Textual Inversion learns a single embedding vector from a few images to represent personal concepts inside the text embedding space of a frozen text-to-image model, enabling their composition in natural language prompts.
CoRR , volume =
15 Pith papers cite this work, alongside 2,607 external citations. Polarity classification is still indexing.
15
Pith papers citing it
2,607
external citations · external index
citation-role summary
method 1
citation-polarity summary
verdicts
UNVERDICTED 15roles
method 1polarities
use method 1representative citing papers
PERL augments frozen CLIP with a shared recurrent reasoning module of roughly 6K parameters that iteratively refines representations via latent token injection, delivering strong base-to-novel and transfer performance across 15 benchmarks.
PluRule is a new multimodal multilingual benchmark showing that state-of-the-art vision-language models perform only marginally better than a trivial baseline at detecting specific rule violations in pluralistic online communities.
The paper introduces the VODA setting for domain adaptation from scratch using vision-language models and presents TS-DRD, which achieves competitive performance on standard benchmarks without source models.
JSAE jointly factorizes pooled vision and language activations in VLMs into aligned interpretable features, revealing layer-dependent asymmetry in additive steering versus suppression on three models.
TB-AVA uses text-mediated gated semantic modulation to enable efficient audio-visual alignment, achieving state-of-the-art results on AVE, AVS, and AVVP benchmarks.
FACTOR uses counterfactual image perturbations to quantify and suppress attribute-dependent predictions in open-vocabulary object detection, improving robustness on corrupted datasets without any training.
BrainROI achieves leading cross-subject brain-captioning results on NSD by combining multi-atlas soft-ROI fusion with interpretable prompt optimization.
SAGE adds duality consistency as an auxiliary reward in GRPO training with a dynamic operation pool to improve spatial reasoning robustness and generalization in VLMs.
GeoStack composes multiple domain experts into VLMs with preserved base knowledge and O(1) inference time via geometric stacking and a weight-folding property.
A new joint spatio-temporal enlargement model for micro-video popularity prediction using frame scoring for long sequences and a topology-aware memory bank for unbounded historical associations.
VANGUARD is a staged-training VLM framework that reports 94% ROC-AUC and 84% F1 on UCF-Crime while adding chain-of-thought reasoning and spatial grounding to video anomaly detection.
A patch-based fusion method extends CLIP to high-resolution images by retaining multi-scale details for improved class-prompted retrieval.
Grad-ECLIP is an equivalent but flawed variant of attention-based interpretation, with two principles proposed to ensure model explanations reflect the original model.
ProtoCLIP improves zero-shot chest X-ray classification in CLIP models by 2-10 AUC points via curated data and prototype-aligned distillation, reaching 0.94 AUC for pneumothorax on VinDr-CXR.
citing papers explorer
-
An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion
Textual Inversion learns a single embedding vector from a few images to represent personal concepts inside the text embedding space of a frozen text-to-image model, enabling their composition in natural language prompts.
-
PERL: Parameter Efficient Reasoning in CLIP Latent Space
PERL augments frozen CLIP with a shared recurrent reasoning module of roughly 6K parameters that iteratively refines representations via latent token injection, delivering strong base-to-novel and transfer performance across 15 benchmarks.
-
PluRule: A Benchmark for Moderating Pluralistic Communities on Social Media
PluRule is a new multimodal multilingual benchmark showing that state-of-the-art vision-language models perform only marginally better than a trivial baseline at detecting specific rule violations in pluralistic online communities.
-
Rethinking the Need for Source Models: Source-Free Domain Adaptation from Scratch Guided by a Vision-Language Model
The paper introduces the VODA setting for domain adaptation from scratch using vision-language models and presents TS-DRD, which achieves competitive performance on standard benchmarks without source models.
-
Steering Vision-Language Models with Joint Sparse Autoencoders
JSAE jointly factorizes pooled vision and language activations in VLMs into aligned interpretable features, revealing layer-dependent asymmetry in additive steering versus suppression on three models.
-
TB-AVA: Text as a Semantic Bridge for Audio-Visual Parameter Efficient Finetuning
TB-AVA uses text-mediated gated semantic modulation to enable efficient audio-visual alignment, achieving state-of-the-art results on AVE, AVS, and AVVP benchmarks.
-
FACTOR: Counterfactual Training-Free Test-Time Adaptation for Open-Vocabulary Object Detection
FACTOR uses counterfactual image perturbations to quantify and suppress attribute-dependent predictions in open-vocabulary object detection, improving robustness on corrupted datasets without any training.
-
Unified Multimodal Brain Decoding via Cross-Subject Soft-ROI Fusion
BrainROI achieves leading cross-subject brain-captioning results on NSD by combining multi-atlas soft-ROI fusion with interpretable prompt optimization.
-
Self-Evolving Spatial Reasoning in Vision Language Models via Geometric Logic Consistency
SAGE adds duality consistency as an auxiliary reward in GRPO training with a dynamic operation pool to improve spatial reasoning robustness and generalization in VLMs.
-
GeoStack: A Framework for Quasi-Abelian Knowledge Composition in VLMs
GeoStack composes multiple domain experts into VLMs with preserved base knowledge and O(1) inference time via geometric stacking and a weight-folding property.
-
Seeing Further and Wider: Joint Spatio-Temporal Enlargement for Micro-Video Popularity Prediction
A new joint spatio-temporal enlargement model for micro-video popularity prediction using frame scoring for long sequences and a topology-aware memory bank for unbounded historical associations.
-
Reasoning-Guided Grounding: Elevating Video Anomaly Detection through Multimodal Large Language Models
VANGUARD is a staged-training VLM framework that reports 94% ROC-AUC and 84% F1 on UCF-Crime while adding chain-of-thought reasoning and spatial grounding to video anomaly detection.
-
DetailCLIP: Injecting Image Details into CLIP's Feature Space
A patch-based fusion method extends CLIP to high-resolution images by retaining multi-scale details for improved class-prompted retrieval.
-
Debunking Grad-ECLIP: A Comprehensive Study on Its Incorrectness and Fundamental Principles for Model Interpretation
Grad-ECLIP is an equivalent but flawed variant of attention-based interpretation, with two principles proposed to ensure model explanations reflect the original model.
-
ProtoCLIP: Prototype-Aligned Latent Refinement for Robust Zero-Shot Chest X-Ray Classification
ProtoCLIP improves zero-shot chest X-ray classification in CLIP models by 2-10 AUC points via curated data and prototype-aligned distillation, reaching 0.94 AUC for pneumothorax on VinDr-CXR.