---
title: "Growing Through Experience — paper by Zhang et al. (2025)"
description: "The authors describe a \"scale paradox\": small models are cheap to train on experience… 60% accuracy. 51 references, cited by 5 papers here."
authors: ["Chunhui Zhang", "Sirui Wang", "Zhongyu Ouyang", "Xiangchi Yuan", "Soroush Vosoughi"]
year: 2025
venue: "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2025.acl-long.409/"
doi: "10.18653/v1/2025.acl-long.409"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/zhang-2025-growing-through-experience-scaling-episodic/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhang-2025-growing-through-experience-scaling-episodic/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/11/) / Growing Through Experience: Scaling Episodic Grounding in Language Models

# Growing Through Experience: Scaling Episodic Grounding in Language Models

**Authors:** [Chunhui Zhang](https://md.research.elamur.ai/free/en/authors/chunhui-zhang/), [Sirui Wang](https://md.research.elamur.ai/free/en/authors/sirui-wang/), [Zhongyu Ouyang](https://md.research.elamur.ai/free/en/authors/zhongyu-ouyang/), [Xiangchi Yuan](https://md.research.elamur.ai/free/en/authors/xiangchi-yuan/) and [Soroush Vosoughi](https://md.research.elamur.ai/free/en/authors/soroush-vosoughi/) · **Year:** 2025 · **Venue:** [Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2025](https://md.research.elamur.ai/free/en/venues/acl/2025/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2025.acl-long.409/) · [PDF](https://aclanthology.org/2025.acl-long.409.pdf) · [DOI 10.18653/v1/2025.acl-long.409](https://doi.org/10.18653/v1/2025.acl-long.409) · [OpenAlex](https://openalex.org/W4412945599)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · [5](https://md.research.elamur.ai/free/en/papers/zhang-2025-growing-through-experience-scaling-episodic/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
The paper addresses how language models can learn from past interaction experience (episodic grounding) to plan physical, multi-step tasks. The authors describe a "scale paradox": small models are cheap to train on experience but lack representational depth, while 70–405B models have that depth but are hard to fine-tune at scale. Their solution is a two-stage weak-to-strong framework. First, Monte Carlo tree search in the VirtualHome simulator gathers successful and failed trajectories, which become instruction and preference data. Second, a small model (under 8B) is post-trained on these episodes. The behavior ratio between this post-trained model and its untuned version then guides DPO-style alignment of a larger Llama3.1 model. Failed plans and deliberately padded, verbose plans serve as negative examples. The method beats strong proprietary LMs by 3.45% on planning and QA benchmarks and holds up better on long plans. This suggests large models can inherit experience-based skills without costly direct training, though the evaluation is limited to simulated environments.

## Key points
- **MCTS data collection:** The reward is +2 for each satisfied goal predicate and −0.1 per timestep spent on irrelevant actions. Fully successful runs are labeled positive; unmet goals and artificially redundant plans are labeled negative.
- **Long-plan robustness:** Few-shot baselines such as Llama3.1-70B and o1-mini fall from above 60% accuracy at step 2 to below 30% at step 8. The proposed method on Llama3.1-70B stays above 70% through step 8.
- **Layer-wise probing:** Early layers (0–20) of the post-trained model score lower than a fine-tuned baseline (about 20% vs. 40%). Later layers (35–70) score higher, peaking at 90% vs. 80%, indicating task knowledge moves toward the output.
- **Average accuracy:** 70B-ours reaches 78.93% versus 77.96% for 70B-ft, without any probing-based post-processing.
