A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods
Paper • 2502.01618 • Published • 10 •
3
Dan Gilliland
dangv
·
AI & ML interests
None yet
Organizations
None yet
commented 5
papers over 1 year ago
OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models
Paper • 2502.01061 • Published • 225 •
23
Demystifying Long Chain-of-Thought Reasoning in LLMs
Paper • 2502.03373 • Published • 58 •
3
Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial?
Paper • 2502.00674 • Published • 13 •
4
Activation Approximations Can Incur Safety Vulnerabilities Even in Aligned LLMs: Comprehensive Analysis and Defense
Paper • 2502.00840 • Published •
3