-
DuoGuard: A Two-Player RL-Driven Framework for Multilingual LLM Guardrails
Paper • 2502.05163 • Published • 22 -
CRANE: Reasoning with constrained LLM generation
Paper • 2502.09061 • Published • 21 -
Investigating the Impact of Quantization Methods on the Safety and Reliability of Large Language Models
Paper • 2502.15799 • Published • 7 -
AISafetyLab: A Comprehensive Framework for AI Safety Evaluation and Improvement
Paper • 2502.16776 • Published • 6
Collections
Discover the best community collections!
Collections including paper arxiv:2507.13255
-
GuardReasoner: Towards Reasoning-based LLM Safeguards
Paper • 2501.18492 • Published • 89 -
Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Merging
Paper • 2412.19512 • Published • 9 -
Course-Correction: Safety Alignment Using Synthetic Preferences
Paper • 2407.16637 • Published • 26 -
Refusal in Language Models Is Mediated by a Single Direction
Paper • 2406.11717 • Published • 14
-
EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters
Paper • 2402.04252 • Published • 31 -
Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation Models
Paper • 2402.03749 • Published • 15 -
ScreenAI: A Vision-Language Model for UI and Infographics Understanding
Paper • 2402.04615 • Published • 45 -
EfficientViT-SAM: Accelerated Segment Anything Model Without Performance Loss
Paper • 2402.05008 • Published • 24
-
DuoGuard: A Two-Player RL-Driven Framework for Multilingual LLM Guardrails
Paper • 2502.05163 • Published • 22 -
CRANE: Reasoning with constrained LLM generation
Paper • 2502.09061 • Published • 21 -
Investigating the Impact of Quantization Methods on the Safety and Reliability of Large Language Models
Paper • 2502.15799 • Published • 7 -
AISafetyLab: A Comprehensive Framework for AI Safety Evaluation and Improvement
Paper • 2502.16776 • Published • 6
-
Analyzing The Language of Visual Tokens
Paper • 2411.05001 • Published • 24 -
Large Multi-modal Models Can Interpret Features in Large Multi-modal Models
Paper • 2411.14982 • Published • 19 -
Rethinking Token Reduction in MLLMs: Towards a Unified Paradigm for Training-Free Acceleration
Paper • 2411.17686 • Published • 19 -
On the Limitations of Vision-Language Models in Understanding Image Transforms
Paper • 2503.09837 • Published • 10
-
DuoGuard: A Two-Player RL-Driven Framework for Multilingual LLM Guardrails
Paper • 2502.05163 • Published • 22 -
CRANE: Reasoning with constrained LLM generation
Paper • 2502.09061 • Published • 21 -
Investigating the Impact of Quantization Methods on the Safety and Reliability of Large Language Models
Paper • 2502.15799 • Published • 7 -
AISafetyLab: A Comprehensive Framework for AI Safety Evaluation and Improvement
Paper • 2502.16776 • Published • 6
-
DuoGuard: A Two-Player RL-Driven Framework for Multilingual LLM Guardrails
Paper • 2502.05163 • Published • 22 -
CRANE: Reasoning with constrained LLM generation
Paper • 2502.09061 • Published • 21 -
Investigating the Impact of Quantization Methods on the Safety and Reliability of Large Language Models
Paper • 2502.15799 • Published • 7 -
AISafetyLab: A Comprehensive Framework for AI Safety Evaluation and Improvement
Paper • 2502.16776 • Published • 6
-
GuardReasoner: Towards Reasoning-based LLM Safeguards
Paper • 2501.18492 • Published • 89 -
Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Merging
Paper • 2412.19512 • Published • 9 -
Course-Correction: Safety Alignment Using Synthetic Preferences
Paper • 2407.16637 • Published • 26 -
Refusal in Language Models Is Mediated by a Single Direction
Paper • 2406.11717 • Published • 14
-
Analyzing The Language of Visual Tokens
Paper • 2411.05001 • Published • 24 -
Large Multi-modal Models Can Interpret Features in Large Multi-modal Models
Paper • 2411.14982 • Published • 19 -
Rethinking Token Reduction in MLLMs: Towards a Unified Paradigm for Training-Free Acceleration
Paper • 2411.17686 • Published • 19 -
On the Limitations of Vision-Language Models in Understanding Image Transforms
Paper • 2503.09837 • Published • 10
-
EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters
Paper • 2402.04252 • Published • 31 -
Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation Models
Paper • 2402.03749 • Published • 15 -
ScreenAI: A Vision-Language Model for UI and Infographics Understanding
Paper • 2402.04615 • Published • 45 -
EfficientViT-SAM: Accelerated Segment Anything Model Without Performance Loss
Paper • 2402.05008 • Published • 24