- **Motivating gap and limitation:** Prior work shows a 1.3B model at 54.76% versus a 405B model at 74.34% on planning. The authors acknowledge that results come only from simulator data, not real robots.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,486 works

🧭 Topics (1): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,894 works

## Cite

Cite as: Chunhui Zhang, Sirui Wang, Zhongyu Ouyang, Xiangchi Yuan and Soroush Vosoughi. 2025. Growing Through Experience: Scaling Episodic Grounding in Language Models. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{zhang2025growing,
  title = {{Growing Through Experience: Scaling Episodic Grounding in Language Models}},
  author = {Chunhui Zhang, Sirui Wang, Zhongyu Ouyang, Xiangchi Yuan and Soroush Vosoughi},
  booktitle = {Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2025},
  doi = {10.18653/v1/2025.acl-long.409},
  url = {https://doi.org/10.18653/v1/2025.acl-long.409}
}
```

- [← previous GATEAU: Selecting Influential Samples for Long Context Alignment](https://md.research.elamur.ai/free/en/papers/si-2025-gateau-selecting-influential-samples-long/)
- [next → HypER: Literature-grounded Hypothesis Generation and Distillation with Provenance](https://md.research.elamur.ai/free/en/papers/vasu-2025-hyper-literature-grounded-hypothesis-generation/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/11/)

## References

51 references, 14 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Alan Baddeley. 1992. Working memory. Science. [find](https://scholar.google.com/scholar?q=Alan+Baddeley%2E+1992%2E+Working+memory%2E+Science%2E)
2. Frederic Charles Bartlett. 1995. Remembering: A study in experimental and social psychology. Cambridge university press. [find](https://scholar.google.com/scholar?q=Frederic+Charles+Bartlett%2E+1995%2E+Remembering%3A+A+study+in+experimental+and+social+psychology%2E+Cambridge+university+press%2E)
3. Sid Black, Leo Gao, Phil Wang, Connor Leahy, and Stella Biderman. 2021. Gpt-neo: Large scale autoregressive language modeling with mesh-tensorflow. EleutherAI. [find](https://scholar.google.com/scholar?q=Sid+Black%2C+Leo+Gao%2C+Phil+Wang%2C+Connor+Leahy%2C+and+Stella+Biderman%2E+2021%2E+Gpt%2Dneo%3A+Large+scale+autoregressive+language+modeling+with+mesh%2Dtensorflow%2E+EleutherAI%2E)
4. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. [Language models are few-shot learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/). In Advances in neural information processing systems.
5. Thomas Carta, Clément Romac, Thomas Wolf, Sylvain Lamprier, Olivier Sigaud, and Pierre-Yves Oudeyer. 2023. Grounding large language models in interactive environments with online reinforcement learning. In International Conference on Machine Learning. [find](https://scholar.google.com/scholar?q=Thomas+Carta%2C+Cl%C3%A9ment+Romac%2C+Thomas+Wolf%2C+Sylvain+Lamprier%2C+Olivier+Sigaud%2C+and+Pierre%2DYves+Oudeyer%2E+2023%2E+Grounding+large+language+models+in+interactive+environments+with+online+reinforcement+learnin)
6. Qiguang Chen, Libo Qin, Jiaqi WANG, Jingxuan Zhou, and Wanxiang Che. 2024. Unlocking the capabilities of thought: A reasoning boundary framework to quantify and optimize chain-of-thought. In Advances in Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=Qiguang+Chen%2C+Libo+Qin%2C+Jiaqi+WANG%2C+Jingxuan+Zhou%2C+and+Wanxiang+Che%2E+2024%2E+Unlocking+the+capabilities+of+thought%3A+A+reasoning+boundary+framework+to+quantify+and+optimize+chain%2Dof%2Dthought%2E+In+Advances+)
