Kejing Xia
3 papers · 2025–2026 · 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
token filtering
(2)
long-context understanding
(2)
state space model
(2)
hidden state
(2)
beam search
(1)
long context
(1)
process reward model
(1)
token reduction
(1)
hybrid inference
(1)
test-time compute
(1)
attention mechanism
(1)
context length generalization
(1)
receptive field
(1)
inference optimization
(1)
best-of-n sampling
(1)
Papers
Think Hard Only When Needed: A Hybrid Best-of-N and Beam Search for Efficient Test-Time Compute
EACL 2026
LAMB: A Training-Free Method to Enhance the Long-Context Understanding of SSMs via Attention-Guided Token Filtering
ACL 2025
LongMamba: Enhancing Mamba's Long-Context Capabilities via Training-Free Receptive Field Enlargement
ICLR 2025