Peng Xu

papers

1,302

total citations

papers (15)

MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI

ICML 2024arXiv

163

citations

Exploring the Limits of Domain-Adaptive Training for Detoxifying Large-Scale Language Models

NEURIPS 2022arXiv

citations

DiffRate : Differentiable Compression Rate for Efficient Vision Transformers

ICCV 2023arXiv

citations

InstructRetro: Instruction Tuning post Retrieval-Augmented Pretraining

ICML 2024arXiv

citations

BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocation

ICLR 2024arXiv

citations

Adaptive Multi-Modal Cross-Entropy Loss for Stereo Matching

CVPR 2024arXiv

citations

LAKE-RED: Camouflaged Images Generation by Latent Background Knowledge Retrieval-Augmented Diffusion

CVPR 2024arXiv

citations

AdsQA: Towards Advertisement Video Understanding

ICCV 2025arXiv

citations

CVFusion: Cross-View Fusion of 4D Radar and Camera for 3D Object Detection

ICCV 2025arXiv

citations

SCKD: Semi-Supervised Cross-Modality Knowledge Distillation for 4D Radar Object Detection

AAAI 2025arXiv

citations

DeepChange: A Long-Term Person Re-Identification Benchmark with Clothes Change

ICCV 2023

citations

p-Laplacian Adaptation for Generative Pre-trained Vision-Language Models

AAAI 2024arXiv

citations

Peng Xu

papers (15)

OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models

Factuality Enhanced Language Models for Open-Ended Text Generation

PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs

MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI

Exploring the Limits of Domain-Adaptive Training for Detoxifying Large-Scale Language Models

DiffRate : Differentiable Compression Rate for Efficient Vision Transformers

InstructRetro: Instruction Tuning post Retrieval-Augmented Pretraining

BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocation

Adaptive Multi-Modal Cross-Entropy Loss for Stereo Matching

LAKE-RED: Camouflaged Images Generation by Latent Background Knowledge Retrieval-Augmented Diffusion

AdsQA: Towards Advertisement Video Understanding

CVFusion: Cross-View Fusion of 4D Radar and Camera for 3D Object Detection

SCKD: Semi-Supervised Cross-Modality Knowledge Distillation for 4D Radar Object Detection

DeepChange: A Long-Term Person Re-Identification Benchmark with Clothes Change

p-Laplacian Adaptation for Generative Pre-trained Vision-Language Models

papers (15)

OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models

Factuality Enhanced Language Models for Open-Ended Text Generation

PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs

MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI

Exploring the Limits of Domain-Adaptive Training for Detoxifying Large-Scale Language Models

DiffRate : Differentiable Compression Rate for Efficient Vision Transformers

InstructRetro: Instruction Tuning post Retrieval-Augmented Pretraining

BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocation

Adaptive Multi-Modal Cross-Entropy Loss for Stereo Matching

LAKE-RED: Camouflaged Images Generation by Latent Background Knowledge Retrieval-Augmented Diffusion

AdsQA: Towards Advertisement Video Understanding

CVFusion: Cross-View Fusion of 4D Radar and Camera for 3D Object Detection

SCKD: Semi-Supervised Cross-Modality Knowledge Distillation for 4D Radar Object Detection

DeepChange: A Long-Term Person Re-Identification Benchmark with Clothes Change

p-Laplacian Adaptation for Generative Pre-trained Vision-Language Models