ICLR 2025 Workshop FM-Wild Submissions

Leveraging the true depth of LLMs
Ramón Calvo González, Daniele Paliotta, Matteo Pagliardini, Martin Jaggi, François Fleuret
- Published: 06 Mar 2025, Last Modified: 06 Mar 2025
- ICLR 2025 FM-Wild Workshop
- Readers: Everyone
xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference
Maximilian Beck, Korbinian Pöppel, Phillip Lippe, Richard Kurle, Patrick M Blies, Günter Klambauer, Sebastian Böck, Sepp Hochreiter
- Published: 06 Mar 2025, Last Modified: 19 Mar 2025
- ICLR 2025 FM-Wild Workshop
- Readers: Everyone
Tiled Flash Linear Attention: More Efficient Linear RNN and xLSTM Kernels
Maximilian Beck, Korbinian Pöppel, Phillip Lippe, Sepp Hochreiter
- Published: 06 Mar 2025, Last Modified: 19 Mar 2025
- ICLR 2025 FM-Wild Workshop
- Readers: Everyone
"Short-length" Adversarial Training Helps LLMs Defend "Long-length" Jailbreak Attacks: Theoretical and Empirical Evidence
Shaopeng Fu, Liang Ding, Di Wang
- Published: 06 Mar 2025, Last Modified: 25 Mar 2025
- ICLR 2025 FM-Wild Workshop
- Readers: Everyone
Unlocking Post-hoc Dataset Inference with Synthetic Data
Bihe Zhao, Pratyush Maini, Franziska Boenisch, Adam Dziedzic
- Published: 06 Mar 2025, Last Modified: 28 Mar 2025
- ICLR 2025 FM-Wild Workshop
- Readers: Everyone
Privacy Auditing for Large Language Models with Natural Identifiers
Lorenzo Rossi, Bartłomiej Marek, Franziska Boenisch, Adam Dziedzic
- Published: 06 Mar 2025, Last Modified: 27 Mar 2025
- ICLR 2025 FM-Wild Workshop
- Readers: Everyone
Foundation Model-Based Data Selection for Dense Prediction Tasks
Niclas Popp, Dan Zhang, Jan Hendrik Metzen, Matthias Hein, Lukas Schott
- Published: 06 Mar 2025, Last Modified: 22 Mar 2025
- ICLR 2025 FM-Wild Workshop
- Readers: Everyone
Beyond Pixels: Enhancing LIME with Hierarchical Features and Segmentation Foundation Models
Patrick Knab, Sascha Marton, Christian Bartelt
- Published: 06 Mar 2025, Last Modified: 19 Mar 2025
- ICLR 2025 FM-Wild Workshop
- Readers: Everyone
Policy-Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbone
Max Sobol Mark, Tian Gao, Georgia Gabriela Sampaio, Mohan Kumar Srirama, Archit Sharma, Chelsea Finn, Aviral Kumar
- Published: 06 Mar 2025, Last Modified: 06 Mar 2025
- ICLR 2025 FM-Wild Workshop
- Readers: Everyone
Diagnosing Robotics Systems Issues with Large Language Models -- A Case Study
Jordis Emilia Herrmann, Aswath Mandakath Gopinath, Mikael Norrlof, Mark Niklas Mueller
- Published: 06 Mar 2025, Last Modified: 24 Mar 2025
- ICLR 2025 FM-Wild Workshop
- Readers: Everyone
MITIGATING CACHE NOISE IN TEST-TIME ADAPTATION FOR LARGE VISION-LANGUAGE MODELS
Haotian Zhai, Xinyu Chen, Can Zhang, TianMing Sha, Ruirui Li
- Published: 06 Mar 2025, Last Modified: 31 Mar 2025
- ICLR 2025 FM-Wild Workshop
- Readers: Everyone
Toward Trustworthy Neural Program Synthesis
Wen-Ding Li, Darren Yan Key, Kevin Ellis
- Published: 06 Mar 2025, Last Modified: 17 Apr 2025
- ICLR 2025 FM-Wild Workshop
- Readers: Everyone
AgentTaxo: Dissecting and Benchmarking Token Distribution of LLM Multi-Agent Systems
Qian Wang, Zhenheng Tang, ZICHEN JIANG, Nuo Chen, Tianyu Wang, Bingsheng He
