SenseBench is the first physics-based benchmark with 10K+ instances and dual protocols to evaluate VLMs on remote sensing low-level perception and diagnostic description, revealing domain bias and specific failure modes.
hub Mixed citations
Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels
Mixed citation behavior. Most common role is baseline (33%).
33
Pith papers citing it
Baseline
33% of classified citations
abstract
The explosion of visual content available online underscores the requirement for an accurate machine assessor to robustly evaluate scores across diverse types of visual contents. While recent studies have demonstrated the exceptional potentials of large multi-modality models (LMMs) on a wide range of related fields, in this work, we explore how to teach them for visual rating aligned with human opinions. Observing that human raters only learn and judge discrete text-defined levels in subjective studies, we propose to emulate this subjective process and teach LMMs with text-defined rating levels instead of scores. The proposed Q-Align achieves state-of-the-art performance on image quality assessment (IQA), image aesthetic assessment (IAA), as well as video quality assessment (VQA) tasks under the original LMM structure. With the syllabus, we further unify the three tasks into one model, termed the OneAlign. In our experiments, we demonstrate the advantage of the discrete-level-based syllabus over direct-score-based variants for LMMs. Our code and the pre-trained weights are released at https://github.com/Q-Future/Q-Align.
hub tools
citation-role summary
baseline 3
method 3
background 2
dataset 1
citation-polarity summary
representative citing papers
Introduces FogAct paired clean-foggy video dataset and FogNet two-stream CLIP model that learns fog-invariant semantic representations via clean-video guidance.
TACache accelerates rectified flow sampling up to 4.14x for text-to-image and 2.11x for text-to-video via offline skip scheduling from cumulative variation thresholds and online velocity reconstruction using historical orthogonal directions.
GTA generates 3D worlds from single images via a two-stage video diffusion process that prioritizes geometry before appearance to improve structural consistency.
EditRefiner uses a perception-reasoning-action-evaluation agent loop and the EditFHF-15K human feedback dataset to refine text-guided image edits more accurately than prior methods.
FuScore uses MLLMs to output continuous quality scores for IVIF images, constructs per-image soft labels from four sub-dimensions, and applies a tripartite objective with Thurstone fidelity to achieve higher correlation with human preferences than prior metrics.
GameScope provides 4,048 multi-codec gaming videos with MOS ratings and attribute annotations, claimed as the first comprehensive dataset for gaming video quality assessment across codecs and content types.
PAMELA provides a multi-user rating dataset and personalized reward model that predicts individual image preferences more accurately than prior population-level aesthetic models.
EduVQA introduces the first concept-aware benchmark for educational AI-generated video assessment and a S2D-MoE framework that jointly evaluates perceptual quality and fine-grained semantic alignment.
LucidFlux is a caption-free image restoration method that conditions a Flux.1 diffusion transformer with a dual-branch module from the degraded input and a proxy restoration plus SigLIP semantic features to outperform baselines on synthetic and real-world data.
PiD is a pixel diffusion decoder that performs latent-to-pixel conversion and 4-8x upsampling in one generative step, enabling early stopping of latent diffusion and achieving sub-second 2048x2048 decoding with claimed better fidelity than cascaded baselines.
The paper releases SR-Ground, a crowdsourced dataset for pixel-level segmentation of six artifact types in super-resolved images, and shows its use for training grounded IQA models and artifact-reducing fine-tuning.
FGSVQA combines CLIP visual encoding with frequency priors and adaptive branch fusion to predict short-form video quality, reporting SRCC 0.736 and PLCC 0.787 on relevant datasets.
FashionChameleon achieves interactive multi-garment video customization in real time by training a teacher model with in-context learning on single-garment pairs, applying streaming distillation, and using training-free KV cache rescheduling.
GeoR-Bench shows top multimodal models reach only 42.7% strict accuracy on geoscience visual reasoning tasks while open-source models reach 10.3%, with outputs often visually plausible yet scientifically inaccurate.
ReasonEdit uses a new CoT dataset and reinforcement learning to produce interpretable, human-aligned evaluations of text-guided image edits.
RGSUD achieves SOTA unsupervised deraining by using IQA-based reward recycling and self-reinforcement to constrain optimization and improve pseudo-paired data quality.
YOGO reformulates stochastic 3D Gaussian Splatting into a deterministic budget-aware system and supplies an ultra-dense dataset to enforce physical fidelity over viewpoint interpolation.
DS-IEQA jointly learns evaluation criteria via feedback-driven prompt optimization and continuous score modeling via token-decoupled distance regression, ranking 4th in the 2026 NTIRE X-AIGC Quality Assessment Track 2 without extra training data.
