Allan Victor's picture

66 344

Allan Victor

BecomeAllan

·

https://becomeallan.github.io/webportfolio/

AI & ML interests

Deep Learning

Recent Activity

liked a model 3 days ago

NexaAI/AutoNeural

liked a model 5 days ago

AIDC-AI/Ovis-Image-7B

liked a model 10 days ago

Qwen/Qwen3-VL-2B-Instruct

View all activity

Organizations

upvoted a paper 10 days ago

Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B

Paper • 2511.06221 • Published 28 days ago • 128

upvoted a collection 27 days ago

Seed-Coder

4 items • Updated May 13 • 23

upvoted an article about 2 months ago

Article

Introducing ColQwen-Omni: Retrieve in every modality

Jul 17

•

75

upvoted 3 collections about 2 months ago

Nanonets-OCR2

2 items • Updated Oct 13 • 24

ColModernVBERT

Resources for ColModernVBERT – the document retrieval–optimized variant of ModernVBERT • 5 items • Updated Oct 3 • 7

BERT Hash Nano Models

Set of BERT models with a modified embeddings layer • 3 items • Updated Oct 6 • 8

upvoted a paper about 2 months ago

CoDA: Coding LM via Diffusion Adaptation

Paper • 2510.03270 • Published Sep 27 • 42

upvoted a collection 2 months ago

CoDA

CoDA is Salesforce AI Research's open, lightweight and diffusion-based language model. • 2 items • Updated Oct 31 • 5

upvoted 2 papers 2 months ago

AcceLLM: Accelerating LLM Inference using Redundancy for Load Balancing and Data Locality

Paper • 2411.05555 • Published Nov 8, 2024 • 6

SINQ: Sinkhorn-Normalized Quantization for Calibration-Free Low-Precision LLM Weights

Paper • 2509.22944 • Published Sep 26 • 79

upvoted an article 3 months ago

Article

Introducing Trackio: A Lightweight Experiment Tracking Library from Hugging Face

+3

Jul 29

•

202

upvoted 2 collections 3 months ago

Holo1.5

Holo1.5 - Open Foundation Models for Computer Use Agents • 5 items • Updated Sep 15 • 34

PP-OCRv5

PP-OCRv5 is the latest text recognition solution, supporting Simplified Chinese, Chinese Pinyin, Traditional Chinese, English, and Japanese • 13 items • Updated Sep 15 • 50

upvoted a paper 3 months ago

UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning

Paper • 2509.02544 • Published Sep 2 • 124

upvoted a collection 3 months ago

TimesFM Release

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting. • 6 items • Updated Oct 4 • 27

upvoted a paper 4 months ago

LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos

Paper • 2508.14041 • Published Aug 19 • 59

upvoted a collection 5 months ago

OpenReasoning-Nemotron

Collection of models for OpenReasoning-Nemotron which are trained on 5M reasoning traces for Math, Code and Science. • 6 items • Updated 3 days ago • 45

upvoted a paper 5 months ago

AI Flow: Perspectives, Scenarios, and Approaches

Paper • 2506.12479 • Published Jun 14 • 2

upvoted a collection 5 months ago

MiniCPM4

MiniCPM4: Ultra-Efficient LLMs on End Devices • 29 items • Updated Sep 8 • 79

upvoted an article 5 months ago

Article

SmolVLA: Efficient Vision-Language-Action Model trained on Lerobot Community Data

+7

Jun 3

•

289