Image de couverture de livre

Words in Motion: Extracting Interpretable Control Vectors for Motion Transformers

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Tas, Omer Sahin, Wagner, Royden
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning Computation and Language Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

JointMotion: Joint Self-Supervision for Joint Motion Prediction
par: Wagner, Royden, et autres
Publié: (2024)

RedMotion: Motion Prediction via Redundancy Reduction
par: Wagner, Royden, et autres
Publié: (2023)

Divide and Merge: Motion and Semantic Learning in End-to-End Autonomous Driving
par: Shen, Yinzhe, et autres
Publié: (2025)

Transformer with Controlled Attention for Synchronous Motion Captioning
par: Radouane, Karim, et autres
Publié: (2024)

SceneMotion: From Agent-Centric Embeddings to Scene-Wide Forecasts
par: Wagner, Royden, et autres
Publié: (2024)

RetroMotion: Retrocausal Motion Forecasting Models are Instructable
par: Wagner, Royden, et autres
Publié: (2025)

Transformer-VQ: Linear-Time Transformers via Vector Quantization
par: Lingle, Lucas D.
Publié: (2023)

BAD: Bidirectional Auto-regressive Diffusion for Text-to-Motion Generation
par: Hosseyni, S. Rohollah, et autres
Publié: (2024)

MoTe: Learning Motion-Text Diffusion Model for Multiple Generation Tasks
par: Wu, Yiming, et autres
Publié: (2024)

Semantic Token Reweighting for Interpretable and Controllable Text Embeddings in CLIP
par: Kim, Eunji, et autres
Publié: (2024)

MotionStream: Real-Time Video Generation with Interactive Motion Controls
par: Shin, Joonghyuk, et autres
Publié: (2025)

Words That Make Language Models Perceive
par: Wang, Sophie L., et autres
Publié: (2025)

LMFormer: Lane based Motion Prediction Transformer
par: Yadav, Harsh, et autres
Publié: (2025)

Towards Understanding Camera Motions in Any Video
par: Lin, Zhiqiu, et autres
Publié: (2025)

Selective, Interpretable, and Motion Consistent Privacy Attribute Obfuscation for Action Recognition
par: Ilic, Filip, et autres
Publié: (2024)

No Training Wheels: Steering Vectors for Bias Correction at Inference Time
par: Gupta, Aviral, et autres
Publié: (2025)

Interpretable Motion-Attentive Maps: Spatio-Temporally Localizing Concepts in Video Diffusion Transformers
par: Jun, Youngjun, et autres
Publié: (2026)

Interpretability Needs a New Paradigm
par: Madsen, Andreas, et autres
Publié: (2024)

Scaling Large Motion Models with Million-Level Human Motions
par: Wang, Ye, et autres
Publié: (2024)

Spatio-Temporal Branching for Motion Prediction using Motion Increments
par: Wang, Jiexin, et autres
Publié: (2023)

CoMotion: Concurrent Multi-person 3D Motion
par: Newell, Alejandro, et autres
Publié: (2025)

Verbalized Representation Learning for Interpretable Few-Shot Generalization
par: Yang, Cheng-Fu, et autres
Publié: (2024)

IPO: Interpretable Prompt Optimization for Vision-Language Models
par: Du, Yingjun, et autres
Publié: (2024)

Model Interpretability and Rationale Extraction by Input Mask Optimization
par: Brinner, Marc, et autres
Publié: (2025)

Multimodal Arabic Captioning with Interpretable Visual Concept Integration
par: Elchafei, Passant, et autres
Publié: (2025)

Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models
par: Gan, Woody Haosheng, et autres
Publié: (2025)

From Diffusion to Flow: Efficient Motion Generation in MotionGPT3
par: Ban, Jaymin, et autres
Publié: (2026)

EchoAgent: Guideline-Centric Reasoning Agent for Echocardiography Measurement and Interpretation
par: Daghyani, Matin, et autres
Publié: (2025)

General Transform: A Unified Framework for Adaptive Transform to Enhance Representations
par: Budiutama, Gekko, et autres
Publié: (2025)

Video Motion Transfer with Diffusion Transformers
par: Pondaven, Alexander, et autres
Publié: (2024)

Moto: Latent Motion Token as the Bridging Language for Learning Robot Manipulation from Videos
par: Chen, Yi, et autres
Publié: (2024)

StyleMotif: Multi-Modal Motion Stylization using Style-Content Cross Fusion
par: Guo, Ziyu, et autres
Publié: (2025)

Interpreting and Controlling Model Behavior via Constitutions for Atomic Concept Edits
par: Kalibhat, Neha, et autres
Publié: (2026)

A Survey on Transformer Compression
par: Tang, Yehui, et autres
Publié: (2024)

Not All Tokens Matter Equally: Dynamic In-context Vector Distillation with Decisive-Token Supervision for Long-form Medical Report Generation
par: Wu, Ning, et autres
Publié: (2026)

CoMusion: Towards Consistent Stochastic Human Motion Prediction via Motion Diffusion
par: Sun, Jiarui, et autres
Publié: (2023)

Exploring the Limits of Zero Shot Vision Language Models for Hate Meme Detection: The Vulnerabilities and their Interpretations
par: Rizwan, Naquee, et autres
Publié: (2024)

CoGen: Learning from Feedback with Coupled Comprehension and Generation
par: Gul, Mustafa Omer, et autres
Publié: (2024)

MatFormer: Nested Transformer for Elastic Inference
par: Devvrit, et autres
Publié: (2023)

Investigating VLM Hallucination from a Cognitive Psychology Perspective: A First Step Toward Interpretation with Intriguing Observations
par: Liu, Xiangrui, et autres
Publié: (2025)