7. Didier Chételat, Joseph Cotnareanu, Rylee Thompson, Yingxue Zhang, and Mark Coates. 2025. In-nerthoughts: Disentangling representations and predictions in large language models. In International Conference on Artificial Intelligence and Statistics. [find](https://scholar.google.com/scholar?q=Didier+Ch%C3%A9telat%2C+Joseph+Cotnareanu%2C+Rylee+Thompson%2C+Yingxue+Zhang%2C+and+Mark+Coates%2E+2025%2E+In%2Dnerthoughts%3A+Disentangling+representations+and+predictions+in+large+language+models%2E+In+International+Confe)
8. Payel Das, Subhajit Chaudhury, Elliot Nelson, Igor Melnyk, Sarathkrishna Swaminathan, Sihui Dai, Aurelie Lozano, Georgios Kollias, Vijil Chenthamarakshan, Jiri Navratil, Soham Dan, and Pin-Yu Chen. 2024. Larimar: Large language models with episodic memory control. In International Conference on Mach… [find](https://scholar.google.com/scholar?q=Payel+Das%2C+Subhajit+Chaudhury%2C+Elliot+Nelson%2C+Igor+Melnyk%2C+Sarathkrishna+Swaminathan%2C+Sihui+Dai%2C+Aurelie+Lozano%2C+Georgios+Kollias%2C+Vijil+Chenthamarakshan%2C+Jiri+Navratil%2C+Soham+Dan%2C+and+Pin%2DYu+Chen%2E+20)
9. Matt Deitke, Eli VanderBilt, Alvaro Herrasti, Luca Weihs, Jordi Salvador, Kiana Ehsani, Winson Han, Eric Kolve, Ali Farhadi, Aniruddha Kembhavi, and Roozbeh Mottaghi. 2022. ProcTHOR: Large-Scale Embodied AI Using Procedural Generation. In Advances in Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=Matt+Deitke%2C+Eli+VanderBilt%2C+Alvaro+Herrasti%2C+Luca+Weihs%2C+Jordi+Salvador%2C+Kiana+Ehsani%2C+Winson+Han%2C+Eric+Kolve%2C+Ali+Farhadi%2C+Aniruddha+Kembhavi%2C+and+Roozbeh+Mottaghi%2E+2022%2E+ProcTHOR%3A+Large%2DScale+Embod)
10. Xingjian Diao, Chunhui Zhang, Tingxuan Wu, Ming Cheng, Zhongyu Ouyang, Weiyi Wu, and Jiang Gui. 2024. Learning musical representations for music performance question answering. In Findings of the 2024 Conference on Empirical Methods in Natural Language Processing. [find](https://scholar.google.com/scholar?q=Xingjian+Diao%2C+Chunhui+Zhang%2C+Tingxuan+Wu%2C+Ming+Cheng%2C+Zhongyu+Ouyang%2C+Weiyi+Wu%2C+and+Jiang+Gui%2E+2024%2E+Learning+musical+representations+for+music+performance+question+answering%2E+In+Findings+of+the+2024)
11. Xingjian Diao, Chunhui Zhang, Weiyi Wu, Zhongyu Ouyang, Peijun Qing, Ming Cheng, Soroush Vosoughi, and Jiang Gui. 2025. Temporal working memory: Query-guided temporal segment refinement for enhanced multimodal understanding. In Findings of the 2025 Annual Conference of the North American Chapter of… [find](https://scholar.google.com/scholar?q=Xingjian+Diao%2C+Chunhui+Zhang%2C+Weiyi+Wu%2C+Zhongyu+Ouyang%2C+Peijun+Qing%2C+Ming+Cheng%2C+Soroush+Vosoughi%2C+and+Jiang+Gui%2E+2025%2E+Temporal+working+memory%3A+Query%2Dguided+temporal+segment+refinement+for+enhanced+m)
12. Bradford C Dickerson and Howard Eichenbaum. 2010. The episodic memory system: neurocircuitry and disorders. Neuropsychopharmacology. [find](https://scholar.google.com/scholar?q=Bradford+C+Dickerson+and+Howard+Eichenbaum%2E+2010%2E+The+episodic+memory+system%3A+neurocircuitry+and+disorders%2E+Neuropsychopharmacology%2E)
13. Danny Driess, Fei Xia, Mehdi S. M. Sajjadi, Corey Lynch, Aakanksha Chowdhery, Brian Ichter, Ayzaan Wahid, Jonathan Tompson, Quan Vuong, Tianhe Yu, Wenlong Huang, Yevgen Chebotar, Pierre Sermanet, Daniel Duckworth, Sergey Levine, Vincent Vanhoucke, Karol Hausman, Marc Toussaint, Klaus Greff, Andy Zen… [find](https://scholar.google.com/scholar?q=Danny+Driess%2C+Fei+Xia%2C+Mehdi+S%2E+M%2E+Sajjadi%2C+Corey+Lynch%2C+Aakanksha+Chowdhery%2C+Brian+Ichter%2C+Ayzaan+Wahid%2C+Jonathan+Tompson%2C+Quan+Vuong%2C+Tianhe+Yu%2C+Wenlong+Huang%2C+Yevgen+Chebotar%2C+Pierre+Sermanet%2C+Dani)
14. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, et al. 2024. [The llama 3 herd of models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/). arXiv preprint arXiv:2407.21783.
