Xin Liu

50

Papers

308

Total Citations

Papers (50)

Double Thompson Sampling for Dueling Bandits

NeurIPS 2016arXiv

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

CohEx: A Generalized Framework for Cohort Explanation

FSBench: A Figure Skating Benchmark for Advancing Artistic Sports Understanding

STDD: Spatio-Temporal Dual Diffusion for Video Generation

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

Learning To Filter: Siamese Relation Network for Robust Tracking

No Frame Left Behind: Full Video Action Recognition

Distractor-Aware Fast Tracking via Dynamic Convolutions and MOT Philosophy

iMiGUE: An Identity-Free Video Dataset for Micro-Gesture Understanding and Emotion Analysis

On the Difficulty of Membership Inference Attacks

Progressive Neighbor Consistency Mining for Correspondence Pruning

Recursive Spatial Transformer (ReST) for Alignment-Free Face Recognition

C2ST: Cross-Modal Contextualized Sequence Transduction for Continuous Sign Language Recognition

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

Improving the Transferability of Adversarial Examples with Resized-Diverse-Inputs, Diversity-Ensemble and Region Fitting

GraphCSPN: Geometry-Aware Depth Completion via Dynamic GCNs

Algorithms with Logarithmic or Sublinear Regret for Constrained Contextual Bandits

Objects Do Not Disappear: Video Object Detection by Single-Frame Object Location Anticipation

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

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

Scene Graph-Grounded Image 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

Multi-Task Temporal Shift Attention Networks for On-Device Contactless Vitals Measurement

An Efficient Pessimistic-Optimistic Algorithm for Stochastic Linear Bandits with General Constraints

SCAMPS: Synthetics for Camera Measurement of Physiological Signals

GLOBEM Dataset: Multi-Year Datasets for Longitudinal Human Behavior Modeling Generalization

Teach Less, Learn More: On the Undistillable Classes in Knowledge Distillation

Self-Supervised Learning via Maximum Entropy Coding

Online Convex Optimization with Hard Constraints: Towards the Best of Two Worlds and Beyond

Sample Efficient Reinforcement Learning in Mixed Systems through Augmented Samples and Its Applications to Queueing Networks

Open Visual Knowledge Extraction via Relation-Oriented Multimodality Model Prompting

Complex Query Answering on Eventuality Knowledge Graph with Implicit Logical Constraints

Enhancing User Intent Capture in Session-Based Recommendation with Attribute Patterns

Recaptured Raw Screen Image and Video Demoiréing via Channel and Spatial Modulations

rPPG-Toolbox: Deep Remote PPG Toolbox

Adaptive Exploration-Exploitation Tradeoff for Opportunistic Bandits