🌫 Diffusion language models - laurynas · Scour

Adaptive Steering and Remasking for Safe Generation in Diffusion Language Models 🎯Reranking

Steering Without Breaking: Mechanistically Informed Interventions for Discrete Diffusion Language Models 🔍AI Interpretability

Where Should Diffusion Enter a Language Model? Geometry-Guided Hidden-State Replacement 🎯Reranking

Guidance Is Not a Hyperparameter: Learning Dynamic Control in Diffusion Language Models 🎮Reinforcement Learning

Beyond Mode-Seeking RL: Trajectory-Balance Post-Training for Diffusion Language Models ⚙Context engineering

Factorization-Error-Free Discrete Diffusion Language Model via Speculative Decoding 📍embeddings

DiffRetriever: Parallel Representative Tokens for Retrieval with Diffusion Language Models 🎯Reranking

Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusion 🎯Reranking

Don't Retrain, Align: Adapting Autoregressive LMs to Diffusion LMs via Representation Alignment 🎯Reranking

Towards Closing the Autoregressive Gap in Language Modeling via Entropy-Gated Continuous Bitstream Diffusion 📍embeddings

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models ⚙Context engineering

ELF: Embedded Language Flows ⚙Context engineering

LEAP: Unlocking dLLM Parallelism via Lookahead Early-Convergence Token Detection 🧪Property-based Testing

No more posts from laurynas's subscribed feeds.

Scour all 25670 feeds Learn more about Feeds

Log in to enable infinite scrolling