5 papers · 1 filter
MemDreamer: Decoupling Perception and Reasoning for Long Video Understanding via Hierarchical Graph Memory and Agentic Retrieval Mechanism
Cong Chen, Guo Gan, Kaixiang Ji +7
Current Vision-Language Models struggle with hours-long videos because processing full-length visual sequences induces prohibitive token explosion and attention dilution. To overco…
Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching
Hao Zhong, Muzhi Zhu, Shenyan Zeng +8
Wide-baseline matching (WBM) requires integrating geometric understanding, viewpoint changes, fine-grained perception, and occlusion reasoning, making it a challenging testbed for…
TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders
Teng Li, Ziyuan Huang, Cong Chen +5
We propose TC-AE, a ViT-based architecture for deep compression autoencoders. Existing methods commonly increase the channel number of latent representations to maintain reconstruc…
HieraTok: Multi-Scale Visual Tokenizer Improves Image Reconstruction and Generation
Cong Chen, Ziyuan Huang, Cheng Zou +6
In this work, we present HieraTok, a novel multi-scale Vision Transformer (ViT)-based tokenizer that overcomes the inherent limitation of modeling single-scale representations. Thi…
PerturboLLaVA: Reducing Multimodal Hallucinations with Perturbative Visual Training
Cong Chen, Mingyu Liu, Chenchen Jing +5
This paper aims to address the challenge of hallucinations in Multimodal Large Language Models (MLLMs) particularly for dense image captioning tasks. To tackle the challenge, we id…