Rein3D generates photorealistic, globally consistent 3D indoor scenes by using a restore-and-refine process where radial panoramic videos are restored via diffusion models and then used to update a 3D Gaussian field.
PAL uses closed-form affine color alignment on prediction-target pairs to discount global photometric discrepancies from the supervision signal, improving restoration across low-level vision tasks.
LumiVideo deploys an LLM-based agent with RAG and Tree of Thoughts to generate ASC-CDL parameters and 3D LUTs for automatic cinematic color grading from raw log video, approaching expert quality.
LucidNFT combines a new LR-referenced consistency reward, decoupled normalization, and a real-degradation dataset to improve perceptual quality in flow-matching super-resolution while preserving input fidelity.
HiFi-Inpaint delivers state-of-the-art detail-preserving human-product images by adding Shared Enhancement Attention and Detail-Aware Loss to reference-based inpainting on a new 40K dataset.
citing papers explorer
-
SenseBench: A Benchmark for Remote Sensing Low-Level Visual Perception and Description in Large Vision-Language Models
SenseBench is the first physics-based benchmark with 10K+ instances and dual protocols to evaluate VLMs on remote sensing low-level perception and diagnostic description, revealing domain bias and specific failure modes.
-
Seeing Through Fog: Towards Fog-Invariant Action Recognition
Introduces FogAct paired clean-foggy video dataset and FogNet two-stream CLIP model that learns fog-invariant semantic representations via clean-video guidance.
-
Accelerating Rectified Flow Models via Trajectory-Aware Caching
TACache accelerates rectified flow sampling up to 4.14x for text-to-image and 2.11x for text-to-video via offline skip scheduling from cumulative variation thresholds and online velocity reconstruction using historical orthogonal directions.
-
GTA: Advancing Image-to-3D World Generation via Geometry Then Appearance Video Diffusion
GTA generates 3D worlds from single images via a two-stage video diffusion process that prioritizes geometry before appearance to improve structural consistency.
-
EditRefiner: A Human-Aligned Agentic Framework for Image Editing Refinement
EditRefiner uses a perception-reasoning-action-evaluation agent loop and the EditFHF-15K human feedback dataset to refine text-guided image edits more accurately than prior methods.
-
Bringing Multimodal Large Language Models to Infrared-Visible Image Fusion Quality Assessment
FuScore uses MLLMs to output continuous quality scores for IVIF images, constructs per-image soft labels from four sub-dimensions, and applies a tripartite objective with Thurstone fidelity to achieve higher correlation with human preferences than prior metrics.
-
GameScope: A Multi-Attribute, Multi-Codec Benchmark Dataset for Gaming Video Quality Assessment
GameScope provides 4,048 multi-codec gaming videos with MOS ratings and attribute annotations, claimed as the first comprehensive dataset for gaming video quality assessment across codecs and content types.
-
Personalizing Text-to-Image Generation to Individual Taste
PAMELA provides a multi-user rating dataset and personalized reward model that predicts individual image preferences more accurately than prior population-level aesthetic models.
-
EduVQA: Towards Concept-Aware Assessment of Educational AI-Generated Videos
EduVQA introduces the first concept-aware benchmark for educational AI-generated video assessment and a S2D-MoE framework that jointly evaluates perceptual quality and fine-grained semantic alignment.
-
LucidFlux: Caption-Free Photo-Realistic Image Restoration via a Large-Scale Diffusion Transformer
LucidFlux is a caption-free image restoration method that conditions a Flux.1 diffusion transformer with a dual-branch module from the degraded input and a proxy restoration plus SigLIP semantic features to outperform baselines on synthetic and real-world data.
-
PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion
PiD is a pixel diffusion decoder that performs latent-to-pixel conversion and 4-8x upsampling in one generative step, enabling early stopping of latent diffusion and achieving sub-second 2048x2048 decoding with claimed better fidelity than cascaded baselines.
-
SR-Ground: Image Quality Grounding for Super-Resolved Content
The paper releases SR-Ground, a crowdsourced dataset for pixel-level segmentation of six artifact types in super-resolved images, and shows its use for training grounded IQA models and artifact-reducing fine-tuning.
-
FGSVQA: Frequency-Guided Short-form Video Quality Assessment
FGSVQA combines CLIP visual encoding with frequency priors and adaptive branch fusion to predict short-form video quality, reporting SRCC 0.736 and PLCC 0.787 on relevant datasets.
-
FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization
FashionChameleon achieves interactive multi-garment video customization in real time by training a teacher model with in-context learning on single-garment pairs, applying streaming distillation, and using training-free KV cache rescheduling.
