Deep Learning

U-RoCX: An xLSTM based Approach to AI-Generated Urdu Text Detection EACL 2026 USE: A Unified Model for Universal Sound Separation and Extraction AAAI 2026 Using BERT to Explore Lexical Semantic Change of Prepositions EACL 2026 UST-Hand: An Uncertainty-aware Spatiotemporal Point Cloud Interaction Network for 3D Self-supervised Hand Pose Estimation CVPR 2026 UTPTrack: Towards Simple and Unified Token Pruning for Visual Tracking CVPR 2026 UTRAG at SemEval-2026 Task 8: History-Aware Query Rewriting and LoRA-Finetuned Generation for Multi-Turn RAG SemEval 2026 UVU: Improving Multimodal Understanding via Vision-Language Unified Autoregressive Paradigm CVPR 2026 VAEVQ: Enhancing Discrete Visual Tokenization Through Variational Modeling AAAI 2026 VAGU & GtS: LLM-Based Benchmark and Framework for Joint Video Anomaly Grounding and Understanding AAAI 2026 Validator-Guided Hard Negative Mining for Masked Language Modeling in Low-Resource Ancient Languages ACL 2026 Valid Inference for Treatment Effects under Multimodal Confounding CLeaR 2026 Valid Survey Simulations with Limited Human Data: The Roles of Prompting, Fine-Tuning, and Rectification ACL 2026 Vanast: Virtual Try-On with Human Image Animation via Synthetic Triplet Supervision CVPR 2026 Vanilla SGD with Momentum Survives Heavy-Tailed Noise: Convergence Analysis without Gradient Clipping or Normalization UAI 2026 VA-p: Variational Policy Alignment for Pixel-Aware Autoregressive Generation CVPR 2026 VARH-AI at SemEval-2026 Task 10: Exploiting Architectural Diversity with Transformer-SSM Ensembles and Confidence-Based Iterative Refinement for Conspiracy Detection SemEval 2026 Variance reduction combining pre-experiment and in-experiment data CLeaR 2026 Variation-aware Vision Token Dropping for Faster Large Vision-Language Models CVPR 2026 V-Attack: Targeting Disentangled Value Features for Controllable Adversarial Attacks on LVLMs CVPR 2026 VCORE: Variance-Controlled Optimization-based Reweighting for Chain-of-Thought Supervision ACL 2026 VCU-Bridge: Hierarchical Visual Connotation Understanding via Semantic Bridging CVPR 2026 VDE: Training-Free Accelerating Rectified Flow Model via Velocity Decomposition and Estimation CVPR 2026 VDFE: Difference-Aware 3D Scene Editing with Non-Intrusive Video Diffusion Priors for Multi-View Consistency and Efficiency CVPR 2026 VDOT: Efficient Unified Video Creation via Optimal Transport Distillation CVPR 2026 VecAttention: Vector-wise Sparse Attention for Accelerating Long Context Inference CVPR 2026