OccProphet: Pushing the Efficiency Frontier of Camera-Only 4D Occupancy Forecasting with an Observer-Forecaster-Refiner Framework
No official code found. Best implementation: JLChen-C/OccProphet (60 stars, MIT, last commit 2026-03-18).
No official code found. Best implementation: JLChen-C/OccProphet (60 stars, MIT, last commit 2026-03-18).
On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement Learning
Non-Stationary Predictions May Be More Informative: Exploring Pseudo-Labels with a Two-Phase Pattern of Training Dynamics
A Study of First-Order Methods with a Deterministic Relative-Error Gradient Oracle
SRTube: Video-Language Pre-Training with Action-Centric Video Tube Features and Semantic Role Labeling
CaDA: Cross-Problem Routing Solver with Constraint-Aware Dual-Attention
On the Adversarial Vulnerability of Label-Free Test-Time Adaptation
@article{chen2026occprophet,
title = {OccProphet: Pushing the Efficiency Frontier of Camera-Only 4D Occupancy Forecasting with an Observer-Forecaster-Refiner Framework},
author = {Junliang Chen and Huaiyuan Xu and Yi Wang and Lap-Pui Chau},
year = {2026},
url = {https://api.semanticscholar.org/CorpusID:0fc93da7b97c36eb51c3333d95ef77ffaf945841},
journal = {ICLR 2025 2025}
}Shows whether official code is linked for this paper.
[](https://codeofpaper.com/paper/0fc93da7b97c36eb51c3333d95ef77ffaf945841)