Active Speaker Detection (ASD) aims to identify who is currently speaking in each frame of a video. Most state-of-the-art approaches rely on late fusion to comb...
In a mathematical model of interacting biological organisms, where external interventions may alter behavior over time, traditional models that assume fixed par...
Early-Exit (EE) is a Large Language Model (LLM) architecture that accelerates inference by allowing easier tokens to be generated using only a subset of the mod...
Autoregressive video diffusion models hold promise for world simulation but are vulnerable to exposure bias arising from the train-test mismatch. While recent w...
Evaluations of image compression performance which include human preferences have generally found that naive distortion functions such as MSE are insufficiently...
We introduce FrontierCS, a benchmark of 156 open-ended problems across diverse areas of computer science, designed and reviewed by experts, including CS PhDs an...
The misuse of AI-driven video generation technologies has raised serious social concerns, highlighting the urgent need for reliable AI-generated video detectors...
Prevailing Vision-Language-Action Models (VLAs) for robotic manipulation are built upon vision-language backbones pretrained on large-scale, but disconnected st...
Semantic communication aims to transmit information most relevant to a task rather than raw data, offering significant gains in communication efficiency for app...
Future AI agents might run autonomously with elevated privileges. If these agents are misaligned, they might abuse these privileges to cause serious damage. The...
Reinforcement learning has become essential for strengthening the reasoning abilities of large language models, yet current exploration mechanisms remain fundam...
This paper presents a unified framework, for the detection, classification, and preliminary localization of anomalies in water distribution networks using multi...
Partial Least Squares (PLS) is a widely used method for data integration, designed to extract latent components shared across paired high-dimensional datasets. ...
With the push towards Exascale computing and data-driven methods, problem sizes have increased dramatically, increasing the computational requirements of the un...
This paper proposes a training data augmentation pipeline that combines synthetic image data with neural style transfer in order to address the vulnerability of...
Large language model (LLM) activations are notoriously difficult to understand, with most existing techniques using complex, specialized methods for interpretin...
Large language models (LLMs) exhibit remarkable capabilities, yet their reasoning remains opaque, raising safety and trust concerns. Attribution methods, which ...
Human beings solve complex problems through critical thinking, where reasoning and evaluation are intertwined to converge toward correct solutions. However, mos...
Raft is a leading consensus algorithm for replicating writes in distributed databases. However, distributed databases also require consistent reads. To guarante...
Continual learning remains a fundamental challenge in machine learning, requiring models to learn from a stream of tasks without forgetting previously acquired ...
State space models (SSMs) are a promising alternative to transformers for language modeling because they use fixed memory during inference. However, this fixed ...
The computational and memory overheads associated with expanding the context window of LLMs severely limit their scalability. A noteworthy solution is vision-te...
Large language models are increasingly adapted to downstream tasks through fine-tuning. Full supervised fine-tuning (SFT) and parameter-efficient fine-tuning (P...
LLMs (Large Language Models) are increasingly used in text processing pipelines to intelligently respond to a variety of inputs and generation tasks. This raise...
