output
20112026
most citedEnd-to-End Neural Ad-hoc Ranking with Kernel Pooling

575 citations

Showing 2024Show all

10 papers · 1 filter

q-bio.NC2024★ 2 cited

Identifying the impact of local connectivity patterns on dynamics in excitatory-inhibitory networks

Yuxiu Shao, David Dahmen, Stefano Recanatesi +2

Networks of excitatory and inhibitory (EI) neurons form a canonical circuit in the brain. Seminal theoretical results on dynamics of such networks are based on the assumption that…

cs.CL2024★ 2 cited

Scalable Data Ablation Approximations for Language Models through Modular Training and Merging

Clara Na, Ian Magnusson, Ananya Harsh Jha +4

Training data compositions for Large Language Models (LLMs) can significantly affect their downstream performance. However, a thorough data ablation study exploring large sets of c…

physics.bio-ph2024★ 2 cited

Hierarchy of chaotic dynamics in random modular networks

Łukasz Kuśmierz, Ulises Pereira-Obilinovic, Zhixin Lu +2

We introduce a model of randomly connected neural populations and study its dynamics by means of the dynamical mean-field theory and simulations. Our analysis uncovers a rich phase…

cs.HC2024★ 14 cited

IdeaSynth: Iterative Research Idea Development Through Evolving and Composing Idea Facets with Literature-Grounded Feedback

Kevin Pu, K. J. Kevin Feng, Tovi Grossman +6

Research ideation involves broad exploring and deep refining ideas. Both require deep engagement with literature. Existing tools focus primarily on idea broad generation, yet offer…

cs.HC2024

CPS-TaskForge: Generating Collaborative Problem Solving Environments for Diverse Communication Tasks

Nikita Haduong, Irene Wang, Bo-Ru Lu +2

Teams can outperform individuals; could adding AI teammates further bolster performance of teams solving problems collaboratively? Collaborative problem solving (CPS) research comm…

cs.CL2024★ 25 cited

On the Evaluation of Machine-Generated Reports

James Mayfield, Eugene Yang, Dawn Lawrie +10

Large Language Models (LLMs) have enabled new ways to satisfy information needs. Although great strides have been made in applying them to settings like document ranking and short-…