University College London

UniversityCollegeLondon's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Articles

Zhouhc 

submitted a paper to Daily Papers 5 months ago

Memento-Skills: Let Agents Design Agents

Paper • 2603.18743 • Published Mar 19 • 59

GoooDte 

submitted a paper to Daily Papers 6 months ago

InnoEval: On Research Idea Evaluation as a Knowledge-Grounded, Multi-Perspective Reasoning Problem

Paper • 2602.14367 • Published Feb 16 • 17

tetrisd 

authored 18 papers 11 months ago

Drawing Conclusions from Draws: Rethinking Preference Semantics in Arena-Style LLM Evaluation

Paper • 2510.02306 • Published Oct 2, 2025 • 4

Words Worth a Thousand Pictures: Measuring and Understanding Perceptual Variability in Text-to-Image Generation

Paper • 2406.08482 • Published Jun 12, 2024

Geospatial Foundational Embedder: Top-1 Winning Solution on EarthVision Embed2Scale Challenge (CVPR 2025)

Paper • 2509.06993 • Published Sep 3, 2025

"Ask Me Anything": How Comcast Uses LLMs to Assist Agents in Real Time

Paper • 2405.00801 • Published May 1, 2024

Strings from the Library of Babel: Random Sampling as a Strong Baseline for Prompt Optimisation

Paper • 2311.09569 • Published Nov 16, 2023

SpeechNet: Weakly Supervised, End-to-End Speech Recognition at Industrial Scale

Paper • 2211.11740 • Published Nov 21, 2022

Inserting Information Bottlenecks for Attribution in Transformers

Paper • 2012.13838 • Published Dec 27, 2020

Howl: A Deployed, Open-Source Wake Word Detection System

Paper • 2008.09606 • Published Aug 21, 2020

Showing Your Work Doesn't Always Work

Paper • 2004.13705 • Published Apr 28, 2020

DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference

Paper • 2004.12993 • Published Apr 27, 2020

Explicit Pairwise Word Interaction Modeling Improves Pretrained Transformers for English Semantic Similarity Tasks

Paper • 1911.02847 • Published Nov 7, 2019

DocBERT: BERT for Document Classification

Paper • 1904.08398 • Published Apr 17, 2019

Distilling Task-Specific Knowledge from BERT into Simple Neural Networks

Paper • 1903.12136 • Published Mar 28, 2019

Deep Residual Learning for Small-Footprint Keyword Spotting

Paper • 1710.10361 • Published Oct 28, 2017

What Would Elsa Do? Freezing Layers During Transformer Fine-Tuning

Paper • 1911.03090 • Published Nov 8, 2019

Rapidly Bootstrapping a Question Answering Dataset for COVID-19

Paper • 2004.11339 • Published Apr 23, 2020

What Do Llamas Really Think? Revealing Preference Biases in Language Model Representations

Paper • 2311.18812 • Published Nov 30, 2023

Rank-without-GPT: Building GPT-Independent Listwise Rerankers on Open-Source Large Language Models

Paper • 2312.02969 • Published Dec 5, 2023 • 14