6 papers
YOLO-PEFT: Parameter-Efficient Fine-Tuning on YOLO Family
Xu Lin, WenJie Nie, Jinlong Peng +4
Generic parameter-efficient fine-tuning (PEFT) methods transferred from language models can fail silently on real-time detectors, whose heterogeneous operators and detection-specif…
VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning
Zhenkun Gao, Yicheng Bao, Jinlong Peng +13
Video understanding is moving beyond closed-context perception toward open-world evidence exploration, a paradigm formalized as Video Deep Research (VDR). However, existing multimo…
ConsistentRFT: Reducing Visual Hallucinations in Flow-based Reinforcement Fine-Tuning
Xiaofeng Tan, Jun Liu, Yuanting Fan +7
Reinforcement Fine-Tuning (RFT) on flow-based models is crucial for preference alignment. However, they often introduce visual hallucinations like over-optimized details and semant…
YOLO-Master: MOE-Accelerated with Specialized Transformers for Enhanced Real-time Detection
Xu Lin, Jinlong Peng, Zhenye Gan +2
Existing Real-Time Object Detection (RTOD) methods commonly adopt YOLO-like architectures for their favorable trade-off between accuracy and speed. However, these models rely on st…
Towards Fine-Grained Vision-Language Alignment for Few-Shot Anomaly Detection
Yuanting Fan, Jun Liu, Xiaochen Chen +5
Few-shot anomaly detection (FSAD) methods identify anomalous regions with few known normal samples. Most existing methods rely on the generalization ability of pre-trained vision-l…
VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Model
Zuwei Long, Yunhang Shen, Chaoyou Fu +11
With the growing requirement for natural human-computer interaction, speech-based systems receive increasing attention as speech is one of the most common forms of daily communicat…