PulseAugur
EN
LIVE 20:29:35
ENTITY MM-DiTs

MM-DiTs

PulseAugur coverage of MM-DiTs — every cluster mentioning MM-DiTs across labs, papers, and developer communities, ranked by signal.

Show in brief
Total · 30d
1
5 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
1
5 over 90d
TIER MIX · 90D
TOPICS
RECENT · PAGE 1/1 · 5 TOTAL
  1. TOOL · CL_300772 ·

    New QK-Edit framework enhances MM-DiT image and video editing

    Researchers have developed QK-Edit, a novel framework designed to enhance the editing capabilities of Multimodal Diffusion Transformers (MM-DiTs) for image and video manipulation. Unlike traditional methods that struggl…

  2. TOOL · CL_200243 ·

    New method erases unwanted concepts in AI image generation models

    Researchers have developed a new tuning-free method for concept erasure in Multimodal Diffusion Transformers (MM-DiTs), which are advanced text-to-image generation models. This technique directly manipulates the model's…

  3. TOOL · CL_191417 ·

    ControlRef framework enhances multi-instance image generation efficiency

    Researchers have introduced ControlRef, a new framework designed to improve the efficiency and precision of layout-guided multi-instance image generation within Multi-Modal Diffusion Transformers (MM-DiTs). This system …

  4. TOOL · CL_129408 ·

    New FairFlow framework tackles stereotype bias in text-to-image AI

    Researchers have developed FairFlow, a new framework designed to address stereotype bias in text-to-image diffusion models, particularly multimodal diffusion transformers (MM-DiTs). The study identifies specific layers …

  5. RESEARCH · CL_53698 ·

    AnchorDiff improves AI concept grounding by reducing visual leakage

    Researchers have introduced AnchorDiff, a novel training-free method designed to improve concept grounding in Multi-Modal Diffusion Transformers (MM-DiTs). This approach tackles the issue of "concept leakage," where vis…