Author name cluster

Da Li

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

12 papers

2 author rows

AAAI Conference 2026 Conference Paper

HierarchicalPrune: Position-Aware Compression for Large-Scale Diffusion Models

Young D. Kwon
Rui Li
Sijia Li
Da Li
Sourav Bhattacharya
Stylianos I. Venieris

State-of-the-art text-to-image diffusion models (DMs) achieve remarkable quality, yet their massive parameter scale (8-11B) poses significant challenges for inferences on resource-constrained devices. In this paper, we present HierarchicalPrune, a novel compression framework grounded in a key observation: DM blocks exhibit distinct functional hierarchies, where early blocks establish semantic structures while later blocks handle texture refinements. HierarchicalPrune synergistically combines three techniques: (1) Hierarchical Position Pruning, which identifies and removes less essential later blocks based on position hierarchy; (2) Positional Weight Preservation, which systematically protects early model portions that are essential for semantic structural integrity; and (3) Sensitivity-Guided Distillation, which adjusts knowledge-transfer intensity based on our discovery of block-wise sensitivity variations. As a result, our framework brings billion-scale diffusion models into a range more suitable for on-device inference, while preserving the quality of the output images. Specifically, combined with INT4 weight quantisation, HierarchicalPrune achieves 77.5-80.4% memory footprint reduction (e.g., from 15.8 GB to 3.2 GB) and 27.9-38.0% latency reduction, measured on server and consumer grade GPUs, with the minimum drop of 2.6% in GenEval score and 7% in HPSv2 score compared to the original model. Finally, our comprehensive user study with 85 participants demonstrates that HierarchicalPrune maintains perceptual quality comparable to the original model while significantly outperforming prior works.

PDF Details DOI

AAAI Conference 2026 Conference Paper

One-Step Generative Policies with Q-Learning: A Reformulation of MeanFlow

Zeyuan Wang
Da Li
Yulin Chen
Ye Shi
Liang Bai
Tianyuan Yu
Yanwei Fu

We introduce a one-step generative policy for offline reinforcement learning that maps *noise* directly to *actions* via a *residual reformulation* of MeanFlow, making it compatible with Q-learning. While one-step Gaussian policies enable fast inference, they struggle to capture complex, multimodal action distributions. Existing flow-based methods improve expressivity but typically rely on distillation and two-stage training when trained with Q-learning. To overcome these limitations, we propose to reformulate MeanFlow to enable *direct noise-to-action generation* by integrating the velocity field and noise-to-action transformation into a single policy network—eliminating the need for separate velocity estimation. We explore several reformulation variants and identify an effective *residual formulation* that supports expressive and stable policy learning. Our method offers three key advantages: 1) efficient one-step noise-to-action generation, 2) expressive modelling of multimodal action distributions, and 3) efficient and stable policy learning via Q-learning in a single-stage training setup. Extensive experiments on 73 tasks across the OGBench and D4RL benchmarks demonstrate that our method achieves strong performance in both offline and offline-to-online reinforcement learning settings.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Run, Ruminate, and Regulate: A Dual-process Thinking System for Vision-and-Language Navigation

Yu Zhong
Zihao Zhang
Rui Zhang
Lingdong Huang
Haihan Gao
Shuo Wang
Da Li
Ruijian Han

Vision-and-Language Navigation (VLN) requires an agent to dynamically explore complex 3D environments following human instructions. Recent research underscores the potential of harnessing large language models (LLMs) for VLN, given their commonsense knowledge and general reasoning capabilities. Despite their strengths, a substantial gap in task completion performance persists between LLM-based approaches and domain experts, as LLMs inherently struggle to comprehend real-world spatial correlations precisely; additionally, LLM inference can make the decision-making process considerably inefficient. To address these issues, we propose a novel dual-process thinking framework dubbed R3, integrating LLMs' generalization capabilities with VLN-specific expertise in a zero-shot manner. The framework comprises three core modules: Runner, Ruminator, and Regulator. The Runner is a lightweight transformer-based expert model that ensures efficient and accurate navigation under regular circumstances. The Ruminator employs a multimodal LLM as the backbone and adopts chain-of-thought (CoT) prompting to elicit structured reasoning from the LLM. The Regulator monitors the navigation progress and controls the appropriate thinking mode according to three criteria, integrating Runner and Ruminator harmoniously. Experimental results illustrate that R3 significantly outperforms other state-of-the-art methods, exceeding 3.28% and 3.30% in SPL and RGSPL respectively on the REVERIE benchmark, highlighting the effectiveness of our method in handling challenging VLN tasks.

