ICLR 2025 Conference Submissions

Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition
Zheyang Xiong, Ziyang Cai, John Cooper, Albert Ge, Vasilis Papageorgiou, Zack Sifakis, Angeliki Giannou, Ziqian Lin, Liu Yang, Saurabh Agarwal, Grigorios Chrysos, Samet Oymak, Kangwook Lee, Dimitris Papailiopoulos
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
An efficient implementation for solving the all pairs minimax path problem in an undirected dense graph
Gangli Liu
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning
Zayne Rea Sprague, Fangcong Yin, Juan Diego Rodriguez, Dongwei Jiang, Manya Wadhwa, Prasann Singhal, Xinyu Zhao, Xi Ye, Kyle Mahowald, Greg Durrett
- Published: 22 Jan 2025, Last Modified: 27 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Provably Efficient and Practical Self-Play for Better LLM Alignment
Yibo Wang, Zikun Zhang, Zhihan Liu, Shenao Zhang, Zhaoran Wang
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Interference Among First-Price Pacing Equilibria: A Bias and Variance Analysis
Luofeng Liao, Christian Kroer, Sergei Leonenkov, Okke Schrijvers, Liang Shi, Nicolas Stier Moses, Congshan Zhang
- Published: 22 Jan 2025, Last Modified: 11 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Worldwide Federated Training of Language Models
Alex Iacob, Lorenzo Sani, Bill Marino, Preslav Aleksandrov, William F. Shen, Nicholas Donald Lane
- 25 Sept 2024 (modified: 13 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
ZCTG: A Zero-Shot Framework for Automatic Video Chaptering and Title Generation
Nupur Thakur, Riti Paul, Baoxin Li
- 25 Sept 2024 (modified: 19 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
PoincareNorm: Rethinking Over-smoothing beyond Dirichlet energy
Weiqi Guan, Zihao Shi
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
WILT: A Multi-Turn, Memorization-Robust Inductive Logic Benchmark for LLMs
Eryk Banatt, Jonathan Yu Cheng, Skanda Vaidyanath, Tiffany Hwu
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification
Zhenwen Liang, Ye Liu, Tong Niu, Xiangliang Zhang, Yingbo Zhou, Semih Yavuz
- 25 Sept 2024 (modified: 16 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Exploiting Structure in Offline Multi-Agent RL: The Benefits of Low Interaction Rank
Wenhao Zhan, Scott Fujimoto, Zheqing Zhu, Jason D. Lee, Daniel Jiang, Yonathan Efroni
- Published: 22 Jan 2025, Last Modified: 27 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Fully-inductive Node Classification on Arbitrary Graphs
Jianan Zhao, Zhaocheng Zhu, Mikhail Galkin, Hesham Mostafa, Michael M. Bronstein, Jian Tang
- Published: 22 Jan 2025, Last Modified: 08 Apr 2025
- ICLR 2025 Poster
- Readers: Everyone
StoryGPT-V: Large Language Models as Consistent Story Visualizers
Xiaoqian Shen, Mohamed Elhoseiny
- 25 Sept 2024 (modified: 13 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Post-hoc Reward Calibration: A Case Study on Length Bias
Zeyu Huang, Zihan Qiu, Zili Wang, Edoardo Ponti, Ivan Titov
- Published: 22 Jan 2025, Last Modified: 28 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
ObscuraCoder: Powering Efficient Code LM Pre-Training Via Obfuscation Grounding
Indraneil Paul, Haoyi Yang, Goran Glavaš, Kristian Kersting, Iryna Gurevych
- Published: 22 Jan 2025, Last Modified: 28 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Successor Representations Enable Emergent Compositional Instruction Following
Vivek Myers, Chunyuan Zheng, Anca Dragan, Kuan Fang, Sergey Levine
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Differentiable Causal Discovery for Latent Hierarchical Causal Models
Parjanya Prajakta Prashant, Ignavier Ng, Kun Zhang, Biwei Huang
- Published: 22 Jan 2025, Last Modified: 01 Apr 2025
- ICLR 2025 Poster
- Readers: Everyone
SyllableLM: Learning Coarse Semantic Units for Speech Language Models
Alan Baade, Puyuan Peng, David Harwath
- Published: 22 Jan 2025, Last Modified: 01 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Exact Community Recovery under Side Information: Optimality of Spectral Algorithms
Julia Gaudio, Nirmit Joshi
- Published: 22 Jan 2025, Last Modified: 10 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths
Kaixuan Huang, Xudong Guo, Mengdi Wang
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Repulsive Latent Score Distillation for Solving Inverse Problems
Nicolas Zilberstein, Morteza Mardani, Santiago Segarra
- Published: 22 Jan 2025, Last Modified: 28 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
H-Direct: Homeostasis-aware Direct Spike Encoding for Deep Spiking Neural Networks
Yechan Kang, Mingyeong Seo, Jeonghee Jo, Hyun Jae Jang, Jongkil Park, Jaewook Kim, Suyoun Lee, Jinkyu Kim, Seongsik Park
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
LipFed: Mitigating Subgroup Bias in Federated Learning with Lipschitz Constraints
Khotso Selialia, Yasra Chandio, Jimi Oke, Fatima M. Anwar
- 25 Sept 2024 (modified: 19 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
ReLIC: A Recipe for 64k Steps of In-Context Reinforcement Learning for Embodied AI
Ahmad Elawady, Gunjan Chhablani, Ram Ramrakhya, Karmesh Yadav, Dhruv Batra, Zsolt Kira, Andrew Szot
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Calibrating Expressions of Certainty
Peiqi Wang, Barbara D. Lam, Yingcheng Liu, Ameneh Asgari-Targhi, Rameswar Panda, William M Wells, Tina Kapur, Polina Golland
- Published: 22 Jan 2025, Last Modified: 01 Apr 2025
- ICLR 2025 Poster
- Readers: Everyone