1 citations · 3 across the 11 of their papers we have counts for
14 papers
Beyond Fixed Visual History: Learning Motion-Adaptive Temporal Receptive Fields for Complex-Terrain Quadruped Locomotion
Hao Zhang, Yuping Yan, Yitian Hong +5
Versatile quadruped locomotion depends on a tight coupling between what the robot perceives and what its body can execute. Yet existing visual controllers typically organize depth…
In-Context Learning for Robots: Methods and Applications
Haojian Huang, Zexi Li, Junhao Guo +36
General-purpose robots must infer what a new task requires and translate that understanding into appropriate physical action. In-context learning (ICL) for robots supports this pro…
Rethinking Attention Locality in Spiking Transformers
Zeqi Zheng, Zizheng Zhu, Yuping Yan +3
Spiking Transformers provide a promising paradigm for efficient visual processing with spike-driven computation, yet their Softmax-free Spiking Self-Attention (SSA) struggles to es…
Self-motion as a structural prior for coherent and robust formation of cognitive maps
Yingchao Yu, Pengfei Sun, Yaochu Jin +7
Most computational accounts of cognitive maps assume that stability is achieved primarily through sensory anchoring, with self-motion contributing to incremental positional updates…
Mitigating Visual Hallucinations via Semantic Curriculum Preference Optimization in MLLMs
Yuanshuai Li, Yuping Yan, Junfeng Tang +3
Multimodal Large Language Models (MLLMs) have significantly improved the performance of various tasks, but continue to suffer from visual hallucinations, a critical issue where gen…
STF: Shallow-Level Temporal Feedback to Enhance Spiking Transformers
Zeqi Zheng, Zizheng Zhu, Yingchao Yu +5
Transformer-based Spiking Neural Networks (SNNs) suffer from a great performance gap compared to floating-point \mbox{Artificial} Neural Networks (ANNs) due to the binary nature of…
Sparse Autoencoders Bridge The Deep Learning Model and The Brain
Ziming Mao, Jia Xu, Zeqi Zheng +4
We present SAE-BrainMap, a novel framework that directly aligns deep learning visual model representations with voxel-level fMRI responses using sparse autoencoders (SAEs). First,…
TDFormer: A Top-Down Attention-Controlled Spiking Transformer
Zizheng Zhu, Yingchao Yu, Zeqi Zheng +2
Traditional spiking neural networks (SNNs) can be viewed as a combination of multiple subnetworks with each running for one time step, where the parameters are shared, and the memb…
Interpretable Zero-shot Learning with Infinite Class Concepts
Zihan Ye, Shreyank N Gowda, Shiming Chen +3
Zero-shot learning (ZSL) aims to recognize unseen classes by aligning images with intermediate class semantics, like human-annotated concepts or class definitions. An emerging alte…
SpiLiFormer: Enhancing Spiking Transformers with Lateral Inhibition
Zeqi Zheng, Yanchen Huang, Yingchao Yu +4
Spiking Neural Networks (SNNs) based on Transformers have garnered significant attention due to their superior performance and high energy efficiency. However, the spiking attentio…
Think Small, Plan Smart: Minimalist Symbolic Abstraction and Heuristic Subspace Search for LLM-Guided Task Planning
Junfeng Tang, Yuping Yan, Zihan Ye +4
Reliable task planning is pivotal for achieving long-horizon autonomy in real-world robotic systems. Large language models (LLMs) offer a promising interface for translating comple…
IP-RSNN: Bi-level Intrinsic Plasticity Enables Learning-to-learn in Recurrent Spiking Neural Networks
Yingchao Yu, Yaochu Jin, Kuangrong Hao +5
Learning-to-learn (L2L), defined as progressively faster learning across similar tasks, is fundamental to both neuroscience and artificial intelligence. However, its neural basis r…
Improved Feature Generating Framework for Transductive Zero-shot Learning
Zihan Ye, Xinyuan Ru, Shiming Chen +3
Feature Generative Adversarial Networks have emerged as powerful generative models in producing high-quality representations of unseen classes within the scope of Zero-shot Learnin…
ZeroDiff: Solidified Visual-Semantic Correlation in Zero-Shot Learning
Zihan Ye, Shreyank N. Gowda, Xiaowei Huang +4
Zero-shot Learning (ZSL) aims to enable classifiers to identify unseen classes. This is typically achieved by generating visual features for unseen classes based on learned visual-…