Heda Wang
9 papers · 2024–2025 · 7 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 · Silver
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(26)
⚡
Prolific Year · Productive
Top co-authors
Research topics
Machine Learning
(8)
Artificial Intelligence
(7)
Core AI
(7)
Natural Language Processing
(5)
Optimization & Theory
(4)
Deep Learning
(3)
Generation
(3)
Learning Types · Machine Learning
(3)
Learning Types · Deep Learning
(3)
Resources & Methods
(3)
Application Areas
(2)
Core Methods
(2)
Computer Science
(1)
Applications · Natural Language Processing
(1)
Applications · Computer Science
(1)
Keywords
large language model
(6)
chain-of-thought reasoning
(2)
benchmark evaluation
(2)
representation learning
(2)
dense retrieval
(1)
demonstration learning
(1)
in-context learning
(1)
document retrieval
(1)
knowledge distillation
(1)
language model alignment
(1)
semantic search
(1)
parameter efficient
(1)
generative model
(1)
early stopping
(1)
expectation-maximization algorithm
(1)
text generation
(1)
latent representation
(1)
pearson correlation
(1)
text embedding
(1)
attention mechanism
(1)
Papers
CogLM: Tracking Cognitive Development of Large Language Models
NAACL 2025
BatchEval: Towards Human-like Text Evaluation
ACL 2024
Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step Reasoning
ICLR 2024
Focused Large Language Models are Stable Many-Shot Learners
EMNLP 2024
Generative Dense Retrieval: Memory Can Be a Burden
EACL 2024
Instruction Embedding: Latent Representations of Instructions Towards Task Identification
NeurIPS 2024
Integrate the Essence and Eliminate the Dross: Fine-Grained Self-Consistency for Free-Form Language Generation
ACL 2024
Poor-Supervised Evaluation for SuperLLM via Mutual Consistency
ACL 2024
Turning Dust into Gold: Distilling Complex Reasoning Capabilities from LLMs by Leveraging Negative Data
AAAI 2024