arXiv Machine Learning
Jun 2
OP-LoRA: The Blessing of Dimensionality
arXiv:2412. 10362v2 Announce Type: replace Abstract: Low-rank adapters (LoRA) enable finetuning of large models with only a small number of parameters.
Prompt2Effect: Training-Free Image-to-Video Model Specialization via LoRA Generation
Related stories
arXiv Computer Vision
Aug 24
ES-VP : Energy-Shaped Dynamic Visual Prompting for Efficient Model Adaptation
ES‑VP introduces Energy‑Shaped Visual Prompting, a method that generates image‑specific prompts through low‑rank initialization and energy‑guided dynamic adaptation. It achieves higher performance than existing single‑prompt and diverse‑prompt approaches while using far fewer parameters. Experiments on five architectures and fifteen datasets show consistent superiority, including a 2.6% accuracy gain over DAM‑VP on CLIP with 590× fewer prompt parameters.
arXiv AI
Aug 7
UniVVT: A Unified End-to-End Framework for High-Fidelity Video Virtual Try-on
arXiv:2608. 05745v1 Announce Type: cross Abstract: Video Virtual Try-On (VVT) synthesizes a video of a person wearing a target garment while preserving identity, motion, and scene dynamics.
arXiv Computer Vision
1d ago
SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models
SolarWM is an open foundation for building interactive video world models, offering a reconfigurable multi‑source data engine that unifies 1.43 million clips from 10 datasets into a consistent, frame‑aligned format. It provides a backbone‑native adaptation framework that preserves native representations of models ranging from 5 B to 33 B parameters, and a three‑stage training recipe combining bidirectional adaptation, teacher‑forced autoregressive initialization, and distribution‑matching distillation. The resulting causal models can interact in real‑time over rollouts from minutes to hours, trained only on 5‑second sequences, and the project releases data, pipeline, recipes, weights, and framework for reproducible research.
arXiv Computer Vision
Aug 25
VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding
arXiv:2607.14935v2 Announce Type: replace Abstract: Recent advances in video understanding have spanned motion, long video, and streaming interaction, driving this field toward real-world application...
arXiv Machine Learning
Jul 21
DA-MergeLoRA: Hypernetwork-Based LoRA Merging for Few-Shot Test-Time Domain Adaptation
arXiv:2607. 17467v1 Announce Type: cross Abstract: Few-shot Test-Time Domain Adaptation (FSTT-DA) seeks to adapt models to novel domains using only a handful of unlabeled target samples.
arXiv Computer Vision
4d ago
Video Generative Models as Geometry Learner
The paper introduces GeoNeXt, a framework that repurposes pretrained video generative models for geometry estimation by framing it as a next‑frame prediction task. Unlike prior methods that either train separate depth/normal models or fine‑tune image diffusion backbones, GeoNeXt jointly models images and geometric targets, leveraging the structured knowledge of video models for more data‑efficient learning. Experiments show zero‑shot monocular depth and surface normal estimation that outperforms existing generative approaches and rivals discriminative state‑of‑the‑art methods while using far less training data.
arXiv Computer Vision
3d ago
Generalization over Memorization: Generalization-Aware Diffusion Adaptation for Single-Image Multi-View Synthesis
arXiv:2608.29233v1 Announce Type: new Abstract: We present the winning solution to the ACM Multimedia 2026 Grand Challenge on Single-Image Guided Multi-Angle Image Synthesis. It ranks first among 293...
arXiv Machine Learning
Jul 31
Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation
arXiv:2607. 27372v1 Announce Type: new Abstract: The deep learning revolution, kicked off by AlexNet, taught us that end-to-end training beats decomposing a problem into hand-designed stages.
arXiv AI
Jul 28
The Visual Bottleneck: Sparse-Frame Adaptation of MLLMs for Joint Spatial-Temporal Video Grounding
arXiv:2607. 24570v1 Announce Type: cross Abstract: Large-scale video platforms process millions of uploads hourly, requiring moderation systems that can localize when and where policy violations occur within each video.
arXiv AI
Jun 30
Spanning the Visual Analogy Space with a Weight Basis of LoRAs
arXiv:2602. 15727v2 Announce Type: replace-cross Abstract: Visual analogy learning enables image editing via demonstration rather than textual description, allowing users to specify complex transformations difficult to articulate in words.
arXiv Computer Vision
1d ago
Learning Zero-Shot Subject-Driven Video Generation Using 1% Compute
arXiv:2504.17816v4 Announce Type: replace Abstract: Subject-driven video generation (SDV-Gen) aims to produce videos of a specific subject by adapting a pretrained video model, enabling personalized...