10 posts published in the last hour
- 23:32A Training-Free Proactive Defense Against Partial Speech Manipulation via Self-Embedding Steganography
- 23:32Position Matters: Feature Inversion Attacks in ViT Split Inference with Token Reduction and Shuffling
- 23:32VLA-Precision: Asymmetric Co-Bootstrapping for Efficient Real-World Online RL of Vision-Language-Action Models
- 23:32TabScope: Question-Adaptive Scope Selection for Table Question Answering
- 23:32PAVE: Predictive Alignment and Value-Guided Evolution for World-Action Policies
- 23:03Are You Sure You’re Sure? On the Impact of Instruction Tuning on Confidence and Lexical Diversity
- 23:03Multi-turn Conversational AI from Text to Multimodal Interaction: Data, Models, Evaluation, and Open Challenges
- 23:03Self-Explanation Tutor for Active Study of CS1 Worked Examples
- 23:03Modeling Human Behavior with Type Vectors Using AI
- 23:03Sixteen models, fewer than two voices: measuring ensemble dispersion where no answer is uniquely correct