Jing Liu

33

Papers

389

Total Citations

Papers (33)

Temporal Adaptive RGBT Tracking with Modality Prompt

Text Prompt with Normality Guidance for Weakly Supervised Video Anomaly Detection

EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models

Open-Vocabulary Video Anomaly Detection

AR-Diffusion: Asynchronous Video Generation with Auto-Regressive Diffusion

Numerical Pruning for Efficient Autoregressive Models

Signed Graph Neural Ordinary Differential Equation for Modeling Continuous-Time Dynamics

Needle In A Video Haystack: A Scalable Synthetic Evaluator for Video MLLMs

ID-Patch: Robust ID Association for Group Photo Personalization

Context-aware Dynamic Pruning for Speech Foundation Models

Efficient Stitchable Task Adaptation

AutoSGNN: Automatic Propagation Mechanism Discovery for Spectral Graph Neural Networks

COAP: Memory-Efficient Training with Correlation-Aware Gradient Projection

Breaking the Encoder Barrier for Seamless Video-Language Understanding

Graph Contrastive Learning with Joint Spectral Augmentation of Attribute and Topology

SpFormer: Spatio-Temporal Modeling for Scanpaths with Transformer

TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models

SC-Tune: Unleashing Self-Consistent Referential Comprehension in Large Vision Language Models

Unveiling Parts Beyond Objects: Towards Finer-Granularity Referring Expression Segmentation

Automated Loss function Search for Class-imbalanced Node Classification

QuartDepth: Post-Training Quantization for Real-Time Depth Estimation on the Edge

Efficient Motion-Aware Video MLLM

ZipVL: Accelerating Vision-Language Models through Dynamic Token Sparsity

Learning Beyond Still Frames: Scaling Vision-Language Models with Video

MotionCtrl: A Real-time Controllable Vision-Language-Motion Model

Scaling Omni-modal Pretraining with Multimodal Context: Advancing Universal Representation Learning Across Modalities

COSMO: Combination of Selective Memorization for Low-cost Vision-and-Language Navigation

M2OST: Many-to-one Regression for Predicting Spatial Transcriptomics from Digital Pathology Images

DiMSOD: A Diffusion-Based Framework for Multi-Modal Salient Object Detection

TRAIL: Trust-Aware Client Scheduling for Semi-Decentralized Federated Learning

FedCross: Intertemporal Federated Learning Under Evolutionary Games

Forget to Flourish: Leveraging Machine-Unlearning on Pretrained Language Models for Privacy Leakage

Channel Merging: Preserving Specialization for Merged Experts