generalization capabilities
The ability of an AI model to apply learned knowledge to new, unseen scenarios, critical for practical deployment in varied settings.
- Approximate Domain Unlearning for Vision-Language Models
- Beyond Benign Overfitting in Nadaraya-Watson Interpolators
- Comprehensive Assessment and Analysis for NSFW Content Erasure in Text-to-Image Diffusion models
- Conditional Panoramic Image Generation via Masked Autoregressive Modeling
- CoreGuard: Safeguarding Foundational Capabilities of LLMs Against Model Stealing in Edge Deployment
- DisasterM3: A Remote Sensing Vision-Language Dataset for Disaster Damage Assessment and Response
- Dynam3D: Dynamic Layered 3D Tokens Empower VLM for Vision-and-Language Navigation
- Efficient Multi-modal Large Language Models via Progressive Consistency Distillation
- Enhancing Personalized Multi-Turn Dialogue with Curiosity Reward
- Exploring the Limits of Vision-Language-Action Manipulation in Cross-task Generalization
- Is Artificial Intelligence Generated Image Detection a Solved Problem?
- K-DeCore: Facilitating Knowledge Transfer in Continual Structured Knowledge Reasoning via Knowledge Decoupling
- Learn and Ensemble Bridge Adapters for Multi-domain Task Incremental Learning
- MERIT: Multilingual Semantic Retrieval with Interleaved Multi-Condition Query
- MMaDA: Multimodal Large Diffusion Language Models
- PC-Net: Weakly Supervised Compositional Moment Retrieval via Proposal-Centric Network
- Physics-informed Reduced Order Modeling of Time-dependent PDEs via Differentiable Solvers
- SViMo: Synchronized Diffusion for Video and Motion Generation in Hand-object Interaction Scenarios
- State-Covering Trajectory Stitching for Diffusion Planners
- THD-BAR: Topology Hierarchical Derived Brain Autoregressive Modeling for EEG Generic Representations
- Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding
- UFO-RL: Uncertainty-Focused Optimization for Efficient Reinforcement Learning Data Selection
- Understanding Data Influence in Reinforcement Finetuning
- Unlocking SLM Potential for Data Analysis Code Generation via Non-Parametric Knowledge Distillation