--- title: "Tao Zhang — author profile and papers — Elamur Research" description: "Tao Zhang, University of Science and Technology of China: 10 papers on Elamur Research (2024–2026), h-index 1 — affiliations, topics…" canonical: "https://research.elamur.ai/free/en/authors/tao-zhang/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/tao-zhang/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Tao Zhang # Tao Zhang Tao Zhang has 10 papers in our library, in 2024–2026, most of them on [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/), [Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/), [Efficient models & compression](https://md.research.elamur.ai/free/en/topics/efficient-models/); often with [Mingan Lin](https://md.research.elamur.ai/free/en/authors/mingan-lin/), [Tianpeng Li](https://md.research.elamur.ai/free/en/authors/tianpeng-li/), [Guosheng Dong](https://md.research.elamur.ai/free/en/authors/guosheng-dong/). 10 papers in our library · 2024–2026 [OpenAlex](https://openalex.org/A5139850041) · [**h-index 1**](https://openalex.org/authors/A5139850041) · [7 works](https://openalex.org/works?filter=author.id:A5139850041) · [1 citations](https://openalex.org/works?filter=author.id:A5139850041&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 10 works in our library](https://md.research.elamur.ai/free/en/authors/tao-zhang/#papers) · [🔗 Cited 120 times in our library](https://md.research.elamur.ai/free/en/authors/tao-zhang/cited-by/) · [⭐ Paper Stars ranking: #7361](https://md.research.elamur.ai/free/en/paper-stars/page/74/#star-7361) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Tao+Zhang) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Tao+Zhang) · [dblp](https://dblp.org/search?q=Tao+Zhang) · [ACL Anthology](https://aclanthology.org/search/?q=Tao+Zhang) ## Affiliations [🎓**University of Science and Technology of China** Hefei · China 2026 · 2 papers*current*](https://md.research.elamur.ai/free/en/universities/university-of-science-and-technology-of-china/) · [🏢**Ant Group** Hangzhou · China 2026 · 1 paper*current*](https://md.research.elamur.ai/free/en/companies/ant-group/) · [🎓**South China University of Technology** Guangzhou · China 2026 · 1 paper*current*](https://md.research.elamur.ai/free/en/universities/south-china-university-of-technology/) · [🎓**Xidian University** Xi'an · China 2026 · 1 paper*current*](https://md.research.elamur.ai/free/en/universities/xidian-university/) 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. 📚 Shelves 11 The field of science this work belongs to (OpenAlex fields).[Computer Science · 10 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Arts and Humanities · 9 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Artificial Intelligence · 10 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Language and Linguistics · 9 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · [Computer Vision and Pattern Recognition · 3 works](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · [Psychology · 1 work](https://md.research.elamur.ai/free/en/shelves/psychology/) · [Signal Processing · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/signal-processing/) · [Experimental and Cognitive Psychology · 1 work](https://md.research.elamur.ai/free/en/shelves/psychology/experimental-and-cognitive-psychology/) · [Information Systems · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · [Social Sciences · 1 work](https://md.research.elamur.ai/free/en/shelves/social-sciences/) · [Sociology and Political Science · 1 work](https://md.research.elamur.ai/free/en/shelves/social-sciences/sociology-and-political-science/) 🧭 Topics 8 Research subjects and languages the work is about.[Language models & pretraining · 4 works](https://md.research.elamur.ai/free/en/topics/language-models/) · [Speech & spoken language · 1 work](https://md.research.elamur.ai/free/en/topics/speech/) · [Reasoning · 2 works](https://md.research.elamur.ai/free/en/topics/reasoning/) · [Information retrieval & search · 1 work](https://md.research.elamur.ai/free/en/topics/information-retrieval/) · [Evaluation & benchmarks · 1 work](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) · [Vision & language · 1 work](https://md.research.elamur.ai/free/en/topics/multimodal/) · [Efficient models & compression · 2 works](https://md.research.elamur.ai/free/en/topics/efficient-models/) · [Bias, fairness & safety · 1 work](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/) ## Works by year ### 2020s [**2026** 4 papers](https://md.research.elamur.ai/free/en/authors/tao-zhang/year/2026/) · [**2025** 4 papers](https://md.research.elamur.ai/free/en/authors/tao-zhang/year/2025/) · [**2024** 2 papers](https://md.research.elamur.ai/free/en/authors/tao-zhang/year/2024/) ## Papers The most cited first (OpenAlex and our library). 1. **[RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinement](https://md.research.elamur.ai/free/en/papers/jiang-2025-rag-star-enhancing-deliberative-reasoning/)** *(2025 · 31 citations)* Large language models often fail on multi-hop questions that require chaining several facts. Tree-search methods such as MCTS help with deliberative reasoning but rely only on the model's internal knowledge. Standard RAG feeds documents straight into generation, which can cause conflicts between retrieved and… 2. **[CFBench: A Comprehensive Constraints-Following Benchmark for LLMs](https://md.research.elamur.ai/free/en/papers/zhang-2025-cfbench-comprehensive-constraints-following-benchmark/)** *(2025 · 30 citations)* CFBench tackles a gap in how LLMs are tested on following instructions that carry many explicit constraints. 