15. Linxi Fan, Guanzhi Wang, Yunfan Jiang, Ajay Mandlekar, Yuncong Yang, Haoyi Zhu, Andrew Tang, De-An Huang, Yuke Zhu, and Anima Anandkumar. 2022. [Minedojo: Building open-ended embodied agents with internet-scale knowledge](https://md.research.elamur.ai/free/en/papers/fan-2022-minedojo-building-open-ended-embodied/). In Advances in Neural Information Processing Systems Datasets and Benchmarks Tr…
16. Zitian Gao, Boye Niu, Xuzheng He, Haotian Xu, Hongzhang Liu, Aiwei Liu, Xuming Hu, and Lijie Wen. 2024. Interpretable contrastive monte carlo tree search reasoning. arXiv preprint arXiv:2410.01707. — [arXiv:2410.01707](https://arxiv.org/abs/2410.01707) [find](https://scholar.google.com/scholar?q=Zitian+Gao%2C+Boye+Niu%2C+Xuzheng+He%2C+Haotian+Xu%2C+Hongzhang+Liu%2C+Aiwei+Liu%2C+Xuming+Hu%2C+and+Lijie+Wen%2E+2024%2E+Interpretable+contrastive+monte+carlo+tree+search+reasoning%2E+arXiv+preprint+arXiv%3A2410%2E01707%2E+%E2%80%94+)
17. Yuxian Gu, Li Dong, Furu Wei, and Minlie Huang. 2024. MiniLLM: Knowledge distillation of large language models. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Yuxian+Gu%2C+Li+Dong%2C+Furu+Wei%2C+and+Minlie+Huang%2E+2024%2E+MiniLLM%3A+Knowledge+distillation+of+large+language+models%2E+In+International+Conference+on+Learning+Representations%2E)
18. Xiaotian Han, Yiren Jian, Xuefeng Hu, Haogeng Liu, Yiqi Wang, Qihang Fan, Yuang Ai, Huaibo Huang, Ran He, Zhenheng Yang, and Quanzeng You. 2024. Infimm-webmath-40b: Advancing multimodal pre-training for enhanced mathematical reasoning. In Proceedings of the 4th Workshop on Mathematical Reasoning and… [find](https://scholar.google.com/scholar?q=Xiaotian+Han%2C+Yiren+Jian%2C+Xuefeng+Hu%2C+Haogeng+Liu%2C+Yiqi+Wang%2C+Qihang+Fan%2C+Yuang+Ai%2C+Huaibo+Huang%2C+Ran+He%2C+Zhenheng+Yang%2C+and+Quanzeng+You%2E+2024%2E+Infimm%2Dwebmath%2D40b%3A+Advancing+multimodal+pre%2Dtraining+f)
19. Wenlong Huang, Pieter Abbeel, Deepak Pathak, and Igor Mordatch. 2022. [Language models as zero-shot planners: Extracting actionable knowledge for embodied agents](https://md.research.elamur.ai/free/en/papers/huang-2022-language-models-zero-shot-planners/). In International conference on machine learning.
