7 papers
ArrowGEV: Grounding Events in Video via Learning the Arrow of Time
Fangxu Yu, Ziyao Lu, Liqiang Niu +2
Grounding events in videos serves as a fundamental capability in video analysis. While Vision Language Models (VLMs) are increasingly employed for this task, existing approaches pr…
WeEdit: A Dataset, Benchmark and Glyph-Guided Framework for Text-centric Image Editing
Hui Zhang, Juntao Liu, Zongkai Liu +4
Instruction-based image editing aims to modify specific content within existing images according to user-provided instructions while preserving non-target regions. Beyond tradition…
UME-R1: Exploring Reasoning-Driven Generative Multimodal Embeddings
Zhibin Lan, Liqiang Niu, Fandong Meng +2
The remarkable success of multimodal large language models (MLLMs) has driven advances in multimodal embeddings, yet existing models remain inherently discriminative, limiting thei…
LLaVE: Large Language and Vision Embedding Models with Hardness-Weighted Contrastive Learning
Zhibin Lan, Liqiang Niu, Fandong Meng +2
Universal multimodal embedding models play a critical role in tasks such as interleaved image-text retrieval, multimodal RAG, and multimodal clustering. However, our empirical resu…
AVG-LLaVA: An Efficient Large Multimodal Model with Adaptive Visual Granularity
Zhibin Lan, Liqiang Niu, Fandong Meng +3
Recently, large multimodal models (LMMs) have achieved significant advancements. When dealing with high-resolution images, dominant LMMs typically divide them into multiple local i…
LaCo: Efficient Layer-wise Compression of Visual Tokens for Multimodal Large Language Models
Juntao Liu, Liqiang Niu, Wenchao Chen +2
Existing visual token compression methods for Multimodal Large Language Models (MLLMs) predominantly operate as post-encoder modules, limiting their potential for efficiency gains.…