70 accepted papers
Deep learning methods have achieved remarkable success in image compressed sensing (CS) task, namely reconstructing a high-fidelity image from its compressed measurement. However, existing methods are deficient in incoherent compressed measurement at sensing phase and implicit measurement representa
Federated learning (FL) is vulnerable to backdoor attacks. Yet sustaining backdoor effectiveness under repeated aggregation remains challenging. Existing methods often rely on heuristic trigger designs or indiscriminant parameter manipulation, leading to rapid decay or detectable anomalies. In this …
Video snapshot compressive imaging (SCI) offers a promising alternative to high-speed cameras by encoding multiple frames into a single 2D measurement. However, SCI requires algorithms to reconstruct the high-speed video, and as resolution increases, reconstruction becomes computationally expensive
Significant progress has been made in spoken question answering (SQA) in recent years. However, many existing methods, including large audio language models, struggle with processing long audio. Follow the success of retrieval augmented generation, a speech-related retriever shows promising in help
Many existing financial math reasoning benchmarks suffer from data contamination and high manual construction costs. To address this, we propose a novel formula-driven approach to dynamically construct math reasoning benchmarks in finance. Our two-stage approach: (1) generates single-formula questio
Glitch tokens—inputs that trigger unpredictable or anomalous behavior in Large Language Models (LLMs)—pose significant challenges to model reliability and safety. Existing detection methods primarily rely on heuristic embedding patterns or statistical anomalies within internal representations, limit
Computer-generated holography (CGH) is a promising technology for next-generation displays. However, generating high-speed, high-quality holographic video requires both high frame rate display and efficient computation, but is constrained by two key limitations: (i) Learning-based models often produ
Recent work explores how real and synthetic data contribute to VLA model generalization. While the \pi-series model has shown the strong effectiveness of large-scale real-robot pre-training, synthetic data has not previously demonstrated comparable capability at scale.This paper provides the first e
Coded Aperture Snapshot Spectral Imaging (CASSI) is an emerging hyperspectral image (HSI) acquisition technique for downstream semantic segmentation. Due to the ill-posedness nature of CASSI systems, typical solutions are compelled to conduct a two-stage reconstruction-then-segmentation pipeline, na
The rapid advancement of 3D scene understanding techniques presents a significant opportunity for enhancing autonomous driving simulation systems. As these systems are increasingly required to operate in complex, large-scale, and unbounded real-world environments, efficient and high-fidelity 3D reco…
The integration of Large Language Models (LLMs) into clinical applications presents transformative potential but is undermined by the critical risk of hallucination, the generation of plausible but factually incorrect information. Such failures pose a direct threat to patient safety and the integrit
We present Mixture-of-Length (MoL), an approach for Question Answering (QA) with context that aims to improve the balance between reasoning quality and response efficiency. Our method introduces a principled difficulty assessment based on information-theoretic principles and a dual-objective reward…
Recent advances in medical multi-modal models focus on specialized image analysis like dermatology, pathology, or radiology. However, they do not fully capture the complexity of real-world clinical diagnostics, which involve heterogeneous inputs and require ongoing contextual understanding during pa
Effectively balancing accuracy and cost is a critical challenge when using large language models (LLMs) for corpus annotation. This paper introduces a novel compression method based on keyword extraction (PCKE) that effectively reduces the number of prompt tokens in text classification annotation ta…
Class-incremental learning (CIL) enables models to learn new classes progressively while preserving knowledge of previously learned ones. Recent advances in this field have shifted towards parameter-efficient fine-tuning techniques, with many approaches building upon the framework that maintains a p…
Password guessing attack is a significant threat to account security. Understanding this attack is crucial for identifying the vulnerabilities of current password systems and for developing more effective methods to protect user accounts. Adaptive password guessing techniques can dynamically adjust…
Large language models (LLMs) have achieved remarkable success across diverse domains. However, their potential as effective language teachers—particularly in complex pedagogical scenarios like teaching Chinese as a second language—remains inadequately assessed. To address this gap, we propose the fi
