Tianjin Huang
13 papers · 2021–2026 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (17) π Academic Marathon (5) π Conference Polyglot (7) π Interdisciplinary Bridge π§ Keyword Pioneer
π£
Hot Topic Early Bird
π
Conference Polyglot
(7)
π
Triple Crown
π
Grand Slam
β‘
Prolific Year
(6)
π
Century Club
(12)
β
The Questioner
Conferences
ICLR (4)
AAAI (3)
ICML (2)
ACML (1)
MICCAI (1)
NIPS (1)
UAI (1)
Top co-authors
Keywords
model compression
(4)
neural network pruning
(2)
neural network sparsification
(2)
feature learning
(1)
transfer learning
(1)
causal discovery
(1)
model robustness
(1)
self-supervised learning
(1)
knowledge distillation
(1)
network pruning
(1)
adversarial training
(1)
neural network optimization
(1)
time series forecasting
(1)
model pruning
(1)
multivariate time series
(1)
convolutional neural network
(1)
ensemble method
(1)
model ensemble
(1)
dynamic sparse training
(1)
weight interpolation
(1)
Papers
TimeCAP: A Channel-Aware Pre-Training Framework for Multivariate Time Series Forecasting
AAAI 2026
Visual Prompting Upgrades Neural Network Sparsification: A Data-Model Perspective
AAAI 2025
Composable Interventions for Language Models
ICLR 2025
SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training
ICLR 2025
Enhancing Robust Fairness via Confusional Spectral Regularization
ICLR 2025
LIFT the Veil for the Truth: Principal Weights Emerge after Rank Reduction for Reasoning-Focused Supervised Fine-Tuning
ICML 2025
LKA: Large Kernel Adapter for Enhanced Medical Image Classification
MICCAI 2025
Lottery Pools: Winning More by Interpolating Tickets without Increasing Training or Inference Cost
AAAI 2023
Are Large Kernels Better Teachers than Transformers for ConvNets?
ICML 2023
Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together!
ICLR 2023
Dynamic Sparsity Is Channel-Level Sparsity Learner
NIPS 2023
Superposing many tickets into one: A performance booster for sparse neural network training
UAI 2022
calibrated adversarial training
ACML 2021