arXiv subjects

Tong Wei

Publications and source records attributed to Tong Wei.

At least 37 records · Page 2Linked to original sources

arXiv2026

KeepLoRA: Continual Learning with Residual Gradient Adaptation

Continual learning for pre-trained vision-language models requires balancing three competing objectives: retaining pre-trained knowledge, preserving knowledge from a sequence of learned tasks, and maintaining the plasticity to acquire new knowledge. This paper presents a simple but effective approach called KeepLoRA to effectively balance these objectives. We first analyze the knowledge retention mechanism within the model parameter space and find that general knowledge is mainly encoded in the principal subspace, while task-specific knowledge is encoded in the residual subspace. Motivated by this finding, KeepLoRA learns new tasks by restricting LoRA parameter updates in the residual subspace to prevent interfering with previously learned capabilities. Specifically, we infuse knowledge for a new task by projecting its gradient onto a subspace orthogonal to both the principal subspace of pre-trained model and the dominant directions of previous task features. Our theoretical and empirical analyses confirm that KeepLoRA balances the three objectives and achieves state-of-the-art performance. The implementation code is available at https://github.com/MaolinLuo/KeepLoRA.

cs.CV↗

arXiv2025

Fundamental Limits for Near-Field Sensing -- Part I: Narrow-Band Systems

Extremely large-scale antenna arrays (ELAAs) envisioned for 6G enable high-resolution sensing. However, the ELAAs worked in extremely high frequency will push operation into the near-field region, where spherical wavefronts invalidate classical far-field models and alter fundamental estimation limits. The purpose of this and the companion paper (Part II) is to develop the theory of fundamental limits for near-field sensing systems in detail. In this paper (Part I), we develop a unified narrow-band near-field signal model for joint parameter sensing of moving targets using the ELAAs. Leveraging the Slepian--Bangs formulation, we derive closed-form Cram'er--Rao bounds (CRBs) for joint estimation of target position, velocity, and radar cross-section (RCS) under the slow-time sampling model. To obtain interpretable insights, we further establish explicit far-field and near-field approximations that reveal how the bounds scale with array aperture, target range, carrier wavelength, and coherent integration length. The resulting expressions expose the roles of self-information terms and their cross terms, clarifying when Fresnel corrections become non-negligible and providing beamformer and algorithm design guidelines for near-field sensing with ELAAs. Simulation results validate the derived CRBs and their far-field and near-field approximations, demonstrating accurate agreement with the analytical scaling laws across representative array sizes and target ranges.

eess.SP↗

arXiv2025

Fundamental Limits for Near-Field Sensing -- Part II: Wide-Band Systems

Near-field sensing with extremely large-scale antenna arrays (ELAAs) in practical 6G systems is expected to operate over broad bandwidths, where delay, Doppler, and spatial effects become tightly coupled across frequency. The purpose of this and the companion paper (Part I) is to develop the unified Cram'er--Rao bounds (CRBs) for sensing systems spanning from far-field to near-field, and narrow-band to wide-band. This paper (Part II) derives fundamental estimation limits for a wide-band near-field sensing systems employing orthogonal frequency-division multiplexing signaling over a coherent processing interval. We establish an exact near-field wide-band signal model that captures frequency-dependent propagation, spherical-wave geometry, and the intrinsic coupling between target location and motion parameters across subcarriers and slow time. Similar as Part I using the Slepian--Bangs formulation, we derive the wide-band Fisher information matrix and the CRBs for joint estimation of target position, velocity, and radar cross-section, and we show how wide-band information aggregates across orthogonal subcarriers. We further develop tractable far-field and near-field approximations which provide design-level insights into the roles of bandwidth, coherent integration length, and array aperture, and clarify when wide-band effects. Simulation results validate the derived CRBs and its approximations, demonstrating close agreement with the analytical scaling laws across representative ranges, bandwidths, and array configurations.

eess.SP↗

arXiv2025

Unleashing the Power of Vision-Language Models for Long-Tailed Multi-Label Visual Recognition

