ICLR 2025

3,703 papers

AgentSquare: Automatic LLM Agent Search in Modular Design Space

Yu Shang, Yu Li, Keyu Zhao, Likai Ma, Jiahe Liu

Manifolds, Random Matrices and Spectral Gaps: The geometric phases of generative diffusion

Enrico Ventura, Beatrice Achilli, Gianluigi Silvestri, Carlo Lucibello, Luca Ambrogioni

A Theory of Initialisation's Impact on Specialisation

Devon Jarvis, Sebastian Lee, Clémentine Carla Juliette Dominé, Andrew M Saxe, Stefano Sarao Mannelli

ParamΔ for Direct Mixing: Post-Train Large Language Model At Zero Cost

Sheng Cao, Mingrui Wu, Karthik Prasad, Yuandong Tian, Zechun Liu

Polynomial Composition Activations: Unleashing the Dynamics of Large Language Models

Zhijian Zhuo, Ya Wang, Yutao Zeng, Xiaoqing Li, Xun Zhou

ConcreTizer: Model Inversion Attack via Occupancy Classification and Dispersion Control for 3D Point Cloud Restoration

Youngseok Kim, Sunwook Hwang, Hyung-Sin Kim, Saewoong Bahk

SFESS: Score Function Estimators for k-Subset Sampling

Klas Wijk, Ricardo Vinuesa, Hossein Azizpour

Schur's Positive-Definite Network: Deep Learning in the SPD cone with structure

Can Pouliquen, Mathurin Massias, Titouan Vayer

Projection Head is Secretly an Information Bottleneck

Zhuo Ouyang, Kaiwen Hu, Qi Zhang, Yifei Wang, Yisen Wang

CausalRivers - Scaling up benchmarking of causal discovery for real-world time-series

Gideon Stein, Maha Shadaydeh, Jan Blunk, Niklas Penzel, Joachim Denzler

Rare event modeling with self-regularized normalizing flows: what can we learn from a single failure?

Charles Dawson, Van Tran, Max Z. Li, Chuchu Fan

Dreamweaver: Learning Compositional World Models from Pixels

Junyeob Baek, Yi-Fu Wu, Gautam Singh, Sungjin Ahn

Addressing Label Shift in Distributed Learning via Entropy Regularization

Zhiyuan Wu, Changkyu Choi, Xiangcheng Cao, Volkan Cevher, Ali Ramezani-Kebrya

Optimality and Adaptivity of Deep Neural Features for Instrumental Variable Regression

Juno Kim, Dimitri Meunier, Arthur Gretton, Taiji Suzuki, Zhu Li

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

Junyeong Park, Junmo Cho, Sungjin Ahn

UniDetox: Universal Detoxification of Large Language Models via Dataset Distillation

Huimin Lu, Masaru Isonuma, Junichiro Mori, Ichiro Sakata

Learning from negative feedback, or positive feedback or both

Abbas Abdolmaleki, Bilal Piot, Bobak Shahriari, Jost Tobias Springenberg, Tim Hertweck

Latent Bayesian Optimization via Autoregressive Normalizing Flows

Seunghun Lee, Jinyoung Park, Jaewon Chu, Minseo Yoon, Hyunwoo J. Kim

Node Identifiers: Compact, Discrete Representations for Efficient Graph Learning

Yuankai Luo, Hongkang Li, Qijiong Liu, Lei Shi, Xiao-ming Wu

Joint Gradient Balancing for Data Ordering in Finite-Sum Multi-Objective Optimization

Hansi Yang, James Kwok

Durable Quantization Conditioned Misalignment Attack on Large Language Models

Peiran Dong, Haowei Li, Song Guo

What's New in My Data? Novelty Exploration via Contrastive Generation

Masaru Isonuma, Ivan Titov

CO-MOT: Boosting End-to-end Transformer-based Multi-Object Tracking via Coopetition Label Assignment and Shadow Sets

Feng Yan, Weixin Luo, Yujie Zhong, Yiyang Gan, Lin Ma

Rethinking Shapley Value for Negative Interactions in Non-convex Games

Wonjoon Chang, Myeongjin Lee, Jaesik Choi

ARLON: Boosting Diffusion Transformers with Autoregressive Models for Long Video Generation

