Deep Learning

Beyond Single View: A Comprehensive Benchmark for Medical Multimodal Large Language Models on Multi-Image Understanding ACL 2026 Beyond Soft Label: Dataset Distillation via Orthogonal Gradient Matching CVPR 2026 Beyond Static Benchmarks: Synthesizing Harmful Content via Persona-based Simulation for Robust Evaluation ACL 2026 Beyond Static Frames: Temporal Aggregate-and-Restore Vision Transformer for Human Pose Estimation CVPR 2026 Beyond Strict Pairing: Arbitrarily Paired Training for High-Performance Infrared and Visible Image Fusion CVPR 2026 Beyond Text Prompts: Precise Concept Erasure through Text-Image Collaboration CVPR 2026 Beyond Text: Visual Description Assembly by Probabilistic Model for CLIP-based Weakly Supervised Semantic Segmentation CVPR 2026 Beyond the Encoder: Joint Encoder-Decoder Contrastive Pre-Training Improves Dense Prediction WACV 2026 Beyond the Golden Data: Resolving the Motion-Vision Quality Dilemma via Timestep Selective Training CVPR 2026 Beyond the Ground Truth: Enhanced Supervision for Image Restoration CVPR 2026 Beyond the Mean: Fisher-Orthogonal Projection for Natural Gradient Descent in Large Batch Training AAAI 2026 Beyond the Static World: Continual Category Discovery under Visual Drift CVPR 2026 Beyond the Static-World: Lifelong Learning for All-in-One Medical Image Restoration CVPR 2026 Beyond Tokens: Dynamic Latent Reasoning via Semantic Residual Refinement AAAI 2026 Beyond Transcripts: A Renewed Perspective on Audio Chaptering ACL 2026 Beyond Unconstrained Features: Neural Collapse for Shallow Neural Networks with General Data JMLR 2026 Beyond Unified Models: A Service-Oriented Approach to Low Latency, Context Aware Phonemization for Real Time TTS EACL 2026 Beyond Weak Supervision: MLLMs-Guided Graded Knowledge Distillation for Unsupervised Camouflaged Object Detection CVPR 2026 Beyond What's Shared: Recovering Lost Unique Information from Intermediate Layers to Boost Multimodal Geo-Foundation Models CVPR 2026 Beyond Wide-Angle Images: Structure-to-Detail Video Portrait Correction via Unsupervised Spatiotemporal Adaptation AAAI 2026 Bezier Degradation Modeling for LiDAR-based Human Motion Capture CVPR 2026 BHCast: Unlocking Black Hole Plasma Dynamics from a Single Blurry Image with Long-Term Forecasting CVPR 2026 Bias Fitting to Mitigate Length Bias of Reward Model in RLHF ACL 2026 Bias In, Bias Out? Finding Unbiased Subnetworks in Vanilla Models CVPR 2026 Bias Is a Subspace, Not a Coordinate: A Geometric Rethinking of Post-hoc Debiasing in Vision-Language Models CVPR 2026