arXiv Computation and Language

Reviser: Revision-Capable Text Generation via Autoregressive Cursor Actions

arXiv Machine Learning
Aug 27

Memory-V2V: Memory-Augmented Video-to-Video Diffusion for Consistent Multi-Turn Editing

Memory-V2V is a memory‑augmented video‑to‑video diffusion framework designed to improve cross‑turn consistency in multi‑turn video editing. It stores previous outputs in an external memory, retrieves relevant edits, and incorporates them via relevance‑aware tokenization and adaptive compression, allowing scalable conditioning without linear computational growth. Experiments on iterative video novel view synthesis and text‑guided long video editing show that Memory‑V2V enhances consistency while preserving visual quality and outperforming strong baselines with modest overhead.

By Dohun Lee, Chun-Hao Paul Huang, Xuelin Chen, Jong Chul Ye, Duygu Ceylan, Hyeonho Jeong
Hugging Face Trending Papers
Jun 10

Context-Driven Incremental Compression for Multi-Turn Dialogue Generation

Modern conversational agents condition on an ever-growing dialogue history at each turn, incurring redundant attention and encoding costs that grow with conversation length. Naive truncation or summarization degrades fidelity, while existing context compressors lack cross-turn memory sharing or revision, causing information loss and compounding errors in long dialogues.

Hugging Face Trending Papers
Jun 11

InterleaveThinker: Reinforcing Agentic Interleaved Generation

Recent image generators have demonstrated impressive photorealism and instruction-following capabilities in single-image generation and editing. However, constrained by their architectures, they cannot achieve interleaved generation (text-image sequence), which has crucial applications in visual narratives, guidance, and embodied manipulation.

arXiv Computation and Language
Sep 7

Detect, Remask, Repair: Diffusion Editing for Faithful Summarization of Evolving Contexts

The paper introduces DETECT-REMASK-REPAIR, a diffusion-based method for updating outdated spans in existing summaries while keeping supported content intact. It identifies, masks, and repairs only the changed regions using masked diffusion language models. Experiments on DialogSum and a new StreamSum benchmark show that this localized repair improves faithfulness, reduces repair time to under half a second, and offers trade‑offs between faithfulness, speed, and preservation of the original summary.

By Hao Zou, Zachary Horvitz, Chandhru Karthick, Zhou Yu, Kathleen McKeown