🧑‍🔬 Yifan Wang

🏛️ Affiliations

🎓Northeastern UniversityBoston · United States2026 · 1 papercurrent🎓Tsinghua Shenzhen International Graduate SchoolShenzhen · China2026 · 1 papercurrent🎓Tsinghua UniversityBeijing · China2026 · 1 papercurrent🎓University of Electronic Science and Technology of ChinaChengdu · China2026 · 1 papercurrent🎓University of International Business and EconomicsBeijing · China2026 · 1 papercurrent

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. A Thorough Examination of Decoding Methods in the Era of LLMs (2024 · 68 citations)
   Decoding strategies turn a next-token predictor into a usable task solver. However, earlier comparisons of these strategies used task-specific models from before the LLM era, and many new methods have appeared since. The authors benchmark deterministic decoders (greedy, beam search, diverse beam search, contrastive…
2. A Survey on Efficient Large Language Model Training: From Data-centric Perspectives (2025 · 14 citations)
   Post-training is the stage where LLMs acquire instruction following, alignment, reasoning and domain skills.
3. RSA-Control: A Pragmatics-Grounded Lightweight Controllable Text Generation Framework (2024 · 7 citations)
   RSA-Control steers a pretrained language model towards a target attribute (for example non-toxic, or easy to read) without training a classifier.
4. Render-of-Thought: Rendering Textual Chain-of-Thought as Images for Visual Latent Reasoning (2026 · 1 citation)
   Chain-of-Thought (CoT) reasoning improves LLM accuracy, but its long outputs slow inference and use a lot of memory.
5. Calibrating Inference Time Alignment with Sequence-level Risk Accumulation (2026)
   LLM defenses against jailbreaks often over-refuse. They block innocuous requests, such as how to "kill" a Linux process, because single tokens look dangerous. This paper presents SEAT, an inference-time decoding framework named for its approach of accumulating risk over whole sequences to calibrate alignment at test…
6. TiKMiX: Efficient Semi-Dynamic Data Mixture via Data Influence for LLM Pre-training (2026)
   Choosing domain proportions for LLM pre-training data is usually done once, either by hand or with proxy models.
7. UnAC: Adaptive Visual Prompting with Abstraction and Stepwise Checking for Complex Multimodal Reasoning (2026)
   Large multimodal models (LMMs) perceive images well but often fail at multi-step reasoning grounded in visual evidence.

🤝 Co-authors here

12 of 23 co-authors with a page, the most papers together first.

• Wei Ju ×2
• Bohan Wu
• Deng Cai
• Hao Wu
• Haoran Yang
• Jingyang Yuan
• Junyu Luo
• Kun Wang
• Ming Zhang
• Nan Yin
• Shiyu Li
• Taifeng Wang

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) ×4: ACL 2026 ×3, ACL 2025
• Conference on Empirical Methods in Natural Language Processing (EMNLP) ×2: EMNLP 2024 ×2
• Findings of the Association for Computational Linguistics: Findings of the Association for Computational Linguistics 2026

🔗 Cited by

Papers of our library cite their works 47 times (of the 149,439 papers whose bibliographies we read); 11 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/yifan-wang/