Search Results for author:
Found 11 papers, 5 papers with code
TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning
Time-series reasoning remains a significant challenge in multimodal large language models (MLLMs) due to the dynamic temporal patterns, ambiguous semantics, and lack of temporal priors.
Bidirectional Distillation: A Mixed-Play Framework for Multi-Agent Generalizable Behaviors
Population-population generalization is a challenging problem in multi-agent reinforcement learning (MARL), particularly when agents encounter unseen co-players.
Group-in-Group Policy Optimization for LLM Agent Training
In this work, we propose Group-in-Group Policy Optimization (GiGPO), a novel RL algorithm that achieves fine-grained credit assignment for LLM agents while preserving the appealing properties of group-based RL: critic-free, low memory, and stable convergence.
Policy Regularization on Globally Accessible States in Cross-Dynamics Reinforcement Learning
Additionally, as the environment dynamics change, certain expert states may become inaccessible, rendering their distributions less valuable for imitation.
Diverse Intra- and Inter-Domain Activity Style Fusion for Cross-Person Generalization in Activity Recognition
We instantiate this concept using a conditional diffusion model and introduce a style-fused sampling strategy to enhance data generation diversity.
Resisting Stochastic Risks in Diffusion Planners with the Trajectory Aggregation Tree
As the structure evolves with the integration of new trajectories, unreliable states are marginalized, and the most impactful nodes are prioritized for decision-making.
Temporal Convolutional Explorer Helps Understand 1D-CNN's Learning Behavior in Time Series Classification from Frequency Domain
While one-dimensional convolutional neural networks (1D-CNNs) have been empirically proven effective in time series classification tasks, we find that there remain undesirable outcomes that could arise in their application, motivating us to further investigate and understand their underlying mechanisms.
FP3O: Enabling Proximal Policy Optimization in Multi-Agent Cooperation with Parameter-Sharing Versatility
Existing multi-agent PPO algorithms lack compatibility with different types of parameter sharing when extending the theoretical guarantee of PPO to cooperative multi-agent reinforcement learning (MARL).
Multi-Level Firing with Spiking DS-ResNet: Enabling Better and Deeper Directly-Trained Spiking Neural Networks
Spiking neural networks (SNNs) are bio-inspired neural networks with asynchronous discrete and sparse characteristics, which have increasingly manifested their superiority in low energy consumption.
GANDSE: Generative Adversarial Network based Design Space Exploration for Neural Network Accelerator Design
To improve the design quality while saving the cost, design automation for neural network accelerators was proposed, where design space exploration algorithms are used to automatically search the optimized accelerator design within a design space.
Toward Taming the Overhead Monster for Data-Flow Integrity
Data-Flow Integrity (DFI) is a well-known approach to effectively detecting a wide range of software attacks.
Hardware Architecture
