Vinh Q. Tran
8 papers · 2022–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (13) π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (5) π£ Hot Topic Early Bird
π
Cross-Pollinator
(12)
π₯
Mega-Team
(20)
β
The Questioner
Conferences
ICLR (4)
ACL (1)
EMNLP (1)
NAACL (1)
NIPS (1)
Top co-authors
Keywords
continual learning
(1)
zero-shot learning
(1)
cross-lingual transfer
(1)
language modeling
(1)
document retrieval
(1)
next-token prediction
(1)
evaluation benchmark
(1)
reasoning evaluation
(1)
reasoning benchmark
(1)
long-range dependency
(1)
multilingual language model
(1)
semantic token
(1)
general reasoning
(1)
forgetting mitigation
(1)
pseudo-query generation
(1)
large language model
(1)
differentiable search index
(1)
fractal analysis
(1)
subword semantic
(1)
transformer memory
(1)
Papers
Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal Sampling
ICLR 2025
BIG-Bench Extra Hard
ACL 2025
Tomato, Tomahto, Tomate: Do Multilingual Language Models Understand Based on Subword-Level Semantic Concepts?
NAACL 2025
Fractal Patterns May Illuminate the Success of Next-Token Prediction
NIPS 2024
UL2: Unifying Language Learning Paradigms
ICLR 2023
DSI++: Updating Transformer Memory with New Documents
EMNLP 2023
Charformer: Fast Character Transformers via Gradient-based Subword Tokenization
ICLR 2022
ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning
ICLR 2022