VINS-120K supplies the first large-scale set of instruction-image-edited-image triplets at ultra-high resolution together with an adaptation strategy that improves detail synthesis.
hub
Learning transferable visual models from natural language supervi- sion
19 Pith papers cite this work. Polarity classification is still indexing.
19
Pith papers citing it
hub tools
citation-role summary
background 2
method 1
citation-polarity summary
representative citing papers
ULF-Loc removes bias from 3DGS landmark features via geometry-weighted fusion and consistency checks, cutting median translation error 17% while using 1/10 training time and 1/6 GPU memory of prior state-of-the-art.
Prefill-Time Intervention (PTI) reduces hallucinations in large vision-language models by applying a one-time modality-aware steering correction to the initial KV cache at the prefill stage rather than during autoregressive decoding.
C-MET transfers emotions from speech to facial video by learning cross-modal semantic vectors with pretrained audio and disentangled expression encoders, yielding 14% higher emotion accuracy on MEAD and CREMA-D even for unseen emotions.
PLUME uses latent-state autoregressive rollouts and a progressive training curriculum to deliver efficient reasoning for universal multimodal embeddings without generating explicit rationales.
VideoCoF adds an explicit reasoning step using edit-region latents in video diffusion models to enable precise mask-free editing and motion alignment with only 50k training pairs.
MDM distills vision-language datasets via joint embedding clustering, weight-space model interpolation, and geometry-aware distribution matching on the unit hypersphere.
StyleTextGen proposes a dual-branch style encoder, text style consistency loss, and mask-guided inference to achieve superior style consistency and cross-lingual performance in multilingual scene text generation on a new bilingual benchmark.
MPerS dynamically mixes semantic guidance from MLLM-generated RS captions with DINOv3 features via MixExperts and Linguistic Query Guided Attention to achieve superior semantic segmentation on three public remote sensing datasets.
EggHand unifies VLA action decoding with viewpoint-aware video-text encoding to forecast egocentric hand poses, achieving SOTA accuracy on EgoExo4D while remaining robust to ego-motion and controllable via language prompts.
TG-DP decouples reconstruction and alignment objectives into separate paths with teacher guidance on visibility patterns, yielding SOTA zero-shot audio-video retrieval gains on AudioSet.
Stellar VLA achieves continual learning in VLA models by maintaining a growing knowledge space and routing tasks to specialized experts conditioned on semantic relations, delivering strong LIBERO benchmark results with only 1% data replay and successful real-world transfer on dual-arm hardware.
Diffusion models show distinct patterns of recognizing versus replicating culturally iconic references, with recognition linked to data frequency, textual uniqueness, popularity, and creation date rather than simple copying.
LEMUR 2 releases a multi-generator, multi-task neural-architecture corpus with real-device latency metadata intended as fuel for LLM-driven AutoML.
SEATrack combines AMG-LoRA for cross-modal attention alignment with HMoE for global relation modeling to improve the performance-efficiency trade-off in multimodal tracking.
CLIP-guided selection of external data plus staged NAFNet training and inference fusion provides an effective pipeline for nighttime image dehazing in the NTIRE 2026 challenge.
An MLLM interpreter generates concise CDL descriptions from diagrams, enabling an off-the-shelf LLM to solve plane geometry problems competitively after training on only 5.5k examples.
Long-LRM++ achieves real-time 14 FPS high-fidelity 360-degree scene reconstruction from 32-64 views by using semi-explicit Gaussians plus a light decoder, matching LaCT quality on DL3DV and improving depth prediction.
Diffusion-generated synthetic latent fingerprints largely preserve finger identity but introduce small local minutiae inconsistencies and global ridge hallucinations when style or reference quality is mismatched.
citing papers explorer
-
VINS-120K: Ultra High-Resolution Image Editing with A Large-Scale Dataset
VINS-120K supplies the first large-scale set of instruction-image-edited-image triplets at ultra-high resolution together with an adaptation strategy that improves detail synthesis.
-
ULF-Loc: Unbiased Landmark Feature for Robust Visual Localization with 3D Gaussian Splatting
ULF-Loc removes bias from 3DGS landmark features via geometry-weighted fusion and consistency checks, cutting median translation error 17% while using 1/10 training time and 1/6 GPU memory of prior state-of-the-art.
-
Prefill-Time Intervention for Mitigating Hallucination in Large Vision-Language Models
Prefill-Time Intervention (PTI) reduces hallucinations in large vision-language models by applying a one-time modality-aware steering correction to the initial KV cache at the prefill stage rather than during autoregressive decoding.
