collaborators
Showing cs.CVShow all

8 papers · 1 filter

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

What Do Visual Tokens Really Encode? Uncovering Sparsity and Redundancy in Multimodal Large Language Models

Yingqi Fan, Junlong Tong, Anhao Zhao +1

Multimodal large language models (MLLMs) project visual tokens into the embedding space of language models, yet the internal structuring and processing of visual semantics remain p…

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

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…