Imagen de Portada

Human detectors are surprisingly powerful reward models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ashutosh, Kumar, Wang, XuDong, Yin, Xi, Grauman, Kristen, Polyak, Adam, Misra, Ishan, Girdhar, Rohit
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

SoundingActions: Learning How Actions Sound from Narrated Egocentric Videos
por: Chen, Changan, et al.
Publicado: (2024)

Learning Skill-Attributes for Transferable Assessment in Video
por: Ashutosh, Kumar, et al.
Publicado: (2025)

LLMs can see and hear without any training
por: Ashutosh, Kumar, et al.
Publicado: (2025)

Generating Illustrated Instructions
por: Menon, Sachit, et al.
Publicado: (2023)

FIction: 4D Future Interaction Prediction from Video
por: Ashutosh, Kumar, et al.
Publicado: (2024)

Learning Object State Changes in Videos: An Open-World Perspective
por: Xue, Zihui, et al.
Publicado: (2023)

SkillSight: Efficient First-Person Skill Assessment with Gaze
por: Wu, Chi Hsuan, et al.
Publicado: (2025)

Stitch-a-Demo: Video Demonstrations from Multistep Descriptions
por: Wu, Chi Hsuan, et al.
Publicado: (2025)

SportSkills: Physical Skill Learning from Sports Instructional Videos
por: Ashutosh, Kumar, et al.
Publicado: (2026)

Detours for Navigating Instructional Videos
por: Ashutosh, Kumar, et al.
Publicado: (2024)

Diffusion Autoencoders are Scalable Image Tokenizers
por: Chen, Yinbo, et al.
Publicado: (2025)

InstanceDiffusion: Instance-level Control for Image Generation
por: Wang, Xudong, et al.
Publicado: (2024)

Toward Diffusible High-Dimensional Latent Spaces: A Frequency Perspective
por: Lai, Bolin, et al.
Publicado: (2025)

ExpertAF: Expert Actionable Feedback from Video
por: Ashutosh, Kumar, et al.
Publicado: (2024)

HieraMamba: Video Temporal Grounding via Hierarchical Anchor-Mamba Pooling
por: An, Joungbin, et al.
Publicado: (2025)

Human Action Anticipation: A Survey
por: Lai, Bolin, et al.
Publicado: (2024)

ExpertEdit: Learning Skill-Aware Motion Editing from Expert Videos
por: Somayazulu, Arjun, et al.
Publicado: (2026)

UniversalVTG: A Universal and Lightweight Foundation Model for Video Temporal Grounding
por: An, Joungbin, et al.
Publicado: (2026)

Vid2Coach: Transforming How-To Videos into Task Assistants
por: Huh, Mina, et al.
Publicado: (2025)

Seeing the Arrow of Time in Large Multimodal Models
por: Xue, Zihui, et al.
Publicado: (2025)

Audio-Visual Camera Pose Estimation with Passive Scene Sounds and In-the-Wild Video
por: Adebi, Daniel, et al.
Publicado: (2025)

Don't Let the Video Speak: Audio-Contrastive Preference Optimization for Audio-Visual Language Models
por: Baid, Ami, et al.
Publicado: (2026)

SelfEval: Leveraging the discriminative nature of generative models for evaluation
por: Rambhatla, Sai Saketh, et al.
Publicado: (2023)

MotiF: Making Text Count in Image Animation with Motion Focal Loss
por: Wang, Shijie, et al.
Publicado: (2024)

Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning
por: Girdhar, Rohit, et al.
Publicado: (2023)

EgoExo-WM: Unlocking Exo Video for Ego World Models
por: Tran, Danny, et al.
Publicado: (2026)

Progress-Aware Video Frame Captioning
por: Xue, Zihui, et al.
Publicado: (2024)

Segment Anything without Supervision
por: Wang, XuDong, et al.
Publicado: (2024)

HOI-Swap: Swapping Objects in Videos with Hand-Object Interaction Awareness
por: Xue, Zihui, et al.
Publicado: (2024)

Put Myself in Your Shoes: Lifting the Egocentric Perspective from Exocentric Videos
por: Luo, Mi, et al.
Publicado: (2024)

Few-View Object Reconstruction with Unknown Categories and Camera Poses
por: Jiang, Hanwen, et al.
Publicado: (2022)

Perceptual Piercing: Human Visual Cue-based Object Detection in Low Visibility Conditions
por: Kumar, Ashutosh
Publicado: (2024)

UnSAMv2: Self-Supervised Learning Enables Segment Anything at Any Granularity
por: Yu, Junwei, et al.
Publicado: (2025)

Generating Multi-Image Synthetic Data for Text-to-Image Customization
por: Kumari, Nupur, et al.
Publicado: (2025)

MistExit: Learning to Exit for Early Mistake Detection in Procedural Videos
por: Majumder, Sagnik, et al.
Publicado: (2026)

Switch-a-View: View Selection Learned from Unlabeled In-the-wild Videos
por: Majumder, Sagnik, et al.
Publicado: (2024)

Personal Visual Context Learning in Large Multimodal Models
por: Xue, Zihui, et al.
Publicado: (2026)

ViewBridge: Curriculum Knowledge Distillation for Activity View-Invariance Under Extreme Viewpoint Changes
por: Somayazulu, Arjun, et al.
Publicado: (2025)

Seeing without Pixels: Perception from Camera Trajectories
por: Xue, Zihui, et al.
Publicado: (2025)

SPOC: Spatially-Progressing Object State Change Segmentation in Video
por: Mandikal, Priyanka, et al.
Publicado: (2025)