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%).
45
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
RED-Aes learns aesthetic changes from edit-induced image pairs and a new RED-20k dataset via three-stage relative ranking training, claiming SOTA generalization over absolute MOS regression.
The SIU²A framework evaluates scientific images for error detection, repair feasibility, and correction quality, showing current multimodal systems have major limitations in preserving scientific validity.
LL-Bench supplies a human-annotated dataset exposing generative model weaknesses in low-level restoration and introduces LL-Score as an MLLM evaluator that outperforms existing quality metrics and can serve as a training reward.
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.
MR-IQA unifies regression and ranking in BIQA via a quality-margin optimization framework in RL, showing competitive performance on six benchmarks.
InteractiveAvatar is a real-time infinite-streaming avatar video generation system using autoregressive distillation, Long-Short Visual Memory for consistency, and a Reasoning-Reaction Module for intent-aware interactions.
Z-Reward trains a 27B reasoning teacher VLM on score distributions via GDSO and distills it via RISD into a 9B student, reaching 89.6% and 88.6% human preference accuracy with 41.3% optimization gain over SFT baseline.
DIRECT decomposes insertion conditions into appearance, 3D geometry proxy, and background context guidances injected separately to achieve pose-controllable high-fidelity object insertion.
TriPS reformulates diffusion posterior sampling as a time-varying control problem and optimizes triadic schedules (decreasing DC and stochasticity, increasing CFG) via template search and GRPO reinforcement learning, outperforming baselines in fidelity and realism.
4KLSDB supplies 129k+ curated 4K images plus validation/test splits to support training of super-resolution and text-to-image diffusion models.
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 at 23.8 FPS via in-context teacher models, streaming distillation, and training-free KV cache rescheduling while using only single-garment data.
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.
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.
-
Beyond Absolute Scores: Relative Edit-induced Difference for Generalizable Image Aesthetic Assessment
RED-Aes learns aesthetic changes from edit-induced image pairs and a new RED-20k dataset via three-stage relative ranking training, claiming SOTA generalization over absolute MOS regression.
-
Towards Characterizing Scientific Image Utility and Upgradability
The SIU²A framework evaluates scientific images for error detection, repair feasibility, and correction quality, showing current multimodal systems have major limitations in preserving scientific validity.
-
LL-Bench: Rethinking Low-Level Vision Evaluation in the Era of Large-Scale Generative Models
LL-Bench supplies a human-annotated dataset exposing generative model weaknesses in low-level restoration and introduces LL-Score as an MLLM evaluator that outperforms existing quality metrics and can serve as a training reward.
-
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.
-
MR-IQA: A Unified Margin View of Regression and Ranking for Blind Image Quality Assessment
MR-IQA unifies regression and ranking in BIQA via a quality-margin optimization framework in RL, showing competitive performance on six benchmarks.
-
InteractiveAvatar: Real-Time Streaming Video Generation for Consistent and Intent-Aware Avatars
InteractiveAvatar is a real-time infinite-streaming avatar video generation system using autoregressive distillation, Long-Short Visual Memory for consistency, and a Reasoning-Reaction Module for intent-aware interactions.
-
Beyond Scalar Rewards by Internalizing Reasoning into Score Distributions
Z-Reward trains a 27B reasoning teacher VLM on score distributions via GDSO and distills it via RISD into a 9B student, reaching 89.6% and 88.6% human preference accuracy with 41.3% optimization gain over SFT baseline.
-
Direct 3D-Aware Object Insertion via Decomposed Visual Proxies
DIRECT decomposes insertion conditions into appearance, 3D geometry proxy, and background context guidances injected separately to achieve pose-controllable high-fidelity object insertion.
-
Triadic Dynamics Aware Diffusion Posterior Sampling for Inverse Problems: Optimizing Guidance and Stochasticity Schedules
TriPS reformulates diffusion posterior sampling as a time-varying control problem and optimizes triadic schedules (decreasing DC and stochasticity, increasing CFG) via template search and GRPO reinforcement learning, outperforming baselines in fidelity and realism.
-
4KLSDB: A Large-Scale Dataset for 4K Image Restoration and Generation
4KLSDB supplies 129k+ curated 4K images plus validation/test splits to support training of super-resolution and text-to-image diffusion models.
-
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 at 23.8 FPS via in-context teacher models, streaming distillation, and training-free KV cache rescheduling while using only single-garment data.
-
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.
-
Embody4D: A Generalist Data Engine for Embodied 4D World Modeling
Embody4D generates novel-view videos from monocular robot videos via a 3D-aware synthesis pipeline, confidence-aware expert modulation, and interaction-aware attention for embodied 4D world modeling.
-
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.
-
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.
-
Can MLLMs Critique Like Humans? Evaluating Open-Ended Aesthetic Reasoning in Multimodal Large Language Models
MLLMs generate verbose, comprehensive, and repetitive aesthetic critiques unlike selective human ones, and reference-based metrics fail to detect this because they capture model house style instead of image-specific content.
-
Archon: A Unified Multimodal Model for Holistic Digital Human Generation
Archon unifies seven modalities via modality-specific tokenizers and an autoregressive backbone pretrained on 72 tasks, plus a 4x-efficient video reparameterization and stepwise 'Thinking in Modality' procedure, and reports superior or comparable results on digital-human tasks.
-
HDRFace: Rethinking Face Restoration with High-Dimensional Representation
HDRFace injects high-dimensional facial features from low-quality and intermediate images into diffusion models via SDFM fusion, reporting gains on SD V2.1-base and Qwen-Image.
-
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.