framework as well as the cloud-mapping integration to study the air quality during the Los Angeles wildfires. Recent advances in large language models have allowed for out-of-the-box automated large-scale data analysis. We use a multi-agent large language system comprised of an Instructor agent and Worker agents. Upon receiving the users' instructions, the Instructor agent retrieves the data from the cloud platform and produces instruction prompts to the Worker agents. The Worker agents then analyze the data and provide summaries. The summaries are finally input back into the Instructor agent, which then provides the final data analysis. We test this system's capability for data-based policy recommendation by assessing our Instructor-Worker LLM system's health recommendations based on air quality during the Los Angeles wildfires.

cs.AI↗

arXiv2025

Exploring Visual Prompting: Robustness Inheritance and Beyond

Visual Prompting (VP), an efficient method for transfer learning, has shown its potential in vision tasks. However, previous works focus exclusively on VP from standard source models, it is still unknown how it performs under the scenario of a robust source model: Can the robustness of the source model be successfully inherited? Does VP also encounter the same trade-off between robustness and generalization ability as the source model during this process? If such a trade-off exists, is there a strategy specifically tailored to VP to mitigate this limitation? In this paper, we thoroughly explore these three questions for the first time and provide affirmative answers to them. To mitigate the trade-off faced by VP, we propose a strategy called Prompt Boundary Loosening (PBL). As a lightweight, plug-and-play strategy naturally compatible with VP, PBL effectively ensures the successful inheritance of robustness when the source model is a robust model, while significantly enhancing VP's generalization ability across various downstream datasets. Extensive experiments across various datasets show that our findings are universal and demonstrate the significant benefits of the proposed strategy.

cs.CV↗

arXiv2025

Cracking the Code: Enhancing Implicit Hate Speech Detection through Coding Classification

The internet has become a hotspot for hate speech (HS), threatening societal harmony and individual well-being. While automatic detection methods perform well in identifying explicit hate speech (ex-HS), they struggle with more subtle forms, such as implicit hate speech (im-HS). We tackle this problem by introducing a new taxonomy for im-HS detection, defining six encoding strategies named codetypes. We present two methods for integrating codetypes into im-HS detection: 1) prompting large language models (LLMs) directly to classify sentences based on generated responses, and 2) using LLMs as encoders with codetypes embedded during the encoding process. Experiments show that the use of codetypes improves im-HS detection in both Chinese and English datasets, validating the effectiveness of our approach across different languages.

cs.CL↗

arXiv2025

Gaussian Building Mesh (GBM): Extract a Building's 3D Mesh with Google Earth and Gaussian Splatting

Recently released open-source pre-trained foundational image segmentation and object detection models (SAM2+GroundingDINO) allow for geometrically consistent segmentation of objects of interest in multi-view 2D images. Users can use text-based or click-based prompts to segment objects of interest without requiring labeled training datasets. Gaussian Splatting allows for the learning of the 3D representation of a scene's geometry and radiance based on 2D images. Combining Google Earth Studio, SAM2+GroundingDINO, 2D Gaussian Splatting, and our improvements in mask refinement based on morphological operations and contour simplification, we created a pipeline to extract the 3D mesh of any building based on its name, address, or geographic coordinates.

cs.CV↗

arXiv2025

BlockPruner: Fine-grained Pruning for Large Language Models

With the rapid growth in the size and complexity of large language models (LLMs), the costs associated with their training and inference have escalated significantly. Research indicates that certain layers in LLMs harbor substantial redundancy, and pruning these layers has minimal impact on the overall performance. While various layer pruning methods have been developed based on this insight, they generally overlook the finer-grained redundancies within the layers themselves. In this paper, we delve deeper into the architecture of LLMs and demonstrate that finer-grained pruning can be achieved by targeting redundancies in multi-head attention (MHA) and multi-layer perceptron (MLP) blocks. We propose a novel, training-free structured pruning approach called BlockPruner. Unlike existing layer pruning methods, BlockPruner segments each Transformer layer into MHA and MLP blocks. It then assesses the importance of these blocks using perplexity measures and applies a heuristic search for iterative pruning. We applied BlockPruner to LLMs of various sizes and architectures and validated its performance across a wide range of downstream tasks. Experimental results show that BlockPruner achieves more granular and effective pruning compared to state-of-the-art baselines.

