11 papers
Taming I2V models for Image HOI Editing: A Cognitive Benchmark and Agentic Self-Correcting Framework
Jiayi Gao, Qingchao Chen, Yuxin Peng +1
Current image editing methods excel at static attributes but fail at complex Human-Object Interactions (HOI), a critical challenge unaddressed by existing benchmarks that conflate…
Learning Taxonomic Trees with Hierarchical Representation Regularization for Large Multimodal Models
Hulingxiao He, Zhi Tan, Yuxin Peng
Taxonomies provide key information about the semantic relationships between concepts and the inherent organization of vision and language. Despite their impressive capabilities, la…
DiCoBench: Benchmarking Multi-Image Fine-Grained Perception via Differential and Commonality Visual Cues
Geng Li, Yuxin Peng
Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated impressive fine-grained perception capabilities. However, existing benchmarks predominantly rely o…
Benchmarking Large Vision-Language Models on Fine-Grained Image Tasks: From Evaluation to Diagnosis
Hong-Tao Yu, Chen-Wei Xie, Yuxin Peng +2
Recent advancements in Large Vision-Language Models (LVLMs) have demonstrated remarkable multimodal perception and reasoning capabilities. While numerous benchmarks have evaluated…
AesFormer: Transform Everyday Photos into Beautiful Memories
Tianxiang Du, Hulingxiao He, Yuxin Peng
In everyday photography, aesthetically appealing moments are often captured with structural flaws (e.g., composition, camera viewpoint, or pose) that existing retouching and portra…
Beyond Binary Success: A Diagnostic Meta-Evaluation Framework for Fine-Grained Manipulation
He-Yang Xu, Pengyuan Zhang, Zongyuan Ge +5
Fine-grained manipulation marks a regime where global scene context no longer suffices, and success hinges on the tight coupling of local attribute grounding, high-fidelity spatial…
Taxonomy-Aware Representation Alignment for Hierarchical Visual Recognition with Large Multimodal Models
Hulingxiao He, Zhi Tan, Yuxin Peng
A high-performing, general-purpose visual understanding model should map visual inputs to a taxonomic tree of labels, identify novel categories beyond the training set for which fe…
Learning to Generate via Understanding: Understanding-Driven Intrinsic Rewarding for Unified Multimodal Models
Jiadong Pan, Liang Li, Yuxin Peng +6
Recently, unified multimodal models (UMMs) have made remarkable progress in integrating visual understanding and generation, demonstrating strong potential for complex text-to-imag…
Venus: Benchmarking and Empowering Multimodal Large Language Models for Aesthetic Guidance and Cropping
Tianxiang Du, Hulingxiao He, Yuxin Peng
The widespread use of smartphones has made photography ubiquitous, yet a clear gap remains between ordinary users and professional photographers, who can identify aesthetic issues…
Fine-R1: Make Multi-modal LLMs Excel in Fine-Grained Visual Recognition by Chain-of-Thought Reasoning
Hulingxiao He, Zijun Geng, Yuxin Peng
Any entity in the visual world can be hierarchically grouped based on shared characteristics and mapped to fine-grained sub-categories. While Multi-modal Large Language Models (MLL…
Benchmarking Large Vision-Language Models on Fine-Grained Image Tasks: A Comprehensive Evaluation
Hong-Tao Yu, Yuxin Peng, Serge Belongie +1
Recent advancements in Large Vision-Language Models (LVLMs) have demonstrated remarkable multimodal perception capabilities, garnering significant attention. While numerous evaluat…