Search

"cross-attention"11 resultsKeyword

LTX-2: Efficient Joint Audio-Visual Foundation Model

Yoav HaCohen, Benny Brazowski et al.Jan 6arXiv

LTX-2 is an open-source model that makes video and sound together from a text prompt, so the picture and audio match in time and meaning.

#text-to-video#text-to-audio#audiovisual generation

Not triaged yet

C2LLM Technical Report: A New Frontier in Code Retrieval via Adaptive Cross-Attention Pooling

Beginner

Jin Qin, Zihan Liao et al.Dec 24arXiv

C2LLM is a new family of code embedding models that helps computers find the right code faster and more accurately.

#code retrieval#embedding model#cross-attention pooling

Not triaged yet

Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking

Intermediate

Mingxin Li, Yanzhao Zhang et al.Jan 8arXiv

This paper builds two teamwork models, Qwen3-VL-Embedding and Qwen3-VL-Reranker, that understand text, images, visual documents, and videos in one shared space so search works across all of them.

#multimodal retrieval#unified embedding space#cross-encoder reranker

Not triaged yet

Composing Concepts from Images and Videos via Concept-prompt Binding

Intermediate

Xianghao Kong, Zeyu Zhang et al.Dec 10arXiv

This paper introduces BiCo, a one-shot way to mix ideas from images and videos by tightly tying each visual idea to the exact words in a prompt.

#BiCo#concept binding#token-level composition

Not triaged yet

CASA: Cross-Attention via Self-Attention for Efficient Vision-Language Fusion

Intermediate

Moritz Böhle, Amélie Royer et al.Dec 22arXiv

CASA is a new way to mix images and text inside a language model that keeps speed and memory low while keeping accuracy high.

#CASA#cross-attention#self-attention

Not triaged yet

Efficient Text-Guided Convolutional Adapter for the Diffusion Model

Intermediate

Aryan Das, Koushik Biswas et al.Feb 16arXiv

This paper introduces Nexus Adapters, tiny helper networks that let a diffusion model follow both a text prompt and a structure map (like edges or depth) at the same time.

#Nexus Adapter#text-guided adapter#cross-attention

Not triaged yet

Fast Autoregressive Video Diffusion and World Models with Temporal Cache Compression and Sparse Attention

Intermediate

Dvir Samuel, Issar Tzachor et al.Feb 2arXiv

The paper makes long video generation much faster and lighter on memory by cutting out repeated work in attention.

#autoregressive video diffusion#KV cache compression#sparse attention

Not triaged yet

MorphAny3D: Unleashing the Power of Structured Latent in 3D Morphing

Intermediate

Xiaokun Sun, Zeyu Cai et al.Jan 1arXiv

MorphAny3D is a training-free way to smoothly change one 3D object into another, even if they are totally different (like a bee into a biplane).

#3D morphing#Structured Latent#SLAT

Not triaged yet

DeContext as Defense: Safe Image Editing in Diffusion Transformers

Intermediate

Linghui Shen, Mingyue Cui et al.Dec 18arXiv

This paper protects your photos from being misused by new AI image editors that can copy your face or style from just one picture.

#Diffusion Transformer#cross-attention#in-context image editing

Not triaged yet

Act2Goal: From World Model To General Goal-conditioned Policy

Intermediate

Pengfei Zhou, Liliang Chen et al.Dec 29arXiv

Robots often get confused on long, multi-step tasks when they only see the final goal image and try to guess the next move directly.

#goal-conditioned policy#visual world model#multi-scale temporal hashing

Not triaged yet

3D-Aware Implicit Motion Control for View-Adaptive Human Video Generation

Intermediate

Zhixue Fang, Xu He et al.Feb 3arXiv

This paper introduces 3DiMo, a new way to control how people move in generated videos while keeping the camera moves flexible through text.

#3D-aware motion#implicit motion encoder#motion tokens

Not triaged yet