A Better Newspaper

Page History

Every revision of this knowledge page since it was created on October 14, 2026. Each entry shows what kind of change was made, how the page grew or shrank, and the source articles that drove it — so the paper's memory is inspectable, not taken on faith.

Updated from new reportingOctober 23, 2026 (+956 chars)

What Makes a Good Unmasking Policy? A Controlled Study of Learned Unmasking in Diffusion Language Models

Updated from new reportingOctober 21, 2026 (+654 chars)

SPELUNKA: A Framework for Finding Unanticipated Associations in Vision-Language Models
Probabilistic Limit Order Book Forecasting with Conditional Diffusion Models
Steered Not Stirred: Effective Reward Tilting using Surrogate Reward Mixing
Enhanced Masked Diffusion Unlearning

Updated from new reportingOctober 15, 2026 (+627 chars)

Discovering Undisclosed Concepts in LoRA Adapters for Diffusion-Based AIGC Models
LEAP: Unlocking dLLM Parallelism via Lookahead Early-Convergence Token Detection
On the Limits of Representation-Based Test-Time Adaptation for Multimodal LLMs

Page createdOctober 14, 2026 (+1,513 chars)

Multi-Stream Residual Computation in Diffusion Language Models
Next-Concept Modeling: Fast, Parallel Coarse-to-Fine Text Generation
Match the Canvas, Not Just the Answer: Predictability-Aware SFT for Diffusion Language Models
HaloBlock: Faster and Better Decoding for Diffusion Large Language Models