cs.CL↗

arXiv2025

E-InMeMo: Enhanced Prompting for Visual In-Context Learning

Large-scale models trained on extensive datasets have become the standard due to their strong generalizability across diverse tasks. In-context learning (ICL), widely used in natural language processing, leverages these models by providing task-specific prompts without modifying their parameters. This paradigm is increasingly being adapted for computer vision, where models receive an input-output image pair, known as an in-context pair, alongside a query image to illustrate the desired output. However, the success of visual ICL largely hinges on the quality of these prompts. To address this, we propose Enhanced Instruct Me More (E-InMeMo), a novel approach that incorporates learnable perturbations into in-context pairs to optimize prompting. Through extensive experiments on standard vision tasks, E-InMeMo demonstrates superior performance over existing state-of-the-art methods. Notably, it improves mIoU scores by 7.99 for foreground segmentation and by 17.04 for single object detection when compared to the baseline without learnable prompts. These results highlight E-InMeMo as a lightweight yet effective strategy for enhancing visual ICL. Code is publicly available at: https://github.com/Jackieam/E-InMeMo

cs.CV↗

arXiv2025

Digital Twin Buildings: 3D Modeling, GIS Integration, and Visual Descriptions Using Gaussian Splatting, ChatGPT/Deepseek, and Google Maps Platform

Urban digital twins are virtual replicas of cities that use multi-source data and data analytics to optimize urban planning, infrastructure management, and decision-making. Towards this, we propose a framework focused on the single-building scale. By connecting to cloud mapping platforms such as Google Map Platforms APIs, by leveraging state-of-the-art multi-agent Large Language Models data analysis using ChatGPT(4o) and Deepseek-V3/R1, and by using our Gaussian Splatting-based mesh extraction pipeline, our Digital Twin Buildings framework can retrieve a building's 3D model, visual descriptions, and achieve cloud-based mapping integration with large language model-based data analytics using a building's address, postal code, or geographic coordinates.

cs.CV↗

arXiv2024

Imposter.AI: Adversarial Attacks with Hidden Intentions towards Aligned Large Language Models

With the development of large language models (LLMs) like ChatGPT, both their vast applications and potential vulnerabilities have come to the forefront. While developers have integrated multiple safety mechanisms to mitigate their misuse, a risk remains, particularly when models encounter adversarial inputs. This study unveils an attack mechanism that capitalizes on human conversation strategies to extract harmful information from LLMs. We delineate three pivotal strategies: (i) decomposing malicious questions into seemingly innocent sub-questions; (ii) rewriting overtly malicious questions into more covert, benign-sounding ones; (iii) enhancing the harmfulness of responses by prompting models for illustrative examples. Unlike conventional methods that target explicit malicious responses, our approach delves deeper into the nature of the information provided in responses. Through our experiments conducted on GPT-3.5-turbo, GPT-4, and Llama2, our method has demonstrated a marked efficacy compared to conventional attack methods. In summary, this work introduces a novel attack method that outperforms previous approaches, raising an important question: How to discern whether the ultimate intent in a dialogue is malicious?

cs.CL↗

arXiv2024

Explainable Image Recognition via Enhanced Slot-attention Based Classifier

The imperative to comprehend the behaviors of deep learning models is of utmost importance. In this realm, Explainable Artificial Intelligence (XAI) has emerged as a promising avenue, garnering increasing interest in recent years. Despite this, most existing methods primarily depend on gradients or input perturbation, which often fails to embed explanations directly within the model's decision-making process. Addressing this gap, we introduce ESCOUTER, a visually explainable classifier based on the modified slot attention mechanism. ESCOUTER distinguishes itself by not only delivering high classification accuracy but also offering more transparent insights into the reasoning behind its decisions. It differs from prior approaches in two significant aspects: (a) ESCOUTER incorporates explanations into the final confidence scores for each category, providing a more intuitive interpretation, and (b) it offers positive or negative explanations for all categories, elucidating "why an image belongs to a certain category" or "why it does not." A novel loss function specifically for ESCOUTER is designed to fine-tune the model's behavior, enabling it to toggle between positive and negative explanations. Moreover, an area loss is also designed to adjust the size of the explanatory regions for a more precise explanation. Our method, rigorously tested across various datasets and XAI metrics, outperformed previous state-of-the-art methods, solidifying its effectiveness as an explanatory tool.

cs.CV↗

arXiv2024

Can multiple-choice questions really be useful in detecting the abilities of LLMs?

