acm-header
Sign In

Communications of the ACM

Latest Research



Technical Perspective: Evaluating Sampled Metrics Is Challenging
From Communications of the ACM

Technical Perspective: Evaluating Sampled Metrics Is Challenging

"On Sampled Metrics for Item Recommendation," by Walid Krichene and Steffen Rendle, exposes a crucial aspect for the evaluation of algorithms and tools: the impact...

On Sampled Metrics for Item Recommendation
From Communications of the ACM

On Sampled Metrics for Item Recommendation

This paper investigates sampled metrics and shows that it is possible to improve the quality of sampled metrics by applying a correction, obtained by minimizing...

Technical Perspective: Leveraging Social Context for Fake News Detection
From Communications of the ACM

Technical Perspective: Leveraging Social Context for Fake News Detection

In "FANG," the authors focus on a strategy of automatically detecting disinformation campaigns on online media with a new graph-based, contextual technique for...

FANG
From Communications of the ACM

FANG: Leveraging Social Context for Fake News Detection Using Graph Representation

We propose Factual News Graph (FANG), a novel graphical social context representation and learning framework for fake news detection.

Technical Perspective: Model Structure Takes Guesswork Out of State Estimation
From Communications of the ACM

Technical Perspective: Model Structure Takes Guesswork Out of State Estimation

"Worst-Case Topological Entropy and Minimal Data Rate for State Estimation of Switched Linear Systems" gives a method for computing the topological entropy of a...

Worst-Case Topological Entropy and Minimal Data Rate for State Estimation of Switched Linear Systems
From Communications of the ACM

Worst-Case Topological Entropy and Minimal Data Rate for State Estimation of Switched Linear Systems

In this paper, we study the problem of estimating the state of a switched linear system when the observation of the system is subject to communication constraints...

Technical Perspective: Neural Radiance Fields Explode on the Scene
From Communications of the ACM

Technical Perspective: Neural Radiance Fields Explode on the Scene

Neural volume rendering exploded onto the scene in 2020, triggered by "NeRF," the impressive paper by Ben Mildenhall et al., on Neural Radiance Fields.

NeRF
From Communications of the ACM

NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis

We present a method that achieves state-of-the-art results for synthesizing novel views of complex scenes by optimizing an underlying continuous volumetric scene...

Technical Perspective: The Importance of WINOGRANDE
From Communications of the ACM

Technical Perspective: The Importance of WINOGRANDE

"WINOGRANDE" explores new methods of dataset development and adversarial filtering, expressly designed to prevent AI systems from making claims of smashing through...

WinoGrande
From Communications of the ACM

WinoGrande: An Adversarial Winograd Schema Challenge at Scale

We introduce WinoGrande, a large-scale dataset of 44k problems, inspired by the original Winograd Schema Challenge, but adjusted to improve both the scale and the...

Technical Perspective: The Quest for Optimal Multi-Item Auctions
From Communications of the ACM

Technical Perspective: The Quest for Optimal Multi-Item Auctions

"Optimal Auctions Through Deep Learning," by Paul Dütting et al., contributes a very interesting and forward-looking new take on the optimal multi-item mechanism...

Optimal Auctions Through Deep Learning
From Communications of the ACM

Optimal Auctions Through Deep Learning

We overview recent research results that show how tools from deep learning are shaping up to become a powerful tool for the automated design of near-optimal auctions...

Technical Perspective: An Elegant Model for Deriving Equations
From Communications of the ACM

Technical Perspective: An Elegant Model for Deriving Equations

"Deriving Equations from Sensor Data Using Dimensional Function Synthesis," by Vasileios Tsoutsouras, et al., addresses the key problem of discovering relationships...

Deriving Equations from Sensor Data Using Dimensional Function Synthesis
From Communications of the ACM

Deriving Equations from Sensor Data Using Dimensional Function Synthesis

We present a new method, which we call dimensional function synthesis, for deriving functions that model the relationship between multiple signals in a physical...

From Communications of the ACM

Technical Perspective: Race Logic Presents a Novel Form of Encoding

"In-Sensor Classification With Boosted Race Trees," by Georgios Tzimpragos, et al., proposes a surprising, novel, and creative approach to post-Moore's Law computing...

In-Sensor Classification With Boosted Race Trees
From Communications of the ACM

In-Sensor Classification With Boosted Race Trees

We demonstrate the potential of a novel form of encoding, race logic, in which information is represented as the delay in the arrival of a signal.

From Communications of the ACM

Technical Perspective: A Chiplet Prototype System for Deep Learning Inference

"Simba," by Yakun Sophia Shao, et al., presents a scalable deep learning accelerator architecture that tackles issues ranging from chip integration technology to...

Simba
From Communications of the ACM

Simba: Scaling Deep-Learning Inference with Chiplet-Based Architecture

This work investigates and quantifies the costs and benefits of using multi-chip-modules with fine-grained chiplets for deep learning inference, an application...

From Communications of the ACM

Technical Perspective: Why Don't Today's Deep Nets Overfit to Their Training Data?

"Understanding Deep Learning (Still) Requires Rethinking Generalization," Chiyuan Zhang, et al., brings a fundamental new theoretical challenge: Why don't today's...

Understanding Deep Learning (Still) Requires Rethinking Generalization
From Communications of the ACM

Understanding Deep Learning (Still) Requires Rethinking Generalization

In this work, we presented a simple experimental framework for interrogating purported measures of generalization.
Sign In for Full Access
» Forgot Password? » Create an ACM Web Account