Dual-Modality Multi-Stage Adversarial Safety Training: Robustifying Multimodal Web Agents Against Cross-Modal Attacks
Research
Research News
New papers, breakthroughs and academic AI research
Zero-Shot Lombard Speech Synthesis with Controllable Style Embeddings
Research
![[b] = [d] - [t] + [p]: Self-supervised Speech Models Discover Phonological Vector Arithmetic](/media/images/2026/10/gen-42af8784bb08561b.webp)
[b] = [d] - [t] + [p]: Self-supervised Speech Models Discover Phonological Vector Arithmetic
Research
D3S2: Diffusion-Guided Dataset Distillation for Semantic Segmentation
Research
PHBA: Prefix-State Hybrid Block Attention
Research
Reinforcement Learning for Hierarchical Reasoning Rewards: Minimax-Optimal Rates with Transformers
Research
AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking
Research
From Shared Demand Patterns to Local Uncertainty: Probabilistic Load Forecasting by Mixing Compact Adaptations
Research
Quantifying Cross-Lingual Transfer in Paralinguistic Speech Tasks
Research
Singular Value Decomposition: A Geometric Rediscovery, Where Proofs Become Algorithms
Research
The Dual Mechanisms of Spatial Variable Binding in Vision-Language Models
Research
Valid for Free: Homophily-Gated Conformal Prediction for Training-Free Node Classification with Tabular Foundation Models
Research