Search Results for author:
Found 27 papers, 11 papers with code
From Strangers to Assistants: Fast Desire Alignment for Embodied Agent-User Adaptation
The ego agent must interact with this proxy user to infer and adapt to the user's latent desires.
SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning
Vision-language-action models (VLAs) show potential as generalist robot policies.
Spiking Transformer:Introducing Accurate Addition-Only Spiking Self-Attention for Transformer
Transformers have demonstrated outstanding performance across a wide range of tasks, owing to their self-attention mechanism, but they are highly energy-consuming.
DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Grasping
Dexterous grasping remains a fundamental yet challenging problem in robotics.
Spiking Transformer: Introducing Accurate Addition-Only Spiking Self-Attention for Transformer
Unlike existing methods that rely solely on binary spiking neurons for all components of the self-attention mechanism, our approach integrates binary, ReLU, and ternary spiking neurons.
GarmentLab: A Unified Simulation and Benchmark for Garment Manipulation
Recent successes in reinforcement learning and vision-based methods offer promising avenues for learning garment manipulation.
Neural Attention Field: Emerging Point Relevance in 3D Scenes for One-Shot Dexterous Grasping
One-shot transfer of dexterous grasps to novel scenes with object and context variations has been a challenging problem.
Learning to Manipulate Anywhere: A Visual Generalizable Framework For Reinforcement Learning
Can we endow visuomotor robots with generalization capabilities to operate in diverse open-world scenarios?
Technique Report of CVPR 2024 PBDL Challenges
The intersection of physics-based vision and deep learning presents an exciting frontier for advancing computer vision technologies.
Take A Shortcut Back: Mitigating the Gradient Vanishing for Training Spiking Neural Networks
However, training an SNN directly poses a challenge due to the undefined gradient of the firing spike process.
Ternary Spike: Learning Ternary Spikes for Spiking Neural Networks
To handle the problem, we propose a ternary spike neuron to transmit information.
Spiking PointNet: Spiking Neural Networks for Point Clouds
We discover that the two huge obstacles limiting the application of SNNs in point clouds are: the intrinsic optimization obstacle of SNNs that impedes the training of a big spiking model with large time steps, and the expensive memory and computation cost of PointNet that makes training a big spiking point model unrealistic.
Sequential Dexterity: Chaining Dexterous Policies for Long-Horizon Manipulation
However, the challenges arise due to the high-dimensional action space of dexterous hand and complex compositional dynamics of the long-horizon tasks.
Membrane Potential Batch Normalization for Spiking Neural Networks
All these BNs are suggested to be used after the convolution layer as usually doing in CNNs.
RMP-Loss: Regularizing Membrane Potential Distribution for Spiking Neural Networks
Spiking Neural Networks (SNNs) as one of the biology-inspired models have received much attention recently.
InfLoR-SNN: Reducing Information Loss for Spiking Neural Networks
The Spiking Neural Network (SNN) has attracted more and more attention recently.
NeuroCLIP: Neuromorphic Data Understanding by CLIP and SNN
However, the neuromorphic data consists of asynchronous event spikes, which makes it difficult to construct a big benchmark to train a power general neural network model, thus limiting the neuromorphic data understanding for ``unseen" objects by deep learning.
Joint A-SNN: Joint Training of Artificial and Spiking Neural Networks via Self-Distillation and Weight Factorization
In this paper, we propose a joint training framework of ANN and SNN, in which the ANN can guide the SNN's optimization.
Learning a Universal Human Prior for Dexterous Manipulation from Human Preference
Generating human-like behavior on robots is a great challenge especially in dexterous manipulation tasks with robotic hands.
Deep Dive Into Gradients: Better Optimization for 3D Object Detection With Gradient-Corrected IoU Supervision
In this paper, we propose a Gradient-Corrected IoU (GCIoU) loss to achieve fast and accurate 3D bounding box regression.
PeakConv: Learning Peak Receptive Field for Radar Semantic Segmentation
However, neither the regular convolution operation nor the modified ones are specific to interpret radar signals.
IM-Loss: Information Maximization Loss for Spiking Neural Networks
To deal with this problem, the Information maximization loss (IM-Loss) that aims at maximizing the information flow in the SNN is proposed in the paper.
Ranked #6 on
Event data classification
on CIFAR10-DVS
Real Spike: Learning Real-valued Spikes for Spiking Neural Networks
Motivated by this assumption, a training-inference decoupling method for SNNs named as Real Spike is proposed, which not only enjoys both unshared convolution kernels and binary spikes in inference-time but also maintains both shared convolution kernels and Real-valued Spikes during training.
End-to-End Affordance Learning for Robotic Manipulation
Such contact prediction process then leads to an end-to-end affordance learning framework that can generalize over different types of manipulation tasks.
Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learning
In this study, we propose the Bimanual Dexterous Hands Benchmark (Bi-DexHands), a simulator that involves two dexterous hands with tens of bimanual manipulation tasks and thousands of target objects.
RecDis-SNN: Rectifying Membrane Potential Distribution for Directly Training Spiking Neural Networks
Unfortunately, with the propagation of binary spikes, the distribution of membrane potential will shift, leading to degeneration, saturation, and gradient mismatch problems, which would be disadvantageous to the network optimization and convergence.
