Search papers, labs, and topics across Lattice.
Affiliation:
3
39
6
In-context learning is not limited to discriminative prediction: frozen transformers run full iterative diffusion and energy-based sampling within a single forward pass.
By focusing on correcting "near-miss" answers, REVES achieves a remarkable +6.5 point improvement over standard RL methods, showcasing a new way to enhance LLM reasoning without extensive computational costs.
By modeling policy gradients as Gaussian processes, this work dramatically reduces the sample complexity in reinforcement learning, offering faster convergence and uncertainty estimates at little extra cost.
