A Safety Report on GPT-5.2, Gemini 3 Pro, Qwen3-VL, Doubao 1.8, Grok 4.1 Fast, Nano Banana Pro, and Seedream 4.5
Paper
• 2601.10527 • Published
• 25
LLM
-
-
PACEvolve: Enabling Long-Horizon Progress-Aware Consistent Evolution
Paper • 2601.10657 • Published • 20 -
TranslateGemma Technical Report
Paper • 2601.09012 • Published • 20 -
Recursive Language Models
Paper • 2512.24601 • Published • 89 -
YaPO: Learnable Sparse Activation Steering Vectors for Domain Adaptation
Paper • 2601.08441 • Published • 8 -
Stable-DiffCoder: Pushing the Frontier of Code Diffusion Large Language Model
Paper • 2601.15892 • Published • 53 -
LLM-in-Sandbox Elicits General Agentic Intelligence
Paper • 2601.16206 • Published • 84 -
HY-MT1.5 Technical Report
Paper • 2512.24092 • Published • 4 -
LongCat-Flash-Thinking-2601 Technical Report
Paper • 2601.16725 • Published • 175 -
Post-LayerNorm Is Back: Stable, ExpressivE, and Deep
Paper • 2601.19895 • Published • 23 -
Scaling Embeddings Outperforms Scaling Experts in Language Models
Paper • 2601.21204 • Published • 100 -
Context Compression via Explicit Information Transmission
Paper • 2602.03784 • Published • 14