Multimodal Learning

SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training ICML 2025 SGMEA: Structure-Guided Multimodal Entity Alignment COLING 2025 Shadow-Activated Backdoor Attacks on Multimodal Large Language Models ACL 2025 Shallow Focus, Deep Fixes: Enhancing Shallow Layers Vision Attention Sinks to Alleviate Hallucination in LVLMs EMNLP 2025 ShapeWords: Guiding Text-to-Image Synthesis with 3D Shape-Aware Prompts CVPR 2025 Sharper and Faster mean Better: Towards More Efficient Vision-Language Model for Hour-scale Long Video Understanding ACL 2025 SHARP: Steering Hallucination in LVLMs via Representation Engineering EMNLP 2025 SheetDesigner: MLLM-Powered Spreadsheet Layout Generation with Rule-Based and Vision-Based Reflection EMNLP 2025 SHE: Streaming-media Hashing Retrieval ICML 2025 SHIFT: Selected Helpful Informative Frame for Video-guided Machine Translation EMNLP 2025 SHIFT: Smoothing Hallucinations by Information Flow Tuning for Multimodal Large Language Models ICCV 2025 ShortV: Efficient Multimodal Large Language Models by Freezing Visual Tokens in Ineffective Layers ICCV 2025 Shot2Story: A New Benchmark for Comprehensive Understanding of Multi-shot Videos ICLR 2025 ShotAdapter: Text-to-Multi-Shot Video Generation with Diffusion Models CVPR 2025 Shot-by-Shot: Film-Grammar-Aware Training-Free Audio Description Generation ICCV 2025 ShotVL: Human-Centric Highlight Frame Retrieval via Language Queries AAAI 2025 Should VLMs be Pre-trained with Image Data? ICLR 2025 ShowMak3r: Compositional TV Show Reconstruction CVPR 2025 ShowUI: One Vision-Language-Action Model for GUI Visual Agent CVPR 2025 SHuBERT: Self-Supervised Sign Language Representation Learning via Multi-Stream Cluster Prediction ACL 2025 SIFT-50M: A Large-Scale Multilingual Dataset for Speech Instruction Fine-Tuning ACL 2025 Sightation Counts: Leveraging Sighted User Feedback in Building a BLV-aligned Dataset of Diagram Descriptions ACL 2025 Sign2Vis: Automated Data Visualization from Sign Language ACL 2025 SignAlignLM: Integrating Multimodal Sign Language Processing into Large Language Models ACL 2025 Sign-IDD: Iconicity Disentangled Diffusion for Sign Language Production AAAI 2025