Topic
safe
Multi-Agent Reinforcement Learning Achieves Superhuman Racing with 50% Fewer Collisions
A new study demonstrates that multi-agent reinforcement learning (MARL) allows quadrotors to achieve superhuman racing performance. Agents trained via league-based self-play outperformed champion humans at over 22 m/s and cut collision rates by 50% versus single-agent baselines, suggesting a new path for safe autonomous systems in shared spaces.
SafeSpec: New Framework Boosts LLM Safety Without Sacrificing Inference Speed
Researchers propose SafeSpec, a safety-aware speculative inference framework that attaches a latent safety head to jointly evaluate semantic validity and safety in a single forward pass. On Qwen3-32B, it reduces attack success rates by 15% while preserving a 2.06x inference speedup on benign workloads, addressing the fundamental incompatibility between existing safety methods and speculative decoding.