Models That Know How Evaluations Are Designed Score Safer
Paper • 2605.28591 • Published • 6
AI & ML interests
LLM, trustworthy AI, AI security, privacy, calibration, hallucination
Recent Activity
View all activity
Papers
Privacy Collapse: Benign Fine-Tuning Can Break Contextual Privacy in Language Models
Is Multilingual LLM Watermarking Truly Multilingual? A Simple Back-Translation Solution
haritzpuerto
authored a
paper 4 days ago
haritzpuerto
submitted a
paper to Daily Papers 4 days ago
ahmedheakl
authored 6
papers 12 days ago
Planner and Executor: Collaboration between Discrete Diffusion And Autoregressive Models in Reasoning
Paper • 2510.15244 • Published
WorldCache: Content-Aware Caching for Accelerated Video World Models
Paper • 2603.22286 • Published • 5
Latent-DARM: Bridging Discrete Diffusion And Autoregressive Models For Reasoning
Paper • 2603.09184 • Published
MASEval: Extending Multi-Agent Evaluation from Models to Systems
Paper • 2603.08835 • Published
DocAtlas: Multilingual Document Understanding Across 80+ Languages
Paper • 2605.12623 • Published • 4
CEPO: RLVR Self-Distillation using Contrastive Evidence Policy Optimization
Paper • 2605.19436 • Published • 14
ahmedheakl
submitted 2
papers to Daily Papers 13 days ago
cemde
authored 4
papers about 2 months ago
Shh, don't say that! Domain Certification in LLMs
Paper • 2502.19320 • Published
Measuring what Matters: Construct Validity in Large Language Model Benchmarks
Paper • 2511.04703 • Published • 8
Privacy Collapse: Benign Fine-Tuning Can Break Contextual Privacy in Language Models
Paper • 2601.15220 • Published • 9
A Stable, Fast, and Fully Automatic Learning Algorithm for Predictive Coding Networks
Paper • 2212.00720 • Published
haritzpuerto
authored a
paper 3 months ago
ahmedheakl
authored a
paper 3 months ago
ahmedheakl
submitted a
paper to Daily Papers 3 months ago
mgubri
authored a
paper 4 months ago
mgubri
updated a
collection 4 months ago
mgubri
submitted a
paper to Daily Papers 4 months ago