Safety
ICLR 2026: 12 papers on making AI systems reliable, efficient, and secure
A 7B agent that beats GPT-4o. Lossless weight compression that speeds up inference by 177%. An arena where 23 teams battled across 103,000 adversarial rounds. This year at ICLR, Lambda is presenting t
A 7B agent that beats GPT-4o. Lossless weight compression that speeds up inference by 177%. An arena where 23 teams battled across 103,000 adversarial rounds. This year at ICLR, Lambda is presenting twelve papers and two workshops with over 20 collaborators across academia and industry. This work covers agents, LLMs, physical AI, and multimodal efficiency, addressing some recurring themes: long-horizon agentic planning under sparse rewards, alignment with safety constraints, structured world modeling, and inference-time efficiency.
Related
- CubeDAgger: Interactive Imitation Learning for Dynamic Systems with Efficient yet Low-risk Interaction
- KD-MARL: Resource-Aware Knowledge Distillation in Multi-Agent Reinforcement Learning
- CIA: Inferring the Communication Topology from LLM-based Multi-Agent Systems
- OVOD-Agent: A Markov-Bandit Framework for Proactive Visual Reasoning and Self-Evolving Detection
Source: Lambda Labs | 2026-04-23