From the 1 of 67 linked papers with an AI index.
4 papers · 1 filter
Safe responses matter: Output-aware safety guardrail mitigate over-refusal in MLLMs
Jiayi Li, Kun Zhan
Existing safety mechanisms for multimodal large language models (MLLMs) face a fundamental trade-off between safety and utility. Model fine-tuning achieves robust safety but compro…
HMPO: Hybrid Median-length Policy Optimization for Chain-of-Thought Compression
Minghui Zheng, Hongxu Chen, Huimin Ren +8
Large language models achieve remarkable performance via extended chain-of-thought (CoT) reasoning, yet this lengthy process incurs substantial inference overhead. Existing CoT com…
FAAR: Format-Aware Adaptive Rounding for NVFP4
Hanglin Li, Shuchang Tian, Chen Lin +2
Deploying large language models (LLMs) on edge devices requires extremely low-bit quantization. Ultra-low precision formats such as NVFP4 offer a promising solution for reducing me…
Hardware Co-Design Scaling Laws via Roofline Modelling for On-Device LLMs
Luoyang Sun, Jiwen Jiang, Yifeng Ding +9
Vision-Language-Action Models (VLAs) have emerged as a key paradigm of Physical AI and are increasingly deployed in autonomous vehicles, robots, and smart spaces. In these resource…