Ali Anwar
5 papers · 2021–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (11) π Conference Polyglot (4) π Interdisciplinary Bridge π Cross-Pollinator (15) π§ Keyword Pioneer
π£
Hot Topic Early Bird
β
The Questioner
Conferences
ICLR (2)
AAAI (1)
EMNLP (1)
NAACL (1)
Top co-authors
Keywords
federated learning
(1)
adversarial robustness
(1)
backdoor attack
(1)
data heterogeneity
(1)
inference efficiency
(1)
beam search
(1)
step-by-step reasoning
(1)
process reward model
(1)
safety classification
(1)
llm output
(1)
large language model
(1)
inference compute
(1)
early rejection
(1)
content detection
(1)
client-side attack
(1)
Papers
Accelerating LLM Reasoning via Early Rejection with Partial Reward Modeling
EMNLP 2025
MAP: Multi-Human-Value Alignment Palette
ICLR 2025
Probe Pruning: Accelerating LLMs through Dynamic Pruning via Model-Probing
ICLR 2025
AID: Adaptive Integration of Detectors for Safe AI with Language Models
NAACL 2025
Curse or Redemption? How Data Heterogeneity Affects the Robustness of Federated Learning
AAAI 2021