EDBT 2026 Demo / reviewers in the wild / expert
Jui-Hung Cheng
dblp:181/5100
· DBLP profile ↗
2ranked-venue papers
0as first author
1since 2021 · last 2025
0000-0003-2865-2943ORCID · corroborated
Domains — the database's venue-derived domains; a paper can count in several
Artificial intelligence and machine learning · 1 · 1 since 2021Graphics, computer vision, multimedia, augmented reality and games · 1
Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.
| Artificial intelligence
1 paper |
Language models and text generation · 77% Efficient and distributed learning · 23% | |
| Software engineering, system software, and programming languages
1 paper |
Compilers and program optimization · 100% |
Topics — the 6 heaviest of 6, each with the papers that count most for it
| Topic | Weight | Papers | Last | Evidence papers |
|---|---|---|---|---|
Natural language and speech › Language models and text generation › decoding › decoding strategy
beam search |
0.9 | 1 | 2025 | Efficient Beam Search for Large Language Models Using Trie-Based Decoding · EMNLP 2025 |
Natural language and speech › Language models and text generation
decoding |
0.9 | 1 | 2025 | Efficient Beam Search for Large Language Models Using Trie-Based Decoding · EMNLP 2025 |
Machine learning › Efficient and distributed learning
inference efficiency |
0.9 | 1 | 2025 | Efficient Beam Search for Large Language Models Using Trie-Based Decoding · EMNLP 2025 |
Natural language and speech › Language models and text generation › large language model inference
KV cache sharing |
0.9 | 1 | 2025 | Efficient Beam Search for Large Language Models Using Trie-Based Decoding · EMNLP 2025 |
Natural language and speech › Language models and text generation › text summarization
abstractive summarization |
0.3 | 1 | 2025 | Efficient Beam Search for Large Language Models Using Trie-Based Decoding · EMNLP 2025 |
Compilers and program optimization
code generation |
0.3 | 1 | 2025 | Efficient Beam Search for Large Language Models Using Trie-Based Decoding · EMNLP 2025 |
Methods — techniques the papers use, named apart from their topics
trie-based parallel decoding · 1.7KV cache sharing · 1.7
| Year | Publication | Venue | Position |
|---|---|---|---|
| 2025 | Efficient Beam Search for Large Language Models Using Trie-Based DecodingabstractThis work presents a novel trie (prefix-tree)based parallel decoding method that addresses the memory inefficiency of batch-based beam search.By sharing a single KV cache across beams with common prefixes, our approach dramatically reduces memory usage and enables efficient decoding.We evaluated our method across three attention architectures, Multi-Head Attention (Phi-3.5-miniinstruct),Grouped Query Attention (Llama-3.1-8B-Instruct),and Sliding Window Attention (Mistral-Small-24B-Instruct-2501), using CN-N/DailyMail for abstractive summarization and HumanEval for code generation.Our experiments demonstrate substantial memory savings (4-8×) and up to 2.4× faster decoding, without compromising generation quality.These results highlight our method's suitability for memory-constrained environments and largescale deployments. Brian J. Chan, Mao Xun Huang, Jui-Hung Cheng, Chao-Ting Chen, Hen-Hsen Huang |
EMNLP | 3 |
| 2016 | A study of product experience obtained from multimodal interactive displays
Shuo-Fang Liu, Jui-Hung Cheng, Wan-Jiun Chen |
Multim. Tools Appl. | 2 |