Related papers: Action-Prior Denoising for Smooth Real-Time Chunki…

Transformer-based document cross-encoder rerankers are a central component of modern information retrieval systems. Despite their success, these models suffer from high computational costs due to processing long query-document sequences at…

Recent advances in robotic policy learning have enabled complex manipulation in real-world environments, yet the execution speed of these policies often lags behind hardware capabilities due to the cost of collecting faster demonstrations.…

Despite success in many challenging problems, reinforcement learning (RL) is still confronted with sample inefficiency, which can be mitigated by introducing prior knowledge to agents. However, many transfer techniques in reinforcement…

Current end-to-end deep Reinforcement Learning (RL) approaches require jointly learning perception, decision-making and low-level control from very sparse reward signals and high-dimensional inputs, with little capability of incorporating…

Recurrent Neural Networks (RNNs) are powerful sequence modeling tools. However, when dealing with high dimensional inputs, the training of RNNs becomes computational expensive due to the large number of model parameters. This hinders RNNs…

The dominant paradigm for video-based action segmentation is composed of two steps: first, for each frame, compute low-level features using Dense Trajectories or a Convolutional Neural Network that encode spatiotemporal information locally,…

In this paper, we analyze the coding delay and the average coding delay of random linear network codes (a.k.a. dense codes) and chunked codes (CC), which are an attractive alternative to dense codes due to their lower complexity, over line…

As it becomes increasingly difficult to monolithically scale a quantum processor, distributed quantum computing (DQC) offers an alternative by distributing qubits across multiple smaller interconnected quantum processor modules. In such an…

Modeling generalized robot control policies poses ongoing challenges for language-guided robot manipulation tasks. Existing methods often struggle to efficiently utilize cross-dataset resources or rely on resource-intensive vision-language…

Although reinforcement learning (RL) has significantly advanced reasoning capabilities in large multimodal language models (MLLMs), its efficacy remains limited for lightweight models essential for edge deployments. To address this issue,…

Temporal repetition counting aims to quantify the repeated action cycles within a video. The majority of existing methods rely on the similarity correlation matrix to characterize the repetitiveness of actions, but their scalability is…

Diffusion-based policies have recently achieved remarkable success in robotics by formulating action prediction as a conditional denoising process. However, the standard practice of sampling from random Gaussian noise often requires…

Pre-training robot policies with a rich set of skills can substantially accelerate the learning of downstream tasks. Prior works have defined pre-training tasks via natural language instructions, but doing so requires tedious human…

Transformers are slow to train on videos due to extremely large numbers of input tokens, even though many video tokens are repeated over time. Existing methods to remove such uninformative tokens either have significant overhead, negating…

LLM-for-time series (TS) methods typically treat time shallowly, injecting positional or prompt-based cues once at the input of a largely frozen decoder, which limits temporal reasoning as this information degrades through the layers. We…

Decision Transformer (DT) formulates offline reinforcement learning as autoregressive sequence modeling, achieving promising results by predicting actions from a sequence of Return-to-Go (RTG), state, and action tokens. However, RTG is a…

Computed tomography (CT) has played a vital role in medical diagnosis, assessment, and therapy planning, etc. In clinical practice, concerns about the increase of X-ray radiation exposure attract more and more attention. To lower the X-ray…

The reasoning pattern of Large language models (LLMs) remains opaque, and Reinforcement learning (RL) typically applies uniform credit across an entire generation, blurring the distinction between pivotal and routine steps. This work…

Despite all the impressive advances of recurrent neural networks, sequential data is still in need of better modelling. Truncated backpropagation through time (TBPTT), the learning algorithm most widely used in practice, suffers from the…

Providing extensive context via prompting is vital for leveraging the capabilities of Large Language Models (LLMs). However, lengthy contexts significantly increase inference latency, as the computational cost of self-attention grows…