Yifan Song
26 papers · 2022–2026 · 8 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
🐝 Cross-Pollinator (12) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (8) 🌈 Renaissance Researcher (9)
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🤝
Dynamic Duo
(17)
⚡
Prolific Year
(11)
🗃️
Keyword Collector
(116)
💎
Century Club
(24)
Conferences
EMNLP (9)
ACL (6)
ICLR (4)
COLING (2)
NAACL (2)
CVPR (1)
ICCV (1)
IJCAI (1)
Top co-authors
Keywords
large language model
(7)
contrastive learning
(4)
catastrophic forgetting
(3)
information bottleneck
(2)
representation learning
(2)
agent system
(2)
text classification
(2)
continual learning
(2)
pretrained language model
(2)
adversarial robustness
(1)
text-to-image synthesis
(1)
video captioning
(1)
knowledge distillation
(1)
knowledge editing
(1)
benchmark evaluation
(1)
neural machine translation
(1)
model calibration
(1)
question answering
(1)
speech recognition
(1)
relation extraction
(1)
Papers
Who Plays Which Role When? Communication Role Dynamics for Peer Recognition and Team Performance Prediction
ACL 2026
ParseJargon: Personalized Real-time Jargon Support in Online Meetings
ACL 2026
More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in KV Cache Compression
EMNLP 2025
Adding Additional Control to One-Step Diffusion with Joint Distribution Matching
ICCV 2025
Exploring Fine-Grained Human Motion Video Captioning
COLING 2025
VL-RewardBench: A Challenging Benchmark for Vision-Language Generative Reward Models
CVPR 2025
The Good, The Bad, and The Greedy: Evaluation of LLMs Should Not Ignore Non-Determinism
NAACL 2025
Decoupled Graph Energy-based Model for Node Out-of-Distribution Detection on Heterophilic Graphs
ICLR 2025
MixEval-X: Any-to-any Evaluations from Real-world Data Mixture
ICLR 2025
Hierarchical Memory Organization for Wikipedia Generation
ACL 2025
Harnessing Webpage UIs for Text-Rich Visual Understanding
ICLR 2025
ISR: Self-Refining Referring Expressions for Entity Grounding
ACL 2025
MPO: Boosting LLM Agents with Meta Plan Optimization
EMNLP 2025
AgentBank: Towards Generalized LLM Agents via Fine-Tuning on 50000+ Interaction Trajectories
EMNLP 2024
Trial and Error: Exploration-Based Trajectory Optimization of LLM Agents
ACL 2024
LongEmbed: Extending Embedding Models for Long Context Retrieval
EMNLP 2024
Watch Every Step! LLM Agent Learning via Iterative Step-level Process Refinement
EMNLP 2024
PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise Training
ICLR 2024
CoUDA: Coherence Evaluation via Unified Data Augmentation
NAACL 2024
InfoCL: Alleviating Catastrophic Forgetting in Continual Text Classification from An Information Theoretic Perspective
EMNLP 2023
Rationale-Enhanced Language Models are Better Continual Relation Learners
EMNLP 2023
Robust Fine-tuning via Perturbation and Interpolation from In-batch Instances
IJCAI 2022
ConFiguRe: Exploring Discourse-level Chinese Figures of Speech
COLING 2022
Calibrating Factual Knowledge in Pretrained Language Models
EMNLP 2022
Learning Robust Representations for Continual Relation Extraction via Adversarial Class Augmentation
EMNLP 2022
The USTC-NELSLIP Offline Speech Translation Systems for IWSLT 2022
ACL 2022