20. Brian Ichter, Anthony Brohan, Yevgen Chebotar, Chelsea Finn, Karol Hausman, Alexander Herzog, Daniel Ho, Julian Ibarz, Alex Irpan, Eric Jang, Ryan Julian, Dmitry Kalashnikov, Sergey Levine, Yao Lu, Carolina Parada, Kanishka Rao, Pierre Sermanet, Alexander T Toshev, Vincent Vanhoucke, Fei Xia, Ted Xi… — [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://md.research.elamur.ai/free/en/papers/ahn-2022-i-i-say-grounding-language/)
21. Yiren Jian, Chongyang Gao, and Soroush Vosoughi. 2023. Bootstrapping vision-language learning with decoupled language pre-training. In Proceedings of the 37th Conference on Neural Information Processing Systems. Spotlight. [find](https://scholar.google.com/scholar?q=Yiren+Jian%2C+Chongyang+Gao%2C+and+Soroush+Vosoughi%2E+2023%2E+Bootstrapping+vision%2Dlanguage+learning+with+decoupled+language+pre%2Dtraining%2E+In+Proceedings+of+the+37th+Conference+on+Neural+Information+Processi)
22. Yiren Jian, Tingkai Liu, Yunzhe Tao, Chunhui Zhang, Soroush Vosoughi, and Hongxia Yang. 2024. Expedited training of visual conditioned language generation via redundancy reduction. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics. Oral Presentation. [find](https://scholar.google.com/scholar?q=Yiren+Jian%2C+Tingkai+Liu%2C+Yunzhe+Tao%2C+Chunhui+Zhang%2C+Soroush+Vosoughi%2C+and+Hongxia+Yang%2E+2024%2E+Expedited+training+of+visual+conditioned+language+generation+via+redundancy+reduction%2E+In+Proceedings+of+t)
23. Chuanyang Jin, Yutong Wu, Jing Cao, Jiannan Xiang, Yen-Ling Kuo, Zhiting Hu, Tomer Ullman, Antonio Torralba, Joshua Tenenbaum, and Tianmin Shu. 2024. [MMToM-QA: Multimodal theory of mind question answering](https://md.research.elamur.ai/free/en/papers/jin-2024-mmtom-qa-multimodal-theory-mind/). In Annual Meeting of the Association for Computational Linguistics.
24. Shuang Li, Xavier Puig, Chris Paxton, Yilun Du, Clinton Wang, Linxi Fan, Tao Chen, De-An Huang, Ekin Akyürek, Anima Anandkumar, et al. 2022. [Pre-trained language models for interactive decision-making](https://md.research.elamur.ai/free/en/papers/li-2022-pre-trained-language-models-interactive/). In Advances in Neural Information Processing Systems.
25. Zheyuan Liu, Guangyao Dou, Xiangchi Yuan, Chunhui Zhang, Zhaoxuan Tan, and Meng Jiang. 2025. [Modality-aware neuron pruning for unlearning in multimodal large language models](https://md.research.elamur.ai/free/en/papers/liu-2025-modality-aware-neuron-pruning-unlearning/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics.
26. Dipendra Misra, Andrew Bennett, Valts Blukis, Eyvind Niklasson, Max Shatkhin, and Yoav Artzi. 2018. Mapping instructions to actions in 3D environments with visual goal prediction. In Conference on Empirical Methods in Natural Language Processing. [find](https://scholar.google.com/scholar?q=Dipendra+Misra%2C+Andrew+Bennett%2C+Valts+Blukis%2C+Eyvind+Niklasson%2C+Max+Shatkhin%2C+and+Yoav+Artzi%2E+2018%2E+Mapping+instructions+to+actions+in+3D+environments+with+visual+goal+prediction%2E+In+Conference+on+Emp)
27. Morris Moscovitch, Roberto Cabeza, Gordon Winocur, and Lynn Nadel. 2016. Episodic memory and beyond: the hippocampus and neocortex in transformation. Annual review of psychology. [find](https://scholar.google.com/scholar?q=Morris+Moscovitch%2C+Roberto+Cabeza%2C+Gordon+Winocur%2C+and+Lynn+Nadel%2E+2016%2E+Episodic+memory+and+beyond%3A+the+hippocampus+and+neocortex+in+transformation%2E+Annual+review+of+psychology%2E)
28. Vishnu P Murty, Oriel FeldmanHall, Lindsay E Hunter, Elizabeth A Phelps, and Lila Davachi. 2016. Episodic memories predict adaptive value-based decision-making. Journal of Experimental Psychology: General. [find](https://scholar.google.com/scholar?q=Vishnu+P+Murty%2C+Oriel+FeldmanHall%2C+Lindsay+E+Hunter%2C+Elizabeth+A+Phelps%2C+and+Lila+Davachi%2E+2016%2E+Episodic+memories+predict+adaptive+value%2Dbased+decision%2Dmaking%2E+Journal+of+Experimental+Psychology%3A+Gen)
29. Andrew Nuxoll and John E Laird. 2004. A cognitive model of episodic memory integrated with a general cognitive architecture. In International Conference on Cognitive Modeling. [find](https://scholar.google.com/scholar?q=Andrew+Nuxoll+and+John+E+Laird%2E+2004%2E+A+cognitive+model+of+episodic+memory+integrated+with+a+general+cognitive+architecture%2E+In+International+Conference+on+Cognitive+Modeling%2E)
30. Hadas Orgad, Michael Toker, Zorik Gekhman, Roi Reichart, Idan Szpektor, Hadas Kotek, and Yonatan Belinkov. 2025. [LLMs know more than they show: On the intrinsic representation of LLM hallucinations](https://md.research.elamur.ai/free/en/papers/orgad-2024-llms-know-more-than-they/). In The International Conference on Learning Representations.