PDF Details DOI

ICML Conference 2025 Conference Paper

Optimal Information Retention for Time-Series Explanations

Jinghang Yue
Jing Wang 0060
Lu Zhang
Shuo Zhang 0015
Da Li
Zhaoyang Ma
Youfang Lin

Explaining deep models for time-series data is crucial for identifying key patterns in sensitive domains, such as healthcare and finance. However, due to the lack of unified optimization criterion, existing explanation methods often suffer from redundancy and incompleteness, where irrelevant patterns are included or key patterns are missed in explanations. To address this challenge, we propose the Optimal Information Retention Principle, where conditional mutual information defines minimizing redundancy and maximizing completeness as optimization objectives. We then derive the corresponding objective function theoretically. As a practical framework, we introduce an explanation framework ORTE, learning a binary mask to eliminate redundant information while mining temporal patterns of explanations. We decouple the discrete mapping process to ensure the stability of gradient propagation, while employing contrastive learning to achieve precise filtering of explanatory patterns through the mask, thereby realizing a trade-off between low redundancy and high completeness. Extensive quantitative and qualitative experiments on synthetic and real-world datasets demonstrate that the proposed principle significantly improves the accuracy and completeness of explanations compared to baseline methods. The code is available at https: //github. com/moon2yue/ORTE_public.

Details

TMLR Journal 2025 Journal Article

TFAR: A Training-Free Framework for Autonomous Reliable Reasoning in Visual Question Answering

Zhuo Zhi
Chen Feng
Adam Daneshmend
Mine Orlu
Andreas Demosthenous
Lu Yin
Da Li
Ziquan Liu

Recent approaches introduce chain-of-thought (CoT) reasoning to mitigate the challenges, such as hallucination and reasoning deficit in multimodal large language models (MLLMs) and enhance performance. However, existing CoT-based methods often rely on extensive data annotation and training. To overcome these limitations, we propose a training-free framework for autonomous and reliable reasoning (TFAR), which only uses common lightweight vision tools to improve the reasoning ability of MLLMs. TFAR enables an MLLM to autonomously and accurately identify relevant regions of interest (RoIs) and support CoT reasoning, without requiring additional training or annotations, and with low computational overhead during inference. However, the use of external tools will introduce noise and uncertainty. To mitigate the uncertainty introduced by external tools and select the optimal pathway, we propose a conformal prediction-based uncertainty quantification method that calibrates the outputs from external tools and dynamically selects the most appropriate tool based on the MLLM’s output uncertainty. Experiments across five datasets demonstrate that TFAR improves performance over the base MLLM by an average of 4.6$\%$, in some cases even outperforming fine-tuned baselines, while maintaining low inference cost. These results offer new insights into training-free CoT guidance for MLLMs and underscore the value of reliable visual tools.

