Optimization & Theory

InTrain: Intrinsic Trainability for Zero-Cost Neural Architecture Search CVPR 2026 Investigating the Histogram Loss in Regression JMLR 2026 Invited Open Problem: Is the Power of Deep Learning over Linear Models Inherently Distribution Dependent? COLT 2026 Is the Attention Matrix Really the Key to Self-Attention in Multivariate Long-Term Time Series Forecasting? ACL 2026 It's Never Too Late: Noise Optimization for Collapse Recovery in Trained Diffusion Models CVPR 2026 Joint Optimization of Camera Model and Deep Neural Network for Image Recognition WACV 2026 Just-in-Time: Training-Free Spatial Acceleration for Diffusion Transformers CVPR 2026 JW-SVD: Bridging the Cross-Modal Mismatch in Post-Training MLLM Compression ACL 2026 Kareus: Joint Reduction of Dynamic and Static Energy in Large Model Training OSDI 2026 Label-Free Cross-Task LoRA Merging with Null-Space Compression CVPR 2026 LADR: Locality-Aware Dynamic Rescue for Efficient Text-to-Image Generation with Diffusion Large Language Models ACL 2026 Layered 4D-Rotor Gaussian Splatting: A Compressed Representation for Long Dynamic Scenes CVPR 2026 Layer-Wise High-Impact Parameter Ratio Optimization in Post-Training Quantization for Large Language Models ACL 2026 LazyVAR: Accelerating Visual Autoregressive Models via Scale-wise Token Pruning and Parallel Group Decoding CVPR 2026 League of LLMs: A Benchmark-Free Paradigm for Mutual Evaluation of Large Language Models ACL 2026 LEAP: Layer-wise Exit-Aware Pretraining for Efficient Transformer Inference ACL 2026 Learned Image Compression via Sparse Attention and Adaptive Frequency CVPR 2026 Learning by Analogy: A Causal Framework for Compositional Generalization CVPR 2026 Learning Differentiable Hierarchies in 3D Gaussian Splatting CVPR 2026 Learning Expressive Random Feature Models via Parametrized Activations UAI 2026 Learning Quantized Continuous Controllers for Integer Hardware L4DC 2026 Learning Straight Flows: Variational Flow Matching for Efficient Generation CVPR 2026 Lens Component Deletion based on Differentiable Ray Tracing CVPR 2026 LESA: Learnable Stage-Aware Predictors for Diffusion Model Acceleration CVPR 2026 LiDeRe: A Lightweight Readout for Fast and Data-Efficient Dense Prediction CVPR 2026