Long-tailed multi-label visual recognition poses a significant challenge, as images typically contain multiple labels with highly imbalanced class distributions, leading to biased models that favor head classes while underperforming on tail classes. Recent efforts have leveraged pre-trained vision-language models, such as CLIP, alongside long-tailed learning techniques to exploit rich visual-textual priors for improved performance. However, existing methods often derive semantic inter-class relationships directly from imbalanced datasets, resulting in unreliable correlations for tail classes due to data scarcity. Moreover, CLIP's zero-shot paradigm is optimized for single-label image-text matching, making it suboptimal for multi-label tasks. To address these issues, we propose the correlation adaptation prompt network (CAPNET), a novel end-to-end framework that explicitly models label correlations from CLIP's textual encoder. The framework incorporates a graph convolutional network for label-aware propagation and learnable soft prompts for refined embeddings. It utilizes a distribution-balanced Focal loss with class-aware re-weighting for optimized training under imbalance. Moreover, it improves generalization through test-time ensembling and realigns visual-textual modalities using parameter-efficient fine-tuning to avert overfitting on tail classes without compromising head class performance. Extensive experiments and ablation studies on benchmarks including VOC-LT, COCO-LT, and NUS-WIDE demonstrate that CAPNET achieves substantial improvements over state-of-the-art methods, validating its effectiveness for real-world long-tailed multi-label visual recognition.

cs.CV↗

arXiv2025

TSPE-GS: Probabilistic Depth Extraction for Semi-Transparent Surface Reconstruction via 3D Gaussian Splatting

3D Gaussian Splatting offers a strong speed-quality trade-off but struggles to reconstruct semi-transparent surfaces because most methods assume a single depth per pixel, which fails when multiple surfaces are visible. We propose TSPE-GS (Transparent Surface Probabilistic Extraction for Gaussian Splatting), which uniformly samples transmittance to model a pixel-wise multi-modal distribution of opacity and depth, replacing the prior single-peak assumption and resolving cross-surface depth ambiguity. By progressively fusing truncated signed distance functions, TSPE-GS reconstructs external and internal surfaces separately within a unified framework. The method generalizes to other Gaussian-based reconstruction pipelines without extra training overhead. Extensive experiments on public and self-collected semi-transparent and opaque datasets show TSPE-GS significantly improves semi-transparent geometry reconstruction while maintaining performance on opaque scenes.

cs.CV↗

arXiv2025

Unlabeled Data vs. Pre-trained Knowledge: Rethinking SSL in the Era of Large Models

Semi-supervised learning (SSL) alleviates the cost of data labeling process by exploiting unlabeled data and has achieved promising results. Meanwhile, with the development of large foundation models, exploiting pre-trained models becomes a promising way to address the label scarcity in the downstream tasks, such as various parameter-efficient fine-tuning techniques. This raises a natural yet critical question: When labeled data is limited, should we rely on unlabeled data or pre-trained models? To investigate this issue, we conduct a fair comparison between SSL methods and pre-trained models (e.g., CLIP) on representative image classification tasks under a controlled supervision budget. Experiments reveal that SSL has met its ``Waterloo" in the era of large models, as pre-trained models show both high efficiency and strong performance on widely adopted SSL benchmarks. This underscores the urgent need for SSL researchers to explore new avenues, such as deeper integration between the SSL and pre-trained models. Furthermore, we investigate the potential of Multi-Modal Large Language Models (MLLMs) in image classification tasks. Results show that, despite their massive parameter scales, MLLMs still face significant performance limitations, highlighting that even a seemingly well-studied task remains highly challenging.

cs.LG↗

arXiv2025

Adaptive Divergence Regularized Policy Optimization for Fine-tuning Generative Models

Balancing exploration and exploitation during reinforcement learning fine-tuning of generative models presents a critical challenge, as existing approaches rely on fixed divergence regularization that creates an inherent dilemma: strong regularization preserves model capabilities but limits reward optimization, while weak regularization enables greater alignment but risks instability or reward hacking. We introduce Adaptive Divergence Regularized Policy Optimization (ADRPO), which automatically adjusts regularization strength based on advantage estimates-reducing regularization for high-value samples while applying stronger regularization to poor samples, enabling policies to navigate between exploration and aggressive exploitation according to data quality. Our implementation with Wasserstein-2 regularization for flow matching generative models achieves remarkable results on text-to-image generation, achieving better semantic alignment and diversity than offline methods like DPO and online methods with fixed regularization like ORW-CFM-W2. ADRPO enables a 2B parameter SD3 model to surpass much larger models with 4.8B and 12B parameters in attribute binding, semantic consistency, artistic style transfer, and compositional control while maintaining generation diversity. ADRPO generalizes to KL-regularized fine-tuning of both text-only LLMs and multi-modal reasoning models, enhancing existing online RL methods like GRPO. In LLM fine-tuning, ADRPO demonstrates an emergent ability to escape local optima through active exploration, while in multi-modal audio reasoning, it outperforms GRPO through superior step-by-step reasoning, enabling a 7B model to outperform substantially larger commercial models including Gemini 2.5 Pro and GPT-4o Audio, offering an effective plug-and-play solution to the exploration-exploitation challenge across diverse generative architectures and modalities.