3. **[Baichuan-Omni-1.5 Technical Report](https://md.research.elamur.ai/free/en/papers/li-2025-baichuan-omni-1-5/)** *(2025 · 28 citations)* Open-source multimodal LLMs mostly pair vision with text. Voice support usually relies on separate ASR and TTS modules, which add latency. End-to-end omni models such as VITA-1.5 and Mini-Omni2 often lose quality when modalities compete, especially on text-only tasks. Baichuan-Omni-1.5 is a single 7B-scale model that… 4. **[Baichuan-Omni Technical Report](https://md.research.elamur.ai/free/en/papers/li-2024-baichuan-omni-technical-report/)** *(2024 · 18 citations)* GPT-4o showed what a single model handling several input types can do, but the open-source community had no comparable system. 5. **[Baichuan-Audio: A Unified Framework for End-to-End Speech Interaction](https://md.research.elamur.ai/free/en/papers/li-2025-baichuan-audio-unified-framework/)** *(2025 · 16 citations)* Cascaded voice assistants chain ASR, an LLM and TTS. This adds latency, compounds errors and discards paralinguistic cues. End-to-end alternatives such as Moshi and GLM-4-Voice tend to lose reasoning ability once speech is added. Baichuan-Audio is a 7B end-to-end audio LLM for real-time bilingual (Chinese/English)… 6. **[MixKVQ: Query-Aware Mixed-Precision KV Cache Quantization for Long-Context Reasoning](https://md.research.elamur.ai/free/en/papers/zhang-2026-mixkvq-query-aware-mixed-precision/)** *(2026 · 5 citations)* Reasoning-oriented LLMs produce very long Chain-of-Thought outputs, so their KV cache consumes large amounts of GPU memory and bandwidth. 7. **[Baichuan Alignment Technical Report](https://md.research.elamur.ai/free/en/papers/lin-2024-baichuan-alignment-technical-report/)** *(2024 · 5 citations)* Alignment methods for large language models are usually kept proprietary or described only in fragments. This technical report from Baichuan Inc. and Peking University sets out the full alignment pipeline behind the Baichuan models. The pipeline has three stages. A Prompt Augmentation System (PAS) automatically… 8. **[DP³: Differentially Private Prompt Perturbation for Multi-turn LLM Inference](https://md.research.elamur.ai/free/en/papers/zheng-2026-dp-3-differentially-private-prompt/)** *(2026)* Prompts sent to black-box LLM APIs can expose sensitive data. A common defence is client-side perturbation under local differential privacy (ε-LDP). Existing token-substitution schemes such as SANTEXT, CUSTEXT, InferDPT and CAPE handle each query in isolation, and this fails in conversations. Tokens that reappear… 9. **[From Narrow Unlearning to Emergent Misalignment in LLMs](https://md.research.elamur.ai/free/en/papers/mushtaq-2026-narrow-unlearning-emergent-misalignment-llms/)** *(2026)* Earlier work found that fine-tuning an aligned LLM on a narrow task, such as writing insecure code, can cause emergent misalignment (EMA): harmful behaviour that spreads to unrelated domains. 10. **[SpecCache: Speculative KV Cache Reuse for Efficient RAG Serving](https://md.research.elamur.ai/free/en/papers/wen-2026-speccache-speculative-kv-cache-reuse/)** *(2026)* RAG prompts grow long when many retrieved chunks are added, which makes the prefill stage slow and delays the first token. ## Co-authors here 12 of 46 co-authors with a page, the most papers together first. - [Mingan Lin](https://md.research.elamur.ai/free/en/authors/mingan-lin/) ×4 - [Tianpeng Li](https://md.research.elamur.ai/free/en/authors/tianpeng-li/) ×4 - [Guosheng Dong](https://md.research.elamur.ai/free/en/authors/guosheng-dong/) ×3 - [Haoze Sun](https://md.research.elamur.ai/free/en/authors/haoze-sun/) ×3 - [Da Pan](https://md.research.elamur.ai/free/en/authors/da-pan/) ×2 - [Fan Yang](https://md.research.elamur.ai/free/en/authors/fan-yang/) ×2 - [Jun Liu](https://md.research.elamur.ai/free/en/authors/jun-liu/) ×2 - [Song Chen](https://md.research.elamur.ai/free/en/authors/song-chen/) ×2 - [Xu Li](https://md.research.elamur.ai/free/en/authors/xu-li/) ×2 - [Yadong Li](https://md.research.elamur.ai/free/en/authors/yadong-li/) ×2 - [Yanjun Shen](https://md.research.elamur.ai/free/en/authors/yanjun-shen/) ×2 - [Zehuan Li](https://md.research.elamur.ai/free/en/authors/zehuan-li/) ×2 ## 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)](https://md.research.elamur.ai/free/en/venues/acl/) ×4: [ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/) ×3, [ACL 2025](https://md.research.elamur.ai/free/en/venues/acl/2025/) - [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/): [Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/) - [Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)](https://md.research.elamur.ai/free/en/venues/naacl/): [NAACL 2025](https://md.research.elamur.ai/free/en/venues/naacl/2025/) ## Cited by Papers of our library cite their works 120 times (of the 149,439 papers whose bibliographies we read); [42 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/tao-zhang/cited-by/). Updated 2 November 2026