Grab a Coffee: Future-Aware Guidance for Discrete Diffusion with Compiled Objectives
cs.AI
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/unitaryai/detoxify
Sources
- Semantic Probabilistic Layers for Neuro-Symbolic Learning
- DLM-SWAI: Steering Diffusion Language Models Before They Unmask
- Conditional Monte Carlo Tree Diffusion for Designing Cell-Type-Specific and Biologically Faithful Regulatory DNA
- DPRM: A Plug-in Doob h transform-induced Token-Ordering Module for Discrete Diffusion Models
- Constrained Decoding for Diffusion Language Models via Efficient Inference over Finite Automata
- Plug-and-Play Guidance for Discrete Diffusion Models via Gradient-Informed Logit Correction
- On Tractable Computation of Expected Predictions
- Fine-Tuning Masked Diffusion for Provable Self-Correction
- Contrastive Distribution Matching for Amortized Sequential Monte Carlo in Discrete Diffusion
- Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review
- Breaking the Factorization Barrier in Diffusion Language Models
- Large Language Diffusion Models
- Reward-Guided Discrete Diffusion via Clean-Sample Markov Chain for Molecule and Biological Sequence Design
- Inference-Time Alignment of Diffusion Models via Trust-Region Iterative Twisted Sequential Monte Carlo
- TRACE Back from the Future: A Probabilistic Reasoning Approach to Controllable Language Generation
- Dream 7B: Diffusion Large Language Models
- The Safety-Aware Denoiser for Text Diffusion Models
- Tractable Control for Autoregressive Language Generation
- Adaptable Logical Control for Large Language Models
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