Related papers: Multi-Intent Detection in User Provided Annotation…
Unsupervised text embedding methods, such as Skip-gram and Paragraph Vector, have been attracting increasing attention due to their simplicity, scalability, and effectiveness. However, comparing to sophisticated deep learning architectures…
Software development projects management is a complex endeavor because it requires dealing with numerous unforeseen events that constantly arise along the way and that go against the expectations that had been established at the beginning.…
Recommender systems take inputs from user history, use an internal ranking algorithm to generate results and possibly optimize this ranking based on feedback. However, often the recommender system is unaware of the actual intent of the user…
Programming-by-example technologies are being deployed in industrial products for real-time synthesis of various kinds of data transformations. These technologies rely on the user to provide few representative examples of the transformation…
Instruction data is crucial for improving the capability of Large Language Models (LLMs) to align with human-level performance. Recent research LIMA demonstrates that alignment is essentially a process where the model adapts instructions'…
Modern AI systems lack a way to express and enforce requirements. Pre-training produces intelligence, and post-training optimizes preferences, but neither guarantees that models reliably satisfy explicit, context-dependent constraints. This…
In the driving scene, the road agents usually conduct frequent interactions and intention understanding of the surroundings. Ego-agent (each road agent itself) predicts what behavior will be engaged by other road users all the time and…
Ordinal user-provided ratings across multiple items are frequently encountered in both scientific and commercial applications. Whilst recommender systems are known to do well on these type of data from a predictive point of view, their…
The emergence of large-scale Mixture of Experts (MoE) models represents a significant advancement in artificial intelligence, offering enhanced model capacity and computational efficiency through conditional computation. However, deploying…
Program synthesis is a class of regression problems where one seeks a solution, in the form of a source-code program, mapping the inputs to their corresponding outputs exactly. Due to its precise and combinatorial nature, program synthesis…
The ability to estimate the perceptual error between images is an important problem in computer vision with many applications. Although it has been studied extensively, however, no method currently exists that can robustly predict visual…
Intent-based networking (IBN) facilitates the representation of consumer expectations in a declarative and domain-independent form. However, mapping intents to service and resource models remains an open challenge. IBN requires handling…
For the 6G mobile networks, in-situ model downloading has emerged as an important use case to enable real-time adaptive artificial intelligence on edge devices. However, the simultaneous downloading of diverse and high-dimensional models to…
The advent of Programmable Data Planes represents an outstanding evolution and complete revolution of the Software- Defined Networking paradigm. The capacity to define the entire behavior of forwarding devices by controlling the packet…
Sparse Mixture of Experts (sMoE) has become a pivotal approach for scaling large vision-language models, offering substantial capacity while maintaining computational efficiency through dynamic, sparse activation of experts. However,…
As software in industry grows in size and complexity, so does the volume of engineering data that companies generate and use. Ideally, this data could be used for many purposes, including informing decisions on engineering priorities.…
We describe MPSE: a Multi-Perspective Simultaneous Embedding method for visualizing high-dimensional data, based on multiple pairwise distances between the data points. Specifically, MPSE computes positions for the points in 3D and provides…
This paper addresses the challenge of jointly modeling user intent diversity and behavioral uncertainty in recommender systems. A unified representation learning framework is proposed. The framework builds a multi-intent representation…
The advancement of socially-aware autonomous vehicles hinges on precise modeling of human behavior. Within this broad paradigm, the specific challenge lies in accurately predicting pedestrian's trajectory and intention. Traditional…
Decision tree ensembles are widely used in critical domains, making robustness and sensitivity analysis essential to their trustworthiness. We study the feature sensitivity problem, which asks whether an ensemble is sensitive to a specified…