PDF Details

ECAI Conference 2024 Conference Paper

Adapt PointFormer: 3D Point Cloud Analysis via Adapting 2D Visual Transformers

Mengke Li 0001
Da Li
Guoqing Yang
Yiu-ming Cheung
Hui Huang 0004

Pre-trained large-scale models have exhibited remarkable efficacy in computer vision, particularly for 2D image analysis. However, when it comes to 3D point clouds, the constrained accessibility of data, in contrast to the vast repositories of images, poses a challenge for the development of 3D pre-trained models. This paper therefore attempts to directly leverage pre-trained models with 2D prior knowledge to accomplish the tasks for 3D point cloud analysis. Accordingly, we propose the Adaptive PointFormer (APF), which fine-tunes pre-trained 2D models with only a modest number of parameters to directly process point clouds, obviating the need for mapping to images. Specifically, we convert raw point clouds into point embeddings for aligning dimensions with image tokens. Given the inherent disorder in point clouds, in contrast to the structured nature of images, we then sequence the point embeddings to optimize the utilization of 2D attention priors. To calibrate attention across 3D and 2D domains and reduce computational overhead, a trainable PointFormer with a limited number of parameters is subsequently concatenated to a frozen pre-trained image model. Extensive experiments on various benchmarks demonstrate the effectiveness of the proposed APF. The source code and more details are available at https: //vcc. tech/research/2024/PointFormer.

Details

EAAI Journal 2024 Journal Article

An algorithm for extracting similar segments of moving target trajectories based on shape matching

Zhihong Ouyang
Lei Xue
Feng Ding
Da Li

Trajectory similarity analysis of moving target is the foundation for mining high-value and regular behavioral information such as motion preferences, activity hotspots and frequent paths. Unlike most trajectory similarity analysis methods aimed at discovering correlations of target activities in time, space or spatio-temporal domains, this paper focuses on the shape matching of target trajectories. If some specific shapes frequently appear in historical trajectories, extracting these local shapes would be beneficial for analyzing the target motion templates and behavior modes. Trajectory segments with similar shapes may not have spatio-temporal correlation, and the shapes also have geometric transformation characteristics such as rotation, scaling and translation. Since the existing trajectory similarity analysis methods cannot be directly applied, an algorithm for extracting similar segments based on shape matching is proposed. First, a new shape descriptor based on signed barycenter distance (SBD) is established. It describes a trajectory as a one-dimensional shape feature sequence, which has the advantage of low computational complexity. Then, the distributed nearest neighbor search strategy is used in the particle swarm optimization (PSO) method, which aims to accelerate the retrieval of trajectory segments with similar shapes and improve the matching accuracy. Experiments on MPEG-7, handwritten character and maneuvering target simulation trajectory data sets show that compared with the existing typical shape descriptors, SBD shape descriptor has advantages in accuracy and noise insensitivity, and the improved PSO method can efficiently and accurately obtain the local shape matching results.

Details DOI

NeurIPS Conference 2023 Conference Paper

FedL2P: Federated Learning to Personalize

Royson Lee
Minyoung Kim
Da Li
Xinchi Qiu
Timothy Hospedales
Ferenc Huszar
Nicholas Lane

Federated learning (FL) research has made progress in developing algorithms for distributed learning of global models, as well as algorithms for local personalization of those common models to the specifics of each client’s local data distribution. However, different FL problems may require different personalization strategies, and it may not even be possible to define an effective one-size-fits-all personalization strategy for all clients: Depending on how similar each client’s optimal predictor is to that of the global model, different personalization strategies may be preferred. In this paper, we consider the federated meta-learning problem of learning personalization strategies. Specifically, we consider meta-nets that induce the batch-norm and learning rate parameters for each client given local data statistics. By learning these meta-nets through FL, we allow the whole FL network to collaborate in learning a customized personalization strategy for each client. Empirical results show that this framework improves on a range of standard hand-crafted personalization baselines in both label and feature shift situations.

