ICLR

Understanding the Impact of Data Domain Extraction on Synthetic Data Privacy

Georgi Ganev, Meenatchi Sundaram Muthu Selva Annamalai, Sofiane Mahiou, Emiliano De Cristofaro

Comments Accepted to the Synthetic Data x Data Access Problem workshop (SynthData), part of ICLR 2025

On the Cone Effect in the Learning Dynamics

Zhanpeng Zhou, Yongyi Yang, Jie Ren, Mahito Sugiyama, Junchi Yan

Comments Accepted by ICLR 2025 workshop DeLTa

Improving Complex Reasoning with Dynamic Prompt Corruption: A soft prompt Optimization Approach

Sinan Fan, Liang Xie, Chen Shen, Ge Teng, Xiaosong Yuan, Xiaofeng Zhang, Chenxi Huang, Wenxiao Wang, Xiaofei He, Jieping Ye

Comments Accepted by ICLR 2025

Efficient Active Imitation Learning with Random Network Distillation

Emilien Biré, Anthony Kobanda, Ludovic Denoyer, Rémy Portelas

Comments Accepted at ICLR 2025

Learned Reference-based Diffusion Sampling for multi-modal distributions

Maxence Noble, Louis Grenioux, Marylou Gabrié, Alain Oliviero Durmus

Comments Accepted at ICLR 2025

Improving Instruction-Following in Language Models through Activation Steering

Alessandro Stolfo, Vidhisha Balachandran, Safoora Yousefi, Eric Horvitz, Besmira Nushi

Comments ICLR 2025

MM-Ego: Towards Building Egocentric Multimodal LLMs for Video QA

Hanrong Ye, Haotian Zhang, Erik Daxberger, Lin Chen, Zongyu Lin, Yanghao Li, Bowen Zhang, Haoxuan You, Dan Xu, Zhe Gan, Jiasen Lu, Yinfei Yang

Comments Accepted by ICLR 2025

DartControl: A Diffusion-Based Autoregressive Motion Model for Real-Time Text-Driven Motion Control

Kaifeng Zhao, Gen Li, Siyu Tang

Comments Updated ICLR camera ready version

FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models

Zhipei Xu, Xuanyu Zhang, Runyi Li, Zecheng Tang, Qing Huang, Jian Zhang

Comments Accepted by ICLR 2025

Convergence of Score-Based Discrete Diffusion Models: A Discrete-Time Analysis

Zikun Zhang, Zixiang Chen, Quanquan Gu

Comments 26 pages, 1 figure

Journal ref The Thirteenth International Conference on Learning Representations, 2025

Adaptive teachers for amortized samplers

Minsu Kim, Sanghyeok Choi, Taeyoung Yun, Emmanuel Bengio, Leo Feng, Jarrid Rector-Brooks, Sungsoo Ahn, Jinkyoo Park, Nikolay Malkin, Yoshua Bengio

Comments ICLR 2025, 27 pages, 12 figures

Block-Attention for Efficient Prefilling

Dongyang Ma, Yan Wang, Lan Tian

Comments ICLR 2025

Efficient Exploration and Discriminative World Model Learning with an Object-Centric Abstraction

Anthony GX-Chen, Kenneth Marino, Rob Fergus

Comments ICLR 2025

Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Andy K. Zhang, Neil Perry, Riya Dulepet, Joey Ji, Celeste Menders, Justin W. Lin, Eliot Jones, Gashon Hussein, Samantha Liu, Donovan Jasper, Pura Peetathawatchai, Ari Glenn, Vikram Sivashankar, Daniel Zamoshchin, Leo Glikbarg, Derek Askaryar, Mike Yang, Teddy Zhang, Rishi Alluri, Nathan Tran, Rinnara Sangpisit, Polycarpos Yiorkadjis, Kenny Osele, Gautham Raghupathi, Dan Boneh, Daniel E. Ho, Percy Liang

Comments ICLR 2025 Oral

SAM-CP: Marrying SAM with Composable Prompts for Versatile Segmentation

Pengfei Chen, Lingxi Xie, Xinyue Huo, Xuehui Yu, Xiaopeng Zhang, Yingfei Sun, Zhenjun Han, Qi Tian

