Runze Xia
3 papers · 2024–2026 · 3 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 ↓
🌍
Conference Polyglot · Bronze
Top co-authors
Research topics
Keywords
uncertainty quantification
(2)
model calibration
(1)
language model
(1)
feed-forward network
(1)
causal intervention
(1)
large language model
(1)
reliability assessment
(1)
model trustworthiness
(1)
hidden state dynamics
(1)
language model trustworthiness
(1)
internal representation analysis
(1)
semantic dynamics
(1)
probabilistic modeling
(1)
decoupled update dynamics
(1)
Papers
DUD: Decoupled Update Dynamics for Reliable Uncertainty Quantification in Large Language Models
ACL 2026
Sampling-Free Uncertainty Quantification via Hidden State Dynamics in Language Models
AAAI 2026
Decoding the Echoes of Vision from fMRI: Memory Disentangling for Past Semantic Information
EMNLP 2024