相关论文: Generalizable Multimodal Large Language Model Edit…

Multimodal large language models (MLLMs) are widely used in vision-language reasoning tasks. However, their vulnerability to adversarial prompts remains a serious concern, as safety mechanisms often fail to prevent the generation of harmful…

Generalization to out-of-distribution (OOD) data is a capability natural to humans yet challenging for machines to reproduce. This is because most learning algorithms strongly rely on the i.i.d.~assumption on source/target data, which is…

Large multimodal language models (MLLMs) have revolutionized natural language processing and visual understanding, but often contain outdated or inaccurate information. Current multimodal knowledge editing evaluations are limited in scope…

Large language models (LLMs) need knowledge updates to meet the ever-growing world facts and correct the hallucinated responses, facilitating the methods of lifelong model editing. Where the updated knowledge resides in memories is a…

Recognizing out-of-distribution (OOD) samples is critical for machine learning systems deployed in the open world. The vast majority of OOD detection methods are driven by a single modality (e.g., either vision or language), leaving the…

Post-training for large language models (LLMs) is constrained by the high cost of acquiring new knowledge or correcting errors and by the unintended side effects that frequently arise from retraining. To address these issues, we introduce…

Instruction tuning -- fine-tuning a large language model (LLM) on pairs of instructions and desired outcomes -- is an approach that enables pre-trained language models to perform real-world tasks and follow human instructions. Its practical…

Ride-hailing platforms face significant challenges in optimizing order dispatching and driver repositioning operations in dynamic urban environments. Traditional approaches based on combinatorial optimization, rule-based heuristics, and…

Diffusion models have significantly improved text-to-image generation, producing high-quality, realistic images from textual descriptions. Beyond generation, object-level image editing remains a challenging problem, requiring precise…

Out-of-distribution (OOD) detection in graphs is critical for ensuring model robustness in open-world and safety-sensitive applications. Existing graph OOD detection approaches typically train an in-distribution (ID) classifier on ID data…

The model editing problem concerns how language models should learn new facts about the world over time. While empirical research on model editing has drawn widespread attention, the conceptual foundations of model editing remain shaky --…

Machine learning models have made incredible progress, but they still struggle when applied to examples from unseen domains. This study focuses on a specific problem of domain generalization, where a model is trained on one source domain…

Knowledge editing techniques, aiming to efficiently modify a minor proportion of knowledge in large language models (LLMs) without negatively impacting performance across other inputs, have garnered widespread attention. However, existing…

Out-of-distribution (OOD) generalization on graphs aims at dealing with scenarios where the test graph distribution differs from the training graph distributions. Compared to i.i.d. data like images, the OOD generalization problem on…

Out-of-distribution (OOD) detection is committed to delineating the classification boundaries between in-distribution (ID) and OOD images. Recent advances in vision-language models (VLMs) have demonstrated remarkable OOD detection…

Existing vision-language models exhibit strong generalization on a variety of visual domains and tasks. However, such models mainly perform zero-shot recognition in a closed-set manner, and thus struggle to handle open-domain visual…

The task of open-set domain generalization (OSDG) involves recognizing novel classes within unseen domains, which becomes more challenging with multiple modalities as input. Existing works have only addressed unimodal OSDG within the…

Existing Visual-Language Models (VLMs) have achieved significant progress by being trained on massive-scale datasets, typically under the assumption that data are independent and identically distributed (IID). However, in real-world…

Large language models (LLMs) acquire a large amount of knowledge through pre-training on vast and diverse corpora. While this endows LLMs with strong capabilities in generation and reasoning, it amplifies risks associated with sensitive,…

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…