LG-Gaze: Learning Geometry-aware Continuous Prompts for Language-Guided Gaze Estimation.- Efficient Training with Denoised Neural Weights.- Learning the Unlearned: Mitigating Feature Suppression in Contrastive Learning.- Integration of Global and Local Representations for Fine-grained Cross-modal Alignment.- Local and Global Flatness for Federated Domain Generalization.- SRPose: Two-view Relative Pose Estimation with Sparse Keypoints.- Deep Reward Supervisions for Tuning Text-to-Image Diffusion Models.- Paying More Attention to Images: A Training-Free Method for Alleviating Hallucination in LVLMs.- Inf-DiT: Upsampling any-resolution image with memory-efficient diffusion transformer..- Implicit Neural Models to Extract Heart Rate from Video.- Boost Your NeRF: A Model-Agnostic Mixture of Experts Framework for High Quality and Efficient Rendering.- PFGS: High Fidelity Point Cloud Rendering via Feature Splatting.- Few-Shot Anomaly-Driven Generation for Anomaly Classification and Segmentation.- E3M: Zero-Shot Spatio-Temporal Video Grounding with Expectation-Maximization Multimodal Modulation.- EMO: Emote Portrait Alive - Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions.- LMT-GP: Combined Latent Mean-Teacher and Gaussian Process for Semi-supervised Low-light Image Enhancement.- Veil Privacy on Visual Data: Concealing Privacy for Humans, Unveiling for DNNs.- Efficient Vision Transformers with Partial Attention.- Generalized Coverage for More Robust Low-Budget Active Learning.- Rasterized Edge Gradients: Handling Discontinuities Differentially.- Enhancing Cross-Subject fMRI-to-Video Decoding with Global-Local Functional Alignment.- FedTSA: A Cluster-based Two-Stage Aggregation Method for Model-heterogeneous Federated Learning.- LLaVA-UHD: an LMM Perceiving any Aspect Ratio and High-Resolution Images.- Learning Natural Consistency Representation for Face Forgery Video Detection.- ZeroI2V: Zero-Cost Adaptation of Pre-Trained Transformers from Image to Video.- Zero-Shot Adaptation for Approximate Posterior Sampling of Diffusion Models in Inverse Problems.- R.A.C.E.: Robust Adversarial Concept Erasure for Secure Text-to-Image Diffusion Model.