10 papers · 1 filter
Rescuing Your Pruning: Rethinking Visual Token Pruning and Post-Training Recovery in MLLMs
Peiran Yin, Hao Wu, Zihao Yang +3
Visual token pruning substantially reduces the inference cost of multimodal large language models (MLLMs), yet existing methods are mostly training-free and plug-and-play. They tre…
Bifocal: Training-Free Mixed Granularity Visual Token Pruning for Multimodal LLMs
Peiran Yin, Hao Wu, Zihao Yang +6
Visual token pruning for multimodal large language models (MLLMs) appears highly effective, with existing methods retaining over 95% of unpruned performance on common VQA benchmark…
ViCoStream: Streaming VideoLLMs Can Run Beyond 100 FPS with Stage-Wise Coordinated Inference
Yang Tan, Junlong Tong, Linan Yue +3
Streaming VideoLLMs must continuously process incoming video while maintaining low query latency, making both video-ingestion throughput and query-time responsiveness critical for…
Think-as-You-See: Streaming Chain-of-Thought Reasoning for Large Vision-Language Models
Jialiang Zhang, Junlong Tong, Junyan Lin +4
Large Vision Language Models (LVLMs) exhibit strong Chain-of-Thought (CoT) capabilities, yet most existing paradigms assume full-video availability before inference, a batch-style…
FireRed-OCR Technical Report
Hao Wu, Haoran Lou, Xinyue Li +19
We present FireRed-OCR, a systematic framework to specialize general VLMs into high-performance OCR models. Large Vision-Language Models (VLMs) have demonstrated impressive general…
InterCoG: Towards Spatially Precise Image Editing with Interleaved Chain-of-Grounding Reasoning
Yecong Wan, Fan Li, Chunwei Wang +3
Emerging unified editing models have demonstrated strong capabilities in general object editing tasks. However, it remains a significant challenge to perform fine-grained editing i…
UTPTrack: Towards Simple and Unified Token Pruning for Visual Tracking
Hao Wu, Xudong Wang, Jialiang Zhang +5
One-stream Transformer-based trackers achieve advanced performance in visual object tracking but suffer from significant computational overhead that hinders real-time deployment. W…
HiDrop: Hierarchical Vision Token Reduction in MLLMs via Late Injection, Concave Pyramid Pruning, and Early Exit
Hao Wu, Yingqi Fan, Jinyang Dai +3
The quadratic computational cost of processing vision tokens in Multimodal Large Language Models (MLLMs) hinders their widespread adoption. While progressive vision token pruning o…
ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention
Wenjie Liu, Hao Wu, Xin Qiu +6
Modern multimodal large language models (MLLMs) adopt a unified self-attention design that processes visual and textual tokens at every Transformer layer, incurring substantial com…
Speak While Watching: Unleashing TRUE Real-Time Video Understanding Capability of Multimodal Large Language Models
Junyan Lin, Junlong Tong, Hao Wu +4
Multimodal Large Language Models (MLLMs) have achieved strong performance across many tasks, yet most systems remain limited to offline inference, requiring complete inputs before…