CoolFace
20 results

LALM

Snooow1029 /MIA_LALM MIA_LALM Audio datasets for Membership Inference Attacks against Large Audio Language Models (arXiv, code). The audio is distributed as one zstd-compressed tar per dataset family. A few large archives download far faster than ~90k individual WAV files (no per-file overhead, no HTTP 429), and each extracts to the exact layout the attack runners expect. Download With the code repository cloned, download each family into MIA_on_dataset/data/ and extract it there —… See the full description on the dataset page: https://huggingface.co/datasets/Snooow1029/MIA_LALM.audio-classification0 likes258 downloads4mo agoHugging FaceLALM-emotional-damage /cosyvoice-instructaudio1K<n<10K0 likes71 downloads1y agoHugging FaceSalesforce /lalm-judge-validation-full-duplex LALM Judge Validation on Full-Duplex Voice Agents Companion dataset for the paper A Reliability Assessment of LALM Audio Judges for Full-Duplex Voice Agents. This repository contains the anonymised ratings, adversarial-defect recall tables, JSON schemas, and analysis scripts used to produce every headline number, table, and figure in that paper. Summary 209 rated stereo sessions: 152 full-duplex agent-client conversations across 13 accent-and-condition strata… See the full description on the dataset page: https://huggingface.co/datasets/Salesforce/lalm-judge-validation-full-duplex.tabularaudio-classification1K<n<10K2 likes62 downloads2mo agoHugging FaceLALM-emotional-vulnerability /cosyvoice-clone LALM Emotional Vulnerability Dataset Overview This dataset contains synthesized malicious speech instructions across multiple emotions and intensity levels to evaluate the safety responsiveness of Large Audio-Language Models (LALMs). The dataset aims to examine how speaker emotion and intensity influence the safety and robustness of AI responses. Dataset Composition Total samples: 8,320 Emotion categories: Neutral: 520 samples Angry: 1560 samples… See the full description on the dataset page: https://huggingface.co/datasets/LALM-emotional-vulnerability/cosyvoice-clone.audio1K<n<10K0 likes49 downloads10mo agoHugging FaceLALM-emotional-damage /cosyvoice-cloneaudio1K<n<10K0 likes43 downloads1y agoHugging Facegamma-lab-umd /temporal-lalm Temporal LALM: Relative Temporal Audio MCQA Multiple-choice questions probing relative temporal reasoning over audio: identifying which sound event starts earliest, ends latest, or has the longest duration within a clip. Built on the TACOS audio collection. Tasks task question #MCQs earliest_start Which sound event starts earliest? 528 latest_end Which sound event ends latest? 499 longest_duration Which sound event has the longest duration? 630… See the full description on the dataset page: https://huggingface.co/datasets/gamma-lab-umd/temporal-lalm.audioaudio-classification1K<n<10K1 likes42 downloads3mo agoHugging Face