cs.LG↗

arXiv2025

Memory-Efficient Fine-Tuning via Low-Rank Activation Compression

The parameter-efficient fine-tuning paradigm has garnered significant attention with the advancement of foundation models. Although numerous methods have been proposed to reduce the number of trainable parameters, their substantial memory overhead remains a critical bottleneck that hinders practical deployment. In this paper, we observe that model activations constitute a major source of memory consumption, especially under large batch sizes and long context lengths; however, the rank of the activations remains consistently low. Motivated by this insight, we propose a memory-efficient fine-tuning approach Low-Rank Activation Compression (LoRAct). Unlike prior work, LoRAct provides a more flexible and versatile compressing strategy that can be applied online during the forward pass without the need for any calibration data. Moreover, LoRAct incorporates a novel sampling-based orthogonal decomposition algorithm specifically designed for low-rank matrices, offering improved computational efficiency and a tighter error bound compared to the widely used RSVD. Experiments on both vision and language tasks demonstrate the effectiveness of LoRAct. Notably, LoRAct further reduces activation memory by approximately 80% in comparison with the widely adopted LoRA method, while maintaining competitive performance. The source code is available at https://github.com/shijxcs/meft.

cs.LG↗

arXiv2025

GTR: Guided Thought Reinforcement Prevents Thought Collapse in RL-based VLM Agent Training

Reinforcement learning with verifiable outcome rewards (RLVR) has effectively scaled up chain-of-thought (CoT) reasoning in large language models (LLMs). Yet, its efficacy in training vision-language model (VLM) agents for goal-directed action reasoning in visual environments is less established. This work investigates this problem through extensive experiments on complex card games, such as 24 points, and embodied tasks from ALFWorld. We find that when rewards are based solely on action outcomes, RL fails to incentivize CoT reasoning in VLMs, instead leading to a phenomenon we termed thought collapse, characterized by a rapid loss of diversity in the agent's thoughts, state-irrelevant and incomplete reasoning, and subsequent invalid actions, resulting in negative rewards. To counteract thought collapse, we highlight the necessity of process guidance and propose an automated corrector that evaluates and refines the agent's reasoning at each RL step. This simple and scalable GTR (Guided Thought Reinforcement) framework trains reasoning and action simultaneously without the need for dense, per-step human labeling. Our experiments demonstrate that GTR significantly enhances the performance and generalization of the LLaVA-7b model across various visual environments, achieving 3-5 times higher task success rates compared to SoTA models with notably smaller model sizes.

cs.CV↗

arXiv2025

Tuning the Right Foundation Models is What you Need for Partial Label Learning

Partial label learning (PLL) seeks to train generalizable classifiers from datasets with inexact supervision, a common challenge in real-world applications. Existing studies have developed numerous approaches to progressively refine and recover ground-truth labels by training convolutional neural networks. However, limited attention has been given to foundation models that offer transferrable representations. In this work, we empirically conduct comprehensive evaluations of 11 foundation models across 13 PLL approaches on 8 benchmark datasets under 3 PLL scenarios. We further propose PartialCLIP, an efficient fine-tuning framework for foundation models in PLL. Our findings reveal that current PLL approaches tend to 1) achieve significant performance gains when using foundation models, 2) exhibit remarkably similar performance to each other, 3) maintain stable performance across varying ambiguity levels, while 4) are susceptible to foundation model selection and adaptation strategies. Additionally, we demonstrate the efficacy of text-embedding classifier initialization and effective candidate label filtering using zero-shot CLIP. Our experimental results and analysis underscore the limitations of current PLL approaches and provide valuable insights for developing more generalizable PLL models. The source code can be found at https://github.com/SEU-hk/PartialCLIP.

cs.LG↗

arXiv2025

LADA: Scalable Label-Specific CLIP Adapter for Continual Learning

Continual learning with vision-language models like CLIP offers a pathway toward scalable machine learning systems by leveraging its transferable representations. Existing CLIP-based methods adapt the pre-trained image encoder by adding multiple sets of learnable parameters, with each task using a partial set of parameters. This requires selecting the expected parameters for input images during inference, which is prone to error that degrades performance. To address this problem, we introduce LADA (Label-specific ADApter). Instead of partitioning parameters across tasks, LADA appends lightweight, label-specific memory units to the frozen CLIP image encoder, enabling discriminative feature generation by aggregating task-agnostic knowledge. To prevent catastrophic forgetting, LADA employs feature distillation for seen classes, preventing their features from being interfered with by new classes. Positioned after the image encoder, LADA prevents gradient flow to the frozen CLIP parameters, ensuring efficient training. Extensive results show that LADA achieves state-of-the-art performance in continual learning settings. The implementation code is available at https://github.com/MaolinLuo/LADA.

