Optimization & Theory

2ndMatch: Finetuning Pruned Diffusion Models via Second-Order Jacobian Matching CVPR 2026 4D Primitive-Mache: Glueing Primitives for Persistent 4D Scene Reconstruction CVPR 2026 A BERTology View of LLM Orchestrations: Token- and Layer-Selective Probes for Efficient Single-Pass Classification ACL 2026 ACBQ: Adaptive Cross-Block Quantization of Large Language Models ACL 2026 Accelerating Autoregressive Video Diffusion via History-Guided Cache and Residual Correction CVPR 2026 Accelerating Diffusion-based Video Editing via Heterogeneous Caching: Beyond Full Computing at Sampled Denoising Timestep CVPR 2026 Accelerating Diffusion Model Training under Minimal Budgets: A Condensation-Based Perspective CVPR 2026 Achieving Cloud-Grade SLOs for Local Mixture-of-Experts Inference through CPU–GPU Hybrid Design OSDI 2026 A Common Interface for Automatic Differentiation JMLR 2026 A Comprehensive Benchmarking and Systematic Analysis of Deep Learning Models for Sonomammogram Segmentation MIDL 2026 AdaBet: Gradient-free Layer Selection for Efficient Training of Deep Neural Networks CVPR 2026 Adapting Lightweight Image-based Counting Models for Video Crowd Counting CVPR 2026 Adaptive Inference for Medical Vision Transformers: Token Reduction or Early Exit? MIDL 2026 Adaptive Spatial and Temporal Redundancy Optimization for Efficient Reasoning in Large Language Models ACL 2026 Adaptive Spectral Feature Forecasting for Diffusion Sampling Acceleration CVPR 2026 AdaRadar: Rate Adaptive Spectral Compression for Radar-based Perception CVPR 2026 AdaSVD: Singular Value Decomposition with Adaptive Mechanisms for Large Multimodal Models CVPR 2026 A Depth Hierarchy for Computing the Maximum in ReLU Networks via Extremal Graph Theory COLT 2026 Advances in PAC-Bayesian certification of deep neural networks: tighter closed-form inequalities and optimization of bounds on non-differentiable losses UAI 2026 A Faster Path to Continual Learning CVPR 2026 A Functional-Space Mean-Field Theory of Partially-Trained Three-Layer Neural Networks JMLR 2026 A Layer-wise Analysis of Supervised Fine-Tuning ACL 2026 Align Once to Explain: Feature Alignment for Scalable B-cosification of Foundational Vision Transformers CVPR 2026 Alloc-MoE: Budget-Aware Expert Activation Allocation for Efficient Mixture-of-Experts Inference ACL 2026 Ambirig at SemEval-2026 Task 5: Distributional Ordinal Modelling for Ambiguous Word Senses in Narrative Contexts SemEval 2026