-
GeoR-Bench: Evaluating Geoscience Visual Reasoning
GeoR-Bench shows top multimodal models reach only 42.7% strict accuracy on geoscience visual reasoning tasks while open-source models reach 10.3%, with outputs often visually plausible yet scientifically inaccurate.
-
ReasonEdit: Towards Interpretable Image Editing Evaluation via Reinforcement Learning
ReasonEdit uses a new CoT dataset and reinforcement learning to produce interpretable, human-aligned evaluations of text-guided image edits.
-
Unpaired Image Deraining Using Reward-Guided Self-Reinforcement Strategy
RGSUD achieves SOTA unsupervised deraining by using IQA-based reward recycling and self-reinforcement to constrain optimization and improve pseudo-paired data quality.
-
You Only Gaussian Once: Controllable 3D Gaussian Splatting for Ultra-Densely Sampled Scenes
YOGO reformulates stochastic 3D Gaussian Splatting into a deterministic budget-aware system and supplies an ultra-dense dataset to enforce physical fidelity over viewpoint interpolation.
-
Redefining Quality Criteria and Distance-Aware Score Modeling for Image Editing Assessment
DS-IEQA jointly learns evaluation criteria via feedback-driven prompt optimization and continuous score modeling via token-decoupled distance regression, ranking 4th in the 2026 NTIRE X-AIGC Quality Assessment Track 2 without extra training data.
-
Rein3D: Reinforced 3D Indoor Scene Generation with Panoramic Video Diffusion Models
Rein3D generates photorealistic, globally consistent 3D indoor scenes by using a restore-and-refine process where radial panoramic videos are restored via diffusion models and then used to update a 3D Gaussian field.
-
On the Global Photometric Alignment for Low-Level Vision
PAL uses closed-form affine color alignment on prediction-target pairs to discount global photometric discrepancies from the supervision signal, improving restoration across low-level vision tasks.
-
LumiVideo: An Intelligent Agentic System for Video Color Grading
LumiVideo deploys an LLM-based agent with RAG and Tree of Thoughts to generate ASC-CDL parameters and 3D LUTs for automatic cinematic color grading from raw log video, approaching expert quality.
-
LucidNFT: LR-Anchored Multi-Reward Preference Optimization for Flow-Based Real-World Super-Resolution
LucidNFT combines a new LR-referenced consistency reward, decoupled normalization, and a real-degradation dataset to improve perceptual quality in flow-matching super-resolution while preserving input fidelity.
-
HiFi-Inpaint: Towards High-Fidelity Reference-Based Inpainting for Generating Detail-Preserving Human-Product Images
HiFi-Inpaint delivers state-of-the-art detail-preserving human-product images by adding Shared Enhancement Attention and Detail-Aware Loss to reference-based inpainting on a new 40K dataset.
-
Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length
Live Avatar enables 45 FPS real-time streaming infinite-length audio-driven avatar generation from a 14B diffusion model via distillation and timestep-forcing pipeline parallelism.
-
Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models
A feed-forward video latent transformer that predicts time-varying 3D Gaussian primitives from one image to produce controllable 4D scenes with appearance, geometry, and motion.
-
Embody4D: A Generalist 4D World Model for Embodied AI
Embody4D generates high-fidelity, view-consistent novel views from monocular videos for embodied scenarios via 3D-aware data synthesis, adaptive noise injection, and interaction-aware attention.
-
FDIM: A Feature-distance-based Generic Video Quality Metric for Versatile Codecs
FDIM is a new hybrid feature-distance video quality metric trained on over 16k sequences that shows strong generalization and correlation with human judgments across ten unseen SDR/HDR datasets and diverse codecs.
-
Q-DeepSight: Incentivizing Thinking with Images for Image Quality Assessment and Refinement
Q-DeepSight proposes a think-with-image multimodal CoT framework trained via RL with perceptual curriculum rewards and evidence gradient filtering to achieve SOTA IQA performance and enable training-free perceptual refinement in image generation.
-
LongCat-Image Technical Report
LongCat-Image delivers a compact 6B-parameter bilingual image generation model that sets new standards for Chinese character rendering accuracy and photorealism while remaining efficient and fully open-source.
-
JoyVASA: Portrait and Animal Image Animation with Diffusion-Based Audio-Driven Facial Dynamics and Head Motion Generation
JoyVASA decouples static 3D facial representations from identity-independent dynamic motion sequences generated by a diffusion transformer to produce audio-driven animations for humans and animals.
-
HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds
HY-World 2.0 generates and reconstructs high-fidelity navigable 3D Gaussian Splatting worlds from text, images, or videos via upgraded panorama, planning, expansion, and composition modules, with released code claiming open-source SOTA performance.
- Generalizable Video Quality Assessment via Weak-to-Strong Learning