PyFi generates a 600K pyramid QA dataset for financial images using adversarial MCTS agents, allowing fine-tuned VLMs to decompose complex questions and achieve 19.52% and 8.06% accuracy gains on Qwen2.5-VL models.
Revisit mixture mod- els for multi-agent simulation: Experimental study within a unified framework
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
abstract
Simulation plays a crucial role in assessing autonomous driving systems, where the generation of realistic multi-agent behaviors is a key aspect. In multi-agent simulation, the primary challenges include behavioral multimodality and closed-loop distributional shifts. In this study, we formulate a unified mixture model (UniMM) framework for generating multimodal agent behaviors, which can cover the mainstream methods including regression-based mixture models and discrete NTP models. Furthermore, we introduce a closed-loop sample generation approach tailored for mixture models to mitigate distributional shifts. Within the UniMM framework, we recognize critical configurations from both the model and data perspectives. We conduct a systematic examination of various model configurations, and comprehensively characterize their effects. Moreover, our investigation into the data configuration highlights the pivotal role of closed-loop samples in achieving realistic simulations. To extend the benefits of closed-loop samples across a broader range of mixture models, we further introduce a temporal disentanglement-and-alignment mechanism to address the shortcut learning and off-policy learning issues. Leveraging insights from our exploration, the distinct variants proposed within the UniMM framework, including discrete, anchor-free, and anchor-based models, all achieve state-of-the-art performance on the WOSAC benchmark.
representative citing papers
Closed-loop on-policy training with a reactive goal-oriented scene decoder cuts collision rates by up to 79.5% in dense traffic compared to standard open-loop baselines.
CRAFT reduces collisions by 31.2% and traffic violations by 33.2% in closed-loop traffic simulation by discovering context-induced failures in what-if rollouts and using a contextual preference evaluator to reweight autoregressive decoding toward globally coherent behaviors.
RLFTSim uses RL fine-tuning on a pre-trained model with a balanced reward to align traffic simulator rollouts to real data distributions and distill goal-conditioned controllability, reporting SOTA realism on the Waymo Open Motion Dataset.
citing papers explorer
-
PyFi: Toward Pyramid-like Financial Image Understanding for VLMs via Adversarial Agents
PyFi generates a 600K pyramid QA dataset for financial images using adversarial MCTS agents, allowing fine-tuned VLMs to decompose complex questions and achieve 19.52% and 8.06% accuracy gains on Qwen2.5-VL models.
-
Goal-Oriented Reactive Simulation for Closed-Loop Trajectory Prediction
Closed-loop on-policy training with a reactive goal-oriented scene decoder cuts collision rates by up to 79.5% in dense traffic compared to standard open-loop baselines.
-
Bridging Local Observation and Global Simulation in Closed-Loop Traffic Modeling
CRAFT reduces collisions by 31.2% and traffic violations by 33.2% in closed-loop traffic simulation by discovering context-induced failures in what-if rollouts and using a contextual preference evaluator to reweight autoregressive decoding toward globally coherent behaviors.
-
RLFTSim: Realistic and Controllable Multi-Agent Traffic Simulation via Reinforcement Learning Fine-Tuning
RLFTSim uses RL fine-tuning on a pre-trained model with a balanced reward to align traffic simulator rollouts to real data distributions and distill goal-conditioned controllability, reporting SOTA realism on the Waymo Open Motion Dataset.