Weida Wang
6 papers · 2024–2026 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Silver
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(18)
🐣
Hot Topic Early Bird
Top co-authors
Research topics
Deep Learning
(5)
Artificial Intelligence
(4)
Core AI
(4)
Models
(3)
Computer Vision
(2)
Machine Learning
(2)
Architectures
(2)
Mathematics & Optimization
(1)
Reinforcement Learning
(1)
Analysis
(1)
Generation
(1)
Learning Types · Machine Learning
(1)
Learning Types · Deep Learning
(1)
Mathematics
(1)
Methods
(1)
Keywords
information theory
(1)
neural network architecture
(1)
reinforcement learning
(1)
few-shot learning
(1)
ensemble learning
(1)
direct preference optimization
(1)
talking face generation
(1)
preference optimization
(1)
computational efficiency
(1)
vision-language model
(1)
dynamic early exit
(1)
multimodal reasoning
(1)
temporal coherence
(1)
latent diffusion model
(1)
temporal consistency
(1)
depth denoising
(1)
multi-source transfer learning
(1)
critic model
(1)
information-theoretic metric
(1)
time-of-flight sensor
(1)
Papers
Step-GRPO: Internalizing Dynamic Early Exit for Efficient Reasoning
ACL 2026
Consistent Time-of-Flight Depth Denoising via Graph-Informed Geometric Attention
ICCV 2025
Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoning
CVPR 2025
Token Statistics Transformer: Linear-Time Attention via Variational Rate Reduction
ICLR 2025
FaceChain-ImagineID: Freely Crafting High-Fidelity Diverse Talking Faces from Disentangled Audio
CVPR 2024
H-ensemble: An Information Theoretic Approach to Reliable Few-Shot Multi-Source-Free Transfer
AAAI 2024