- Published: 06 Mar 2025, Last Modified: 07 Apr 2025
- ICLR 2025 FM-Wild Workshop
- Readers: Everyone
Optimizing Test-Time Compute via Meta Reinforcement Finetuning
Yuxiao Qu, Matthew Y. R. Yang, Amrith Setlur, Lewis Tunstall, Edward Emanuel Beeching, Ruslan Salakhutdinov, Aviral Kumar
- Published: 06 Mar 2025, Last Modified: 06 Mar 2025
- ICLR 2025 FM-Wild Workshop
- Readers: Everyone
Automated Benchmark Generation for Repository-Level Coding Tasks
Konstantinos Vergopoulos, Mark Niklas Mueller, Martin Vechev
- Published: 06 Mar 2025, Last Modified: 24 Mar 2025
- ICLR 2025 FM-Wild Workshop
- Readers: Everyone
WorkflowAgent: Towards Specialized Web Agents Using Production-Scale Workflow Data
Junhong Shen, Atishay Jain, Zedian Xiao, Ishan Amlekar, Mouad Hadji, Aaron Podolny, Ameet Talwalkar
- Published: 06 Mar 2025, Last Modified: 18 Mar 2025
- ICLR 2025 FM-Wild Workshop
- Readers: Everyone
PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding
Wei Chow, Jiageng Mao, Boyi Li, Daniel Seita, Vitor Campagnolo Guizilini, Yue Wang
- Published: 06 Mar 2025, Last Modified: 06 Mar 2025
- ICLR 2025 FM-Wild Workshop
- Readers: Everyone
OpenRAG: Optimizing RAG End-to-End via In-Context Retrieval Learning
Jiawei Zhou, Lei Chen
- Published: 06 Mar 2025, Last Modified: 22 Mar 2025
- ICLR 2025 FM-Wild Workshop
- Readers: Everyone
Cheap and Effective Personalization of Foundation Language Models for Imitating a User's Writing Style
Armand Mihai Nicolicioiu, Eugenia Iofinova, Andrej Jovanovic, Eldar Kurtic, Mahdi Nikdan, Andrei Panferov, Ilia Markov, Nir N Shavit, Dan Alistarh
- Published: 06 Mar 2025, Last Modified: 18 Mar 2025
- ICLR 2025 FM-Wild Workshop
- Readers: Everyone
Detecting Covariate Shifts With Vision-Language Foundation Models
Alvin Heng, Harold Soh
- Published: 06 Mar 2025, Last Modified: 26 Mar 2025
- ICLR 2025 FM-Wild Workshop
- Readers: Everyone
ReFocus: Visual Editing as a Chain of Thought for Structured Image Understanding
Xingyu Fu, Minqian Liu, Zhengyuan Yang, John Richard Corring, Yijuan Lu, Jianwei Yang, Dan Roth, Dinei Florencio, Cha Zhang
- Published: 06 Mar 2025, Last Modified: 01 Apr 2025
- ICLR 2025 FM-Wild Workshop
- Readers: Everyone
MLLM CAN SEE? DYNAMIC CORRECTION DECODING FOR HALLUCINATION MITIGATION
Chenxi Wang, Xiang Chen, Ningyu Zhang, Bozhong Tian, Haoming Xu, Shumin Deng, Huajun Chen
- Published: 06 Mar 2025, Last Modified: 18 Mar 2025
- ICLR 2025 FM-Wild Workshop
- Readers: Everyone
FlipAttack: Jailbreak LLMs via Flipping
Yue Liu, Xiaoxin He, Miao Xiong, Jinlan Fu, Shumin Deng, YINGWEI MA, Jiaheng Zhang, Bryan Hooi
- Published: 06 Mar 2025, Last Modified: 27 Mar 2025
- ICLR 2025 FM-Wild Workshop
- Readers: Everyone
TPP-LLM: Modeling Temporal Point Processes by Efficiently Fine-Tuning Large Language Models
Zefang Liu, Yinzhu Quan
- Published: 06 Mar 2025, Last Modified: 19 Mar 2025
- ICLR 2025 FM-Wild Workshop
- Readers: Everyone
GuardReasoner: Towards Reasoning-based LLM Safeguards
Yue Liu, Hongcheng Gao, Shengfang Zhai, Jun Xia, Tianyi Wu, Zhiwei Xue, Yulin Chen, Kenji Kawaguchi, Jiaheng Zhang, Bryan Hooi
- Published: 06 Mar 2025, Last Modified: 27 Mar 2025
- ICLR 2025 FM-Wild Workshop
- Readers: Everyone