Xiang Li

31

Papers

262

Total Citations

Papers (31)

Decoding Natural Images from EEG for Object Recognition

ImageFolder: Autoregressive Image Generation with Folded Tokens

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer

Multi-Sensor Object Anomaly Detection: Unifying Appearance, Geometry, and Internal Properties

From Words to Worth: Newborn Article Impact Prediction with LLM

Multi-clue Consistency Learning to Bridge Gaps Between General and Oriented Object in Semi-supervised Detection

In-Hand 3D Object Reconstruction from a Monocular RGB Video

Incorporating Geo-Diverse Knowledge into Prompting for Increased Geographical Robustness in Object Recognition

Understanding Representation Dynamics of Diffusion Models via Low-Dimensional Modeling

AltNeRF: Learning Robust Neural Radiance Field via Alternating Depth-Pose Optimization

Symmetry Strikes Back: From Single-Image Symmetry Detection to 3D Generation

REOBench: Benchmarking Robustness of Earth Observation Foundation Models

Hierarchically Controlled Deformable 3D Gaussians for Talking Head Synthesis

Handows: A Palm-Based Interactive Multi-Window Management System in Virtual Reality

DISTA-Net: Dynamic Closely-Spaced Infrared Small Target Unmixing

Coupling-based Convergence Diagnostic and Stepsize Scheme for Stochastic Gradient Descent

Distribution-aware Fairness Learning in Medical Image Segmentation From A Control-Theoretic Perspective

TreeEval: Benchmark-Free Evaluation of Large Language Models through Tree Planning

SimpleVQA: Multimodal Factuality Evaluation for Multimodal Large Language Models

CrossKD: Cross-Head Knowledge Distillation for Object Detection

PromptKD: Unsupervised Prompt Distillation for Vision-Language Models

VA3: Virtually Assured Amplification Attack on Probabilistic Copyright Protection for Text-to-Image Generative Models

QDFormer: Towards Robust Audiovisual Segmentation in Complex Environments with Quantization-based Semantic Decomposition

RSAR: Restricted State Angle Resolver and Rotated SAR Benchmark

InstanceCap: Improving Text-to-Video Generation via Instance-aware Structured Caption

A General Framework for Learning from Weak Supervision

Completing Visual Objects via Bridging Generation and Segmentation

Advancing Textual Prompt Learning with Anchored Attributes

Position: TrustLLM: Trustworthiness in Large Language Models

Backdoor Attacks on Neural Networks via One-Bit Flip

Leveraging Large Language Models for Node Generation in Few-Shot Learning on Text-Attributed Graphs