NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
292 results for “keyword:"diffusion language models"” in ICLR 2027. 41 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Mask-On: Compact Activation-Calibrated Merging for Autoregressive and Diffusion Language Models▼1.2k1.67
[PDF]WHAT DOES FFN COMPRESSION CHANGE DOWNSTREAM? SAME-STATE CAUSAL RESTORATION IN DIFFUSION LANGUAGE MODELS▼1351.33
[PDF]Unmask the State: State-Adaptive Strategy Selection for Masked Diffusion Language Models▼1.2k1.67
[PDF]Low-Confidence Remasking Traps Flexibility: Realizing Arbitrary-Order Potential for Diverse Rollouts in Diffusion LLMs▲5103.00
[PDF]A Ticket from Marginals to Joints: Coupled-Noise Distillation for One-Step Block Generation in Diffusion Language Models▼1.2k1.67
[PDF]Targeted Remasking: Token-to-Mask Refinement as Inference-Time Correction for Diffusion Language Models▼5.3k1.33
[PDF]Early-Bird Decoding: Accelerating Diffusion LLMs with Learnable Block Sizes and Parallel Sampling▲1.7k3.33
[PDF]Conflux: Self-Refining Unified Diffusion LLM with Cross-Paradigm On-Policy Distillation▼1.2k3.00
[PDF]The Answer Is Not the State: Trajectory-Level Corrigibility in Diffusion Language Models▼6.2k2.67
[PDF]Cola2: Co-Adaptive Hierarchical Language Modeling with Continuous Semantic Compression and Balanced Discrete Generation▼4.5k2.67
[PDF]Factual Access States in Diffusion Language Models: From Mechanism to Knowledge Editing and Retrieval▲5103.00
[PDF]InvExplain: An Agentic Interpretation Framework for SAE Features via Training-Free Diffusion Inversion▼5.8k2.33
[PDF]Factorization-Guided Training and Inference for Diffusion-Drafted Speculative Decoding▲3.0k2.33
[PDF]Commit Locally, Exit Globally: Coordinating Adaptive Sampling and Early Exit in Diffusion Language Models▲14k3.00
[PDF]DIGAA: Decoupling Information Gathering and Accurate Answering in Retrieval-Augmented Diffusion Language Models▲9.2k2.67
[PDF]PulseCol: Periodically Refreshed Column-Sparse Attention for Accelerating Diffusion Language Models▲3.0k2.33
[PDF]One Latent, Many Tokens: Jointly Learning Compressed Embeddings for Efficient Language Diffusion▼4.5k2.67
Withdrawn or desk rejected (41)
[PDF]Commit Order, Not Commit Rate: Answer Availability and Prefix Preservation in Diffusion Language ModelsWithdrawn1.67
[PDF]The Truncation Trap: Silent Failure of Fixed-Window Diffusion Likelihood and Information Estimators under Representation DriftWithdrawn1.00