Related papers: Dynamic Cross-Modal Prompt Generation for Multimod…

Recent advances in Multimodal Large Language Models (MLLMs) have spurred significant progress in Chain-of-Thought (CoT) reasoning. Building on the success of Deepseek-R1, researchers extended multimodal reasoning to post-training paradigms…

Multimodal Large Language Models (MLLMs) have gained significant attention due to their impressive capabilities in multimodal understanding. However, existing methods rely heavily on extensive modal-specific pretraining and joint-modal…

Prompt tuning has emerged as an effective rehearsal-free technique for class-incremental learning (CIL) that learns a tiny set of task-specific parameters (or prompts) to instruct a pre-trained transformer to learn on a sequence of tasks.…

Prompt-learning has become a new paradigm in modern natural language processing, which directly adapts pre-trained language models (PLMs) to $cloze$-style prediction, autoregressive modeling, or sequence to sequence generation, resulting in…

Multi-species animal pose estimation has emerged as a challenging yet critical task, hindered by substantial visual diversity and uncertainty. This paper challenges the problem by efficient prompt learning for Vision-Language Pretrained…

Continual learning aims to enable a single model to learn a sequence of tasks without catastrophic forgetting. Top-performing methods usually require a rehearsal buffer to store past pristine examples for experience replay, which, however,…

Large language models (LLMs) have shown remarkable reasoning capabilities, yet aligning such abilities to small language models (SLMs) remains a challenge due to distributional mismatches and limited model capacity. Existing reasoning…

Improving the generalization ability of Vision-Language Pre-trained Models (VLMs) under test-time data distribution shifts remains a critical challenge. The existing Test-Time Adaptation (TTA) methods fall short in fully leveraging the…

Adapting Large Multimodal Models (LMMs) to real-world scenarios poses the dual challenges of learning from sequential data streams while handling frequent modality incompleteness, a task known as Continual Missing Modality Learning (CMML).…

Recently, the advances in vision-language models, including contrastive pretraining and instruction tuning, have greatly pushed the frontier of multimodal AI. However, owing to the large-scale and hence expensive pretraining, the efficiency…

Large-scale foundation models, such as CLIP, have demonstrated impressive zero-shot generalization performance on downstream tasks, leveraging well-designed language prompts. However, these prompt learning techniques often struggle with…

Modern deep models are trained on large real-world datasets, where data quality varies and redundancy is common. Data-centric approaches such as dataset pruning have shown promise in improving training efficiency and model performance.…

Multimodal deepfake detection (MDD) aims to uncover manipulations across visual, textual, and auditory modalities, thereby reinforcing the reliability of modern information systems. Although large vision-language models (LVLMs) exhibit…

Soft prompt learning methods are effective for adapting vision-language models (VLMs) to downstream tasks. Nevertheless, empirical evidence reveals a tendency of existing methods that they overfit seen classes and exhibit degraded…

Panoptic segmentation, combining semantic and instance segmentation, stands as a cutting-edge computer vision task. Despite recent progress with deep learning models, the dynamic nature of real-world applications necessitates continual…

Multimodal language models now integrate text, audio, and video for unified reasoning. Yet existing RL post-training pipelines treat all input signals as equally relevant, ignoring which modalities each task actually requires. This…

Despite significant progress, Vision-Language Models (VLMs) still struggle with complex visual reasoning, where multi-step dependencies cause early errors to cascade through the reasoning chain. Existing post-training paradigms are limited:…

To address the instability of unguided reasoning paths in standard Chain-of-Thought prompting, recent methods guide large language models (LLMs) by first eliciting a single reasoning strategy. However, relying on just one strategy for each…

Scaling long-context capabilities is crucial for Multimodal Large Language Models (MLLMs). However, real-world multimodal datasets are extremely heterogeneous. Existing training frameworks predominantly rely on static parallelism…

Multimodal large language models (MLLMs) have garnered widespread attention from researchers due to their remarkable understanding and generation capabilities in visual language tasks (e.g., visual question answering). However, the rapid…