🧑‍🔬 Guanhua Chen

🏛️ Affiliations

🎓Southern University of Science and TechnologyShenzhen · China2025–2026 · 28 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. Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models (2025 · 16 citations)
   Large Reasoning Models such as OpenAI o1, DeepSeek R1 and QwQ solve hard math and coding problems by producing long chains of thought.
2. SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks (2026 · 8 citations)
   Reinforcement learning with verifiable rewards is a common way to improve LLM reasoning, but the two main options each have a cost.
3. G2: Guided Generation for Enhanced Output Diversity in LLMs (2025 · 6 citations)
   LLMs often return near-identical answers when asked the same question repeatedly. This hurts creative writing, best-of-N selection, synthetic data creation and test-time scaling for reasoning. Raising the sampling temperature adds variety but lowers quality, and re-prompting with earlier answers can drift away from…
4. No More Stale Feedback: Co-Evolving Critics for Open-World Agent Learning (2026 · 3 citations)
   Critique-guided reinforcement learning supplements sparse outcome rewards for LLM agents with natural-language feedback.
5. Modeling LLM Unlearning as an Asymmetric Two-Task Learning Problem (2026 · 2 citations)
   LLM unlearning aims to erase targeted knowledge, such as hazardous biosecurity or cybersecurity facts or personal data, while keeping the model generally useful.
6. Beyond Static Rules: Automated Discovery of Latent Vulnerabilities in Text-to-SQL (2026)
   LLM-based Text-to-SQL systems score well on benchmarks such as Spider and BIRD, but they can still fail in hidden ways.
7. CAPruner: Conceptual-Adjacent Scene Graph Pruner for Enhancing 3D Spatial Reasoning of Large Language Models (2026)
   LLM-based systems for 3D vision-language (3D-VL) tasks often describe a scene to the model as a graph of objects and their pairwise spatial relations.
8. Evaluating Memory Capability in Continuous Lifelog Scenario (2026)
   Smart glasses and pocket recorders with always-on microphones can capture a person's everyday spoken interactions.
9. GIFT: Guided Fine-Tuning and Transfer for Enhancing Instruction-Tuned Language Models (2026)
   Adapting instruction-tuned LLMs to a specific domain is risky: fine-tuning them directly can disturb the balance of skills built during post-training.
10. InstructDiff: Domain-Adaptive Data Selection via Contrastive Entropy for Efficient LLM Fine-Tuning (2026)
    Fine-tuning LLMs on entire instruction datasets is expensive and yields diminishing returns. Existing data-selection techniques also tend to work only in the domain they were designed for: methods tuned for general instruction-following transfer poorly to reasoning, and vice versa. InstructDiff addresses this with a…
11. Representation-Guided Parameter-Efficient LLM Unlearning (2026)
    Removing memorized private or harmful content from LLMs without retraining is hard. LoRA-based unlearning methods such as FILA and VILA pick which weights to modify using Fisher-information importance scores. Because of superposition, a single parameter often serves many concepts, so these scores cannot cleanly…

🤝 Co-authors here

12 of 39 co-authors with a page, the most papers together first.

• Yun Chen ×7
• Yang Liu ×5
• Peng Li ×4
• Yixia Li ×4
• Jian Yang ×2
• Jianjie Zheng ×2
• Jiehui Zhao ×2
• Lei Yang ×2
• Zeguan Xiao ×2
• Zhiwen Ruan ×2
• Boyang Xue
• Derek F. Wong

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) ×6: ACL 2026 ×6
• Findings of the Association for Computational Linguistics ×3: Findings of the Association for Computational Linguistics 2026 ×3
• Conference on Empirical Methods in Natural Language Processing (EMNLP): EMNLP 2025

🔗 Cited by

Papers of our library cite their works 34 times (of the 149,439 papers whose bibliographies we read); 16 citing papers with a page here →.

Updated 2 November 2026

↑ back to top

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