Fengli Xu
9 papers · 2021–2026 · 5 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 ↓+1 more ↓ Show less ↑
π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (23) π Grand Slam
ποΈ
Keyword Collector
(55)
Venues
Top co-authors
Research topics
Artificial Intelligence
(8)
Core AI
(8)
Machine Learning
(5)
Deep Learning
(3)
Architectures
(2)
Core Methods
(2)
Models
(2)
Optimization & Theory
(2)
Computer Vision
(1)
Data Science & Analytics
(1)
Natural Language Processing
(1)
Analysis
(1)
Application Areas
(1)
Applications Β· Data Science & Analytics
(1)
Applications Β· Natural Language Processing
(1)
Keywords
large language model
(2)
trajectory prediction
(1)
hybrid language model
(1)
feature disentanglement
(1)
bayesian sampling
(1)
language model
(1)
reward model
(1)
tool use
(1)
text embedding
(1)
sparse autoencoder
(1)
prompt optimization
(1)
retrieval-augmented generation
(1)
value model
(1)
citation prediction
(1)
graph structure
(1)
core citation
(1)
candidate retrieval
(1)
node representation
(1)
llm agent
(1)
attention mechanism
(1)
Papers
AgentSwift: Efficient LLM Agent Design via Value-Guided Hierarchical Search
AAAI 2026
Controllable LLM Reasoning via Sparse Autoencoder-Based Steering
ACL 2026
Diffuse Thinking: Exploring Diffusion Language Models as Efficient Thought Proposers for Reasoning
ACL 2026
ResMAS: Resilience Optimization in LLM-based Multi-agent Systems
AAAI 2026
AgentSquare: Automatic LLM Agent Search in Modular Design Space
ICLR 2025
Token Signature: Predicting Chain-of-Thought Gains with Token Decoding Feature in Large Language Models
ICML 2025
HLM-Cite: Hybrid Language Model Workflow for Text-based Scientific Citation Prediction
NeurIPS 2024
AttnMove: History Enhanced Trajectory Recovery via Attentional Network
AAAI 2021
Automorphic Equivalence-aware Graph Neural Network
NeurIPS 2021