Related papers: TeNet: Text-to-Network for Compact Policy Synthesi…
Modern approaches to text to speech require the entire input character sequence to be processed before any audio is synthesised. This latency limits the suitability of such models for time-sensitive tasks like simultaneous interpretation.…
Current end-to-end spoken language models (SLMs) have made notable progress, yet they still encounter considerable response latency. This delay primarily arises from the autoregressive generation of speech tokens and the reliance on complex…
In addition to the unprecedented ability in imaginary creation, large text-to-image models are expected to take customized concepts in image generation. Existing works generally learn such concepts in an optimization-based manner, yet…
This work develops an LLM-based optimization framework ensuring strict constraint satisfaction in network optimization. While LLMs possess contextual reasoning capabilities, existing approaches often fail to enforce constraints, causing…
Trajectory prediction in urban mixed-traffic zones (a.k.a. shared spaces) is critical for many intelligent transportation systems, such as intent detection for autonomous driving. However, there are many challenges to predict the…
The development of control policies for multi-robot systems traditionally follows a complex and labor-intensive process, often lacking the flexibility to adapt to dynamic tasks. This has motivated research on methods to automatically create…
The classification of short texts is a common subtask in Information Retrieval (IR). Recent advances in graph machine learning have led to interest in graph-based approaches for low resource scenarios, showing promise in such settings.…
Foundation models are transforming machine learning across many modalities, with in-context learning replacing classical model training. Recent work on tabular data hints at a similar opportunity to build foundation models for…
A robot's ability to understand or ground natural language instructions is fundamentally tied to its knowledge about the surrounding world. We present an approach to grounding natural language utterances in the context of factual…
Language-conditioned policies have recently gained substantial adoption in robotics as they allow users to specify tasks using natural language, making them highly versatile. While much research has focused on improving the action…
Skilled robot task learning is best implemented by predictive action policies due to the inherent latency of sensorimotor processes. However, training such predictive policies is challenging as it involves finding a trajectory of motor…
Recent advancements in Large Language Models (LLMs) have substantially evolved Multi-Agent Systems (MASs) capabilities, enabling systems that not only automate tasks but also leverage near-human reasoning capabilities. To achieve this,…
Video-text retrieval is an important yet challenging task in vision-language understanding, which aims to learn a joint embedding space where related video and text instances are close to each other. Most current works simply measure the…
We introduce DreamGen, a simple yet highly effective 4-stage pipeline for training robot policies that generalize across behaviors and environments through neural trajectories - synthetic robot data generated from video world models.…
Training language models (LMs) and their application agents is increasingly costly due to large datasets and models, making test failures difficult to bear. Simplified language environments serve as primordial training and testing grounds,…
How to incorporate external knowledge into a neural dialogue model is critically important for dialogue systems to behave like real humans. To handle this problem, memory networks are usually a great choice and a promising way. However,…
Hierarchical control for robotics has long been plagued by the need to have a well defined interface layer to communicate between high-level task planners and low-level policies. With the advent of LLMs, language has been emerging as a…
AI policy guidance is predominantly written as prose, which practitioners must first convert into executable rules before frameworks can evaluate or enforce them. This manual step is slow, error-prone, difficult to scale, and often delays…
Decentralized cooperation in partially-observable multi-agent systems requires effective communications among agents. To support this effort, this work focuses on the class of problems where global communications are available but may be…
Learning abstract state representations and knowledge is crucial for long-horizon robot planning. We present InterPreT, an LLM-powered framework for robots to learn symbolic predicates from language feedback of human non-experts during…