Mehrdad Farajtabar
30 papers · 2013–2026 · 11 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 ↓+11 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (70) π Conference Polyglot Β· Gold π Academic Marathon Β· Half π Interdisciplinary Bridge Β· Gold π£ Hot Topic Early Bird
π
Grand Slam
π€
Dynamic Duo
(11)
π
Keyword Champion
π§
Keyword Pioneer
π
Renaissance Researcher
(8)
π₯
Unstoppable Β· Silver
β‘
Prolific Year Β· Productive
π
Conference Pioneer
π
Century Club Β· Bronze
π
Trend Setter
ποΈ
Keyword Collector
(151)
Venues
Top co-authors
Research topics
Machine Learning
(26)
Artificial Intelligence
(13)
Optimization & Theory
(13)
Deep Learning
(11)
Core AI
(10)
Learning Types Β· Machine Learning
(10)
Core Methods
(9)
Application Areas
(8)
Mathematics & Optimization
(6)
Reinforcement Learning
(5)
Bayesian & Probabilistic
(5)
Learning Types Β· Deep Learning
(5)
Methods
(5)
Optimization
(5)
Data Science & Analytics
(4)
Keywords
continual learning
(6)
catastrophic forgetting
(5)
hawkes process
(5)
point process
(5)
social network
(4)
convex optimization
(4)
neural network
(3)
model compression
(3)
large language model
(3)
neural network optimization
(3)
knowledge distillation
(3)
temporal point process
(3)
off-policy evaluation
(2)
multivariate hawkes process
(2)
information diffusion
(2)
network evolution
(2)
social network analysis
(2)
transfer learning
(2)
vision foundation model
(2)
adversarial robustness
(1)
Papers
Reasoningβs Razor: Reasoning Improves Accuracy but Hurts Recall at Critical Operating Points in Safety and Hallucination Detection
EACL 2026
GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models
ICLR 2025
Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting
ICML 2025
TiC-LM: A Web-Scale Benchmark for Time-Continual LLM Pretraining
ACL 2025
Knowledge Transfer from Vision Foundation Models for Efficient Training of Small Task-specific Models
ICML 2024
LLM in a flash: Efficient Large Language Model Inference with Limited Memory
ACL 2024
ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models
ICLR 2024
TiC-CLIP: Continual Training of CLIP Models
ICLR 2024
Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset Reinforcement
ICCV 2023
Wide Neural Networks Forget Less Catastrophically
ICML 2022
Linear Mode Connectivity in Multitask and Continual Learning
ICLR 2021
A Maximum-Entropy Approach to Off-Policy Evaluation in Average-Reward MDPs
NeurIPS 2020
Improved Knowledge Distillation via Teacher Assistant
AAAI 2020
Learning to Incentivize Other Learning Agents
NeurIPS 2020
Orthogonal Gradient Descent for Continual Learning
AISTATS 2020
Self-Distillation Amplifies Regularization in Hilbert Space
NeurIPS 2020
Understanding the Role of Training Regimes in Continual Learning
NeurIPS 2020
Cross-View Policy Learning for Street Navigation
ICCV 2019
DyRep: Learning Representations over Dynamic Graphs
ICLR 2019
Discrete Interventions in Hawkes Processes with Applications in Invasive Species Management
IJCAI 2018
More Robust Doubly Robust Off-policy Evaluation
ICML 2018
COEVOLVE: A Joint Point Process Model for Information Diffusion and Network Evolution
JMLR 2017
Fake News Mitigation via Point Process Based Intervention
ICML 2017
Wasserstein Learning of Deep Generative Point Process Models
NeurIPS 2017
Learning Granger Causality for Hawkes Processes
ICML 2016
Multistage Campaigning in Social Networks
NeurIPS 2016
Back to the Past: Source Identification in Diffusion Networks from Partially Observed Cascades
AISTATS 2015
COEVOLVE: A Joint Point Process Model for Information Diffusion and Network Co-evolution
NeurIPS 2015
Shaping Social Activity by Incentivizing Users
NeurIPS 2014
From Local Similarity to Global Coding: An Application to Image Classification
CVPR 2013