3 papers
cs.AI2026
DANGERLENS: Probing Dangerous Representations Hidden by Safety Alignment
Tianzhuo Yang, Shaoheng Yan, Lin Lu +5
Safety alignment teaches language models to refuse harmful requests, yet the internal accessibility of hazardous concepts can retain traces of earlier training. Can checkpoints wit…
cs.LG2026
STQuant: Spatio-Temporal Adaptive Framework for Optimizer Quantization in Large Multimodal Model Training
Minglu Liu, Cunchen Hu, Liangliang Xu +3
Quantization is an effective way to reduce the memory cost of large-scale model training. However, most existing methods adopt fixed-precision policies, which ignore the fact that…
cs.CL2026
CCR-Bench: A Comprehensive Benchmark for Evaluating LLMs on Complex Constraints, Control Flows, and Real-World Cases
Xiaona Xue, Yiqiao Huang, Jiacheng Li +9
Enhancing the ability of large language models (LLMs) to follow complex instructions is critical for their deployment in real-world applications. However, existing evaluation metho…