相关论文: QueST: Self-Supervised Skill Abstractions for Lear…

Video transformers have recently emerged as a competitive alternative to 3D CNNs for video understanding. However, due to their large number of parameters and reduced inductive biases, these models require supervised pretraining on…

Deep neural network (DNN)-based policy models, such as vision-language-action (VLA) models, excel at automating complex decision-making from multi-modal inputs. However, scaling these models greatly increases computational overhead,…

Auto-regressive Large Language Models (LLMs) demonstrate remarkable performance across different domains such as vision and language processing. However, due to sequential processing through a stack of transformer layers, autoregressive…

Humans are able to seamlessly visually imitate others, by inferring their intentions and using past experience to achieve the same end goal. In other words, we can parse complex semantic knowledge from raw video and efficiently translate…

Inspired by the success of the Transformer architecture in natural language processing and computer vision, we investigate the use of Transformers in Reinforcement Learning (RL), specifically in modeling the environment's dynamics using…

Identifying statistical regularities in solutions to some tasks in multi-task reinforcement learning can accelerate the learning of new tasks. Skill learning offers one way of identifying these regularities by decomposing pre-collected…

Improving the efficiency of inference in Large Language Models (LLMs) is a critical area of research. Post-training Quantization (PTQ) is a popular technique, but it often faces challenges at low-bit levels, particularly in downstream…

Large Language Models (LLMs) have been shown to be capable of performing high-level planning for long-horizon robotics tasks, yet existing methods require access to a pre-defined skill library (e.g. picking, placing, pulling, pushing,…

Long video understanding is a complex task that requires both spatial detail and temporal awareness. While Vision-Language Models (VLMs) obtain frame-level understanding capabilities through multi-frame input, they suffer from information…

Large language models (LLMs) encode a diverse range of linguistic features within their latent representations, which can be harnessed to steer their output toward specific target characteristics. In this paper, we modify the internal…

Learning or identifying dynamics from a sequence of high-dimensional observations is a difficult challenge in many domains, including reinforcement learning and control. The problem has recently been studied from a generative perspective…

Large language models (LLMs) have shown impressive abilities in leveraging pretrained knowledge through prompting, but they often struggle with unseen tasks, particularly in data-scarce scenarios. While cross-task in-context learning offers…

Shared-autonomy imitation learning lets a human correct a robot in real time, mitigating covariate-shift errors. Yet existing approaches ignore two critical factors: (i) the operator's cognitive load and (ii) the risk created by delayed or…

Cross-task generalization is a core challenge in open-world robotic manipulation, and the key lies in extracting transferable manipulation knowledge from seen tasks. Recent in-context learning approaches leverage seen task demonstrations to…

While state-of-the-art contrastive Self-Supervised Learning (SSL) models produce results competitive with their supervised counterparts, they lack the ability to infer latent variables. In contrast, prescribed latent variable (LV) models…

Diffusion models have shown superior performance in real-world video super-resolution (VSR). However, the slow processing speeds and heavy resource consumption of diffusion models hinder their practical application and deployment.…

Large language models (LLMs) face significant challenges in processing long contexts due to the linear growth of the key-value (KV) cache and quadratic complexity of self-attention. Existing approaches address these bottlenecks separately:…

Modern foundation models such as large language models (LLMs) and large multi-modal models (LMMs) require a massive amount of computational and memory resources. We propose a new framework to convert such LLMs/LMMs into a reduced-dimension…

Current work on Visual Question Answering (VQA) explore deterministic approaches conditioned on various types of image and question features. We posit that, in addition to image and question pairs, other modalities are useful for teaching…

Transformer-based architectures have become the de-facto standard models for a wide range of Natural Language Processing tasks. However, their memory footprint and high latency are prohibitive for efficient deployment and inference on…