Feiteng Fang
12 papers · 2024–2026 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (5) 🐝 Cross-Pollinator (12)
🌍
Conference Polyglot
(5)
🐝
Cross-Pollinator
(12)
👥
Mega-Team
(26)
🗃️
Keyword Collector
(57)
⚡
Prolific Year
(7)
💎
Century Club
(11)
❓
The Questioner
Conferences
ACL (6)
EMNLP (3)
COLING (1)
NAACL (1)
NIPS (1)
Top co-authors
Keywords
large language model
(6)
multimodal large language model
(3)
higher-order perception
(2)
benchmark evaluation
(2)
reward model
(2)
hallucination mitigation
(2)
transfer learning
(1)
dialogue generation
(1)
policy optimization
(1)
speech synthesis
(1)
direct preference optimization
(1)
multimodal learning
(1)
image captioning
(1)
adversarial training
(1)
reward modeling
(1)
bradley-terry model
(1)
model alignment
(1)
preference learning
(1)
noise robustness
(1)
instruction tuning
(1)
Papers
Act-Adaptive Margin: Dynamically Calibrating Reward Models for Subjective Ambiguity
ACL 2026
CPO: Addressing Reward Ambiguity in Role-playing Dialogue via Comparative Policy Optimization
EMNLP 2025
COIG-CQIA: Quality is All You Need for Chinese Instruction Fine-tuning
NAACL 2025
LIME: Less Is More for MLLM Evaluation
ACL 2025
Reverse Preference Optimization for Complex Instruction Following
ACL 2025
Can MLLMs Understand the Deep Implication Behind Chinese Images?
ACL 2025
Expanding before Inferring: Enhancing Factuality in Large Language Models through Premature Layers Interpolation
EMNLP 2025
OmniCharacter: Towards Immersive Role-Playing Agents with Seamless Speech-Language Personality Interaction
ACL 2025
CLHA: A Simple Yet Effective Contrastive Learning Framework for Human Alignment
COLING 2024
Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Training
ACL 2024
II-Bench: An Image Implication Understanding Benchmark for Multimodal Large Language Models
NIPS 2024
DEFT: Distribution-guided Efficient Fine-Tuning for Human Alignment
EMNLP 2024