transformer

Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts ICML 2025 MTSTRec: Multimodal Time-Aligned Shared Token Recommender ICML 2025 Multi-band Frequency Reconstruction for Neural Psychoacoustic Coding ICML 2025 Nonlinear transformers can perform inference-time feature learning ICML 2025 Normalizing Flows are Capable Generative Models ICML 2025 On Exact Bit-level Reversible Transformers Without Changing Architecture ICML 2025 On-the-Fly Adaptive Distillation of Transformer to Dual-State Linear Attention for Long-Context LLM Serving ICML 2025 On the Training Convergence of Transformers for In-Context Classification of Gaussian Mixtures ICML 2025 ParticleFormer: A 3D Point Cloud World Model for Multi-Object, Multi-Material Robotic Manipulation CoRL 2025 PDE-Transformer: Efficient and Versatile Transformers for Physics Simulations ICML 2025 PENCIL: Long Thoughts with Short Memory ICML 2025 Positional Attention: Expressivity and Learnability of Algorithmic Computation ICML 2025 Reconstructing Cell Lineage Trees from Phenotypic Features with Metric Learning ICML 2025 Reinforced Learning Explicit Circuit Representations for Quantum State Characterization from Local Measurements ICML 2025 Relational Object-Centric Actor-Critic CLeaR 2025 Representation Shattering in Transformers: A Synthetic Study with Knowledge Editing ICML 2025 Rethinking Addressing in Language Models via Contextualized Equivariant Positional Encoding ICML 2025 Robust Noise Attenuation via Adaptive Pooling of Transformer Outputs ICML 2025 Scalable Equilibrium Sampling with Sequential Boltzmann Generators ICML 2025 SCENT: Robust Spatiotemporal Learning for Continuous Scientific Data via Scalable Conditioned Neural Fields ICML 2025 Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization Challenges ICML 2025 Self-Supervised Transformers as Iterative Solution Improvers for Constraint Satisfaction ICML 2025 Supercharging Graph Transformers with Advective Diffusion ICML 2025 TabICL: A Tabular Foundation Model for In-Context Learning on Large Data ICML 2025 Test-Time Training Provably Improves Transformers as In-context Learners ICML 2025