Zongyi Li, Shujie Hu, Shujie LIU, Long Zhou, Jeongsoo Choi

QA-Calibration of Language Model Confidence Scores

Putra Manggala, Atalanti A. Mastakouri, Elke Kirschbaum, Shiva Kasiviswanathan, Aaditya Ramdas

Offline Hierarchical Reinforcement Learning via Inverse Optimization

Carolin Schmidt, Daniele Gammelli, James Harrison, Marco Pavone, Filipe Rodrigues

RecFlow: An Industrial Full Flow Recommendation Dataset

Qi Liu, Kai Zheng, Rui Huang, Wuchao Li, Kuo Cai

ELICIT: LLM Augmentation Via External In-context Capability

Futing Wang, Jianhao Yan, Yue Zhang, Tao LIN

Influence-Guided Diffusion for Dataset Distillation

Mingyang Chen, JIAWEI DU, Bo Huang, Yi Wang, Xiaobo Zhang

Equivariant Denoisers Cannot Copy Graphs: Align Your Graph Diffusion Models

Najwa Laabid, Severi Rissanen, Markus Heinonen, Arno Solin, Vikas Garg

ChroKnowledge: Unveiling Chronological Knowledge of Language Models in Multiple Domains

Yein Park, Chanwoong Yoon, Jungwoo Park, Donghyeon Lee, Minbyul Jeong

CR-CTC: Consistency regularization on CTC for improved speech recognition

Zengwei Yao, Wei Kang, Xiaoyu Yang, Fangjun Kuang, Liyong Guo

Imputation for prediction: beware of diminishing returns.

Marine Le Morvan, Gael Varoquaux

Oscillatory State-Space Models

T. Konstantin Rusch, Daniela Rus

How Does Vision-Language Adaptation Impact the Safety of Vision Language Models?

Seongyun Lee, Geewook Kim, Jiyeon Kim, Hyunji Lee, Hoyeon Chang

Agents' Room: Narrative Generation through Multi-step Collaboration

Fantine Huot, Reinald Kim Amplayo, Jennimaria Palomaki, Alice Shoshana Jakobovits, Elizabeth Clark

Adaptive Gradient Clipping for Robust Federated Learning

Youssef Allouah, Rachid Guerraoui, Nirupam Gupta, Ahmed Jellouli, Geovani Rizk

Transformers Provably Solve Parity Efficiently with Chain of Thought

Juno Kim, Taiji Suzuki

Sketch2Diagram: Generating Vector Diagrams from Hand-Drawn Sketches

Itsumi Saito, Haruto Yoshida, Keisuke Sakaguchi

KinPFN: Bayesian Approximation of RNA Folding Kinetics using Prior-Data Fitted Networks

Dominik Scheuer, Frederic Runge, Jörg K.H. Franke, Michael T. Wolfinger, Christoph Flamm

ProtPainter: Draw or Drag Protein via Topology-guided Diffusion

Zhengxi Lu, Shizhuo Cheng, Tintin Jiang, Yan Zhang, Min Zhang

Words in Motion: Extracting Interpretable Control Vectors for Motion Transformers

Omer Sahin Tas, Royden Wagner

Triples as the Key: Structuring Makes Decomposition and Verification Easier in LLM-based TableQA

Zhen Yang, Ziwei Du, Minghan Zhang, Wei Du, Jie Chen

Utilitarian Algorithm Configuration for Infinite Parameter Spaces

Devon R. Graham, Kevin Leyton-brown

The Effectiveness of Curvature-Based Rewiring and the Role of Hyperparameters in GNNs Revisited

Floriano Tori, Vincent Holst, Vincent Ginis

Cached Multi-Lora Composition for Multi-Concept Image Generation

Xiandong Zou, Mingzhu Shen, Christos-Savvas Bouganis, Yiren Zhao

Magnetic Preference Optimization: Achieving Last-iterate Convergence for Language Model Alignment

Mingzhi Wang, Chengdong Ma, Qizhi Chen, Linjian Meng, Yang Han

Decoupled Finetuning for Domain Generalizable Semantic Segmentation

Jaehyun Pahk, Donghyeon Kwon, Seong Joon Oh, Suha Kwak

Harnessing Diversity for Important Data Selection in Pretraining Large Language Models

