Pasquale Minervini

pminervini's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 9 papers 12 days ago

Unveiling and Consulting Core Experts in Retrieval-Augmented MoE-based LLMs

Paper • 2410.15438 • Published Oct 20, 2024

PosterSum: A Multimodal Benchmark for Scientific Poster Summarization

Paper • 2502.17540 • Published Feb 24 • 3

Self-Training Large Language Models for Tool-Use Without Demonstrations

Paper • 2502.05867 • Published Feb 9

Q-Filters: Leveraging QK Geometry for Efficient KV Cache Compression

Paper • 2503.02812 • Published Mar 4 • 10

Parameter-Efficient Fine-Tuning of LLaMA for the Clinical Domain

Paper • 2307.03042 • Published Jul 6, 2023

An Analysis of Decoding Methods for LLM-based Agents for Faithful Multi-Hop Question Answering

Paper • 2503.23415 • Published Mar 30 • 1

MedDistant19: Towards an Accurate Benchmark for Broad-Coverage Biomedical Relation Extraction

Paper • 2204.04779 • Published Apr 10, 2022

PiCSAR: Probabilistic Confidence Selection And Ranking

Paper • 2508.21787 • Published Aug 29 • 4

Learning GUI Grounding with Spatial Reasoning from Visual Feedback

Paper • 2509.21552 • Published Sep 25 • 11

authored a paper 3 months ago

Inverse Scaling in Test-Time Compute

Paper • 2507.14417 • Published Jul 19 • 27

authored 2 papers 5 months ago

MMLongBench: Benchmarking Long-Context Vision-Language Models Effectively and Thoroughly

Paper • 2505.10610 • Published May 15 • 53

Neurosymbolic Diffusion Models

Paper • 2505.13138 • Published May 19 • 35

authored 6 papers 9 months ago

FLARE: Faithful Logic-Aided Reasoning and Exploration

Paper • 2410.11900 • Published Oct 14, 2024 • 4

SynDARin: Synthesising Datasets for Automated Reasoning in Low-Resource Languages

Paper • 2406.14425 • Published Jun 20, 2024 • 2

Analysing the Residual Stream of Language Models Under Knowledge Conflicts

Paper • 2410.16090 • Published Oct 21, 2024 • 7

Mixtures of In-Context Learners

Paper • 2411.02830 • Published Nov 5, 2024 • 2

Aligning Generalisation Between Humans and Machines

Paper • 2411.15626 • Published Nov 23, 2024

Lost in Time: Clock and Calendar Understanding Challenges in Multimodal LLMs

Paper • 2502.05092 • Published Feb 7 • 8

authored a paper 12 months ago

Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering

Paper • 2410.15999 • Published Oct 21, 2024 • 20

authored a paper about 1 year ago

Adapting Neural Link Predictors for Data-Efficient Complex Query Answering

Paper • 2301.12313 • Published Jan 29, 2023 • 1