Deep Learning

When Local Rules Create Global Order: Self-Organized Representation Learning for Latent Diffusion Models CVPR 2026 When LoRA Betrays: Backdooring Text-to-Image Models by Masquerading as Benign Adapters CVPR 2026 When Morphology Hides in Plain Sight: Breaking the Isolation in Vietnamese and Beyond ACL 2026 When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models CVPR 2026 When Pretty Isn't Useful: Investigating Why Modern Text-to-Image Models Fail as Reliable Training Data Generators CVPR 2026 When Robots Obey the Patch: Universal Transferable Patch Attacks on Vision-Language-Action Models CVPR 2026 When Safety Collides: Resolving Multi-Category Harmful Conflicts in Text-to-Image Diffusion via Adaptive Safety Guidance CVPR 2026 When Token Pruning is Worse than Random: Understanding Visual Token Information in VLLMs CVPR 2026 When transformers learn “impossible” languages, what do they learn? CoNLL 2026 When Transformers Meet Mamba: A Hybrid Transformer-Mamba Network for Video Object Detection CVPR 2026 When Understanding Becomes a Risk: Authenticity and Safety Risks in the Emerging Image Generation Paradigm CVPR 2026 When Visualizing is the First Step to Reasoning: MIRA, a Benchmark for Visual Chain-of-Thought CVPR 2026 Where Culture Fades: Revealing the Cultural Gap in Text-to-Image Generation CVPR 2026 Where is the Watermark? Interpretable Watermark Detection at the Block Level WACV 2026 Which Concepts to Forget and How to Refuse? Decomposing Concepts for Continual Unlearning in Large Vision-Language Models CVPR 2026 WhisperDiari: A Whisper-Based Speaker Diarization Framework in Token Space Leveraging Semantic and Speaker Information for Better Text Adaptability AAAI 2026 Who to Trust? Aggregating Client Predictions in Federated Distillation. UAI 2026 WHU-MARS: A Multispectral Aerial-Ground Benchmark Towards Any-Scenario Person Re-Identification CVPR 2026 Why "Classic" Transformers Are Shallow and A Depth-Enabling Technique JMLR 2026 Why Does RL Generalize Better Than SFT? A Data-Centric Perspective on VLM Post-Training CVPR 2026 Why Do More Experts Fail? A Theoretical Analysis of Model Merging ACL 2026 Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets ACL 2026 Why Mean Pooling Works: Quantifying Second-Order Collapse in Text Embeddings ACL 2026 Why Not Hyperparameter-Friendly Optimisation? A Monotonic Adaptive Norm Rescaling Approach For Long-Tailed Recognition CVPR 2026 Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics ACL 2026