SPILLWAY: Separating Target Admission from Sanitization to Defend Tool-Using Agents against Prompt Injection Paper • 2611.07222 • Published 14 days ago • 66
BirdDreams: Joint Perspective and BEV Video Generation for a Plausible, Reactive Driving World Model Paper • 2611.14815 • Published 8 days ago • 57
Factorized MLLM Embeddings for Composed Image Retrieval Paper • 2611.05193 • Published 15 days ago • 48
DreamX: Video Diffusion Model is a Universal Latent Action Learner Paper • 2611.05377 • Published 15 days ago • 58
ThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning Paper • 2610.37666 • Published 22 days ago • 59
FL4N: Feed-forward Latent Model for 4D Novel View Synthesis Paper • 2610.35854 • Published 23 days ago
EgoSpeak: Learning When to Speak for Egocentric Conversational Agents in the Wild Paper • 2502.14892 • Published Feb 17, 2025 • 6
DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding Paper • 2411.19527 • Published Nov 29, 2024 • 11
Speaking Beyond Language: A Large-Scale Multimodal Dataset for Learning Nonverbal Cues from Video-Grounded Dialogues Paper • 2506.00958 • Published Jun 1, 2025 • 20
DreamX: Video Diffusion Model is a Universal Latent Action Learner Paper • 2611.05377 • Published 15 days ago • 58
L3G-World: Real-Time Infinite World Generation with Latent 3D Gaussian Memory Paper • 2610.40614 • Published 20 days ago • 49
ThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning Paper • 2610.37666 • Published 22 days ago • 59
Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction Paper • 2610.12299 • Published Oct 8 • 56
Tetris3D: 3D Scene Generation With Objects That Fit Together Paper • 2610.10539 • Published Oct 7 • 50
GRACE: Generation-aware latent compression for efficient video generation Paper • 2610.10524 • Published Oct 7 • 66