31. Xavier Puig, Kevin Ra, Marko Boben, Jiaman Li, Tingwu Wang, Sanja Fidler, and Antonio Torralba. 2018. Virtualhome: Simulating household activities via programs. In IEEE conference on computer vision and pattern recognition. [find](https://scholar.google.com/scholar?q=Xavier+Puig%2C+Kevin+Ra%2C+Marko+Boben%2C+Jiaman+Li%2C+Tingwu+Wang%2C+Sanja+Fidler%2C+and+Antonio+Torralba%2E+2018%2E+Virtualhome%3A+Simulating+household+activities+via+programs%2E+In+IEEE+conference+on+computer+vision+a)
32. Xavier Puig, Tianmin Shu, Shuang Li, Zilin Wang, Yuan-Hong Liao, Joshua B. Tenenbaum, Sanja Fidler, and Antonio Torralba. 2021. Watch-and-help: A challenge for social perception and human-{ai} collaboration. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Xavier+Puig%2C+Tianmin+Shu%2C+Shuang+Li%2C+Zilin+Wang%2C+Yuan%2DHong+Liao%2C+Joshua+B%2E+Tenenbaum%2C+Sanja+Fidler%2C+and+Antonio+Torralba%2E+2021%2E+Watch%2Dand%2Dhelp%3A+A+challenge+for+social+perception+and+human%2D%7Bai%7D+collabo)
33. Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, and Chelsea Finn. 2024. [Direct preference optimization: Your language model is secretly a reward model](https://md.research.elamur.ai/free/en/papers/rafailov-2023-direct-preference-optimization-language-model/). In Advances in Neural Information Processing Systems.
34. Karan Singhal, Shekoofeh Azizi, Tao Tu, S Sara Mahdavi, Jason Wei, Hyung Won Chung, Nathan Scales, Ajay Tanwani, Heather Cole-Lewis, Stephen Pfohl, et al. 2023. [Large language models encode clinical knowledge](https://md.research.elamur.ai/free/en/papers/singhal-2022-large-language-models-encode-clinical/). Nature.
35. Kai Sun, Yifan Xu, Hanwen Zha, Yue Liu, and Xin Luna Dong. 2024. Head-to-tail: How knowledgeable are large language models (LLMs)? A.K.A. will LLMs replace knowledge graphs? In Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. [find](https://scholar.google.com/scholar?q=Kai+Sun%2C+Yifan+Xu%2C+Hanwen+Zha%2C+Yue+Liu%2C+and+Xin+Luna+Dong%2E+2024%2E+Head%2Dto%2Dtail%3A+How+knowledgeable+are+large+language+models+%28LLMs%29%3F+A%2EK%2EA%2E+will+LLMs+replace+knowledge+graphs%3F+In+Conference+of+the+North)
36. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023a. [Llama: Open and efficient foundation language models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-open-efficient-foundation-language/). arXiv preprint arXiv:2302.13971.
37. Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, et al. 2023b. [Llama 2: Open foundation and fine-tuned chat models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-2-open-foundation-fine/). arXiv:2307.09288.
