Jiwei Tang
8 papers · 2025–2026 · 4 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 · Bronze
🗺️
Taxonomy Completionist
(19)
⭐
Rising Star
(8)
⚡
Prolific Year · Productive
Top co-authors
Research topics
Artificial Intelligence
(7)
Core AI
(7)
Deep Learning
(4)
Machine Learning
(4)
Natural Language Processing
(2)
Application Areas
(2)
Architectures
(2)
Learning Types · Deep Learning
(2)
Core Methods
(1)
Generation
(1)
Learning Paradigms
(1)
Learning Types · Machine Learning
(1)
Optimization & Theory
(1)
Resources & Methods
(1)
Techniques
(1)
Keywords
context compression
(3)
large language model
(3)
attention mechanism
(2)
zero-shot learning
(1)
policy optimization
(1)
sequential decision making
(1)
knowledge distillation
(1)
question answering
(1)
text summarization
(1)
instruction tuning
(1)
np-hard optimization
(1)
recommendation system
(1)
retrieval-augmented generation
(1)
context window
(1)
in-context example
(1)
training-free method
(1)
long context
(1)
prompt compression
(1)
token-level compression
(1)
long-context modeling
(1)
Papers
CoMeT: Collaborative Memory Transformer for Efficient Long Context Modeling
ACL 2026
CoS: Towards Optimal Event Scheduling via Chain-of-Scheduling
AAAI 2026
GMSA: Enhancing Context Compression via Group Merging and Layer Semantic Alignment
ACL 2026
Length-Adaptive Interest Network for Balancing Long and Short Sequence Modeling in CTR Prediction
AAAI 2026
Read As Human: Compressing Context via Parallelizable Close Reading and Skimming
ACL 2026
DAST: Context-Aware Compression in LLMs via Dynamic Allocation of Soft Tokens
ACL 2025
Perception Compressor: A Training-Free Prompt Compression Framework in Long Context Scenarios
NAACL 2025
RAISE: Reinforced Adaptive Instruction Selection For Large Language Models
EMNLP 2025