Related papers: GPA-RAM: Grasp-Pretraining Augmented Robotic Atten…
Deep reinforcement learning (RL) agents are able to learn contact-rich manipulation tasks by maximizing a reward signal, but require large amounts of experience, especially in environments with many obstacles that complicate exploration. In…
Human-human interaction generation has garnered significant attention in motion synthesis due to its vital role in understanding humans as social beings. However, existing methods typically rely on transformer-based architectures, which…
Despite the superior performance of Large language models on many NLP tasks, they still face significant limitations in memorizing extensive world knowledge. Recent studies have demonstrated that leveraging the Retrieval-Augmented…
Recent efforts on image restoration have focused on developing "all-in-one" models that can handle different degradation types and levels within single model. However, most of mainstream Transformer-based ones confronted with dilemma…
Transformer-based methods have achieved remarkable performance in event-based object detection, owing to the global modeling ability. However, they neglect the influence of non-event and noisy regions and process them uniformly, leading to…
Robots' ability to follow language instructions and execute diverse 3D manipulation tasks is vital in robot learning. Traditional imitation learning-based methods perform well on seen tasks but struggle with novel, unseen ones due to…
Deploying autonomous robots that can learn new skills from demonstrations is an important challenge of modern robotics. Existing solutions often apply end-to-end imitation learning with Vision-Language Action (VLA) models or symbolic…
To enable a mobile manipulator to perform human tasks from a single teaching demonstration is vital to flexible manufacturing. We call our proposed method MMPA (Mobile Manipulator Process Automation with One-shot Teaching). Currently, there…
Achieving precise and generalizable grasping across diverse objects and environments is essential for intelligent and collaborative robotic systems. However, existing approaches often struggle with ambiguous affordance reasoning and limited…
Subgraph matching has garnered increasing attention for its diverse real-world applications. Given the dynamic nature of real-world graphs, addressing evolving scenarios without incurring prohibitive overheads has been a focus of research.…
General matrix multiplication (GEMM) on spatial accelerators is highly sensitive to mapping choices in both execution efficiency and energy consumption. However, the mapping space exhibits combinatorial explosion, which makes it extremely…
The machine learning community has witnessed impressive advancements since large language models (LLMs) first appeared. Yet, their massive memory consumption has become a significant roadblock to large-scale training. For instance, a 7B…
LLM agents acting in structured environments fail in operational rather than conversational ways, and reliability depends on procedural knowledge of the environment. Prior self-improvement methods accumulate natural-language guidance…
Embodied foundation models are gaining increasing attention for their zero-shot generalization, scalability, and adaptability to new tasks through few-shot post-training. However, existing models rely heavily on real-world data, which is…
Reward design remains a critical bottleneck in visual reinforcement learning (RL) for robotic manipulation. In simulated environments, rewards are conventionally designed based on the distance to a target position. However, such precise…
The Transformer model has demonstrated success across a wide range of domains, including in Multi-Agent Reinforcement Learning (MARL) where the Multi-Agent Transformer (MAT) has emerged as a leading algorithm in the field. However, a…
Temporal modeling is crucial for various video learning tasks. Most recent approaches employ either factorized (2D+1D) or joint (3D) spatial-temporal operations to extract temporal contexts from the input frames. While the former is more…
Inspired by the recent success of the Mamba architecture in vision and language domains, we introduce a Unified Attention-Mamba (UAM) backbone. Unlike previous hybrid approaches that integrate Attention and Mamba modules in fixed…
State space models (SSMs) with selection mechanisms and hardware-aware architectures, namely Mamba, have recently demonstrated significant promise in long-sequence modeling. Since the self-attention mechanism in transformers has quadratic…
Task Parametrized Gaussian Mixture Models (TP-GMM) are a sample-efficient method for learning object-centric robot manipulation tasks. However, there are several open challenges to applying TP-GMMs in the wild. In this work, we tackle three…