Related papers: Learning to Anticipate Future with Dynamic Context…

In an era where wearable technology is reshaping applications, Scene Text Detection and Recognition (STDR) becomes a straightforward choice through the lens of egocentric vision. Leveraging Meta's Project Aria smart glasses, this paper…

Continual relation extraction is an important task that focuses on extracting new facts incrementally from unstructured text. Given the sequential arrival order of the relations, this task is prone to two serious challenges, namely…

Imagining potential outcomes of actions before execution helps agents make more informed decisions, a prospective thinking ability fundamental to human cognition. However, mainstream model-free Reinforcement Learning (RL) methods lack the…

How can a robot safely navigate around people with complex motion patterns? Deep Reinforcement Learning (DRL) in simulation holds some promise, but much prior work relies on simulators that fail to capture the nuances of real human motion.…

Pre-trained deep neural networks (DNNs) are being widely deployed by industry for making business decisions and to serve users; however, a major problem is model decay, where the DNN's predictions become more erroneous over time, resulting…

Lane change in dense traffic typically requires the recognition of an appropriate opportunity for maneuvers, which remains a challenging problem in self-driving. In this work, we propose a chance-aware lane-change strategy with high-level…

We present a novel approach for long-term human trajectory prediction in indoor human-centric environments, which is essential for long-horizon robot planning in these environments. State-of-the-art human trajectory prediction methods are…

In-context learning (ICL) enables generalization to new tasks with minimal labeled data. However, mainstream ICL approaches rely on a gridding strategy, which lacks the flexibility required for vision applications. We introduce Temporal, a…

Disentangled Representation Learning (DRL) aims to learn a model capable of identifying and disentangling the underlying factors hidden in the observable data in representation form. The process of separating underlying factors of variation…

Traditional end-to-end contextual robust optimization models are trained for specific contextual data, requiring complete retraining whenever new contextual information arrives. This limitation hampers their use in online decision-making…

The latent world model provides a promising way to learn policies in a compact latent space for tasks with high-dimensional observations, however, its generalization across diverse environments with unseen dynamics remains challenging.…

Modern scene text recognition systems often depend on large end-to-end architectures that require extensive training and are prohibitively expensive for real-time scenarios. In such cases, the deployment of heavy models becomes impractical…

Recent dialogue systems rely on turn-based spoken interactions, requiring accurate Automatic Speech Recognition (ASR). Errors in ASR can significantly impact downstream dialogue tasks. To address this, using dialogue context from user and…

Anticipating future actions is a key component of intelligence, specifically when it applies to real-time systems, such as robots or autonomous cars. While recent works have addressed prediction of raw RGB pixel values, we focus on…

Deep reinforcement learning (RL) has shown great empirical successes, but suffers from brittleness and sample inefficiency. A potential remedy is to use a previously-trained policy as a source of supervision. In this work, we refer to these…

Information retrieval (IR) in dynamic data streams is a crucial task, as shifts in data distribution degrade the performance of AI-powered IR systems. To mitigate this issue, memory-based continual learning has been widely adopted for IR.…

LLM unlearning is a technique to remove the impacts of undesirable knowledge from the model without retraining from scratch, which is indispensable towards trustworthy AI. Existing unlearning methods face significant limitations:…

A major challenge in the Deep RL (DRL) community is to train agents able to generalize their control policy over situations never seen in training. Training on diverse tasks has been identified as a key ingredient for good generalization,…

The ability to anticipate possible future human actions is essential for a wide range of applications, including autonomous driving and human-robot interaction. Consequently, numerous methods have been introduced for action anticipation in…

Model Predictive Control (MPC) is a powerful control strategy widely utilized in domains like energy management, building control, and autonomous systems. However, its effectiveness in real-world settings is challenged by the need to…