· ai
[Paper] Data-Centric Visual Development for Self-Driving Labs
Self-driving laboratories offer a promising path toward reducing the labor-intensive, time-consuming, and often irreproducible workflows in the biological scien...
-
- · ai
[Paper] Visual Sync: Multi-Camera Synchronization via Cross-View Object Motion
Today, people can easily record memorable moments, ranging from concerts, sports events, lectures, family gatherings, and birthday parties with multiple consume...
- · ai
[Paper] Objects in Generated Videos Are Slower Than They Appear: Models Suffer Sub-Earth Gravity and Don't Know Galileo's Principle...for now
Video generators are increasingly evaluated as potential world models, which requires them to encode and understand physical laws. We investigate their represen...
- · ai
[Paper] Generative Video Motion Editing with 3D Point Tracks
Camera and object motions are central to a video's narrative. However, precisely editing these captured motions remains a significant challenge, especially unde...
- · ai
[Paper] TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models
Unified multimodal models (UMMs) aim to jointly perform multimodal understanding and generation within a single framework. We present TUNA, a native UMM that bu...
- · ai
[Paper] Improved Mean Flows: On the Challenges of Fastforward Generative Models
MeanFlow (MF) has recently been established as a framework for one-step generative modeling. However, its ``fastforward'' nature introduces key challenges in bo...
- · ai
[Paper] AirSim360: A Panoramic Simulation Platform within Drone View
The field of 360-degree omnidirectional understanding has been receiving increasing attention for advancing spatial intelligence. However, the lack of large-sca...
- · ai
[Paper] The Art of Scaling Test-Time Compute for Large Language Models
Test-time scaling (TTS) -- the dynamic allocation of compute during inference -- is a promising direction for improving reasoning in large language models (LLMs...
- · ai
[Paper] Learning Visual Affordance from Audio
We introduce Audio-Visual Affordance Grounding (AV-AG), a new task that segments object interaction regions from action sounds. Unlike existing approaches that ...
- · ai
[Paper] AlignSAE: Concept-Aligned Sparse Autoencoders
Large Language Models (LLMs) encode factual knowledge within hidden parametric spaces that are difficult to inspect or control. While Sparse Autoencoders (SAEs)...
- · ai
[Paper] Learning Sim-to-Real Humanoid Locomotion in 15 Minutes
Massively parallel simulation has reduced reinforcement learning (RL) training time for robots from days to minutes. However, achieving fast and reliable sim-to...
- · ai
[Paper] RoaD: Rollouts as Demonstrations for Closed-Loop Supervised Fine-Tuning of Autonomous Driving Policies
Autonomous driving policies are typically trained via open-loop behavior cloning of human demonstrations. However, such policies suffer from covariate shift whe...