相关论文: Mind the Interference: Retaining Pre-trained Knowl…

Vision-language models (VLMs) are widely assumed to exhibit in-context learning (ICL), a property similar to that of their language-only counterparts. While recent work suggests VLMs can perform multimodal ICL (MM-ICL), studies show they…

Learning general-purpose reasoning capabilities has long been a challenging problem in AI. Recent research in large language models (LLMs), such as DeepSeek-R1, has shown that reinforcement learning techniques like GRPO can enable…

Continual instruction tuning enables large language models (LLMs) to learn incrementally while retaining past knowledge, whereas existing methods primarily focus on how to retain old knowledge rather than on selecting which new knowledge to…

In a real-world setting, object instances from new classes can be continuously encountered by object detectors. When existing object detectors are applied to such scenarios, their performance on old classes deteriorates significantly. A few…

Vision-Language Models (VLMs) demonstrate remarkable zero-shot generalization to unseen tasks, but fall short of the performance of supervised methods in generalizing to downstream tasks with limited data. Prompt learning is emerging as a…

Recent advancements in autonomous driving have relied on data-driven approaches, which are widely adopted but face challenges including dataset bias, overfitting, and uninterpretability. Drawing inspiration from the knowledge-driven nature…

Machine unlearning in Vision-Language Models (VLMs) is typically performed at the image or instance level, making it difficult to precisely remove target knowledge without affecting unrelated semantics. This issue is especially pronounced…

Semi-supervised learning (SSL) has emerged as a practical solution for addressing data scarcity challenges by leveraging unlabeled data. Recently, vision-language models (VLMs), pre-trained on massive image-text pairs, have demonstrated…

Visual reasoning (VR), which is crucial in many fields for enabling human-like visual understanding, remains highly challenging. Recently, compositional visual reasoning approaches, which leverage the reasoning abilities of large language…

Reinforcement Learning (RL) provides a framework in which agents can be trained, via trial and error, to solve complex decision-making problems. Learning with little supervision causes RL methods to require large amounts of data, rendering…

The field of continual deep learning is an emerging field and a lot of progress has been made. However, concurrently most of the approaches are only tested on the task of image classification, which is not relevant in the field of…

Pre-trained language models (LMs) have been shown to memorize a substantial amount of knowledge from the pre-training corpora; however, they are still limited in recalling factually correct knowledge given a certain context. Hence, they…

Diffusion Language Models (DLMs) offer attractive advantages over Auto-Regressive (AR) models, such as full-attention parallel decoding and flexible generation. However, standard DLM training uses a static, single-step masked prediction…

Model editing aims to update knowledge to add new concepts and change relevant information without retraining. Lifelong editing is a challenging task, prone to disrupting previously learned concepts, especially for Vision Language Models…

Large Language Models (LLMs) encounter challenges with the unique syntax of specific domains, such as biomolecules. Existing fine-tuning or modality alignment techniques struggle to bridge the domain knowledge gap and understand complex…

Vision-Language Pre-training (VLP) shows remarkable progress with the assistance of extremely heavy parameters, which challenges deployment in real applications. Knowledge distillation is well recognized as the essential procedure in model…

Vision-and-language (V-L) tasks require the system to understand both vision content and natural language, thus learning fine-grained joint representations of vision and language (a.k.a. V-L representations) is of paramount importance.…

While Large Language Models (LLMs) acquire vast knowledge during pre-training, they often lack domain-specific, new, or niche information. Continual pre-training (CPT) attempts to address this gap but suffers from catastrophic forgetting…

Vision-language models (VLMs) extend the conventional large language models by integrating visual data, enabling richer multimodal reasoning and significantly broadens the practical applications of AI. However, including visual inputs also…

Large pre-trained vision-language models, such as CLIP, have shown remarkable generalization capabilities across various tasks when appropriate text prompts are provided. However, adapting these models to specific domains, like remote…