38. E Tulving. 1983. Elements of episodic memory. Oxford University Press. [find](https://scholar.google.com/scholar?q=E+Tulving%2E+1983%2E+Elements+of+episodic+memory%2E+Oxford+University+Press%2E)
39. Francisco J Varela, Eleanor Rosch, and Evan Thompson. 1992. The embodied mind, revised edition: Cognitive science and human experience. MIT press. [find](https://scholar.google.com/scholar?q=Francisco+J+Varela%2C+Eleanor+Rosch%2C+and+Evan+Thompson%2E+1992%2E+The+embodied+mind%2C+revised+edition%3A+Cognitive+science+and+human+experience%2E+MIT+press%2E)
40. Ben Wang and Aran Komatsuzaki. 2021. Gpt-j-6b: A 6 billion parameter autoregressive language model. [find](https://scholar.google.com/scholar?q=Ben+Wang+and+Aran+Komatsuzaki%2E+2021%2E+Gpt%2Dj%2D6b%3A+A+6+billion+parameter+autoregressive+language+model%2E)
41. Chaoqi Wang, Yibo Jiang, Chenghao Yang, Han Liu, and Yuxin Chen. 2024a. Beyond reverse KL: Generalizing direct preference optimization with diverse divergence constraints. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Chaoqi+Wang%2C+Yibo+Jiang%2C+Chenghao+Yang%2C+Han+Liu%2C+and+Yuxin+Chen%2E+2024a%2E+Beyond+reverse+KL%3A+Generalizing+direct+preference+optimization+with+diverse+divergence+constraints%2E+In+International+Conference+)
42. Guanzhi Wang, Yuqi Xie, Yunfan Jiang, Ajay Mandlekar, Chaowei Xiao, Yuke Zhu, Linxi Fan, and Anima Anandkumar. 2024b. Voyager: An open-ended embodied agent with large language models. Transactions on Machine Learning Research. [find](https://scholar.google.com/scholar?q=Guanzhi+Wang%2C+Yuqi+Xie%2C+Yunfan+Jiang%2C+Ajay+Mandlekar%2C+Chaowei+Xiao%2C+Yuke+Zhu%2C+Linxi+Fan%2C+and+Anima+Anandkumar%2E+2024b%2E+Voyager%3A+An+open%2Dended+embodied+agent+with+large+language+models%2E+Transactions+on+)
43. Zihao Wang, Shaofei Cai, Guanzhou Chen, Anji Liu, Xiaojian Ma, and Yitao Liang. 2023. Describe, explain, plan and select: Interactive planning with LLMs enables open-world multi-task agents. In Advances in Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=Zihao+Wang%2C+Shaofei+Cai%2C+Guanzhou+Chen%2C+Anji+Liu%2C+Xiaojian+Ma%2C+and+Yitao+Liang%2E+2023%2E+Describe%2C+explain%2C+plan+and+select%3A+Interactive+planning+with+LLMs+enables+open%2Dworld+multi%2Dtask+agents%2E+In+Advanc)
44. Jason Wei, Yi Tay, Rishi Bommasani, Colin Raffel, Barret Zoph, Sebastian Borgeaud, Dani Yogatama, Maarten Bosma, Denny Zhou, Donald Metzler, Ed H. Chi, Tatsunori Hashimoto, Oriol Vinyals, Percy Liang, Jeff Dean, and William Fedus. 2022. [Emergent abilities of large language models](https://md.research.elamur.ai/free/en/papers/wei-2022-emergent-abilities-large-language-models/). Transactions on Ma…
45. Jiannan Xiang, Tianhua Tao, Yi Gu, Tianmin Shu, Zirui Wang, Zichao Yang, and Zhiting Hu. 2023. Language models meet world models: Embodied experiences enhance language models. In Advances in Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=Jiannan+Xiang%2C+Tianhua+Tao%2C+Yi+Gu%2C+Tianmin+Shu%2C+Zirui+Wang%2C+Zichao+Yang%2C+and+Zhiting+Hu%2E+2023%2E+Language+models+meet+world+models%3A+Embodied+experiences+enhance+language+models%2E+In+Advances+in+Neural+In)