PDF Details

TMLR Journal 2023 Journal Article

Worst-case Feature Risk Minimization for Data-Efficient Learning

Jingshi Lei
Da Li
Chengming Xu
Liming Fang
Timothy Hospedales
Yanwei Fu

Deep learning models typically require massive amounts of annotated data to train a strong model for a task of interest. However, data annotation is time-consuming and costly. How to use labeled data from a related but distinct domain, or just a few samples to train a satisfactory model are thus important questions. To achieve this goal, models should resist overfitting to the specifics of the training data in order to generalize well to new data. This paper proposes a novel Worst-case Feature Risk Minimization (WFRM) method that helps improve model generalization. Specifically, we tackle a minimax optimization problem in feature space at each training iteration. Given the input features, we seek the feature perturbation that maximizes the current training loss and then minimizes the training loss of the worst-case features. By incorporating our WFRM during training, we significantly improve model generalization under distributional shift – Domain Generalization (DG) and in the low-data regime – Few-shot Learning (FSL). We theoretically analyze WFRM and find the key reason why it works better than ERM – it induces an empirical risk-based semi-adaptive $L_{2}$ regularization of the classifier weights, enabling a better risk-complexity trade-off. We evaluate WFRM on two data-efficient learning tasks, including three standard DG benchmarks of PACS, VLCS, OfficeHome and the most challenging FSL benchmark Meta-Dataset. Despite the simplicity, our method consistently improves various DG and FSL methods, leading to the new state-of-the-art performances in all settings. Codes & models will be released at https://github.com/jslei/WFRM.

PDF Details

NeurIPS Conference 2021 Conference Paper

A Channel Coding Benchmark for Meta-Learning

Rui Li
Ondrej Bohdal
Rajesh K Mishra
Hyeji Kim
Da Li
Nicholas Lane
Timothy Hospedales

Meta-learning provides a popular and effective family of methods for data-efficient learning of new tasks. However, several important issues in meta-learning have proven hard to study thus far. For example, performance degrades in real-world settings where meta-learners must learn from a wide and potentially multi-modal distribution of training tasks; and when distribution shift exists between meta-train and meta-test task distributions. These issues are typically hard to study since the shape of task distributions, and shift between them are not straightforward to measure or control in standard benchmarks. We propose the channel coding problem as a benchmark for meta-learning. Channel coding is an important practical application where task distributions naturally arise, and fast adaptation to new tasks is practically valuable. We use this benchmark to study several aspects of meta-learning, including the impact of task distribution breadth and shift on meta-learner performance, which can be controlled in the coding problem. Going forward, this benchmark provides a tool for the community to study the capabilities and limitations of meta-learning, and to drive research on practically robust and effective meta-learners.

PDF Details

AAAI Conference 2021 Conference Paper

Simple and Effective Stochastic Neural Networks

Tianyuan Yu
Yongxin Yang
Da Li
Timothy Hospedales
Tao Xiang

Stochastic neural networks (SNNs) are currently topical, with several paradigms being actively investigated including dropout, Bayesian neural networks, variational information bottleneck (VIB) and noise regularized learning. These neural network variants impact several major considerations, including generalization, network compression, robustness against adversarial attack and label noise, and model calibration. However, many existing networks are complicated and expensive to train, and/or only address one or two of these practical considerations. In this paper we propose a simple and effective stochastic neural network (SE-SNN) architecture for discriminative learning by directly modeling activation uncertainty and encouraging high activation variability. Compared to existing SNNs, our SE-SNN is simpler to implement and faster to train, and produces state of the art results on network compression by pruning, adversarial defense, learning with label noise, and model calibration.

PDF Details

AAAI Conference 2018 Conference Paper

Learning to Generalize: Meta-Learning for Domain Generalization

Da Li
Yongxin Yang
Yi-Zhe Song
Timothy Hospedales

Domain shift refers to the well known problem that a model trained in one source domain performs poorly when applied to a target domain with different statistics. Domain Generalization (DG) techniques attempt to alleviate this issue by producing models which by design generalize well to novel testing domains. We propose a novel meta-learning method for domain generalization. Rather than designing a speciﬁc model that is robust to domain shift as in most previous DG work, we propose a model agnostic training procedure for DG. Our algorithm simulates train/test domain shift during training by synthesizing virtual testing domains within each mini-batch. The meta-optimization objective requires that steps to improve training domain performance should also improve testing domain performance. This meta-learning procedure trains models with good generalization ability to novel domains. We evaluate our method and achieve state of the art results on a recent cross-domain image classiﬁcation benchmark, as well demonstrating its potential on two classic reinforcement learning tasks.

PDF Details