Yiwei Li
33 papers · 2021–2026 · 10 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
🐝 Cross-Pollinator (5) 🌍 Conference Polyglot (9) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌈 Renaissance Researcher (7)
🌈
Renaissance Researcher
(7)
🌍
Conference Polyglot
(9)
🤝
Dynamic Duo
(24)
🏆
Keyword Champion
(2)
💎
Century Club
(31)
⚡
Prolific Year
(5)
❓
The Questioner
🗃️
Keyword Collector
(153)
🔥
Unstoppable
(5)
Conferences
ACL (12)
AAAI (4)
EMNLP (4)
ICLR (3)
NAACL (3)
NIPS (3)
EACL (1)
IJCNLP (1)
MICCAI (1)
MIDL (1)
Top co-authors
Keywords
large language model
(10)
dialogue generation
(8)
representation learning
(4)
knowledge distillation
(4)
dialogue system
(3)
text generation
(3)
latent variable
(3)
in-context learning
(2)
variational inference
(2)
response diversity
(2)
benchmark evaluation
(2)
self-supervised learning
(2)
language model alignment
(2)
chain-of-thought reasoning
(2)
response generation
(2)
latent variable model
(2)
conditional variational autoencoder
(2)
mathematical reasoning
(2)
embedding space
(1)
attention mechanism
(1)
Papers
LLM-Powered Benchmark Factory: Reliable, Generic, and Efficient
ACL 2026
TTT-UNet: Enhancing U-Net with Test-Time Training Layers for Biomedical Image Segmentation
MIDL 2026
From Sub-Ability Diagnosis to Human-Aligned Generation: Bridging the Gap for Text Length Control via MarkerGen
ACL 2025
SceneX: Procedural Controllable Large-Scale Scene Generation
AAAI 2025
Jailbreaking? One Step Is Enough!
ACL 2025
Beyond One-Size-Fits-All: Tailored Benchmarks for Efficient Evaluation
ACL 2025
Revisiting Self-Consistency from Dynamic Distributional Alignment Perspective on Answer Aggregation
ACL 2025
InsBank: Evolving Instruction Subset for Ongoing Alignment
EMNLP 2025
Speculative Decoding for Multi-Sample Inference
EMNLP 2025
UniCBE: An Uniformity-driven Comparing Based Evaluation Framework with Unified Multi-Objective Optimization
ICLR 2025
ECHOPulse: ECG Controlled Echocardio-gram Video Generation
ICLR 2025
SAMed-2: Selective Memory Enhanced Medical Segment Anything Model
MICCAI 2025
CogLM: Tracking Cognitive Development of Large Language Models
NAACL 2025
Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning
NAACL 2025
Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step Reasoning
ICLR 2024
Instruction Embedding: Latent Representations of Instructions Towards Task Identification
NIPS 2024
Generative Dense Retrieval: Memory Can Be a Burden
EACL 2024
Focused Large Language Models are Stable Many-Shot Learners
EMNLP 2024
Turning Dust into Gold: Distilling Complex Reasoning Capabilities from LLMs by Leveraging Negative Data
AAAI 2024
Eye-gaze Guided Multi-modal Alignment for Medical Representation Learning
NIPS 2024
Integrate the Essence and Eliminate the Dross: Fine-Grained Self-Consistency for Free-Form Language Generation
ACL 2024
BatchEval: Towards Human-like Text Evaluation
ACL 2024
Dynamic Stochastic Decoding Strategy for Open-Domain Dialogue Generation
ACL 2024
Poor-Supervised Evaluation for SuperLLM via Mutual Consistency
ACL 2024
Towards Diverse, Relevant and Coherent Open-Domain Dialogue Generation via Hybrid Latent Variables
AAAI 2023
Heterogeneous-Branch Collaborative Learning for Dialogue Generation
AAAI 2023
Towards Fewer Hallucinations in Knowledge-Grounded Dialogue Generation via Augmentative and Contrastive Knowledge-Dialogue
ACL 2023
NewsDialogues: Towards Proactive News Grounded Conversation
ACL 2023
Better Correlation and Robustness: A Distribution-Balanced Self-Supervised Learning Framework for Automatic Dialogue Evaluation
NIPS 2023
Modeling Complex Dialogue Mappings via Sentence Semantic Segmentation Guided Conditional Variational Auto-Encoder
EMNLP 2022
Diversifying Neural Dialogue Generation via Negative Distillation
NAACL 2022
Generating Relevant and Coherent Dialogue Responses using Self-Separated Conditional Variational AutoEncoders
IJCNLP 2021
Generating Relevant and Coherent Dialogue Responses using Self-Separated Conditional Variational AutoEncoders
ACL 2021