ICML Spotlight Papers

406 papers found • Page 2 of 9

Elucidating the Design Space of Multimodal Protein Language Models

Cheng-Yen Hsieh, Xinyou Wang, Daiheng Zhang et al.

ICML 2025spotlightarXiv:2504.11454

Emergence and Effectiveness of Task Vectors in In-Context Learning: An Encoder Decoder Perspective

Seungwook Han, Jinyeop Song, Jeff Gore et al.

ICML 2025spotlightarXiv:2412.12276

Enforcing Latent Euclidean Geometry in Single-Cell VAEs for Manifold Interpolation

Alessandro Palma, Sergei Rybakov, Leon Hetzel et al.

ICML 2025spotlightarXiv:2507.11789
5
citations

Enhancing Certified Robustness via Block Reflector Orthogonal Layers and Logit Annealing Loss

Bo-Han Lai, Pin-Han Huang, Bo-Han Kung et al.

ICML 2025spotlightarXiv:2505.15174

Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition

Zheyang Xiong, Jack Cai, John Cooper et al.

ICML 2025spotlightarXiv:2410.05603

Exogenous Isomorphism for Counterfactual Identifiability

Yikang Chen, Dehui du

ICML 2025spotlightarXiv:2505.02212

Feature Learning beyond the Lazy-Rich Dichotomy: Insights from Representational Geometry

Chi-Ning Chou, Hang Le, Yichen Wang et al.

ICML 2025spotlightarXiv:2503.18114

Feature learning from non-Gaussian inputs: the case of Independent Component Analysis in high dimensions

Fabiola Ricci, Lorenzo Bardone, Sebastian Goldt

ICML 2025spotlightarXiv:2503.23896
1
citations

Federated Generalised Variational Inference: A Robust Probabilistic Federated Learning Framework

Terje Mildner, Oliver Hamelijnck, Paris Giampouras et al.

ICML 2025spotlightarXiv:2502.00846

FedSSI: Rehearsal-Free Continual Federated Learning with Synergistic Synaptic Intelligence

Yichen Li, Yuying Wang, Haozhao Wang et al.

ICML 2025spotlight

Feynman-Kac Correctors in Diffusion: Annealing, Guidance, and Product of Experts

Marta Skreta, Tara Akhound-Sadegh, Viktor Ohanesian et al.

ICML 2025spotlightarXiv:2503.02819
34
citations

Fishers for Free? Approximating the Fisher Information Matrix by Recycling the Squared Gradient Accumulator

YuXin Li, Felix Dangel, Derek Tam et al.

ICML 2025spotlightarXiv:2507.18807

FlashTP: Fused, Sparsity-Aware Tensor Product for Machine Learning Interatomic Potentials

Seung Lee, Hojoon Kim, Yutack Park et al.

ICML 2025spotlight

Flopping for FLOPs: Leveraging Equivariance for Computational Efficiency

Georg Bökman, David Nordström, Fredrik Kahl

ICML 2025spotlightarXiv:2502.05169

FlowDrag: 3D-aware Drag-based Image Editing with Mesh-guided Deformation Vector Flow Fields

Gwanhyeong Koo, Sunjae Yoon, Younghwan Lee et al.

ICML 2025spotlightarXiv:2507.08285

From Language Models over Tokens to Language Models over Characters

Tim Vieira, Benjamin LeBrun, Mario Giulianelli et al.

ICML 2025spotlightarXiv:2412.03719

From Mechanistic Interpretability to Mechanistic Biology: Training, Evaluating, and Interpreting Sparse Autoencoders on Protein Language Models

Etowah Adams, Liam Bai, Minji Lee et al.

ICML 2025spotlight
28
citations

Functional Alignment Can Mislead: Examining Model Stitching

Damian Smith, Harvey Mannering, Antonia Marcu

ICML 2025spotlight

G-Adaptivity: optimised graph-based mesh relocation for finite element methods

James Rowbottom, Georg Maierhofer, Teo Deveney et al.

ICML 2025spotlightarXiv:2407.04516

G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks

Guibin Zhang, Yanwei Yue, Xiangguo Sun et al.

ICML 2025spotlightarXiv:2410.11782

Generalized Random Forests Using Fixed-Point Trees

David Fleischer, David A Stephens, Archer Yang

ICML 2025spotlightarXiv:2306.11908

Geometric Hyena Networks for Large-scale Equivariant Learning

Artem Moskalev, Mangal Prakash, Junjie Xu et al.

ICML 2025spotlightarXiv:2505.22560
4
citations

Geometric Representation Condition Improves Equivariant Molecule Generation

Zian Li, Cai Zhou, Xiyuan Wang et al.

ICML 2025spotlightarXiv:2410.03655

GMAIL: Generative Modality Alignment for generated Image Learning

Shentong Mo, Sukmin Yun

ICML 2025spotlight

Graph Adaptive Autoregressive Moving Average Models

Moshe Eliasof, Alessio Gravina, Andrea Ceni et al.

