LLM as a Broken Telephone: Iterative Generation Distorts Information Paper • 2502.20258 • Published 10 days ago • 18
Babel: Open Multilingual Large Language Models Serving Over 90% of Global Speakers Paper • 2503.00865 • Published 8 days ago • 55
AISafetyLab: A Comprehensive Framework for AI Safety Evaluation and Improvement Paper • 2502.16776 • Published 14 days ago • 5
Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization Alignment Paper • 2502.16894 • Published 14 days ago • 26
Benchmarking Temporal Reasoning and Alignment Across Chinese Dynasties Paper • 2502.16922 • Published 14 days ago • 7
Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path? Paper • 2502.15657 • Published 16 days ago • 5
MLGym: A New Framework and Benchmark for Advancing AI Research Agents Paper • 2502.14499 • Published 18 days ago • 177
SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features Paper • 2502.14786 • Published 17 days ago • 128
InfiR : Crafting Effective Small Language Models and Multimodal Small Language Models in Reasoning Paper • 2502.11573 • Published 21 days ago • 9
Why Safeguarded Ships Run Aground? Aligned Large Language Models' Safety Mechanisms Tend to Be Anchored in The Template Region Paper • 2502.13946 • Published 18 days ago • 9
Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention Paper • 2502.11089 • Published 22 days ago • 141
Learning Getting-Up Policies for Real-World Humanoid Robots Paper • 2502.12152 • Published 20 days ago • 37
Precise Parameter Localization for Textual Generation in Diffusion Models Paper • 2502.09935 • Published 24 days ago • 11
Diverse Inference and Verification for Advanced Reasoning Paper • 2502.09955 • Published 24 days ago • 17
TransMLA: Multi-head Latent Attention Is All You Need Paper • 2502.07864 • Published 26 days ago • 46