Xin Liu

23

Papers

216

Total Citations

Papers (23)

ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference

Scaling Wearable Foundation Models

AUFormer: Vision Transformers are Parameter-Efficient Facial Action Unit Detectors

A Comprehensive Overhaul of Multimodal Assistant with Small Language Models

Predicting Emergent Abilities with Infinite Resolution Evaluation

CATANet: Efficient Content-Aware Token Aggregation for Lightweight Image Super-Resolution

DiffFAS: Face Anti-Spoofing via Generative Diffusion Models

FSBench: A Figure Skating Benchmark for Advancing Artistic Sports Understanding

CohEx: A Generalized Framework for Cohort Explanation

EgoTrigger: Toward Audio-Driven Image Capture for Human Memory Enhancement in All-Day Energy-Efficient Smart Glasses

STDD: Spatio-Temporal Dual Diffusion for Video Generation

Re-Attentional Controllable Video Diffusion Editing

Exploring the Better Multimodal Synergy Strategy for Vision-Language Models

Task-Adaptive Prompted Transformer for Cross-Domain Few-Shot Learning

FedUV: Uniformity and Variance for Heterogeneous Federated Learning

AutoLUT: LUT-Based Image Super-Resolution with Automatic Sampling and Adaptive Residual Learning

No Pains, More Gains: Recycling Sub-Salient Patches for Efficient High-Resolution Image Recognition

Distribution Prototype Diffusion Learning for Open-set Supervised Anomaly Detection

ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning

DADM: Dual Alignment of Domain and Modality for Face Anti-spoofing

Period-LLM: Extending the Periodic Capability of Multimodal Large Language Model

Zero-shot Video Restoration and Enhancement Using Pre-Trained Image Diffusion Model

Scene Graph-Grounded Image Generation