ICML 2025spotlight

Graph Diffusion for Robust Multi-Agent Coordination

Xianghua Zeng, Hang Su, Zhengyi Wang et al.

ICML 2025spotlight

Great Models Think Alike and this Undermines AI Oversight

Shashwat Goel, Joschka Strüber, Ilze Amanda Auzina et al.

ICML 2025spotlightarXiv:2502.04313

HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation

Tianwei Lin, Wenqiao Zhang, Sijing Li et al.

ICML 2025spotlightarXiv:2502.09838
63
citations

Hide & Seek: Transformer Symmetries Obscure Sharpness & Riemannian Geometry Finds It

Marvin F, da Silva, Felix Dangel, Sageev Oore

ICML 2025spotlightarXiv:2505.05409

Hyperspherical Normalization for Scalable Deep Reinforcement Learning

Hojoon Lee, Youngdo Lee, Takuma Seno et al.

ICML 2025spotlightarXiv:2502.15280

Identifying Causal Direction via Variational Bayesian Compression

Quang-Duy Tran, Bao Duong, Phuoc Nguyen et al.

ICML 2025spotlightarXiv:2505.07503

Implicit Language Models are RNNs: Balancing Parallelization and Expressivity

Mark Schoene, Babak Rahmani, Heiner Kremer et al.

ICML 2025spotlight

Improving Consistency Models with Generator-Augmented Flows

Thibaut Issenhuth, Sangchul Lee, Ludovic Dos Santos et al.

ICML 2025spotlightarXiv:2406.09570

Improving Zero-Shot Adversarial Robustness in Vision-Language Models by Closed-form Alignment of Adversarial Path Simplices

Junhao Dong, Piotr Koniusz, Yifei Zhang et al.

ICML 2025spotlight

Independence Tests for Language Models

Sally Zhu, Ahmed Ahmed, Rohith Kuditipudi et al.

ICML 2025spotlightarXiv:2502.12292

InfoSAM: Fine-Tuning the Segment Anything Model from An Information-Theoretic Perspective

Yuanhong Zhang, Muyao Yuan, Weizhan Zhang et al.

ICML 2025spotlightarXiv:2505.21920

Instance Correlation Graph-based Naive Bayes

Chengyuan Li, Liangxiao Jiang, Wenjun Zhang et al.

ICML 2025spotlight

Invariant Deep Uplift Modeling for Incentive Assignment in Online Marketing via Probability of Necessity and Sufficiency

Zexu Sun, Qiyu Han, Hao Yang et al.

ICML 2025spotlight

Investigating Non-Transitivity in LLM-as-a-Judge

Yi Xu, Laura Ruis, Tim Rocktäschel et al.

ICML 2025spotlightarXiv:2502.14074
19
citations

Is Complex Query Answering Really Complex?

Cosimo Gregucci, Bo Xiong, Daniel Hernández et al.

ICML 2025spotlightarXiv:2410.12537

Jacobian Sparse Autoencoders: Sparsify Computations, Not Just Activations

Lucy Farnik, Tim Lawson, Conor Houghton et al.

ICML 2025spotlightarXiv:2502.18147
6
citations

Language Models May Verbatim Complete Text They Were Not Explicitly Trained On

Ken Ziyu Liu, Christopher A. Choquette Choo, Matthew Jagielski et al.

ICML 2025spotlightarXiv:2503.17514

Large Language Model-driven Large Neighborhood Search for Large-Scale MILP Problems

Huigen Ye, Hua Xu, An Yan et al.

ICML 2025spotlight

Latent Diffusion Planning for Imitation Learning

Amber Xie, Oleh Rybkin, Dorsa Sadigh et al.

ICML 2025spotlightarXiv:2504.16925

Layer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision Language Models

Saketh Bachu, Erfan Shayegani, Rohit Lal et al.

ICML 2025spotlightarXiv:2411.04291
2
citations

Learning Dynamics under Environmental Constraints via Measurement-Induced Bundle Structures

Dongzhe Zheng, Wenjie Mei

ICML 2025spotlightarXiv:2505.19521
1
citations

Learning Parametric Distributions from Samples and Preferences

Marc Jourdan, Gizem Yüce, Nicolas Flammarion

ICML 2025spotlightarXiv:2505.23557

Learning Safety Constraints for Large Language Models

Xin Chen, Yarden As, Andreas Krause

ICML 2025spotlightarXiv:2505.24445
7
citations

Learning the RoPEs: Better 2D and 3D Position Encodings with STRING

Connor Schenck, Isaac Reid, Mithun Jacob et al.

ICML 2025spotlightarXiv:2502.02562
11
citations

Learning to (Learn at Test Time): RNNs with Expressive Hidden States

Yu Sun, Xinhao Li, Karan Dalal et al.

ICML 2025spotlightarXiv:2407.04620