Optimization & Theory

UniVBench: Towards Unified Evaluation for Video Foundation Models CVPR 2026 Universal Neural Architecture Space: Covering ConvNets, Transformers and Everything in Between WACV 2026 Unleashing Low-Bit Inference on Ascend NPUs: A Comprehensive Evaluation of HiFloat Formats ACL 2026 Upsample Anything: A Simple and Hard to Beat Baseline for Feature Upsampling CVPR 2026 Vanilla SGD with Momentum Survives Heavy-Tailed Noise: Convergence Analysis without Gradient Clipping or Normalization UAI 2026 Variation-aware Vision Token Dropping for Faster Large Vision-Language Models CVPR 2026 VCORE: Variance-Controlled Optimization-based Reweighting for Chain-of-Thought Supervision ACL 2026 VDE: Training-Free Accelerating Rectified Flow Model via Velocity Decomposition and Estimation CVPR 2026 VecAttention: Vector-wise Sparse Attention for Accelerating Long Context Inference CVPR 2026 VecInfer: Efficient LLM Inference with Low-Bit KV Cache via Outlier-Suppressed Vector Quantization ACL 2026 VGA-Bench: A Unified Benchmark and Multi-Model Framework for Video Aesthetics and Generation Quality Evaluation CVPR 2026 VideoRealBench: A Chain-of-Thought Realism Evaluation Benchmark for Generated Human-Centric Videos CVPR 2026 VisPCO: Visual Token Pruning Configuration Optimization via Budget-Aware Pareto-Frontier Learning for Vision-Language Models ACL 2026 Vista-LLM: Decoupled Query-Guided Visual Token Pruning for Efficient Long-Video Large Language Models ACL 2026 ViT$^3$: Unlocking Test-Time Training in Vision CVPR 2026 VLM-Pruner: Buffering for Spatial Sparsity in an Efficient VLM Centrifugal Token Pruning Paradigm CVPR 2026 VLM-PTQ: Efficient Post-Training Quantization for Large Vision-Language Models CVPR 2026 VL-RouterBench: A Benchmark for Vision-Language Model Routing CVPR 2026 VTC: DNN Compilation with Virtual Tensors for Data Movement Elimination OSDI 2026 VVS: Accelerating Speculative Decoding for Visual Autoregressive Generation via Partial Verification Skipping CVPR 2026 WeightLoRA: Keep Only Necessary Adapters ACL 2026 What Fine-Tuning Changes: A Radiomic Lens on Prostate Foundation Model Representations MIDL 2026 What Is It Like to Be a Noise? An Entropy-based Gaussian Noise Regularization for Diffusion Models CVPR 2026 What Matters in Practical Learned Image Compression CVPR 2026 When Both Layers Learn: Training Dynamics of Representing Linear Models via ReLU Networks COLT 2026