Xi Liu

papers

473

total citations

papers (12)

MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models

ECCV 2024arXiv

199

citations

CustomListener: Text-guided Responsive Interaction for User-friendly Listening Head Generation

CVPR 2024arXiv

citations

Adversarial Locomotion and Motion Imitation for Humanoid Policy Learning

NEURIPS 2025arXiv

citations

Test-time Adaptation for Cross-modal Retrieval with Query Shift

ICLR 2025arXiv

citations

ARIG: Autoregressive Interactive Head Generation for Real-time Conversations

ICCV 2025arXiv

citations

Latent Radiance Fields with 3D-aware 2D Representations

ICLR 2025arXiv

citations

Learning from Few Samples: Transformation-Invariant SVMs with Composition and Locality at Multiple Scales

NEURIPS 2022arXiv

citations

Xi Liu

papers (12)

MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models

Wukong: Towards a Scaling Law for Large-Scale Recommendation

TC4D: Trajectory-Conditioned Text-to-4D Generation

AccFlow: Backward Accumulation for Long-Range Optical Flow

Reinforced Few-Shot Acquisition Function Learning for Bayesian Optimization

SensorLM: Learning the Language of Wearable Sensors

CustomListener: Text-guided Responsive Interaction for User-friendly Listening Head Generation

Adversarial Locomotion and Motion Imitation for Humanoid Policy Learning

Test-time Adaptation for Cross-modal Retrieval with Query Shift

ARIG: Autoregressive Interactive Head Generation for Real-time Conversations

Latent Radiance Fields with 3D-aware 2D Representations

Learning from Few Samples: Transformation-Invariant SVMs with Composition and Locality at Multiple Scales

papers (12)

MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models

Wukong: Towards a Scaling Law for Large-Scale Recommendation

TC4D: Trajectory-Conditioned Text-to-4D Generation

AccFlow: Backward Accumulation for Long-Range Optical Flow

Reinforced Few-Shot Acquisition Function Learning for Bayesian Optimization

SensorLM: Learning the Language of Wearable Sensors

CustomListener: Text-guided Responsive Interaction for User-friendly Listening Head Generation

Adversarial Locomotion and Motion Imitation for Humanoid Policy Learning

Test-time Adaptation for Cross-modal Retrieval with Query Shift

ARIG: Autoregressive Interactive Head Generation for Real-time Conversations

Latent Radiance Fields with 3D-aware 2D Representations

Learning from Few Samples: Transformation-Invariant SVMs with Composition and Locality at Multiple Scales