cs.CV↗

arXiv2025

Weakly-Supervised Contrastive Learning for Imprecise Class Labels

Contrastive learning has achieved remarkable success in learning effective representations, with supervised contrastive learning often outperforming self-supervised approaches. However, in real-world scenarios, data annotations are often ambiguous or inaccurate, meaning that class labels may not reliably indicate whether two examples belong to the same class. This limitation restricts the applicability of supervised contrastive learning. To address this challenge, we introduce the concept of ``continuous semantic similarity'' to define positive and negative pairs. Instead of directly relying on imprecise class labels, we measure the semantic similarity between example pairs, which quantifies how closely they belong to the same category by iteratively refining weak supervisory signals. Based on this concept, we propose a graph-theoretic framework for weakly-supervised contrastive learning, where semantic similarity serves as the graph weights. Our framework is highly versatile and can be applied to many weakly-supervised learning scenarios. We demonstrate its effectiveness through experiments in two common settings, i.e., noisy label and partial label learning, where existing methods can be easily integrated to significantly improve performance. Theoretically, we establish an error bound for our approach, showing that it can approximate supervised contrastive learning under mild conditions. The implementation code is available at https://github.com/Speechless-10308/WSC.

cs.LG↗

arXiv2025

LIFT+: Lightweight Fine-Tuning for Long-Tail Learning

The fine-tuning paradigm has emerged as a prominent approach for addressing long-tail learning tasks in the era of foundation models. However, the impact of fine-tuning strategies on long-tail learning performance remains unexplored. In this work, we disclose that existing paradigms exhibit a profound misuse of fine-tuning methods, leaving significant room for improvement in both efficiency and accuracy. Specifically, we reveal that heavy fine-tuning (fine-tuning a large proportion of model parameters) can lead to non-negligible performance deterioration on tail classes, whereas lightweight fine-tuning demonstrates superior effectiveness. Through comprehensive theoretical and empirical validation, we identify this phenomenon as stemming from inconsistent class conditional distributions induced by heavy fine-tuning. Building on this insight, we propose LIFT+, an innovative lightweight fine-tuning framework to optimize consistent class conditions. Furthermore, LIFT+ incorporates semantic-aware initialization, minimalist data augmentation, and test-time ensembling to enhance adaptation and generalization of foundation models. Our framework provides an efficient and accurate pipeline that facilitates fast convergence and model compactness. Extensive experiments demonstrate that LIFT+ significantly reduces both training epochs (from $\sim$100 to $\leq$15) and learned parameters (less than 1%), while surpassing state-of-the-art approaches by a considerable margin. The source code is available at https://github.com/shijxcs/LIFT-plus.

cs.CV↗

arXiv2024

Optimal and Efficient Algorithms for Decentralized Online Convex Optimization

We investigate decentralized online convex optimization (D-OCO), in which a set of local learners are required to minimize a sequence of global loss functions using only local computations and communications. Previous studies have established $O(n^{5/4}ρ^{-1/2}\sqrt{T})$ and ${O}(n^{3/2}ρ^{-1}\log T)$ regret bounds for convex and strongly convex functions respectively, where $n$ is the number of local learners, $ρ<1$ is the spectral gap of the communication matrix, and $T$ is the time horizon. However, there exist large gaps from the existing lower bounds, i.e., $Ω(n\sqrt{T})$ for convex functions and $Ω(n)$ for strongly convex functions. To fill these gaps, in this paper, we first develop a novel D-OCO algorithm that can respectively reduce the regret bounds for convex and strongly convex functions to $\tilde{O}(nρ^{-1/4}\sqrt{T})$ and $\tilde{O}(nρ^{-1/2}\log T)$. The primary technique is to design an online accelerated gossip strategy that enjoys a faster average consensus among local learners. Furthermore, by carefully exploiting spectral properties of a specific network topology, we enhance the lower bounds for convex and strongly convex functions to $Ω(nρ^{-1/4}\sqrt{T})$ and $Ω(nρ^{-1/2}\log T)$, respectively. These results suggest that the regret of our algorithm is nearly optimal in terms of $T$, $n$, and $ρ$ for both convex and strongly convex functions. Finally, we propose a projection-free variant of our algorithm to efficiently handle practical applications with complex constraints. Our analysis reveals that the projection-free variant can achieve ${O}(nT^{3/4})$ and ${O}(nT^{2/3}(\log T)^{1/3})$ regret bounds for convex and strongly convex functions with nearly optimal $\tilde{O}(ρ^{-1/2}\sqrt{T})$ and $\tilde{O}(ρ^{-1/2}T^{1/3}(\log T)^{2/3})$ communication rounds, respectively.