Chi Zhang, Huaping Zhong, Kuan Zhang, Chengliang Chai, Rui Wang

Decoupled Subgraph Federated Learning

Javad Aliakbari, Johan Östman, Alexandre Graell i Amat

Gumbel Counterfactual Generation From Language Models

Shauli Ravfogel, Anej Svete, Vésteinn Snæbjarnarson, Ryan Cotterell

Multi-Resolution Decomposable Diffusion Model for Non-Stationary Time Series Anomaly Detection

Guojin Zhong, Pan Wang, Jin Yuan, Zhiyong Li, Long Chen

Efficiently Democratizing Medical LLMs for 50 Languages via a Mixture of Language Family Experts

Guorui Zheng, Xidong Wang, Juhao Liang, Nuo Chen, Yuping Zheng

Neuron-based Multifractal Analysis of Neuron Interaction Dynamics in Large Models

Xiongye Xiao, Heng Ping, Chenyu Zhou, Defu Cao, Yaxing Li

Physiome-ODE: A Benchmark for Irregularly Sampled Multivariate Time-Series Forecasting Based on Biological ODEs

Christian Klötergens, Vijaya Krishna Yalavarthi, Randolf Scholz, Maximilian Stubbemann, Stefan Born

How Much is Unseen Depends Chiefly on Information About the Seen

Seongmin Lee, Marcel Boehme

Exact Computation of Any-Order Shapley Interactions for Graph Neural Networks

Maximilian Muschalik, Fabian Fumagalli, Paolo Frazzetto, Janine Strotherm, Luca Hermes

RAPID: Retrieval Augmented Training of Differentially Private Diffusion Models

Tanqiu Jiang, Changjiang Li, Fenglong Ma, Ting Wang

Emergent Orientation Maps —— Mechanisms, Coding Efficiency and Robustness

Haixin Zhong, Haoyu Wang, Wei P Dai, Yuchao Huang, Mingyi Huang

EMMA: Empowering Multi-modal Mamba with Structural and Hierarchical Alignment

Yifei Xing, Xiangyuan Lan, Ruiping Wang, Dongmei Jiang, Wenjun Huang

SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models

Jiale Cheng, Xiao Liu, Cunxiang Wang, Xiaotao Gu, Yida Lu

PFGuard: A Generative Framework with Privacy and Fairness Safeguards

Soyeon Kim, Yuji Roh, Geon Heo, Steven Euijong Whang

Attention as a Hypernetwork

Simon Schug, Seijin Kobayashi, Yassir Akram, João Sacramento, Razvan Pascanu

On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent

Bingrui Li, Wei Huang, Andi Han, Zhanpeng Zhou, Taiji Suzuki

Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference Optimization

Junkang Wu, Yuexiang Xie, Zhengyi Yang, Jiancan Wu, Jiawei Chen

Improving Uncertainty Estimation through Semantically Diverse Language Generation

Lukas Aichberger, Kajetan Schweighofer, Mykyta Ielanskyi, Sepp Hochreiter

Improving Reasoning Performance in Large Language Models via Representation Engineering

Bertram Højer, Oliver Simon Jarvis, Stefan Heinrich

Optimizing Backward Policies in GFlowNets via Trajectory Likelihood Maximization

Timofei Gritsaev, Nikita Morozov, Sergey Samsonov, Daniil Tiapkin

Elliptic Loss Regularization

Ali Hasan, Haoming Yang, Yuting Ng, Vahid Tarokh

EcoFace: Audio-Visual Emotional Co-Disentanglement Speech-Driven 3D Talking Face Generation

Jiajian Xie, Shengyu Zhang, Mengze Li, Chengfei Lv, Zhou Zhao

Noise-conditioned Energy-based Annealed Rewards (NEAR): A Generative Framework for Imitation Learning from Observation

Anish Abhijit Diwan, Julen Urain, Jens Kober, Jan Peters

Learn Your Reference Model for Real Good Alignment

Alexey Gorbatovski, Boris Shaposhnikov, Alexey Malakhov, Nikita Surnachev, Yaroslav Aksenov

Audio Large Language Models Can Be Descriptive Speech Quality Evaluators

Chen Chen, Yuchen Hu, Siyin Wang, Helin Wang, Zhehuai Chen

On the Expressiveness of Rational ReLU Neural Networks With Bounded Depth

Gennadiy Averkov, Christopher Hojny, Maximilian Merkert

Long-Short Decision Transformer: Bridging Global and Local Dependencies for Generalized Decision-Making

