DiMOS: Doob-Guided Inference-Time Multi-Objective Search for Scientific Design
cs.AI
Submitted: 2026-10-05
Updated: 2026-10-05
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Multi-Objective-Guided Discrete Flow Matching for Controllable Biological Sequence Design
- Ctrl-DNA: Controllable Cell-Type-Specific Regulatory DNA Design via Constrained RL
- DEFT: Efficient Fine-Tuning of Diffusion Models by Learning the Generalised $h$-transform
- Plug-and-Play Controllable Generation for Discrete Masked Models
- Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review
- Simple Guidance Mechanisms for Discrete Diffusion Models
- Simplified and Generalized Masked Diffusion for Discrete Data
- Inference-Time Alignment in Diffusion Models with Reward-Guided Generation: Tutorial and Review
- Training-Free Adaptation of Diffusion Models via Doob's $h$-Transform
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems