Efficient Computing

The GeometricKernels Package: Heat and Matérn Kernels for Geometric Learning on Manifolds, Meshes, and Graphs JMLR 2025 The Graph’s Apprentice: Teaching an LLM Low-Level Knowledge for Circuit Quality Estimation IJCAI 2025 The Green KNIGHT: Green Machine Translation with Knowledge-Distilled, Narrow, Inexpensive, Greedy, Hybrid Transformers EMNLP 2025 The Hidden Joules: Evaluating the Energy Consumption of Vision Backbones for Progress Towards More Efficient Model Inference ICML 2025 The Impact of Inference Acceleration on Bias of LLMs NAACL 2025 The Inter-Intra Modal Measure: A Predictive Lens on Fine-Tuning Outcomes in Vision-Language Models ICCV 2025 The Power of Simplicity in LLM-Based Event Forecasting ACL 2025 The Price of Freedom: Exploring Expressivity and Runtime Tradeoffs in Equivariant Tensor Products ICML 2025 The Price of Linear Time: Error Analysis of Structured Kernel Interpolation ICML 2025 ThermalGaussian: Thermal 3D Gaussian Splatting ICLR 2025 The Sharpness Disparity Principle in Transformers for Accelerating Language Model Pre-Training ICML 2025 Thesis Proposal: Efficient Methods for Natural Language Generation/Understanding Systems IJCNLP 2025 The Sparse-Plus-Low-Rank Quasi-Newton Method for Entropic-Regularized Optimal Transport ICML 2025 The Unreasonable Ineffectiveness of the Deeper Layers ICLR 2025 Thickness-aware E(3)-Equivariant 3D Mesh Neural Networks ICML 2025 Thinking Before Running! Efficient Code Generation with Thorough Exploration and Optimal Refinement ACL 2025 Thinking in Granularity: Dynamic Quantization for Image Super-Resolution by Intriguing Multi-Granularity Clues AAAI 2025 Think-Search-Patch: A Retrieval-Augmented Reasoning Framework for Repository-Level Code Repair EMNLP 2025 ThinkSwitcher: When to Think Hard, When to Think Fast EMNLP 2025 ThinK: Thinner Key Cache by Query-Driven Pruning ICLR 2025 Thought calibration: Efficient and confident test-time scaling EMNLP 2025 ThunderKittens: Simple, Fast, and Adorable Kernels ICLR 2025 TidalDecode: Fast and Accurate LLM Decoding with Position Persistent Sparse Attention ICLR 2025 TIDES: Technical Information Discovery and Extraction System EMNLP 2025 Tiered Memory Management Beyond Hotness OSDI 2025