Albina Burlova
3 papers · 2026–2026 · 1 venue · 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.
Venues
Top co-authors
Research topics
Keywords
language model
(1)
world knowledge
(1)
common sense
(1)
learned pooling
(1)
frontier model
(1)
latent compression
(1)
detector
(1)
auroc
(1)
web
(1)
context budget
(1)
vla models
(1)
act2answer
(1)
embodied answer-selection
(1)
layerwise intent probing
(1)
answer perplexity
(1)
direct projection
(1)
selector-specific readers
(1)
likelihood signals
(1)
Papers
Does VLA Even Know the Basics? Limitations in Commonsense and World Knowledge of VLA Models
EMNLP 2026
PAWN++ in the Wild: Evaluating AI-Generated Text Detection on the Web
EMNLP 2026
What Should Occupy the Context Budget? Latent Compression versus Budget-Matched Truncation in Document QA
EMNLP 2026