Multiple-choice questions (MCQs) are widely used in the evaluation of large language models (LLMs) due to their simplicity and efficiency. However, there are concerns about whether MCQs can truly measure LLM's capabilities, particularly in knowledge-intensive scenarios where long-form generation (LFG) answers are required. The misalignment between the task and the evaluation method demands a thoughtful analysis of MCQ's efficacy, which we undertake in this paper by evaluating nine LLMs on four question-answering (QA) datasets in two languages: Chinese and English. We identify a significant issue: LLMs exhibit an order sensitivity in bilingual MCQs, favoring answers located at specific positions, i.e., the first position. We further quantify the gap between MCQs and long-form generation questions (LFGQs) by comparing their direct outputs, token logits, and embeddings. Our results reveal a relatively low correlation between answers from MCQs and LFGQs for identical questions. Additionally, we propose two methods to quantify the consistency and confidence of LLMs' output, which can be generalized to other QA evaluation benchmarks. Notably, our analysis challenges the idea that the higher the consistency, the greater the accuracy. We also find MCQs to be less reliable than LFGQs in terms of expected calibration error. Finally, the misalignment between MCQs and LFGQs is not only reflected in the evaluation performance but also in the embedding space. Our code and models can be accessed at https://github.com/Meetyou-AI-Lab/Can-MC-Evaluate-LLMs.

cs.CL↗

arXiv2023

Concatenated Masked Autoencoders as Spatial-Temporal Learner

Learning representations from videos requires understanding continuous motion and visual correspondences between frames. In this paper, we introduce the Concatenated Masked Autoencoders (CatMAE) as a spatial-temporal learner for self-supervised video representation learning. For the input sequence of video frames, CatMAE keeps the initial frame unchanged while applying substantial masking (95%) to subsequent frames. The encoder in CatMAE is responsible for encoding visible patches for each frame individually; subsequently, for each masked frame, the decoder leverages visible patches from both previous and current frames to reconstruct the original image. Our proposed method enables the model to estimate the motion information between visible patches, match the correspondences between preceding and succeeding frames, and ultimately learn the evolution of scenes. Furthermore, we propose a new data augmentation strategy, Video-Reverse (ViRe), which uses reversed video frames as the model's reconstruction targets. This further encourages the model to utilize continuous motion details and correspondences to complete the reconstruction, thereby enhancing the model's capabilities. Compared to the most advanced pre-training methods, CatMAE achieves a leading level in video segmentation tasks and action recognition tasks.

cs.CV↗

arXiv2023

BESTMVQA: A Benchmark Evaluation System for Medical Visual Question Answering

Medical Visual Question Answering (Med-VQA) is a very important task in healthcare industry, which answers a natural language question with a medical image. Existing VQA techniques in information systems can be directly applied to solving the task. However, they often suffer from (i) the data insufficient problem, which makes it difficult to train the state of the arts (SOTAs) for the domain-specific task, and (ii) the reproducibility problem, that many existing models have not been thoroughly evaluated in a unified experimental setup. To address these issues, this paper develops a Benchmark Evaluation SysTem for Medical Visual Question Answering, denoted by BESTMVQA. Given self-collected clinical data, our system provides a useful tool for users to automatically build Med-VQA datasets, which helps overcoming the data insufficient problem. Users also can conveniently select a wide spectrum of SOTA models from our model library to perform a comprehensive empirical study. With simple configurations, our system automatically trains and evaluates the selected models over a benchmark dataset, and reports the comprehensive results for users to develop new techniques or perform medical practice. Limitations of existing work are overcome (i) by the data generation tool, which automatically constructs new datasets from unstructured clinical data, and (ii) by evaluating SOTAs on benchmark datasets in a unified experimental setup. The demonstration video of our system can be found at https://youtu.be/QkEeFlu1x4A. Our code and data will be available soon.

cs.AI↗

arXiv2023

Towards Robust and Accurate Visual Prompting

Visual prompting, an efficient method for transfer learning, has shown its potential in vision tasks. However, previous works focus exclusively on VP from standard source models, it is still unknown how it performs under the scenario of a robust source model: Whether a visual prompt derived from a robust model can inherit the robustness while suffering from the generalization performance decline, albeit for a downstream dataset that is different from the source dataset? In this work, we get an affirmative answer of the above question and give an explanation on the visual representation level. Moreover, we introduce a novel technique named Prompt Boundary Loose (PBL) to effectively mitigates the suboptimal results of visual prompt on standard accuracy without losing (or even significantly improving) its adversarial robustness when using a robust model as source model. Extensive experiments across various datasets show that our findings are universal and demonstrate the significant benefits of our proposed method.