cs.LG↗

arXiv2024

Breaking the Frame: Visual Place Recognition by Overlap Prediction

Visual place recognition methods struggle with occlusions and partial visual overlaps. We propose a novel visual place recognition approach based on overlap prediction, called VOP, shifting from traditional reliance on global image similarities and local features to image overlap prediction. VOP proceeds co-visible image sections by obtaining patch-level embeddings using a Vision Transformer backbone and establishing patch-to-patch correspondences without requiring expensive feature detection and matching. Our approach uses a voting mechanism to assess overlap scores for potential database images. It provides a nuanced image retrieval metric in challenging scenarios. Experimental results show that VOP leads to more accurate relative pose estimation and localization results on the retrieved image pairs than state-of-the-art baselines on a number of large-scale, real-world indoor and outdoor benchmarks. The code is available at https://github.com/weitong8591/vop.git.

cs.CV↗

arXiv2024

Revisiting Discrete Soft Actor-Critic

We study the adaption of Soft Actor-Critic (SAC), which is considered as a state-of-the-art reinforcement learning (RL) algorithm, from continuous action space to discrete action space. We revisit vanilla discrete SAC and provide an in-depth understanding of its Q value underestimation and performance instability issues when applied to discrete settings. We thereby propose Stable Discrete SAC (SDSAC), an algorithm that leverages entropy-penalty and double average Q-learning with Q-clip to address these issues. Extensive experiments on typical benchmarks with discrete action space, including Atari games and a large-scale MOBA game, show the efficacy of our proposed method. Our code is at: https://github.com/coldsummerday/SD-SAC.git.

cs.LG↗

arXiv2024

Dual-Valued Functions of Dual Matrices with Applications in Causal Emergence

Dual continuation, an innovative insight into extending the real-valued functions of real matrices to the dual-valued functions of dual matrices with a foundation of the Gâteaux derivative, is proposed. Theoretically, the general forms of dual-valued vector and matrix norms, the remaining properties in the real field, are provided. In particular, we focus on the dual-valued vector $p$-norm $(1\!\leq\! p\!\leq\!\infty)$ and the unitarily invariant dual-valued Ky Fan $p$-$k$-norm $(1\!\leq\! p\!\leq\!\infty)$. The equivalence between the dual-valued Ky Fan $p$-$k$-norm and the dual-valued vector $p$-norm of the first $k$ singular values of the dual matrix is then demonstrated. Practically, we define the dual transitional probability matrix (DTPM), as well as its dual-valued effective information (${\rm{EI_d}}$). Additionally, we elucidate the correlation between the ${\rm{EI_d}}$, the dual-valued Schatten $p$-norm, and the dynamical reversibility of a DTPM. Through numerical experiments on a dumbbell Markov chain, our findings indicate that the value of $k$, corresponding to the maximum value of the infinitesimal part of the dual-valued Ky Fan $p$-$k$-norm by adjusting $p$ in the interval $[1,2)$, characterizes the optimal classification number of the system for the occurrence of the causal emergence.

math.NA↗

arXiv2024

An iteration-free approach to excitation harmonization

Sinusoidal excitation is particularly popular for testing structures in the nonlinear regime. Due to the nonlinear behavior and the inevitable feedback of the structure on the exciter, higher harmonics in the applied excitation are generated. This is undesired, because the acquired response may deviate substantially from that of the structure under purely sinusoidal excitation, in particular if one of the higher harmonics engages into resonance. We present a new approach to suppress those higher excitation harmonics and thus the unwanted exciter-structure interaction: Higher harmonics are added to the voltage input to the shaker whose Fourier coefficients are adjusted via feedback control until the excitation is purely sinusoidal. The stability of this method is analyzed for a simplified model; the resulting closed-form expressions are useful, among others, to select an appropriate exciter configuration, including the drive point. A practical procedure for the control design is suggested. The proposed method is validated in virtual and real experiments of internally resonant structures, in the two common configurations of force excitation via a stinger and base excitation. Excellent performance is achieved already when using the same control gains for all harmonics, throughout the tested range of amplitudes and frequencies, even in the strongly nonlinear regime. Compared to the iterative state of the art, it is found that the proposed method is simpler to implement, enables faster testing and it is easy to achieve a lower harmonic distortion.

eess.SY↗