22 accepted papers
Semi-supervised learning (SSL) faces significant challenges in realistic scenarios where labeled data is extremely scarce and unlabeled data follows unknown, arbitrary distributions. We formalize this critical yet under-explored paradigm as Universal Semi-supervised Learning (UniSSL). Existing metho…
Multimodal Large Language Models (MLLMs) integrate text and images for complex reasoning tasks, but efficiently utilizing image remains a challenge due to redundancy and noise. Traditional methods take the entire image features as visual prompt into the MLLMs, leading to excessive visual tokens tha
Tensor Compressive Sensing (TCS) has gained significant attention recently due to its strong ability to preserve the multidimensional structure of data. However, existing TCS methods face three critical challenges: 1) Biased approximation of tensor rank imposed by the convex surrogate Tensor Nucle
Deploying large language models (LLMs) on untrusted hardware entails a risk of weight extraction, which can lead to unauthorized replication and misuse of the model. A practical approach is to leverage Trusted Execution Environments (TEEs) and protect model security by obfuscating model weights. How…
Multimodal Large Language Models (MLLMs) have achieved remarkable progress in vision-language understanding, yet how they internally integrate visual and textual information remains poorly understood. To bridge this gap, we perform a systematic layer-wise masking analysis across multiple architectur
Document-level Event Extraction (DEE) aims to identify event information from a given document. The two challenges of this task are the event arguments scattering across differrent sentences and the multiple events within a single document. In this paper, we propose a novel Dynamic Structure Hypergr…
Structure-based molecule optimization (SBMO) aims to optimize molecules with both continuous coordinates and discrete types against protein targets. A promising direction is to exert gradient guidance on generative models given its remarkable success in images, but it is challenging to guide discret…
Tensor Robust Principal Component Analysis (TRPCA) has emerged as a powerful technique for low-rank tensor recovery. To achieve better recovery performance, a variety of TNN (Tensor Nuclear Norm) based low-rank regularizers have been proposed case by case, lacking a general and flexible framework. I
Multimodal knowledge graph embedding refers to learning multimodal entities and their relation representations in a low-dimensional space. However, existing multimodal embedding models tend to ignore the inherent structure of knowledge graphs. To address this issue, we propose a novel multimodal kno…
Model editing enables targeted updates to the knowledge of large language models (LLMs) with minimal retraining. Among existing approaches, locate-then-edit methods constitute a prominent paradigm: they first identify critical layers, then compute residuals at the final critical layer based on the t…
The general capabilities of large language models (LLMs) make them the infrastructure for various AI applications, but updating their inner knowledge requires significant resources. Recent model editing is a promising technique for efficiently updating a small amount of knowledge of LLMs and has att…
Large language models (LLMs) generate human-aligned content under certain safety constraints. However, the current known technique “jailbreak prompt” can circumvent safety-aligned measures and induce LLMs to output malicious content. Research on Jailbreaking can help identify vulnerabilities in LLMs
Text generation with citations makes it easy to verify the factuality of Large Language Models’ (LLMs) generations. Existing one-step generation studies expose distinct shortages in answer refinement and in-context demonstration matching. In light of these challenges, we propose R2-MGA, a Retrieval…
The early diagnosis of focal liver lesions (FLLs) plays a key role in the successful treatment of liver cancer. To effectively diagnose focal liver lesions, we used contrast-enhanced ultrasound (CEUS) to diagnose FLLs. A hybrid CNN and Transformer network is used to extract local and global spatio-t…
Human intention understanding in untrimmed videos aims to watch a natural video and predict what the person’s intention is. Currently, exploration of predicting human intentions in untrimmed videos is far from enough. On the one hand, untrimmed videos with mixed actions and backgrounds have a signif…
Model editing techniques modify a minor proportion of knowledge in Large Language Models (LLMs) at a relatively low cost, which have demonstrated notable success. Existing methods assume Transformer Layer (TL) hidden states are values of key-value memories of the Feed-Forward Network (FFN). They usu…
Offline reinforcement learning (RL) struggles in environments with rich and noisy inputs, where the agent only has access to a fixed dataset without environment interactions. Past works have proposed common workarounds based on the pre-training of state representations, followed by policy training.…
Recently, physical adversarial attacks have been presented to evade DNNs-based object detectors. To ensure the security, many scenarios are simultaneously deployed with visible sensors and infrared sensors, leading to the failures of these single-modal physical attacks. To show the potential risks u…
"Adversarial training is an effective approach for improving the robustness of deep neural networks against adversarial attacks. Although bringing reliable robustness, adversarial training (AT) will reduce the performance of identifying clean examples. Meanwhile, Adversarial training can bring more…
Few-shot named entity recognition (NER) enables us to build a NER system for a new domain using very few labeled examples. However, existing prototypical networks for this task suffer from roughly estimated label dependency and closely distributed prototypes, thus often causing misclassifications. T…
Current perception models in autonomous driving have become notorious for greatly relying on a mass of annotated data to cover unseen cases and address the long-tail problem. On the other hand, learning from unlabeled large-scale collected data and incrementally self-training powerful recognition mo…
Span-based joint extraction models have shown their efficiency on entity recognition and relation extraction. These models regard text spans as candidate entities and span tuples as candidate relation tuples. Span semantic representations are shared in both entity recognition and relation extraction…