--- title: "Idan Shenfeld — author profile and papers — Elamur Research" description: "Idan Shenfeld, Massachusetts Institute of Technology: 3 papers on Elamur Research (2024–2026), h-index 5 — affiliations, topics, co-authors…" canonical: "https://research.elamur.ai/free/en/authors/idan-shenfeld/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/idan-shenfeld/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Idan Shenfeld # Idan Shenfeld Idan Shenfeld has 3 papers in our library, in 2024–2026, most of them on [Efficient models & compression](https://md.research.elamur.ai/free/en/topics/efficient-models/); often with [Jonas Hubotter](https://md.research.elamur.ai/free/en/authors/jonas-hubotter/), [Mehul Damani](https://md.research.elamur.ai/free/en/authors/mehul-damani/), [Andi Peng](https://md.research.elamur.ai/free/en/authors/andi-peng/). 3 papers in our library · 2024–2026 [OpenAlex](https://openalex.org/A5052622748) · [**h-index 5**](https://openalex.org/authors/A5052622748) · [22 works](https://openalex.org/works?filter=author.id:A5052622748) · [69 citations](https://openalex.org/works?filter=author.id:A5052622748&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 3 works in our library](https://md.research.elamur.ai/free/en/authors/idan-shenfeld/#papers) · [🔗 Cited 182 times in our library](https://md.research.elamur.ai/free/en/authors/idan-shenfeld/cited-by/) · [1 more in our library without a page yet](#also) · [⭐ Paper Stars ranking: #7313](https://md.research.elamur.ai/free/en/paper-stars/page/74/#star-7313) 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=Idan+Shenfeld) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Idan+Shenfeld) · [dblp](https://dblp.org/search?q=Idan+Shenfeld) · [ACL Anthology](https://aclanthology.org/search/?q=Idan+Shenfeld) ## Affiliations [🎓**Massachusetts Institute of Technology** Cambridge · United States 2024–2026 · 12 papers*current*](https://md.research.elamur.ai/free/en/universities/massachusetts-institute-of-technology/) 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 5 The field of science this work belongs to (OpenAlex fields).[Arts and Humanities · 3 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Computer Science · 3 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Artificial Intelligence · 3 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Language and Linguistics · 3 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · [Information Systems · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) 🧭 Topics 1 Research subjects and languages the work is about.[Efficient models & compression · 1 work](https://md.research.elamur.ai/free/en/topics/efficient-models/) ## Works by year ### 2020s [**2026** 2 papers](https://md.research.elamur.ai/free/en/authors/idan-shenfeld/year/2026/) · [**2024** 1 paper](https://md.research.elamur.ai/free/en/authors/idan-shenfeld/year/2024/) ## Papers The most cited first (OpenAlex and our library). 1. **[Reinforcement Learning via Self-Distillation](https://md.research.elamur.ai/free/en/papers/hubotter-2026-reinforcement-learning-self-distillation/)** *(2026 · 74 citations)* Policy-gradient RL with verifiable rewards, such as GRPO, gets only one scalar score per attempt. That makes it hard to tell which tokens caused a failure, and learning stops when every rollout in a group gets the same score. The authors point out that many environments also return text explaining the outcome, such… 2. **[Self-Distillation Enables Continual Learning](https://md.research.elamur.ai/free/en/papers/shenfeld-2026-self-distillation-enables-continual-learning/)** *(2026 · 62 citations)* Foundation models usually stop learning after deployment. Fine-tuning them on new data with supervised fine-tuning (SFT) tends to erase earlier abilities, because SFT trains on a fixed external data distribution, which makes it off-policy. On-policy reinforcement learning forgets less, but it requires a reward… 3. **[Learning How Hard to Think: Input-Adaptive Allocation of LM Computation](https://md.research.elamur.ai/free/en/papers/damani-2024-learning-hard-think-input-adaptive/)** *(2024 · 22 citations)* Costly decoding strategies such as best-of-k sampling with reranking, or calling a stronger model, improve LM outputs, but they are usually applied uniformly to every query. ## All works 4 works of theirs in our library, the most cited first; 3 with a page here, the others link their original until we summarise them. 1. [**Reinforcement Learning via Self-Distillation arXiv:2601.20802**Jonas Hubotter, Frederike Lubeck, Lejs Behric, et al.*2026 · 74 citations*](https://md.research.elamur.ai/free/en/papers/hubotter-2026-reinforcement-learning-self-distillation/) 2. [**Self-Distillation Enables Continual Learning arXiv:2601.19897**Idan Shenfeld, Mehul Damani, Jonas Hubotter, et al.*2026 · 62 citations*](https://md.research.elamur.ai/free/en/papers/shenfeld-2026-self-distillation-enables-continual-learning/) 3. **[Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty ↗](https://arxiv.org/abs/2507.16806) arXiv (Cornell University) · no summary yet**Mehul Damani et al.*2025 · 24 citations* 4. [**Learning How Hard to Think: Input-Adaptive Allocation of LM Computation arXiv:2410.04707**Mehul Damani, Idan Shenfeld, Andi Peng, et al.*2024 · 22 citations*](https://md.research.elamur.ai/free/en/papers/damani-2024-learning-hard-think-input-adaptive/) ## Co-authors here 6 co-authors with a page, the most papers together first. - [Jonas Hubotter](https://md.research.elamur.ai/free/en/authors/jonas-hubotter/) ×2 - [Mehul Damani](https://md.research.elamur.ai/free/en/authors/mehul-damani/) ×2 - [Andi Peng](https://md.research.elamur.ai/free/en/authors/andi-peng/) - [Carlos Guestrin](https://md.research.elamur.ai/free/en/authors/carlos-guestrin/) - [Ido Hakimi](https://md.research.elamur.ai/free/en/authors/ido-hakimi/) - [Jacob Andreas](https://md.research.elamur.ai/free/en/authors/jacob-andreas/) ## Cited by Papers of our library cite their works 182 times (of the 149,439 papers whose bibliographies we read); [38 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/idan-shenfeld/cited-by/). Updated 3 November 2026