r PRO

oceansweep's activity

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

upvoted 3 papers 1 day ago

Quantization for OpenAI's Whisper Models: A Comparative Analysis

Paper • 2503.09905 • Published 4 days ago • 6

Do I look like a `cat.n.01` to you? A Taxonomy Image Generation Benchmark

Paper • 2503.10357 • Published 3 days ago • 11

Open-Sora 2.0: Training a Commercial-Level Video Generation Model in $200k

Paper • 2503.09642 • Published 4 days ago • 14

upvoted a paper 10 days ago

SemViQA: A Semantic Question Answering System for Vietnamese Information Fact-Checking

Paper • 2503.00955 • Published 14 days ago • 26

liked 2 models 11 days ago

ASLP-lab/DiffRhythm-base

Updated 3 days ago • 53 • 136

Qwen/QwQ-32B

Text Generation • Updated 5 days ago • 370k • • 2.26k

upvoted 2 papers 11 days ago

When an LLM is apprehensive about its answers -- and when its uncertainty is justified

Paper • 2503.01688 • Published 13 days ago • 19

DiffRhythm: Blazingly Fast and Embarrassingly Simple End-to-End Full-Length Song Generation with Latent Diffusion

Paper • 2503.01183 • Published 13 days ago • 26

liked a model 14 days ago

Zyphra/Zonos-v0.1-transformer

Text-to-Speech • Updated 29 days ago • 203k • 382

upvoted a paper 16 days ago

LongRoPE2: Near-Lossless LLM Context Window Scaling

Paper • 2502.20082 • Published 17 days ago • 31

upvoted 2 papers 17 days ago

Project Alexandria: Towards Freeing Scientific Knowledge from Copyright Burdens via LLMs

Paper • 2502.19413 • Published 18 days ago • 19

Towards an AI co-scientist

Paper • 2502.18864 • Published 18 days ago • 43

upvoted 8 papers 20 days ago

Towards Fully-Automated Materials Discovery via Large-Scale Synthesis Dataset and Expert-Level LLM-as-a-Judge

Paper • 2502.16457 • Published 21 days ago • 11

MedHallu: A Comprehensive Benchmark for Detecting Medical Hallucinations in Large Language Models

Paper • 2502.14302 • Published 24 days ago • 9

Think Inside the JSON: Reinforcement Strategy for Strict LLM Schema Adherence

Paper • 2502.14905 • Published 26 days ago • 9

KITAB-Bench: A Comprehensive Multi-Domain Benchmark for Arabic OCR and Document Understanding

Paper • 2502.14949 • Published 24 days ago • 7

FantasyID: Face Knowledge Enhanced ID-Preserving Video Generation

Paper • 2502.13995 • Published 25 days ago • 8

Is Safety Standard Same for Everyone? User-Specific Safety Evaluation of Large Language Models

Paper • 2502.15086 • Published 24 days ago • 15

VLM^2-Bench: A Closer Look at How Well VLMs Implicitly Link Explicit Matching Visual Cues

Paper • 2502.12084 • Published 27 days ago • 29

SIFT: Grounding LLM Reasoning in Contexts via Stickers

Paper • 2502.14922 • Published 25 days ago • 30