Tag
Cascade is a hierarchical framework for LLM unlearning that minimizes recoverability through multi-level controls, improving upon existing methods by reducing residual knowledge in intermediate representations while maintaining utility.
DiDrive is a risk-aware hierarchical diffusion framework for safe offline reinforcement learning in autonomous driving that improves performance in complex traffic scenarios through integrated representation learning and distribution correction optimization.
This paper proposes SIGMA, a hierarchical collaboration framework for cooperative multi-agent reinforcement learning that learns robust representations under noisy observations by exploiting cooperation structures through density-based grouping and aggregation methods.
This paper studies LLMs for parent-order execution in algorithmic trading, introducing PACE, a hierarchical framework that outperforms traditional baselines on Shenzhen Stock Exchange data and suggests LLMs can complement human traders.
Proposes HRO, a hierarchical LLM-driven framework for zero-shot object goal navigation that mimics human coarse-to-fine spatial reasoning, achieving superior success rate and generalization on Gibson and HM3D datasets.
Wan-Dancer introduces a hierarchical framework for generating minute-scale coherent dances from music, addressing long-duration choreography generation.
Wan-Dancer is a hierarchical framework for generating long-duration, coherent dance videos from music, with model weights and inference code released on Hugging Face.
3D HAMSTER enhances robot manipulation by using a vision-language model with depth encoding to generate 3D trajectories for point cloud-based control, outperforming 2D-guided baselines.
This paper introduces Tree of Evidence (ToE), a hierarchical and explainable claim verification framework that dynamically retrieves and aggregates multi-source evidence using reinforcement learning. Experiments show 4-24 percentage point improvements over baselines, especially against adversarially poisoned inputs from Generative Engine Optimization.
TrajGenAgent proposes a hierarchical LLM agent framework that decouples macro-level activity planning from micro-level spatiotemporal instantiation for realistic human mobility trajectory generation without fine-tuning. It also introduces an anomaly-detection-based evaluation for behavioral fidelity.
This paper introduces HieraRAG, a hierarchical framework for determining optimal granularity in RAG benchmarks. It generates 5,872 synthetic QA pairs across three dimensions and finds that ideal granularity varies by dimension, offering a portable procedure for practitioners.