Chen Wei
- Papers
- 24
Cite
Notes
Only stored in your browser.
Authored papers
24MiroEval: Benchmarking Multimodal Deep Research Agents in Process and Outcome
arXiv 2026
MEMO: Memory-Augmented Model Context Optimization for Robust Multi-Turn Multi-Agent LLM Games
arXiv 2026
Chain of World: World Model Thinking in Latent Motion
arXiv 2026
PyVision-RL: Forging Open Agentic Vision Models via RL
arXiv 2026
Perception Encoder: The best visual embeddings are not at the output of the network
arXiv 2025
Play to Generalize: Learning to Reason Through Game Play
arXiv 2025
Scaling Spatial Intelligence with Multimodal Foundation Models
arXiv 2025
PyVision: Agentic Vision with Dynamic Tooling
arXiv 2025
The Quest for Generalizable Motion Generation: Data, Model, and Evaluation
arXiv 2025
Vision-Language-Vision Auto-Encoder: Scalable Knowledge Distillation from Diffusion Models
arXiv 2025
FreeGraftor: Training-Free Cross-Image Feature Grafting for Subject-Driven Text-to-Image Generation
arXiv 2025
SMPLest-X: Ultimate Scaling for Expressive Human Pose and Shape Estimation
arXiv 2025
ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery
arXiv 2024
Models Are Codes: Towards Measuring Malicious Code Poisoning Attacks on Pre-trained Model Hubs
arXiv 2024
AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation
CVPR 2024 1
WHAC: World-grounded Humans and Cameras
arXiv 2024
SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation
smpler-x-scaling-up-expressive-human-pose-and
Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles
arXiv 2023
Masked Autoencoders Enable Efficient Knowledge Distillers
CVPR 2023 1
C3KG: A Chinese Commonsense Conversation Knowledge Graph
arXiv 2022
Unleashing the Power of Visual Prompting At the Pixel Level
arXiv 2022
Masked Feature Prediction for Self-Supervised Visual Pre-Training
CVPR 2022 1
iBOT: Image BERT Pre-Training with Online Tokenizer
arXiv 2021
Writing Polishment with Simile: Task, Dataset and A Neural Approach
arXiv 2020
Affiliations
Frequent co-authors
10from 24 papers