Self-Rewarding Sequential Monte Carlo for Masked Diffusion Language Models
cs.LG
Submitted: 2026-02-02
Updated: 2026-11-09
Code: https://github.com/Algolzw/self-rewarding-smc
Project page: http://skylion007.github.io/OpenWebTextCorpus
Terminology
Sources
- LLaDA2.0: Scaling Up Diffusion Language Models to 100B
- Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
- Inference-Time Scaling of Diffusion Language Models via Trajectory Refinement
- Plug and Play Language Models: A Simple Approach to Controlled Text Generation
- Scaling Diffusion Language Models via Adaptation from Autoregressive Models
- Soft-Masked Diffusion Language Models
- dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching
- Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlo
- Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps
- Scaling up Masked Diffusion Models on Text
- Large Language Diffusion Models
- Simple Guidance Mechanisms for Discrete Diffusion Models
- Inference-Time Alignment in Diffusion Models with Reward-Guided Generation: Tutorial and Review
- Remasking Discrete Diffusion Models with Inference-Time Scaling
- Fast-dLLM v2: Efficient Block-Diffusion LLM
- Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding
- Dream 7B: Diffusion Large Language Models
- Masked Diffusion Models are Secretly Time-Agnostic Masked Models and Exploit Inaccurate Categorical Sampling
- LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models
Related papers
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis
- (Mis)generalization of Helpful-Only Fine-tuning