Large Language Models (LLMs) and Retrieval Augmented Generation (RAG) methods have demonstrated significant potential on tasks across multiple domains. However, ellipses and coreferences, as common phenomena in dialogue scenes, pose challenges to LLMs’ understanding and RAG’s retrieval accuracy. The…
Image deblurring plays a crucial role in enhancing visual clarity across various applications. Although most deep learning approaches primarily focus on sRGB images, which inherently lose critical information during the image signal processing pipeline, RAW images, being unprocessed and linear, poss…
As a crucial method in prompt engineering, In-Context Learning (ICL) enhances the generalization and knowledge utilization capabilities of Large Language Models (LLMs) (Dong et al., 2024). However, the lengthy retrieved contexts and limited token throughput in autoregressive models significantly con
Large language models (LLMs) exhibit excellent performance in natural language processing (NLP), but remain highly sensitive to the quality of input queries, especially when these queries contain misleading or inaccurate information. Existing methods focus on correcting the output, but they often ov…
Universal Information Extraction (UIE) has garnered significant attention due to its ability to address model explosion problems effectively. Extractive UIE can achieve strong performance using a relatively small model, making it widely adopted. Extractive UIEs generally rely on task instructions fo…
Symbolic music is represented in two distinct forms: two-dimensional, visually intuitive score images, and one-dimensional, standardized text annotation sequences. While large language models have shown extraordinary potential in music, current research has primarily focused on unimodal symbol seque…
Current efforts to learn scalable policies in robotic manipulation primarily fall into two categories: one focuses on "action," which involves behavior cloning from extensive collections of robotic data, while the other emphasizes "vision," enhancing model generalization by pre-training representati…
Deep-unrolling and plug-and-play (PnP) approaches have become the de-facto standard solvers for single-pixel imaging (SPI) inverse problem. PnP approaches, a class of iterative algorithms where regularization is implicitly performed by an off-the-shelf deep denoiser, are flexible for varying compres…
Accurate and reliable 3D object detection is crucial for autonomous driving, normally achieved using camera-only or camera-LiDAR fusion methods based on BEV (Bird’s Eye View) perspective. However, visual perception through cameras alone faces significant challenges, such as ambiguous depth estimatio…
As a kind of multi-step attack, the APT attack is long-term, highly hidden, and usually exploits novel vulnerabilities. To detect and respond to APT attacks, security analysts need to analyze a large number of system logs and network traffic to determine the sequence of activities executed by APT at…
Recently, there have been significant advancements in music generation. However, existing models primarily focus on creating modern pop songs, making it challenging to produce ancient music with distinct rhythms and styles, such as ancient Chinese SongCi. In this paper, we introduce SongSong, the fi…
In coded aperture snapshot spectral imaging (CASSI), the captured measurement entangles spatial and spectral information, posing a severely ill-posed inverse problem for hyperspectral images (HSIs) reconstruction. Moreover, the captured radiance inherently depends on scene illumination, making it di…
Large Language Models (LLMs) have achieved impressive accomplishments in recent years. However, the increasing memory consumption of KV cache has possessed a significant challenge to the inference system. Eviction methods have revealed the inherent redundancy within the KV cache, demonstrating its p…
In-context learning (ICL) has emerged as a powerful paradigm for task adaptation in large language models (LLMs), where models infer underlying task structures from a few demonstrations. However, ICL remains susceptible to biases that arise from prior knowledge and contextual demonstrations, which c
With the increasing prevalence of personal information breaches, targeted password guessing based on user-specific data has emerged as a serious security threat. Existing targeted password guessing attacks primarily rely on traditional statistical language models, which have limited capability in ad…
Large language models (LLMs) have demonstrated remarkable capabilities, but their power comes with significant security considerations. While extensive research has been conducted on the safety of LLMs in chat mode, the security implications of their function calling feature have been largely overlo…
Variational Autoencoder (VAE) has been used as password generative model for trawling attack in multiple works. Its sample distribution can be easily changed by controling the mean and variance of the prior distribution, which makes it natively suitable for dynamic attack scenario. Combining transfo…
Uncovering cause-effect relationships from observational time series is fundamental to understanding complex systems. While many methods infer static causal graphs, real-world systems often exhibit *dynamic causality*—where relationships evolve over time. Accurately capturing these temporal dynamics…
