Tao Wei
14 papers · 2016–2026 · 8 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
π Interdisciplinary Bridge π Conference Polyglot (7) π Academic Marathon (9) π£ Hot Topic Early Bird π Cross-Pollinator (12)
π
Conference Polyglot
(7)
π
Academic Marathon
(9)
π£
Hot Topic Early Bird
π§¬
Topic Evolution
π
Century Club
(12)
π
Trend Setter
π₯
Unstoppable
(5)
Conferences
INTERSPEECH (4)
AAAI (2)
ICCV (2)
ICML (2)
ACL (1)
CVPR (1)
EMNLP (1)
ICLR (1)
Top co-authors
Research topics
Keywords
neural network
(2)
speech recognition
(2)
inference acceleration
(2)
automatic speech recognition
(2)
attention mechanism
(1)
knowledge distillation
(1)
3d reconstruction
(1)
hidden state
(1)
object detection
(1)
model architecture
(1)
multi-modal learning
(1)
speech synthesis
(1)
language identification
(1)
gaussian splatting
(1)
intent detection
(1)
instruction following
(1)
saliency map
(1)
deep model
(1)
data augmentation
(1)
transfer learning
(1)
Papers
SRSplat: Feed-Forward Super-Resolution Gaussian Splatting from Sparse Multi-View Images
AAAI 2026
Revisiting the Reliability of Language Models in Instruction-Following
ACL 2026
Growing a Twig to Accelerate Large Vision-Language Models
ICCV 2025
Kona: An Efficient Privacy-Preservation Framework for KNN Classification by Communication Optimization
ICML 2025
βIβve Decided to Leakβ: Probing Internals Behind Prompt Leakage Intents
EMNLP 2025
Dual-Prior Augmented Decoding Network for Long Tail Distribution in HOI Detection
AAAI 2024
E-Paraformer: A Faster and Better Parallel Transformer for Non-autoregressive End-to-End Mandarin Speech Recognition
INTERSPEECH 2024
Improving End-to-End Modeling For Mandarin-English Code-Switching Using Lightweight Switch-Routing Mixture-of-Experts
INTERSPEECH 2023
Counterfactual-based Saliency Map: Towards Visual Contrastive Explanations for Neural Networks
ICCV 2023
Fairness-Aware Adversarial Perturbation Towards Bias Mitigation for Deployed Deep Models
CVPR 2022
Towards Efficiently Learning Monotonic Alignments for Attention-based End-to-End Speech Recognition
INTERSPEECH 2022
FFM: A Frame Filtering Mechanism To Accelerate Inference Speed For Conformer In Speech Recognition
INTERSPEECH 2022
Fooling Detection Alone is Not Enough: Adversarial Attack against Multiple Object Tracking
ICLR 2020
Network Morphism
ICML 2016