CARVIEW

MOTORHOMES

Select Language

HTTP/2 200 server: GitHub.com content-type: text/html; charset=utf-8 last-modified: Mon, 21 Apr 2025 19:30:22 GMT access-control-allow-origin: * strict-transport-security: max-age=31556952 etag: W/"68069cce-c645" expires: Sun, 28 Dec 2025 23:45:52 GMT cache-control: max-age=600 content-encoding: gzip x-proxy-cache: MISS x-github-request-id: 7BEC:1F53DD:815FAC:91453F:6951BED8 accept-ranges: bytes age: 0 date: Sun, 28 Dec 2025 23:35:52 GMT via: 1.1 varnish x-served-by: cache-bom-vanm7210035-BOM x-cache: MISS x-cache-hits: 0 x-timer: S1766964952.142832,VS0,VE220 vary: Accept-Encoding x-fastly-request-id: c716de871a69ad33cbb7128ce629fdadca2d8078 content-length: 9857 The 2nd Workshop on Foundation Models in the Wild

ICLR 2025 Workshop on

Foundation Models in the Wild

April 27, 2025

The workshop will be held in a hybrid format.

ICML 2024

News

Accepted papers are now available at OpenReview!
Please follow us on Twitter for the latest news, or join us on the Slack for workshop issues and active discussions.
Call for reviewers: We are actively looking for reviewers to join the program committee for the workshop. We encourage all interested researchers to apply, especially those from underrepresented groups. Prior reviewer experience is a nice-to-have, but not required. Interest and familiarity with subject matters related to the workshop is required. If you are interested, please fill out the application form to join us.
Call for papers: Workshop submission portal open at OpenReview: https://openreview.net/group?id=ICLR.cc/2025/Workshop/FM-Wild

About

In the era of AI-driven transformations, foundation models (FMs) have become pivotal in various applications, from natural language processing to computer vision. These models, with their immense capabilities, reshape the future of scientific research and the broader human society, but also introduce challenges in their in-the-wild deployments. The Workshop on FMs in the wild delves into the urgent need for these models to be useful when deployed in our societies. The significance of this topic cannot be overstated, as the real-world implications of these models impact everything from daily information access to critical decision-making in fields like medicine and finance. Stakeholders, from developers to end-users, care deeply about this because the successful integration of FMs into in-the-wild frameworks necessitates a careful consideration of many properties, including adaptivity, reliability, efficiency, and reasoning ability.

Key Problems We Aim to Address

In-the-wild Adaptation

How can we leverage techniques such as Retrieval-Augmented Generation (RAG), In-context Learning (ICL), or Fine-tuning (FT) to adapt FMs for specific domains, such as drug discovery, education, or clinical health?

Reasoning and Planning

How can FMs be enhanced to tackle more complex in-the-wild tasks that require multi-step reasoning or decision-making, such as multi-hop question answering, mathematical problem-solving, theorem proving, code generation, or robot planning scenarios?

Reliability and Responsibility

How can FMs work reliably outside their training distribution? And how can we address issues like hallucination, fairness, ethics, safety and privacy within the society?

Practical Limitations in Deployment

How can FMs tackle challenges in practical applications, such as system constraints, memory requirements, response time demands, data acquisition barriers, and computational costs for inference-time scaling and long-context input?

Call for Papers

The Workshop on Foundation Models in the Wild@ICLR 2025 invite submissions from researchers in the fields of machine learning pertaining to foundation models and its in-the wild applications. Additionally, we welcome contributions from scholars in the natural sciences (such as physics, chemistry, and biology) and social sciences (including pedagogy and sociology) that necessitate the use of foundation models.

Key Dates

Paper Deadline: February 10, 2025 (AoE, Extended)
Notification: March 5, 2025, (AoE)
Camera-ready: March 20, 2025, (AoE)

Deadlines are strict and will not be extended under any circumstances. All deadlines follow the Anywhere on Earth (AoE) timezone.

Submission Site

Submit papers through the Foundation Models in the Wild Workshop Submission Portal on OpenReview (Workshop Submission Portal )

Scope

We welcome contributions across a broad spectrum of topics, including but not limited to:

Innovations in techniques for customizing models to individual user preferences, tasks, or domains
Advancements in the reasoning and planning abilities of FMs in complex real-world challenges
Theoretical and empirical investigations into the reliability and responsibility of various FMs
Strategies for overcoming practical limitations (e.g., memory, time, data) of FMs in broad applications
Methods for integrating multiple modalities (e.g., text, images, action) into a unified in-the-wild framework
Discussions on FM agents that perform intricate tasks through interaction with the environment
In-depth discussions exploring the in-the-wild deployments and applications of FMs
Benchmark methodologies for assessing FMs in real-world settings

Submission Guidelines

Format: All submissions must be a single PDF file. We welcome high-quality original papers in the following two tracks:

Tiny papers: between 2 and 4 pages
Long Papers: between 6 and 9 pages

References and appendices are not included in the page limit, but the main text must be self-contained. Reviewers are not required to read beyond the main text

Style file: You must format your submission using the ICLR 2025 LaTeX style file. For your convenience, we have modified the main conference style file to refer to our workshop: iclr_fmwild.sty. Please include the references and supplementary materials in the same PDF. The maximum file size for submissions is 50MB. Submissions that violate the ICLR style (e.g., by decreasing margins or font sizes) or page limits may be rejected without further review.

