Skip to content
conftrace_

Optimization & Theory

7,804 papers (27 classified directly here)

Subtopics · a paper can sit in several, so these overlap

Optimization (1,960) Model Compression (1,896) Efficient Computing (1,780) Theory (1,239) Neural Network Optimization (1,004) Evaluation (533) Regularization (177) Loss Functions (157) Interpretability (128) Stochastic Methods (119) Generalization (115) Sparse Optimization (25)

Papers per year

16
60
675
1,352
'10
'15
'20
'25

Papers (including subtopics)

Optimal Expert-Attention Allocation in Mixture-of-Experts: A Scalable Law for Dynamic Model Design ACL 2026 Optimal L2 Regularization in High-dimensional Continual Linear Regression ALT 2026 Optimal Learning Rate Schedules under Functional Scaling Laws: Power Decay and Warmup–Stable–Decay (Extended Abstract) COLT 2026 Optimal Neural Network Approximation of Smooth Compositional Functions on Sets with Low Intrinsic Dimension COLT 2026 Optimal Software Pipelining and Warp Specialization for Tensor Core GPUs OSDI 2026 Optimization and Generalization of Gradient Descent for Shallow ReLU Networks with Minimal Width JMLR 2026 Optimizing Attention with Mirror Descent: Generalized Max-Margin Token Selection JMLR 2026 Optimizing Packing and Shuffling Strategies for Enhanced Performance in Generative Language Models ACL 2026 Parallelised Differentiable Straightest Geodesics for 3D Meshes CVPR 2026 PDR: A Plug-and-Play Positional Decay Framework for LLM Pre-training Data Detection ACL 2026 PDTrim: Targeted Pruning for Prefill-Decode Disaggregation in Inference ACL 2026 Peek2: Regex-free Byte-level Byte-Pair Encoding Pretokenizer for LLM Inference on Edge Devices ACL 2026 PE-QAT: Parameter-Efficient Quantization-Aware Training for Large Language Models ACL 2026 Pip-Stereo: Progressive Iterations Pruner for Iterative Optimization based Stereo Matching CVPR 2026 PixelRush: Ultra-Fast, Training-Free High-Resolution Image Generation via One-step Diffusion CVPR 2026 Pluggable Pruning with Contiguous Layer Distillation for Diffusion Transformers CVPR 2026 PointCNN++: Performant Convolution on Native Points CVPR 2026 POINTS-Long: Adaptive Dual-Mode Visual Reasoning in MLLMs CVPR 2026 Post-training Feature Pruning for Fundus Images Classification CVPR 2026 POUR: A Provably Optimal Method for Unlearning Representation via Neural Collapse CVPR 2026 PP-OCRv5: A Specialized 5M-Parameter Model Rivaling Billion-Parameter Vision-Language Models on OCR Tasks CVPR 2026 Price of metric universality in vector quantization is at most 0.11 bit COLT 2026 Probing Functional Correctness in Diffusion Language Models ACL 2026 Profiling-Free Mixed-Precision Quantization for MoE LLMs via Fuzzy Rule Interpolation ACL 2026 Progressive Neural Architecture Generation CVPR 2026