Copertina

Not Too Generative, Not Too Discriminative: The Human Alignment Sweet Spot

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ortega, Jorge Chang, Lan, Bastien Le, Serre, Thomas, Boutin, Victor
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Saliency strikes back: How filtering out high frequencies improves white-box explanations
di: Muzellec, Sabine, et al.
Pubblicazione: (2023)

Large Language Models can Share Images, Too!
di: Lee, Young-Jun, et al.
Pubblicazione: (2023)

Debiasing Central Fixation Confounds Reveals a Peripheral "Sweet Spot" for Human-like Scanpaths in Hard-Attention Vision
di: Pan, Pengcheng, et al.
Pubblicazione: (2026)

Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization
di: Fel, Thomas, et al.
Pubblicazione: (2023)

Looks Too Good To Be True: An Information-Theoretic Analysis of Hallucinations in Generative Restoration Models
di: Cohen, Regev, et al.
Pubblicazione: (2024)

Understanding Visual Feature Reliance through the Lens of Complexity
di: Fel, Thomas, et al.
Pubblicazione: (2024)

Better artificial intelligence does not mean better models of biology
di: Linsley, Drew, et al.
Pubblicazione: (2025)

Latent Representation Matters: Human-like Sketches in One-shot Drawing Tasks
di: Boutin, Victor, et al.
Pubblicazione: (2024)

OpenSDI: Spotting Diffusion-Generated Images in the Open World
di: Wang, Yabin, et al.
Pubblicazione: (2025)

SUGAR: A Sweeter Spot for Generative Unlearning of Many Identities
di: Nguyen, Dung Thuy, et al.
Pubblicazione: (2025)

Discriminative Flow Matching Via Local Generative Predictors
di: Jha, Om Govind, et al.
Pubblicazione: (2026)

Choosing the right basis for interpretability: Psychophysical comparison between neuron-based and dictionary-based representations
di: Colin, Julien, et al.
Pubblicazione: (2024)

Implicit Preference Alignment for Human Image Animation
di: Wang, Yuanzhi, et al.
Pubblicazione: (2026)

SweetTok: Semantic-Aware Spatial-Temporal Tokenizer for Compact Video Discretization
di: Tan, Zhentao, et al.
Pubblicazione: (2024)

Beyond the Doors of Perception: Vision Transformers Represent Relations Between Objects
di: Lepori, Michael A., et al.
Pubblicazione: (2024)

Progressive Prompt Detailing for Improved Alignment in Text-to-Image Generative Models
di: Saichandran, Ketan Suhaas, et al.
Pubblicazione: (2025)

RareSpot: Spotting Small and Rare Wildlife in Aerial Imagery with Multi-Scale Consistency and Context-Aware Augmentation
di: Zhang, Bowen, et al.
Pubblicazione: (2025)

Explaining Human Comparisons using Alignment-Importance Heatmaps
di: Truong, Nhut, et al.
Pubblicazione: (2024)

Too Vivid to Be Real? Benchmarking and Calibrating Generative Color Fidelity
di: Fang, Zhengyao, et al.
Pubblicazione: (2026)

Parrot Captions Teach CLIP to Spot Text
di: Lin, Yiqi, et al.
Pubblicazione: (2023)

On Diversity in Discriminative Neural Networks
di: Oubaha, Brahim, et al.
Pubblicazione: (2024)

MiraGe: Multimodal Discriminative Representation Learning for Generalizable AI-Generated Image Detection
di: Shi, Kuo, et al.
Pubblicazione: (2025)

CODE: Confident Ordinary Differential Editing
di: van Delft, Bastien, et al.
Pubblicazione: (2024)

SpotEdit: Selective Region Editing in Diffusion Transformers
di: Qin, Zhibin, et al.
Pubblicazione: (2025)

Text-Enhanced Panoptic Symbol Spotting in CAD Drawings
di: Liu, Xianlin, et al.
Pubblicazione: (2025)

InstructOCR: Instruction Boosting Scene Text Spotting
di: Duan, Chen, et al.
Pubblicazione: (2024)

Sign Spotting Disambiguation using Large Language Models
di: Low, JianHe, et al.
Pubblicazione: (2025)

GloTSFormer: Global Video Text Spotting Transformer
di: Wang, Han, et al.
Pubblicazione: (2024)

Robusto-1 Dataset: Comparing Humans and VLMs on real out-of-distribution Autonomous Driving VQA from Peru
di: Cusipuma, Dunant, et al.
Pubblicazione: (2025)

EMMA: Empowering Multi-modal Mamba with Structural and Hierarchical Alignment
di: Xing, Yifei, et al.
Pubblicazione: (2024)

Enhancing Medical Large Vision-Language Models via Alignment Distillation
di: Chang, Aofei, et al.
Pubblicazione: (2025)

AlignMamba: Enhancing Multimodal Mamba with Local and Global Cross-modal Alignment
di: Li, Yan, et al.
Pubblicazione: (2024)

UniPose: A Unified Multimodal Framework for Human Pose Comprehension, Generation and Editing
di: Li, Yiheng, et al.
Pubblicazione: (2024)

AI's Blind Spots: Geographic Knowledge and Diversity Deficit in Generated Urban Scenario
di: Beneduce, Ciro, et al.
Pubblicazione: (2025)

Cognitive Alignment At No Cost: Inducing Human Attention Biases For Interpretable Vision Transformers
di: Knights, Ethan
Pubblicazione: (2026)

Beyond Human-prompting: Adaptive Prompt Tuning with Semantic Alignment for Anomaly Detection
di: Chen, Pi-Wei, et al.
Pubblicazione: (2025)

VladVA: Discriminative Fine-tuning of LVLMs
di: Ouali, Yassine, et al.
Pubblicazione: (2024)

Efficient Training for Human Video Generation with Entropy-Guided Prioritized Progressive Learning
di: Li, Changlin, et al.
Pubblicazione: (2025)

Distilling Generative-Discriminative Representations for Very Low-Resolution Face Recognition
di: Zhang, Junzheng, et al.
Pubblicazione: (2024)

Online Iterative Self-Alignment for Radiology Report Generation
di: Xiao, Ting, et al.
Pubblicazione: (2025)