10 papers
Representation Distribution Matching for One-Step Visual Generation
Lan Feng, Wuyang Li, Eloi Zablocki +2
We elucidate the design space of Representation Distribution Matching (RDM), our name for the paradigm that trains a one-step image generator by matching generated and reference fe…
Drift-Resistant Navigation World Model with Anchored Epipolar Guidance
Po-Chien Luan, Zimin Xia, Wuyang Li +2
We propose Drift-Resistant Navigation World Model, a generative model that mitigates both perceptual drift and geometric drift in conventional rollout-based navigation world models…
Social-Mamba: Socially-Aware Trajectory Forecasting with State-Space Models
Po-Chien Luan, Wuyang Li, Yang Gao +1
Human trajectory forecasting is crucial for safe navigation in crowded environments, requiring models that balance accuracy with computational efficiency. Efficiently modeling soci…
EverAnimate: Minute-Scale Human Animation via Latent Flow Restoration
Wuyang Li, Yang Gao, Mariam Hassan +4
We propose EverAnimate, an efficient post-training method for long-horizon animated video generation that preserves visual quality and character identity. Long-form animation remai…
Team-Based Self-Play With Dual Adaptive Weighting for Fine-Tuning LLMs
Wu Li, Yigeng Zhou, Zesheng Shi +3
While recent self-training approaches have reduced reliance on human-labeled data for aligning LLMs, they still face critical limitations: (i) sensitivity to synthetic data quality…
Grounded World Model: Latent Planning with Language Goals
Quanyi Li, Lan Feng, Haonan Zhang +4
World models such as DINO-WM and LeWM specify the goal with an image, which is difficult to obtain in advance for novel tasks. We present the Grounded World Model (GWM), a latent w…
Anchored Video Generation: Decoupling Scene Construction and Temporal Synthesis in Text-to-Video Diffusion Models
Mariam Hassan, Bastien Van Delft, Wuyang Li +1
State-of-the-art Text-to-Video (T2V) diffusion models can generate visually impressive results, yet they still frequently fail to compose complex scenes or follow logical temporal…
Stable Video Infinity: Infinite-Length Video Generation with Error Recycling
Wuyang Li, Wentao Pan, Po-Chien Luan +2
We propose Stable Video Infinity (SVI) that is able to generate infinite-length videos with high temporal consistency, plausible scene transitions, and controllable streaming story…
RAP: 3D Rasterization Augmented End-to-End Planning
Lan Feng, Yang Gao, Eloi Zablocki +5
Imitation learning for end-to-end driving trains policies only on expert demonstrations. Once deployed in a closed loop, such policies lack recovery data: small mistakes cannot be…
VoxDet: Rethinking 3D Semantic Occupancy Prediction as Dense Object Detection
Wuyang Li, Zhu Yu, Alexandre Alahi
3D semantic occupancy prediction aims to reconstruct the 3D geometry and semantics of the surrounding environment. With dense voxel labels, prior works typically formulate it as a…