Awesome Computer Vision
📄
Papers
🧭
Topics
🔥
Trending
🗺️
Map
🏆
Leaderboards
🎓
Learn
🤖
Ask AI
⋯
More
👥
Authors
📚
Reading Packs
📊
Datasets
🛠️
Tools
📰
News
📝
Blogs
✉️
Newsletter
🎯
Research Radar
🔖
Saved
+ Add Paper
☾
☀
← authors
·
overview
Loading author…
🤖
Ask AI
Lei Hou — most-cited papers & profile · Computer Vision
← authors
·
overview
Lei Hou
28
papers ·
2
citations ·
30
h-index
Nanjing University of Information Science and Technology · People's Liberation Army 401 Hospital · Tsinghua University
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
VerIF: Verification Engineering for Reinforcement Learning in Instruction Following
2025 · 1 citations
VerIF: Verification Engineering for Reinforcement Learning in Instruction Following
2025 · 1 citations
Where Steering Signals Come From: Activation Source Selection in Activation Steering
2026
Boundary-Guided Policy Optimization for Memory-efficient RL of Diffusion Large Language Models
2025
DeepPrune: Parallel Scaling without Inter-trace Redundancy
2025
Establishing Trustworthy LLM Evaluation via Shortcut Neuron Analysis
2025
Pairwise RM: Perform Best-of-N Sampling with Knockout Tournament
2025
ReaRAG: Knowledge-guided Reasoning Enhances Factuality of Large Reasoning Models with Iterative Retrieval Augmented Generation
2025
AGENTIF: Benchmarking Instruction Following of Large Language Models in Agentic Scenarios
2025
Are Reasoning Models More Prone to Hallucination?
2025
DeepPrune: Parallel Scaling without Inter-trace Redundancy
2025
Boundary-Guided Policy Optimization for Memory-efficient RL of Diffusion Large Language Models
2025
AGENTIF: Benchmarking Instruction Following of Large Language Models in Agentic Scenarios
2025
MRCEval: A Comprehensive, Challenging and Accessible Machine Reading Comprehension Benchmark
2025
Pre-training Language Model Incorporating Domain-specific Heterogeneous Knowledge into A Unified Representation
2021
Topics
Training Techniques
Evaluation
In-Context Learning
Fine-Tuning
Reinforcement Learning
Safety & Alignment
reasoning
RAG
Efficiency
Prompting