Image de couverture de livre

SPG: Sandwiched Policy Gradient for Masked Diffusion Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wang, Chenyu, Rashidinejad, Paria, Su, DiJia, Jiang, Song, Wang, Sid, Zhao, Siyan, Zhou, Cai, Shen, Shannon Zejiang, Chen, Feiyu, Jaakkola, Tommi, Tian, Yuandong, Liu, Bo
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Sail into the Headwind: Alignment via Robust Rewards and Dynamic Labels against Reward Hacking
par: Rashidinejad, Paria, et autres
Publié: (2024)

GaLore 2: Large-Scale LLM Pre-Training by Gradient Low-Rank Projection
par: Su, DiJia, et autres
Publié: (2025)

Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces
par: Su, DiJia, et autres
Publié: (2024)

Inpainting-Guided Policy Optimization for Diffusion Large Language Models
par: Zhao, Siyan, et autres
Publié: (2025)

Examining Reasoning LLMs-as-Judges in Non-Verifiable LLM Post-Training
par: Liu, Yixin, et autres
Publié: (2026)

Solve the Loop: Attractor Models for Language and Reasoning
par: Fein-Ashley, Jacob, et autres
Publié: (2026)

Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning
par: Su, DiJia, et autres
Publié: (2025)

Next Semantic Scale Prediction via Hierarchical Diffusion Language Models
par: Zhou, Cai, et autres
Publié: (2025)

Learning Diffusion Models with Flexible Representation Guidance
par: Wang, Chenyu, et autres
Publié: (2025)

Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy Prefixes
par: Setlur, Amrith, et autres
Publié: (2026)

Training Large Language Models to Reason in a Continuous Latent Space
par: Hao, Shibo, et autres
Publié: (2024)

Beyond A*: Better Planning with Transformers via Search Dynamics Bootstrapping
par: Lehnert, Lucas, et autres
Publié: (2024)

In-Context Symmetries: Self-Supervised Learning through Contextual World Models
par: Gupta, Sharut, et autres
Publié: (2024)

Continuously Tempered Diffusion Samplers
par: Erives, Ezra, et autres
Publié: (2025)

Correcting Diffusion Generation through Resampling
par: Liu, Yujian, et autres
Publié: (2023)

Coevolutionary Continuous Discrete Diffusion: Make Your Diffusion Language Model a Latent Reasoner
par: Zhou, Cai, et autres
Publié: (2025)

CrispEdit: Low-Curvature Projections for Scalable Non-Destructive LLM Editing
par: Ikram, Zarif, et autres
Publié: (2026)

Thought calibration: Efficient and confident test-time scaling
par: Wu, Menghua, et autres
Publié: (2025)

Diffusion Domain Expansion: Learning to Coordinate Pre-trained Diffusion Models
par: Lifar, Egor, et autres
Publié: (2026)

Calibrated Selective Classification
par: Fisch, Adam, et autres
Publié: (2022)

Equivariant Scalar Fields for Molecular Docking with Fast Fourier Transforms
par: Jing, Bowen, et autres
Publié: (2023)

Verlet Flows: Exact-Likelihood Integrators for Flow-Based Generative Models
par: Erives, Ezra, et autres
Publié: (2024)

LEAPS: A discrete neural sampler via locally equivariant networks
par: Holderrieth, Peter, et autres
Publié: (2025)

AI-based Methods for Simulating, Sampling, and Predicting Protein Ensembles
par: Jing, Bowen, et autres
Publié: (2025)

AlphaFold Meets Flow Matching for Generating Protein Ensembles
par: Jing, Bowen, et autres
Publié: (2024)

Hamiltonian Score Matching and Generative Flows
par: Holderrieth, Peter, et autres
Publié: (2024)

Fine-Tuning Discrete Diffusion Models via Reward Optimization with Applications to DNA and Protein Design
par: Wang, Chenyu, et autres
Publié: (2024)

Dirichlet Flow Matching with Applications to DNA Sequence Design
par: Stark, Hannes, et autres
Publié: (2024)

An Information Criterion for Controlled Disentanglement of Multimodal Data
par: Wang, Chenyu, et autres
Publié: (2024)

DisCo-Diff: Enhancing Continuous Diffusion Models with Discrete Latents
par: Xu, Yilun, et autres
Publié: (2024)

The road ahead for functional foods: Promising opportunities amidst industry challenges
par: Ali Rashidinejad
Publié: (2024)

Bioactive compounds from New Zealand's native edible plants: Their role in future functional foods
par: Ali Rashidinejad
Publié: (2024)

Diffusion models in protein structure and docking
par: Jason Yim, et autres
Publié: (2024)

Online Reasoning Calibration: Test-Time Training Enables Generalizable Conformal LLM Reasoning
par: Zhou, Cai, et autres
Publié: (2026)

ProxelGen: Generating Proteins as 3D Densities
par: Faltings, Felix, et autres
Publié: (2025)

Fictitious Synthetic Data Can Improve LLM Factuality via Prerequisite Learning
par: Liu, Yujian, et autres
Publié: (2024)

Revisiting Who's Harry Potter: Towards Targeted Unlearning from a Causal Intervention Perspective
par: Liu, Yujian, et autres
Publié: (2024)

Harmonic Self-Conditioned Flow Matching for Multi-Ligand Docking and Binding Site Design
par: Stärk, Hannes, et autres
Publié: (2023)

Generative Modeling of Molecular Dynamics Trajectories
par: Jing, Bowen, et autres
Publié: (2024)

Protein FID: Improved Evaluation of Protein Structure Generative Models
par: Faltings, Felix, et autres
Publié: (2025)