Yifan Zeng
5 papers · 2025–2025 · 2 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
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(17)
⭐
Rising Star
(5)
⚡
Prolific Year · Productive
Top co-authors
Research topics
Artificial Intelligence
(5)
Core AI · Artificial Intelligence
(5)
Machine Learning
(3)
Deep Learning
(2)
Natural Language Processing
(2)
Applications · Natural Language Processing
(2)
Learning Types · Machine Learning
(2)
Optimization & Theory
(2)
Computer Vision
(1)
Applications · Computer Vision
(1)
Core AI · Computer Vision
(1)
Domain-Specific
(1)
Learning Types · Deep Learning
(1)
Models
(1)
Resources & Methods
(1)
Keywords
language model alignment
(2)
information retrieval
(1)
preference optimization
(1)
multimodal learning
(1)
safety alignment
(1)
reinforcement learning from human feedback
(1)
iterative refinement
(1)
pairwise ranking
(1)
multimodal retrieval
(1)
adversarial attack
(1)
tree search
(1)
language model
(1)
best-of-n sampling
(1)
retrieval-augmented generation
(1)
inference-time alignment
(1)
generative optimization
(1)
scalable optimization
(1)
margin-based loss
(1)
agent system
(1)
llm agent
(1)
Papers
A Common Pitfall of Margin-based Language Model Alignment: Gradient Entanglement
ICLR 2025
Divide, Optimize, Merge: Scalable Fine-Grained Generative Optimization for LLM Agents
EMNLP 2025
SimpleDoc: Multi‐Modal Document Understanding with Dual‐Cue Page Retrieval and Iterative Refinement
EMNLP 2025
The Ranking Blind Spot: Decision Hijacking in LLM-based Text Ranking
EMNLP 2025
TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling
EMNLP 2025