Jason Cong
6 papers · 2023–2025 · 5 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
(16)
⚡
Prolific Year · Productive
Top co-authors
Research topics
Machine Learning
(5)
Application Areas
(5)
Artificial Intelligence
(3)
Core AI
(3)
Optimization & Theory · Machine Learning
(3)
Deep Learning
(2)
Natural Language Processing
(2)
Resources & Methods
(2)
Computer Science
(1)
Applications
(1)
Architectures
(1)
Learning Types
(1)
Models
(1)
Optimization & Theory · Deep Learning
(1)
Techniques
(1)
Keywords
speculative decoding
(2)
high-level synthesis
(2)
hardware design
(2)
efficient inference
(1)
neural network optimization
(1)
efficient computing
(1)
energy efficiency
(1)
spaced repetition
(1)
model inference
(1)
language model
(1)
data selection
(1)
mixture of expert
(1)
data efficiency
(1)
inference optimization
(1)
perplexity reduction
(1)
hierarchical memory
(1)
beam search
(1)
commonsense reasoning
(1)
language model inference
(1)
field programmable gate array
(1)
Papers
Accelerating Large Language Model Pretraining via LFR Pedagogy: Learn, Focus, and Review
CoNLL 2025
Dynamic-Width Speculative Beam Decoding for LLM Inference
AAAI 2025
Hierarchical Mixture of Experts: Generalizable Learning for High-Level Synthesis
AAAI 2025
HMT: Hierarchical Memory Transformer for Efficient Long Context Language Processing
NAACL 2025
Optimized Multi-Token Joint Decoding With Auxiliary Model for LLM Inference
ICLR 2025
Towards a Comprehensive Benchmark for High-Level Synthesis Targeted to FPGAs
NeurIPS 2023