-
Cross-Modal Emotion Transfer for Emotion Editing in Talking Face Video
C-MET transfers emotions from speech to facial video by learning cross-modal semantic vectors with pretrained audio and disentangled expression encoders, yielding 14% higher emotion accuracy on MEAD and CREMA-D even for unseen emotions.
-
PLUME: Latent Reasoning Based Universal Multimodal Embedding
PLUME uses latent-state autoregressive rollouts and a progressive training curriculum to deliver efficient reasoning for universal multimodal embeddings without generating explicit rationales.
-
VideoCoF: Unified Video Editing with Temporal Reasoner
VideoCoF adds an explicit reasoning step using edit-region latents in video diffusion models to enable precise mask-free editing and motion alignment with only 50k training pairs.
-
Multimodal Distribution Matching for Vision-Language Dataset Distillation
MDM distills vision-language datasets via joint embedding clustering, weight-space model interpolation, and geometry-aware distribution matching on the unit hypersphere.
-
StyleTextGen: Style-Conditioned Multilingual Scene Text Generation
StyleTextGen proposes a dual-branch style encoder, text style consistency loss, and mask-guided inference to achieve superior style consistency and cross-lingual performance in multilingual scene text generation on a new bilingual benchmark.
-
MPerS: Dynamic MLLM MixExperts Perception-Guided Remote Sensing Scene Segmentation
MPerS dynamically mixes semantic guidance from MLLM-generated RS captions with DINOv3 features via MixExperts and Linguistic Query Guided Attention to achieve superior semantic segmentation on three public remote sensing datasets.
-
EggHand: A Multimodal Foundation Model for Egocentric Hand Pose Forecasting
EggHand unifies VLA action decoding with viewpoint-aware video-text encoding to forecast egocentric hand poses, achieving SOTA accuracy on EgoExo4D while remaining robust to ego-motion and controllable via language prompts.
-
Semantic Noise Reduction via Teacher-Guided Dual-Path Audio-Visual Representation Learning
TG-DP decouples reconstruction and alignment objectives into separate paths with teacher guidance on visibility patterns, yielding SOTA zero-shot audio-video retrieval gains on AudioSet.
-
Continually Evolving Skill Knowledge in Vision Language Action Model
Stellar VLA achieves continual learning in VLA models by maintaining a growing knowledge space and routing tasks to specialized experts conditioned on semantic relations, delivering strong LIBERO benchmark results with only 1% data replay and successful real-world transfer on dual-arm hardware.
-
The Persistence of Cultural Memory: Investigating Multimodal Iconicity in Diffusion Models
Diffusion models show distinct patterns of recognizing versus replicating culturally iconic references, with recognition linked to data frequency, textual uniqueness, popularity, and creation date rather than simple copying.
-
LEMUR 2: Unlocking Neural Network Diversity for AI
LEMUR 2 releases a multi-generator, multi-task neural-architecture corpus with real-device latency metadata intended as fuel for LLM-driven AutoML.
-
SEATrack: Simple, Efficient, and Adaptive Multimodal Tracker
SEATrack combines AMG-LoRA for cross-modal attention alignment with HMoE for global relation modeling to improve the performance-efficiency trade-off in multimodal tracking.
-
CLIP-Guided Data Augmentation for Night-Time Image Dehazing
CLIP-guided selection of external data plus staged NAFNet training and inference fusion provides an effective pipeline for nighttime image dehazing in the NTIRE 2026 challenge.
-
Concise Geometric Description as a Bridge: Unleashing the Potential of LLM for Plane Geometry Problem Solving
An MLLM interpreter generates concise CDL descriptions from diagrams, enabling an off-the-shelf LLM to solve plane geometry problems competitively after training on only 5.5k examples.
-
Long-LRM++: Preserving Fine Details in Feed-Forward Wide-Coverage Reconstruction
Long-LRM++ achieves real-time 14 FPS high-fidelity 360-degree scene reconstruction from 32-64 views by using semi-explicit Gaussians plus a light decoder, matching LaCT quality on DL3DV and improving depth prediction.
-
Intra-finger Variability of Diffusion-based Latent Fingerprint Generation
Diffusion-generated synthetic latent fingerprints largely preserve finger identity but introduce small local minutiae inconsistencies and global ridge hallucinations when style or reference quality is mismatched.