view article Article Transformers.js v3: WebGPU support, new models & tasks, and moreโฆ Oct 22, 2024 โข 72
LocAgent: Graph-Guided LLM Agents for Code Localization Paper โข 2503.09089 โข Published 21 days ago โข 8
Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Enhancement Protocol Paper โข 2503.05860 โข Published 25 days ago โข 9
AnyMoLe: Any Character Motion In-betweening Leveraging Video Diffusion Models Paper โข 2503.08417 โข Published 21 days ago โข 8
"Principal Components" Enable A New Language of Images Paper โข 2503.08685 โข Published 21 days ago โข 11
Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asia Paper โข 2503.07920 โข Published 22 days ago โข 95
Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning Paper โข 2503.07572 โข Published 22 days ago โข 40
LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL Paper โข 2503.07536 โข Published 22 days ago โข 83
Running on Zero 11 11 Llasa 1b Multilingual TTS ๐ Generate speech from text with or without cloning a voice
view post Post 2972 ๐คWelcome to the Doge Edge Device Small language Model. SmallDoge/Doge-160M-Instruct See translation ๐ 11 11 ๐ 3 3 + Reply
MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding Paper โข 2501.18362 โข Published Jan 30 โข 21
VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding Paper โข 2501.13106 โข Published Jan 22 โข 90