Search papers, labs, and topics across Lattice.
3
0
6
1
Past post-training successes often turn toxic when reapplied to drifted checkpoints, making pre-training experience authorization essential to prevent autonomous self-improvement loops from wasting compute and destabilizing model weights.
Forget static hyperparameters: DVAO dynamically adjusts reward weights based on variance, leading to more stable and effective multi-objective RLHF.
Stop relying on stochasticity: this work shows how distilling experience into hierarchical knowledge unlocks more effective and stable LLM-based agentic search.