Passwords are widely used for website authentication, but they are vulnerable to guessing attacks. To measure password guessability, the commonly used approach involves modeling the distribution of passwords with a password probability model and then estimating the guessability using Monte Carlo met…
Large Language Models (LLMs) excel in generation tasks, yet their causal attention mechanisms limit performance in embedding tasks. While bidirectional modeling may enhance embeddings, naively fine-tuning unidirectional models bidirectionally severely degrades generative performance. To investigate…
Multi-modal aspect-based sentiment analysis (MABSA) has recently attracted increasing attention. The span-based extraction methods, such as FSUIE, demonstrate strong performance in sentiment analysis due to their joint modeling of input sequences and target labels. However, previous methods still ha…
Single-pixel imaging (SPI) is a potential computational imaging technique which produces image by solving an ill-posed reconstruction problem from few measurements captured by a single-pixel detector. Deep learning has achieved impressive success on SPI reconstruction. However previous poor reconstr…
Semantic entity recognition is an important task in the field of visually-rich document understanding. It distinguishes the semantic types of text by analyzing the position relationship between text nodes and the relation between text content. The existing document understanding models mainly focus…
Chain-of-thought (CoT) reasoning has exhibited impressive performance in language models for solving complex tasks and answering questions. However, many real-world questions require multi-modal information, such as text and images. Previous research on multi-modal CoT has primarily focused on extra…
The first step to apply deep learning techniques for symbolic music understanding is to transform musical pieces (mainly in MIDI format) into sequences of predefined tokens like note pitch, note velocity, and chords. Subsequently, the sequences are fed into a neural sequence model to accomplish spec…
Estimating robot pose and joint angles is significant in advanced robotics, enabling applications like robot collaboration and online hand-eye calibration. However, the introduction of unknown joint angles makes prediction more complex than simple robot pose estimation, due to its higher dimensional…
In this paper we explore the potential of Snapshot Com- pressive Imaging (SCI) technique for recovering the under- lying 3D scene representation from a single temporal com- pressed image. SCI is a cost-effective method that enables the recording of high-dimensional data such as hyperspec- tral or te…
The prevalent approach for optimizing pre-trained language models in downstream tasks is fine-tuning. However, it is both time-consuming and memory-inefficient. In response, a more efficient method called Prefix Tuning, which insert learnable vectors into each Transformer layers, has been proposed a…
Benchmark plays a pivotal role in assessing the advancements of large language models (LLMs). While numerous benchmarks have been proposed to evaluate LLMs’ capabilities, there is a notable absence of a dedicated benchmark for assessing their musical abilities. To address this gap, we present ZIQI-E…
The image-based multimodal automatic speech recognition (ASR) model enhances speech recognition performance by incorporating audio-related image. However, some works suggest that introducing image information to model does not help improving ASR performance. In this paper, we propose a novel approac…
Video snapshot compressive imaging (SCI) aims to capture a sequence of video frames with only a single shot of a 2D detector, whose backbones rest in optical modulation patterns (also known as masks) and a computational reconstruction algorithm. Advanced deep learning algorithms and mature hardware…
Modeling password distributions is a fundamental problem in password security, benefiting the research and applications on password guessing, password strength meters, honey password vaults, etc. As one of the best segment-based password models, WordPCFG has been proposed to capture individual seman…
Automatic coding of International Classification of Diseases (ICD) is a multi-label text categorization task that involves extracting disease or procedure codes from clinical notes. Despite the application of state-of-the-art natural language processing (NLP) techniques, there are still challenges i…
Previous works on video object segmentation (VOS) are trained on densely annotated videos. Nevertheless, acquiring annotations in pixel level is expensive and time-consuming. In this work, we demonstrate the feasibility of training a satisfactory VOS model on sparsely annotated videos--we merely req…
In this paper, we propose a novel light-weight feature integration and fusion method to enhance the discriminative ability of deep convolutional features for the task of fine-grained vehicle recognition. The proposed method is built on the deep convolutional layers from which the discriminative part…