cs.CV↗

arXiv2023

Instruct Me More! Random Prompting for Visual In-Context Learning

Large-scale models trained on extensive datasets, have emerged as the preferred approach due to their high generalizability across various tasks. In-context learning (ICL), a popular strategy in natural language processing, uses such models for different tasks by providing instructive prompts but without updating model parameters. This idea is now being explored in computer vision, where an input-output image pair (called an in-context pair) is supplied to the model with a query image as a prompt to exemplify the desired output. The efficacy of visual ICL often depends on the quality of the prompts. We thus introduce a method coined Instruct Me More (InMeMo), which augments in-context pairs with a learnable perturbation (prompt), to explore its potential. Our experiments on mainstream tasks reveal that InMeMo surpasses the current state-of-the-art performance. Specifically, compared to the baseline without learnable prompt, InMeMo boosts mIoU scores by 7.35 and 15.13 for foreground segmentation and single object detection tasks, respectively. Our findings suggest that InMeMo offers a versatile and efficient way to enhance the performance of visual ICL with lightweight training. Code is available at https://github.com/Jackieam/InMeMo.

cs.CV↗

arXiv2023

MPrompt: Exploring Multi-level Prompt Tuning for Machine Reading Comprehension

The large language models have achieved superior performance on various natural language tasks. One major drawback of such approaches is they are resource-intensive in fine-tuning new datasets. Soft-prompt tuning presents a resource-efficient solution to fine-tune the pre-trained language models (PLMs) while keeping their weight frozen. Existing soft prompt methods mainly focus on designing the input-independent prompts that steer the model to fit the domain of the new dataset. Those methods often ignore the fine-grained information about the task and context of the text. In this paper, we propose a multi-level prompt tuning (MPrompt) method for machine reading comprehension. It utilizes prompts at task-specific, domain-specific, and context-specific levels to enhance the comprehension of input semantics at different granularities. We also propose an independence constraint to steer each domain-specific prompt to focus on information within its domain to avoid redundancy. Moreover, we present a prompt generator that incorporates context-related knowledge in the prompt generation to enhance contextual relevancy. We conducted extensive experiments on 12 benchmarks of various QA formats and achieved an average improvement of 1.94\% over the state-of-the-art methods.

cs.CL↗

arXiv2023

CARE-MI: Chinese Benchmark for Misinformation Evaluation in Maternity and Infant Care

The recent advances in natural language processing (NLP), have led to a new trend of applying large language models (LLMs) to real-world scenarios. While the latest LLMs are astonishingly fluent when interacting with humans, they suffer from the misinformation problem by unintentionally generating factually false statements. This can lead to harmful consequences, especially when produced within sensitive contexts, such as healthcare. Yet few previous works have focused on evaluating misinformation in the long-form (LF) generation of LLMs, especially for knowledge-intensive topics. Moreover, although LLMs have been shown to perform well in different languages, misinformation evaluation has been mostly conducted in English. To this end, we present a benchmark, CARE-MI, for evaluating LLM misinformation in: 1) a sensitive topic, specifically the maternity and infant care domain; and 2) a language other than English, namely Chinese. Most importantly, we provide an innovative paradigm for building LF generation evaluation benchmarks that can be transferred to other knowledge-intensive domains and low-resourced languages. Our proposed benchmark fills the gap between the extensive usage of LLMs and the lack of datasets for assessing the misinformation generated by these models. It contains 1,612 expert-checked questions, accompanied with human-selected references. Using our benchmark, we conduct extensive experiments and found that current Chinese LLMs are far from perfect in the topic of maternity and infant care. In an effort to minimize the reliance on human resources for performance evaluation, we offer off-the-shelf judgment models for automatically assessing the LF output of LLMs given benchmark questions. Moreover, we compare potential solutions for LF generation evaluation and provide insights for building better automated metrics.

cs.CL↗

arXiv2023

TCRA-LLM: Token Compression Retrieval Augmented Large Language Model for Inference Cost Reduction

Since ChatGPT released its API for public use, the number of applications built on top of commercial large language models (LLMs) increase exponentially. One popular usage of such models is leveraging its in-context learning ability and generating responses given user queries leveraging knowledge obtained by retrieval augmentation. One problem of deploying commercial retrieval-augmented LLMs is the cost due to the additionally retrieved context that largely increases the input token size of the LLMs. To mitigate this, we propose a token compression scheme that includes two methods: summarization compression and semantic compression. The first method applies a T5-based model that is fine-tuned by datasets generated using self-instruct containing samples with varying lengths and reduce token size by doing summarization. The second method further compresses the token size by removing words with lower impact on the semantic. In order to adequately evaluate the effectiveness of the proposed methods, we propose and utilize a dataset called Food-Recommendation DB (FRDB) focusing on food recommendation for women around pregnancy period or infants. Our summarization compression can reduce 65% of the retrieval token size with further 0.3% improvement on the accuracy; semantic compression provides a more flexible way to trade-off the token size with performance, for which we can reduce the token size by 20% with only 1.6% of accuracy drop.

cs.CL↗