Foundation Models in the Wild @ ICLR 2025

Foundation Models in the Wild workshop series (next @iclr_conf 2025)

[Foundation Models in the Wild @ ICLR 2025 @FM_in_Wild]

🤩 It's happening today!
Join us at the 2nd Workshop on Foundation Models in the Wild — Hall 4, #6, Singapore EXPO!

🔥 10 amazing invited talks
🔥 12 exciting oral presentations
🔥 Cutting-edge ideas and lively discussions

🚀 Don't miss it — come say hi and explore the future of in-the-wild foundation models with us!

[Beidi Chen @BeidiChen]

Say hello to Multiverse — the Everything Everywhere All At Once of generative modeling.
💥 Lossless, adaptive, and gloriously parallel
🌀 Now open-sourced: https://t.co/nygi9LSZLt
I was amazed how easily we could extract the intrinsic parallelism of even SOTA autoregressive LLMs—just by restructuring a few examples from their reasoning traces and training with Multiverse modeling. 🤯
#AI #Multiverse #LLM #Parallelism

[Foundation Models in the Wild @ ICLR 2025 @FM_in_Wild]

The Afternoon Session will include another four Invited Talks, six Oral Talks, and one Poster Session.

[Foundation Models in the Wild @ ICLR 2025 @FM_in_Wild]

The Morning Session will include six Invited Talks, six Oral Talks, and one Poster Session.

[Foundation Models in the Wild @ ICLR 2025 @FM_in_Wild]

The Morning Session will include six Invited Talks, six Oral Talks, and one Poster Session.

[Foundation Models in the Wild @ ICLR 2025 @FM_in_Wild]

🤩 It's happening today!
Join us at the 2nd Workshop on Foundation Models in the Wild — Hall 4, #6, Singapore EXPO!

🔥 10 amazing invited talks
🔥 12 exciting oral presentations
🔥 Cutting-edge ideas and lively discussions

🚀 Don't miss it — come say hi and explore the future of in-the-wild foundation models with us!

[Foundation Models in the Wild @ ICLR 2025 @FM_in_Wild]

😀We're delighted to announce that the review stage of our 2nd FM-Wild Workshop at ICLR has successfully concluded. We extend our sincere gratitude to all authors and reviewers for their valuable contributions.

👉The accepted papers are now available at: https://t.co/eaIKWgYAEl

🚀This year, we received an impressive 140 submissions and are proud to have accepted 100 high-quality papers. We're currently scratching our heads trying to pick just 10 for oral presentations—talk about a tough call! We'll be making these difficult decisions in the coming days, so stay tuned.

👐We continue to welcome sponsorships in any form to help make this workshop even more impactful. Your support would be greatly appreciated!

We look forward to an exciting workshop and to seeing you at ICLR 2025!

[Xinyu Yang @Xinyu2ML]

📢 Announcing our new work "APE: Faster and Longer Context-Augmented Generation via Adaptive Parallel Encoding" @iclr_conf
🚀 Enabling the efficient combination of multiple contexts with negligible prefilling cost
💅 Re-using the context window of LLMs to accommodate more and longer retrieved texts

🔘 APE is targeted at scenarios where the generation is augmented with external texts for better performance.
🔘 It avoids the efficiency and performance bottleneck in sequence encoding by eliminating the on-the-fly prefilling of long sequences including multiple texts.
🔘 It pre-computes and caches the KV states of each text separately for direct loading during inference. Our training-free alignments ensure performance recovery.

Curious how? Check it out 👇
🔗 Website: https://t.co/KKxHXK2QNp
📜 Paper: https://t.co/u6eNNvPUEd
💻 Code: APE is targeted on scenarios in which the generation is augmented with external contexts for better performance.

[Foundation Models in the Wild @ ICLR 2025 @FM_in_Wild]

We have extended the submission deadline to Feb 10, 2025 (AOE). Look forward to seeing your papers!

[Foundation Models in the Wild @ ICLR 2025 @FM_in_Wild]

🚀Excited to announce the 2nd Workshop on Foundation Models in the Wild at @iclr_conf 2025 (April 27 or 28, Singapore).

‼️We welcome submissions! Please consider submitting your work here: https://t.co/4l5XCZWMTj (deadline: Fed 3, 2025, AOE)

💠Topics:
🔸In-the-wild Adaptation of FMs
🔸Reasoning and planning abilities in real contexts
🔸Reliability and responsibility of various FMs
🔸Practical limitations of FMs in deployments
🔸Benchmarking FMs in real-world settings

🌟Speakers: @AnimaAnandkumar, @xinyun_chen_, @chelseabfinn, @tatsu_hashimoto, @rzshokri, @jietang, @tydsh, @vidal_rene

🧑‍🤝‍🧑Organizers: @Xinyu2ML, @HuaxiuYaoML, @mohitban47, @BeidiChen, @han_junlin, @Pavel_Izmailov, @peterljq, @PangWeiKoh, @WeijiaShi2, @qu_wenjie, @philiptorr, @zhaoywang_CS, @SonglinYang4, @LukeZettlemoyer, @jiahengzhang96

✍️ Interested in joining our Program Committee to help review? Please fill out the nomination form (https://t.co/9MTB548u14)!

😃Hope to see you in Singapore or virtually in April, stay tuned for more info.

[Foundation Models in the Wild @ ICLR 2025 @FM_in_Wild]

🚀Excited to announce the 2nd Workshop on Foundation Models in the Wild at @iclr_conf 2025 (April 27 or 28, Singapore).

‼️We welcome submissions! Please consider submitting your work here: https://t.co/4l5XCZWMTj (deadline: Fed 3, 2025, AOE)

💠Topics:
🔸In-the-wild Adaptation of FMs
🔸Reasoning and planning abilities in real contexts
🔸Reliability and responsibility of various FMs
🔸Practical limitations of FMs in deployments
🔸Benchmarking FMs in real-world settings

🌟Speakers: @AnimaAnandkumar, @xinyun_chen_, @chelseabfinn, @tatsu_hashimoto, @rzshokri, @jietang, @tydsh, @vidal_rene

🧑‍🤝‍🧑Organizers: @Xinyu2ML, @HuaxiuYaoML, @mohitban47, @BeidiChen, @han_junlin, @Pavel_Izmailov, @peterljq, @PangWeiKoh, @WeijiaShi2, @qu_wenjie, @philiptorr, @zhaoywang_CS, @SonglinYang4, @LukeZettlemoyer, @jiahengzhang96

✍️ Interested in joining our Program Committee to help review? Please fill out the nomination form (https://t.co/9MTB548u14)!

😃Hope to see you in Singapore or virtually in April, stay tuned for more info.