🧑‍🔬 Trung Le

🏛️ Affiliations

🎓Monash UniversityMelbourne · Australia2026 · 7 paperscurrent

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. EMO: Embedding Model Distillation via Intra-Model Relation and Optimal Transport Alignments (2025 · 10 citations)
   Large text embedding models such as LLM2Vec are expensive to deploy. Knowledge distillation can compress them, but it gets harder when the teacher and the student split text with different tokenizers. Earlier cross-tokenizer KD (CTKD) methods mostly match final outputs or logits. They ignore the relational knowledge…
2. CTPD: Cross Tokenizer Preference Distillation (2026 · 8 citations)
   Small language models are cheaper to deploy but harder to align with human preferences. One remedy is to distill alignment from a larger, already-aligned teacher, so the expensive alignment step is paid only once. The richest form of this is white-box distillation, which uses the teacher's logits rather than its…
3. Beyond Coherence: Improving Temporal Consistency and Interpretability in Dynamic Topic Models (2026 · 1 citation)
   Dynamic topic models track how themes in timestamped collections appear, change and fade. The authors identify three weaknesses in current approaches. Encoders learn only from bag-of-words counts and ignore knowledge in pre-trained language models. Topics in neighbouring time slices are usually linked one-to-one, so…
4. Layer-Wise High-Impact Parameter Ratio Optimization in Post-Training Quantization for Large Language Models (2026)
   Post-training quantization (PTQ) of LLMs works well at 4 bits but degrades badly at around 2–3 bits. A major cause is a small set of high-impact weights. Earlier fixes such as AWQ, CherryQ and SqueezeLLM protect these weights with one fixed ratio for every layer. Some of them also use element-wise or non-uniform…
5. LLM-XTM: Enhancing Cross-Lingual Topic Models with Large Language Models (2026)
   Cross-lingual topic models try to find themes shared across languages. They depend on limited bilingual resources such as seed dictionaries, document embeddings or parallel corpora, so paired topics often drift apart in meaning. Earlier LLM-assisted methods either query the model for every document, which is costly…
6. MemORAI: Memory Organization and Retrieval via Adaptive Graph Intelligence for LLM Conversational Agents (2026)
   LLM-based conversational agents cannot remember users across long, multi-session interactions. Current graph-based memory stores also have problems: they keep too much generic chatter, they cannot show which dialogue turn a fact came from, and they rank evidence the same way regardless of the question. MemORAI…

🤝 Co-authors here

9 co-authors with a page, the most papers together first.

• Linh Ngo Van ×5
• Nguyen Thi Ngoc Diep ×3
• Dinh Viet Sang ×2
• Minh Chu Xuan ×2
• Cuong Pham
• Ngan Nguyen
• Thien Huu Nguyen
• Truong Nguyen
• Tu Vu

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Annual Meeting of the Association for Computational Linguistics (ACL) ×2: ACL 2026 ×2
• Findings of the Association for Computational Linguistics ×2: Findings of the Association for Computational Linguistics 2026 ×2
• Conference on Empirical Methods in Natural Language Processing (EMNLP): EMNLP 2025

🔗 Cited by

Papers of our library cite their works 17 times (of the 149,439 papers whose bibliographies we read); 3 citing papers with a page here →.

Updated 1 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/trung-le/