Margaret Li
9 papers · 2019–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π Conference Polyglot (4) π Academic Marathon (6) π Renaissance Researcher (5) π Interdisciplinary Bridge π Cross-Pollinator (15)
πΊοΈ
Taxonomy Completionist
(19)
π§
Keyword Pioneer
π£
Hot Topic Early Bird
π§¬
Topic Evolution
Conferences
ACL (3)
NAACL (3)
ICLR (2)
EMNLP (1)
Top co-authors
Keywords
dialogue system
(2)
reinforcement learning
(1)
zero-shot learning
(1)
transfer learning
(1)
model calibration
(1)
natural language inference
(1)
cross-lingual transfer
(1)
natural language generation
(1)
dialogue generation
(1)
text generation
(1)
toxicity detection
(1)
model architecture
(1)
adversarial training
(1)
affective computing
(1)
maximum likelihood
(1)
model ensemble
(1)
model scaling
(1)
inference efficiency
(1)
parameter efficiency
(1)
conversational agent
(1)
Papers
(Mis)Fitting Scaling Laws: A Survey of Scaling Law Fitting Techniques in Deep Learning
ICLR 2025
Byte Latent Transformer: Patches Scale Better Than Tokens
ACL 2025
In-Context Pretraining: Language Modeling Beyond Document Boundaries
ICLR 2024
Breaking the Curse of Multilinguality with Cross-lingual Expert Language Models
EMNLP 2024
Overconfidence in the Face of Ambiguity with Adversarial Data
NAACL 2022
How to Motivate Your Dragon: Teaching Goal-Driven Agents to Speak and Act in Fantasy Worlds
NAACL 2021
Bot-Adversarial Dialogue for Safe Conversational Agents
NAACL 2021
Donβt Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training
ACL 2020
Towards Empathetic Open-domain Conversation Models: A New Benchmark and Dataset
ACL 2019