Match the Canvas, Not Just the Answer: Predictability-Aware SFT for Diffusion Language Models
cs.LG, cs.AI, cs.CL
Submitted: 2026-10-13
Updated: 2026-10-13
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- TRIMS: Trajectory-Ranked Instruction Masked Supervision for Diffusion Language Models
- Training Verifiers to Solve Math Word Problems
- Residual Context Diffusion Language Models
- LaViDa: A Large Diffusion Language Model for Multimodal Understanding
- Trace-Based On-Policy Distillation for Masked Diffusion Language Models
- Back on Track: Aligning Rewards and States for Reasoning in Diffusion Large Language Models
- NaRA: Noise-Aware LoRA for Parameter-Efficient Fine-Tuning of Diffusion LLMs
- Learn Hard Problems During RL with Reference Guided Fine-tuning
- KodCode: A Diverse, Challenging, and Verifiable Synthetic Dataset for Coding
- Dream 7B: Diffusion Large Language Models
- d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks