Flip-Flop Consistency: Unsupervised Training for Robustness to Prompt Perturbations in LLMs
Research
Research News
New papers, breakthroughs and academic AI research
Scenario-Based Compositional Statistical Model Checking for Safety Specifications
Research
Sparse Autoencoders Can Capture Language-Specific Concepts Across Diverse Languages
Research
RFG: Self-Improving Diffusion Large Language Models with Reward-Free Guidance
Research
Cross-Lingual Summarization as a Black-Box Watermark Removal Attack
Research
MCA: Modality Composition Awareness for Robust Composed Multimodal Retrieval
Research
Oolong: Evaluating Long Context Reasoning and Aggregation Capabilities
Research
Lens3D: Target-Conditioned Visual Foveation for Fine-Grained 3D Understanding
Research
Video Encoders Built on Image Representations
Research
RealtimeWAM: One-Step Asynchronous World Action Models
Research
Talk Like You: Imitating How You Speak in Real-Time Talking Head Generation
Research
EulerESG: Automating ESG Disclosure Analysis with LLMs
Research