Haotian Fu

PRF: Parallel Resonate and Fire Neuron for long sequence learning in Spiking Neural Networks

Yulong Huang, Zunchang Liu, Xiaopeng Lin, Hongwei Ren et autres

Effective and efficient intracortical brain signal decoding with spiking neural networks

Haotian Fu, Peng Zhang, Yang Song, Herui Zhang et autres

cn (code pays fourni par la source)

Learning Stateful Predictive Knowledge From Experience

Yan Song, Xidong Feng, Bo Liu, Xinyu Cui et autres

As large language model (LLM) agents increasingly learn from experience, they primarily rely on trajectory-level reflection to extract insights. Viewed through the lens of predictive knowledge, we argue that this approach operates on episodic hindsight rather than predictive foresight, yielding brittle, path-dependent …

Learning Stateful Predictive Knowledge From Experience

Yan Song, Xidong Feng, Bo Liu, Xinyu Cui et autres

As large language model (LLM) agents increasingly learn from experience, they primarily rely on trajectory-level reflection to extract insights. Viewed through the lens of predictive knowledge, we argue that this approach operates on episodic hindsight rather than predictive foresight, yielding brittle, path-dependent …

cn, gb, sg, us (code pays fourni par la source)

RVPF-YOLO: A robust visual person-following framework for mobile robots based on enhanced YOLO model

Dongzhao Song, Mingsong Chen, Chizhou Zhang, Haotian Fu et autres

cn (code pays fourni par la source)

SkillWrapper: Generative Predicate Invention for Task-level Robot Planning

Ziyi Yang, Benned Hedegaard, Ahmed Jaafar, Yichen Wei et autres

Generalizing from individual skill executions to long-horizon tasks is a core challenge in building autonomous robots. A promising direction is learning high-level, symbolic representations of low-level robot skills, enabling abstract reasoning independent of the low-level state space. Recent advances in foundation models …

Spiking Neural Network for Intra-cortical Brain Signal Decoding

Yang Song, Haotian Fu, Herui Zhang, Peng Zhang et autres

Decoding brain signals accurately and efficiently is crucial for intra-cortical brain-computer interfaces. Traditional decoding approaches based on neural activity vector features suffer from low accuracy, whereas deep learning based approaches have high computational cost. To improve both the decoding accuracy and efficiency, …

Knowledge Retention for Continual Model-Based Reinforcement Learning

Yixiang Sun, Haotian Fu, Michael L. Littman, George Konidaris

We propose DRAGO, a novel approach for continual model-based reinforcement learning aimed at improving the incremental development of world models across a sequence of tasks that differ in their reward functions but not the state space or dynamics. DRAGO comprises two key …

Effective and Efficient Intracortical Brain Signal Decoding with Spiking Neural Networks

Haotian Fu, Peng Zhang, Yang Song, Herui Zhang et autres

cn (code pays fourni par la source)

Learning Parameterized Skills from Demonstrations

Vedant Gupta, Haotian Fu, Calvin Luo, Yiding Jiang et autres

us (code pays fourni par la source)

Scalable Event Cloud Network for Event-based Classification

Hongwei Ren, Fei Ma, Xiaopeng Lin, Yuetong Fang et autres

Event cameras are biologically inspired sensors garnering significant attention from both industry and academia. Mainstream methods favor frame and voxel representations, which reach a satisfactory performance while introducing time-consuming transformations, bulky models, and sacrificing fine-grained temporal information. Alternatively, Point Cloud representation demonstrates …

Natural Language Reinforcement Learning

Xidong Feng, Bo Liu, Haotian Fu, Ziyu Wan et autres

Artificial intelligence progresses towards the "Era of Experience," where agents are expected to learn from continuous, grounded interaction. We argue that traditional Reinforcement Learning (RL), which typically represents value as a scalar, can restrict agent's deep understanding of environments and hinders the …