46. Ivory Yang, Weicheng Ma, Chunhui Zhang, and Soroush Vosoughi. 2025a. Is it navajo? accurate language detection in endangered athabaskan languages. In Proceedings of the 2025 Annual Conference of the North American Chapter of the Association for Computational Linguistics. Oral Presentation. [find](https://scholar.google.com/scholar?q=Ivory+Yang%2C+Weicheng+Ma%2C+Chunhui+Zhang%2C+and+Soroush+Vosoughi%2E+2025a%2E+Is+it+navajo%3F+accurate+language+detection+in+endangered+athabaskan+languages%2E+In+Proceedings+of+the+2025+Annual+Conference+of+the+N)
47. Ivory Yang, Chunhui Zhang, Yuxin Wang, Zhongyu Ouyang, and Soroush Vosoughi. 2025b. Visibility as survival: Generalizing nlp for native alaskan language identification. In Findings of the 63rd Annual Meeting of the Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Ivory+Yang%2C+Chunhui+Zhang%2C+Yuxin+Wang%2C+Zhongyu+Ouyang%2C+and+Soroush+Vosoughi%2E+2025b%2E+Visibility+as+survival%3A+Generalizing+nlp+for+native+alaskan+language+identification%2E+In+Findings+of+the+63rd+Annual+)
48. Sherry Yang, Yilun Du, Seyed Kamyar Seyed Ghasemipour, Jonathan Tompson, Leslie Pack Kaelbling, Dale Schuurmans, and Pieter Abbeel. 2024. Learning interactive real-world simulators. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Sherry+Yang%2C+Yilun+Du%2C+Seyed+Kamyar+Seyed+Ghasemipour%2C+Jonathan+Tompson%2C+Leslie+Pack+Kaelbling%2C+Dale+Schuurmans%2C+and+Pieter+Abbeel%2E+2024%2E+Learning+interactive+real%2Dworld+simulators%2E+In+International+C)
49. Zhifan Ye, Kejing Xia, Yonggan Fu, Xin Dong, Jihoon Hong, Xiangchi Yuan, Shizhe Diao, Jan Kautz, Pavlo Molchanov, and Yingyan Celine Lin. 2025. Long-mamba: Enhancing mamba’s long-context capabilities via training-free receptive field enlargement. In International Conference on Learning Representatio… [find](https://scholar.google.com/scholar?q=Zhifan+Ye%2C+Kejing+Xia%2C+Yonggan+Fu%2C+Xin+Dong%2C+Jihoon+Hong%2C+Xiangchi+Yuan%2C+Shizhe+Diao%2C+Jan+Kautz%2C+Pavlo+Molchanov%2C+and+Yingyan+Celine+Lin%2E+2025%2E+Long%2Dmamba%3A+Enhancing+mamba%E2%80%99s+long%2Dcontext+capabilities+)
50. Jifan Yu, Xiaozhi Wang, Shangqing Tu, Shulin Cao, Daniel Zhang-Li, Xin Lv, Hao Peng, Zijun Yao, Xiaohan Zhang, Hanming Li, Chunyang Li, Zheyuan Zhang, Yushi Bai, Yantao Liu, Amy Xin, Kaifeng Yun, Linlu GONG, Nianyi Lin, Jianhui Chen, Zhili Wu, Yunjia Qi, Weikai Li, Yong Guan, Kaisheng Zeng, Ji Qi, H… [find](https://scholar.google.com/scholar?q=Jifan+Yu%2C+Xiaozhi+Wang%2C+Shangqing+Tu%2C+Shulin+Cao%2C+Daniel+Zhang%2DLi%2C+Xin+Lv%2C+Hao+Peng%2C+Zijun+Yao%2C+Xiaohan+Zhang%2C+Hanming+Li%2C+Chunyang+Li%2C+Zheyuan+Zhang%2C+Yushi+Bai%2C+Yantao+Liu%2C+Amy+Xin%2C+Kaifeng+Yun%2C+Linl)
51. Config 70B-base 70B-ft 70B-ours 70B-probing Chunhui Zhang, Yiren Jian, Zhongyu Ouyang, and Soroush Vosoughi. 2025a. Pretrained image-text models are secretly video captioners. In Proceedings of the 2025 Annual Conference of the North American Chapter of the Association for Computational Linguistics.… [find](https://scholar.google.com/scholar?q=Config+70B%2Dbase+70B%2Dft+70B%2Dours+70B%2Dprobing+Chunhui+Zhang%2C+Yiren+Jian%2C+Zhongyu+Ouyang%2C+and+Soroush+Vosoughi%2E+2025a%2E+Pretrained+image%2Dtext+models+are+secretly+video+captioners%2E+In+Proceedings+of+the+20)

*Updated 2 November 2026*