Deep Learning

Vision Transformers Need More Than Registers CVPR 2026 VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Models CVPR 2026 VisPCO: Visual Token Pruning Configuration Optimization via Budget-Aware Pareto-Frontier Learning for Vision-Language Models ACL 2026 VisRef: Visual Refocusing while Thinking Improves Test-Time Scaling in Multi-Modal Large Reasoning Models CVPR 2026 VISTA: A Vision and Intent-Aware Social Attention Framework for Multi-Agent Trajectory Prediction WACV 2026 Vista-LLM: Decoupled Query-Guided Visual Token Pruning for Efficient Long-Video Large Language Models ACL 2026 ViSTA: Visual Storytelling using Multi-modal Adapters for Text-to-Image Diffusion Models WACV 2026 ViStoryBench: Comprehensive Benchmark Suite for Story Visualization CVPR 2026 VisualAD: Language-Free Zero-Shot Anomaly Detection via Vision Transformer CVPR 2026 Visual-Aware CoT: Achieving High-Fidelity Visual Consistency in Unified Models CVPR 2026 Visual Bridge: Universal Visual Perception Representations Generating AAAI 2026 Visual Diffusion Models are Geometric Solvers CVPR 2026 Visual-Friendly Concept Protection via Selective Adversarial Perturbations AAAI 2026 ViT$^3$: Unlocking Test-Time Training in Vision CVPR 2026 VitaGlyph: Vitalizing Artistic Typography with Flexible Dual-branch Diffusion Models WACV 2026 VITAL: Vision-Encoder-centered Pre-training for LMMs in Visual Quality Assessment CVPR 2026 VITA: Variational Pretraining of Transformers for Climate-Robust Crop Yield Forecasting AAAI 2026 ViTE: Virtual Graph Trajectory Expert Router for Pedestrian Trajectory Prediction AAAI 2026 ViTPrompt: Training-Free Prompt Refinement with Visual Tokens for Open-Vocabulary Detection CVPR 2026 VIVA: VLM-Guided Instruction-Based Video Editing with Reward Optimization CVPR 2026 VividAnimator: An End-to-End Audio and Pose-driven Half-Body Human Animation Framework WACV 2026 VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model AAAI 2026 VLA Models Are More Generalizable Than You Think: Revisiting Physical and Spatial Modeling CVPR 2026 VL-Eraser: Vacuum Distillation for Machine Unlearning in Vision-Language Models CVPR 2026 VLIC: Vision-Language Models As Perceptual Judges for Human-Aligned Image Compression CVPR 2026