Dual-submission and non-archival policy: We welcome ongoing and unpublished work. We will also accept papers that are under review at the time of submission, or that have been recently accepted, , provided they do not breach any dual-submission or anonymity policies of those venues. The workshop is a non-archival venue and will not have official proceedings. Workshop submissions can be subsequently or concurrently submitted to other venues.

Visibility: Submissions and reviews will not be public. Only accepted papers will be made public.

Double-blind reviewing: All submissions must be anonymized and may not contain any identifying information that may violate the double-blind reviewing policy. This policy applies to any supplementary or linked material as well, including code. If you are including links to any external material, it is your responsibility to guarantee anonymous browsing. Please do not include acknowledgements at submission time. If you need to cite one of your own papers, you should do so with adequate anonymization to preserve double-blind reviewing. Any papers found to be violating this policy will be rejected.

Contact: For any questions, please contact us at fmwild2025@googlegroups.com.

Schedule

This is the tentative schedule of the workshop. All slots are provided in local time.

Morning Session

08:00 - 08:15	Breakfast
08:15 - 08:30	Introduction and Opening Remarks
08:30 - 09:00	Invited Talk 1: René Vidal
09:00 - 09:30	Invited Talk 2: Jean Kossaifi
09:30 - 10:00	Invited Talk 3: Xinyun Chen
10:00 - 10:30	Invited Talk 4: Junchi Yan
10:30 - 11:00	Invited Talk 5: Tatsunori Hashimoto
11:00 - 11:30	Invited Talk 6: Reza Shokri
11:30 - 11:35	Oral Talk 1: Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning
11:35 - 11:40	Oral Talk 2: CARROT: A Cost Aware Rate Optimal Router
11:40 - 11:45	Oral Talk 3: DeltaProduct: Increasing the Expressivity of DeltaNet Through Products of Householders
11:45 - 11:50	Oral Talk 4: All It Takes Is One Prompt: An Autonomous LLM-MA System
11:50 - 11:55	Oral Talk 5: Reliable and Efficient Amortized Model-based Evaluation
11:55 - 12:00	Oral Talk 6: PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding
12:00 - 13:30	Lunch Break
12:30 - 13:30	Poster Session 1

Afternoon Session

13:30 - 14:00	Invited Talk 7: Le Song
14:00 - 14:30	Invited Talk 8: Yuandong Tian
14:30 - 15:00	Invited Talk 9: Chelsea Finn
15:00 - 15:30	Invited Talk 10: Guohao Li
15:30 - 15:35	Oral Talk 7: Demystifying Long Chain-of-Thought Reasoning in LLMs
15:35 - 15:40	Oral Talk 8: Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation
15:40 - 15:45	Oral Talk 9: Infinite Leagues Under the Sea: Realistic 3D Underwater Terrain Generation Augmented by Visual Foundation Models
15:45 - 15:50	Oral Talk 10: Towards Universal Offline Black-Box Optimization via Learning String Embedding Space
15:50 - 15:55	Oral Talk 11: RoboMorph: Evolving Robot Morphology using Large Language Models
15:55 - 16:00	Oral Talk 12: Geneshift: Impact of different scenario shift on Jailbreaking LLM
16:00 - 16:15	Best Paper Awards and Closing Remarks
16:15 - 17:15	Poster Session 2

News

About

Key Problems We Aim to Address

Call for Papers

Key Dates

Submission Site

Scope

Submission Guidelines

Schedule

Morning Session

Afternoon Session

Invited Speakers

Xinyun Chen

Chelsea Finn

Tatsunori Hashimoto

Jean Kossaifi

Guohao Li

Reza Shokri

Le Song

Yuandong Tian

René Vidal

Junchi Yan

Workshop Organizers

Xinyu Yang

Huaxiu Yao

Mohit Bansal

Beidi Chen

Junlin Han

Pavel Izmailov

Jinqi Luo

Pang Wei Koh

Weijia Shi

Wenjie Qu

Philip Torr

Zhaoyang Wang

Songlin Yang

Luke Zettlemoyer

Jiaheng Zhang