Recently almost all the mainstream deepfake detection methods use Convolutional Neural Networks (CNN) as their backbone. However, due to the overreliance on local texture information which is usually determined by forgery methods of training data, these CNN-based methods cannot generalize well to un…
Entity alignment (EA) aims to identify equivalent entities from different Knowledge Graphs (KGs), which is a fundamental task for integrating KGs. Throughout its development, Graph Convolutional Network (GCN) has become one of the mainstream methods for EA. These GCN-based methods learn the represen…
Multi-label few-shot image classification (ML-FSIC) is the task of assigning descriptive labels to previously unseen images, based on a small number of training examples. A key feature of the multi-label setting is that images often have multiple labels, which typically refer to different regions of…
Knowledge distillation (KD) has witnessed its powerful capability in learning compact models in object detection. Previous KD methods for object detection mostly focus on imitating deep features within the imitation regions instead of logit mimicking on classification due to the inefficiency in dist…
Passwords have been widely used in online authentication, and they form the front line that protects our data security and privacy. But the security of password may be easily harmed by insecure password generator. Massive reports state that users are always keen to generate new passwords by reusing…
To date there are few researches on the semantic information of passwords, which leaves a gap preventing us from fully understanding the passwords characteristic and security. We propose a new password probability model for semantic information based on Markov Chain with both generalization and accu…
Unsupervised aspect detection (UAD) aims at automatically extracting interpretable aspects and identifying aspect-specific segments (such as sentences) from online reviews. However, recent deep learning based topic models, specifically aspect-based autoencoder, suffer from several problems such as e…
Recent research has been remarkable in recurrent neural networks (RNNs) on sequence-to-sequence problems for image caption, and promising in convolutional neural networks (CNNs) on spatial analysis problems for image detection and sematic segmentation problems. In this paper, based on recurrent neur…
The aim of few-shot learning (FSL) is to learn how to recognize image categories from a small number of training examples. A central challenge is that the available training examples are normally insufficient to determine which visual features are most characteristic of the considered categories. To…
Recent years have witnessed increased interests in scene text recognition (STR). Current state-of-the-art (SOTA) approaches adopt sequence-to-sequence (Seq2Seq) structure to leverage the mutual interaction between images and textual information. However, these methods still struggle to recognize tex…
Probabilistic context-free grammars (PCFGs) have been pro-posed to capture password distributions, and further been used in password guessing attacks and password strength meters. However, current PCFGs suffer from the limitation of inaccurate segmentation of password, which leads to misestimation o…
Few-shot learning aims to recognize unseen images of new classes with only a few training examples. While great progress has been made with deep learning technology, most metric-based works rely on the measurement based on global feature representation of images, which is sensitive to background fac…
The contrastive pre-training of a recognition model on a large dataset of unlabeled data often boosts the model’s performance on downstream tasks like image classification. However, in domains such as medical imaging, collecting unlabeled data can be challenging and expensive. In this work, we consi…
Recent studies show that small perturbations in video frames could misguide single object trackers. However, such attacks have been mainly designed for digital-domain videos (i.e., perturbation on full images), which makes them practically infeasible to evaluate the adversarial vulnerability of trac…
In this paper, we propose a new few-shot text classification method. Compared with supervised learning methods which require a large corpus of labeled documents, our method aims to make it possible to classify unlabeled text with few labeled data. To achieve this goal, we take advantage of advanced…
Filter pruning is one of the most effective ways to accelerate and compress convolutional neural networks (CNNs). In this work, we propose a global filter pruning algorithm called Gate Decorator, which transforms a vanilla CNN module by multiplying its output by the channel-wise scaling factors (i.e…
Non-invasive Glucose Measurement (NGM) technology is promising and desired for patients with hyperglycemia or hypoglycemia. In various kinds of NGM technologies, a prediction algorithm model plays a special role that is to map a group of physical signals to a glucose level of a person at a given tim…
We propose in this paper a low-rank and sparse decomposition based image hashing algorithm, aiming to summarize the structural information and sparse salient components of digital image to compact digest. More specifically, we leverage compressive sampling and random projection to separately aggrega…