Comments Accepted by ICLR 2025; codes:https://github.com/ucas-vg/SAM-CP

Scalable Bayesian Learning with posteriors

Samuel Duffield, Kaelan Donatella, Johnathan Chiu, Phoebe Klett, Daniel Simpson

Journal ref Published as a conference paper at ICLR 2025

Fourier Sliced-Wasserstein Embedding for Multisets and Measures

Tal Amir, Nadav Dym

Comments ICLR 2025 camera-ready

Rethinking Channel Dimensions to Isolate Outliers for Low-bit Weight Quantization of Large Language Models

Jung Hwan Heo, Jeonghoon Kim, Beomseok Kwon, Byeongwook Kim, Se Jung Kwon, Dongsoo Lee

Comments ICLR 2024

GMValuator: Similarity-based Data Valuation for Generative Models

Jiaxi Yang, Wenglong Deng, Benlin Liu, Yangsibo Huang, James Zou, Xiaoxiao Li

Journal ref ICLR 2025

MotionDreamer: One-to-Many Motion Synthesis with Localized Generative Masked Transformer

Yilin Wang, Chuan Guo, Yuxuan Mu, Muhammad Gohar Javed, Xinxin Zuo, Juwei Lu, Hai Jiang, Li Cheng

Comments ICLR 2025 acceptance

Improving the evaluation of samplers on multi-modal targets

Louis Grenioux, Maxence Noble, Marylou Gabrié

Comments Accepted at ICLR 2025 workshop "Frontiers in Probabilistic Inference: Learning meets Sampling"

Mechanistic Anomaly Detection for "Quirky" Language Models

David O. Johnston, Arkajyoti Chakraborty, Nora Belrose

Comments ICLR Building Trust Workshop 2025

From Tokens to Lattices: Emergent Lattice Structures in Language Models

Bo Xiong, Steffen Staab

Comments ICLR 2025

Training Neural Networks as Recognizers of Formal Languages

Alexandra Butoi, Ghazal Khalighinejad, Anej Svete, Josef Valvoda, Ryan Cotterell, Brian DuSell

Comments 44 pages, 3 figures. ICLR 2025. Official camera-ready version; applies minor corrections to previous version

Re-Ex: Revising after Explanation Reduces the Factual Errors in LLM Responses

Juyeon Kim, Jeongeun Lee, Yoonho Chang, Chanyeol Choi, Junseong Kim, Jy-yong Sohn

Comments ICLR 2024 Workshop on Reliable and Responsible Foundation Models

AstroLLaVA: towards the unification of astronomical data and natural language

Sharaf Zaman, Michael J. Smith, Pranav Khetarpal, Rishabh Chakrabarty, Michele Ginolfi, Marc Huertas-Company, Maja Jabłońska, Sandor Kruk, Matthieu Le Lain, Sergio José Rodríguez Méndez, Dimitrios Tanoglidis

Comments 8 pages, 3 figures, accepted to SCI-FM@ICLR 2025. Code at https://w3id.org/UniverseTBD/AstroLLaVA

No Equations Needed: Learning System Dynamics Without Relying on Closed-Form ODEs

Krzysztof Kacprzyk, Mihaela van der Schaar

Comments To appear in the Proceedings of the Thirteenth International Conference on Learning Representations (ICLR 2025)

RelCon: Relative Contrastive Learning for a Motion Foundation Model for Wearable Data

Maxwell A. Xu, Jaya Narain, Gregory Darnell, Haraldur Hallgrimsson, Hyewon Jeong, Darren Forde, Richard Fineman, Karthik J. Raghuram, James M. Rehg, Shirley Ren

Comments Accepted to ICLR 2025. Code here: https://github.com/maxxu05/relcon

Journal ref The Thirteenth International Conference on Learning Representations (ICLR), 2025

MrSteve: Instruction-Following Agents in Minecraft with What-Where-When Memory

Junyeong Park, Junmo Cho, Sungjin Ahn

Comments Accepted to ICLR 2025

Cat, Rat, Meow: On the Alignment of Language Model and Human Term-Similarity Judgments

Lorenz Linhardt, Tom Neuhäuser, Lenka Tětková, Oliver Eberle

Comments ICLR 2025 Workshop on Representational Alignment (Re-Align)