Jincheng Wang, Penny Karanasou, Pengyuan Wei, Elia Gatti, Diego Martinez Plasencia

TOP-ERL: Transformer-based Off-Policy Episodic Reinforcement Learning

Ge Li, Dong Tian, Hongyi Zhou, Xinkai Jiang, Rudolf Lioutikov

A new framework for evaluating model out-of-distribution generalisation for the biochemical domain

Raul Fernandez-Diaz, Hoang Thanh Lam, Vanessa Lopez, Denis C. Shields

Simple, Good, Fast: Self-Supervised World Models Free of Baggage

Jan Robine, Marc Höftmann, Stefan Harmeling

XAIguiFormer: explainable artificial intelligence guided transformer for brain disorder identification

Hanning Guo, Farah Abdellatif, Yu Fu, N. Jon Shah, Abigail Morrison

RetroInText: A Multimodal Large Language Model Enhanced Framework for Retrosynthetic Planning via In-Context Representation Learning

Chenglong Kang, Xiaoyi Liu, Fei Guo

Systematic Relational Reasoning With Epistemic Graph Neural Networks

Irtaza Khalid, Steven Schockaert

Endowing Visual Reprogramming with Adversarial Robustness

Shengjie Zhou, Xin Cheng, Haiyang Xu, Ming Yan, Tao Xiang

Optimal Strong Regret and Violation in Constrained MDPs via Policy Optimization

Francesco Emanuele Stradi, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti

Adversarial Policy Optimization for Offline Preference-based Reinforcement Learning

Hyungkyu Kang, Min-hwan Oh

Approximating Full Conformal Prediction for Neural Network Regression with Gauss-Newton Influence

Dharmesh Tailor, Alvaro Correia, Eric Nalisnick, Christos Louizos

CipherPrune: Efficient and Scalable Private Transformer Inference

Yancheng Zhang, Jiaqi Xue, Mengxin Zheng, Mimi Xie, Mingzhe Zhang

Persistent Pre-training Poisoning of LLMs

Yiming Zhang, Javier Rando, Ivan Evtimov, Jianfeng Chi, Eric Michael Smith

Geometry Image Diffusion: Fast and Data-Efficient Text-to-3D with Image-Based Surface Representation

Slava Elizarov, Ciara Rowles, Simon Donné

Controlling Space and Time with Diffusion Models

Daniel Watson, Saurabh Saxena, Lala Li, Andrea Tagliasacchi, David J. Fleet

Beyond Mere Token Analysis: A Hypergraph Metric Space Framework for Defending Against Socially Engineered LLM Attacks

Manohar Kaul, Aditya Saibewar, Sadbhavana Babar

In Search of Forgotten Domain Generalization

Prasanna Mayilvahanan, Roland S. Zimmermann, Thaddäus Wiedemer, Evgenia Rusak, Attila Juhos

GIFT: Unlocking Full Potential of Labels in Distilled Dataset at Near-zero Cost

Xinyi Shang, peng sun, Tao LIN

On a Connection Between Imitation Learning and RLHF

Teng Xiao, Yige Yuan, Mingxiao Li, Zhengyu Chen, Vasant G Honavar

Tool-Planner: Task Planning with Clusters across Multiple Tools

Yanming Liu, Xinyue Peng, Jiannan Cao, Shi Bo, Yuwei Zhang

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words

Gouki Minegishi, Hiroki Furuta, Yusuke Iwasawa, Yutaka Matsuo

Preference Diffusion for Recommendation

Shuo Liu, An Zhang, Guoqing Hu, Hong Qian, Tat-Seng Chua

The Case for Cleaner Biosignals: High-fidelity Neural Compressor Enables Transfer from Cleaner iEEG to Noisier EEG

Francesco S. Carzaniga, Gary Tom Hoppeler, Michael Hersche, Kaspar Schindler, Abbas Rahimi

Divergence-Regularized Discounted Aggregation: Equilibrium Finding in Multiplayer Partially Observable Stochastic Games

Runyu Lu, Yuanheng Zhu, Dongbin Zhao

MLLM as Retriever: Interactively Learning Multimodal Retrieval for Embodied Agents

Junpeng Yue, Xinrun Xu, Börje F. Karlsson, Zongqing Lu