Liang Chen

24

Papers

494

Total Citations

1

Affiliations

Affiliations

School of Computer Science, Peking University

Papers (24)

An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models

Omni-MATH: A Universal Olympiad Level Mathematic Benchmark for Large Language Models

NTPP: Generative Speech Language Modeling for Dual-Channel Spoken Dialogue via Next-Token-Pair Prediction

Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning

Blind Image Deblurring With Local Maximum Gradient Prior

Learning a Non-Blind Deblurring Network for Night Blurry Images

Blind Deblurring for Saturated Images

Self-Supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detection

Geometric Anchor Correspondence Mining With Uncertainty Modeling for Universal Domain Adaptation

Improved Test-Time Adaptation for Domain Generalization

Domain Generalization via Rationale Invariance

OID: Outlier Identifying and Discarding in Blind Image Deblurring

Enhanced Sparse Model for Blind Deblurring

Perceiving and Modeling Density for Image Dehazing

CAR: Class-Aware Regularizations for Semantic Segmentation

Medusa: A Multi-Scale High-order Contrastive Dual-Diffusion Approach for Multi-View Clustering

One Last Attention for Your Vision-Language Model

VQCNIR: Clearer Night Image Restoration with Vector-Quantized Codebook

Parameter-Efficient Fine-Tuning with Discrete Fourier Transform

Large-batch Optimization for Dense Visual Predictions: Training Faster R-CNN in 4.2 Minutes

OST: Improving Generalization of DeepFake Detection via One-Shot Test-Time Training

On the Pareto Front of Multilingual Neural Machine Translation

Towards Hybrid-grained Feature Interaction Selection for Deep Sparse Network

Learning Semantic Representations for Unsupervised Domain Adaptation