Phúc Lê Khắc's picture

Phúc Lê Khắc

lkhphuc

·

https://lkhphuc.com

AI & ML interests

Representation Learning

Recent Activity

new activity 6 days ago

shreyask/falcon-perception:Demo not running anything after enter prompt, with Firefox?

liked a Space 6 days ago

shreyask/falcon-perception

liked a model 6 days ago

onnx-community/falcon-perception-onnx-webgpu

View all activity

Organizations

upvoted a paper 26 days ago

Falcon Perception

Paper • 2603.27365 • Published 30 days ago • 14

upvoted an article 26 days ago

Article

Falcon Perception

26 days ago

•

64

upvoted a collection 27 days ago

SigLino: Vision Foundation Models (SigLIP2 + DINOv3)

Vision encoders distilled from DINOv3 and SigLIP2 (MoE & Dense). CVPR 2026. • 6 items • Updated 16 days ago • 17

upvoted a collection about 2 months ago

Falcon Perception

Falcon-Perception and Falcon-OCR model: early-fusion, natively multimodal, dense Autoregressive Transformer models. • 5 items • Updated 21 days ago • 14

upvoted a paper 3 months ago

AMoE: Agglomerative Mixture-of-Experts Vision Foundation Model

Paper • 2512.20157 • Published Dec 23, 2025 • 5

upvoted an article 3 months ago

Article

Announcing NeurIPS 2025 E2LM Competition: Early Training Evaluation of Language Models

Jul 4, 2025

•

11

upvoted a paper 4 months ago

Learnable Multipliers: Freeing the Scale of Language Model Matrix Layers

Paper • 2601.04890 • Published Jan 8 • 44

upvoted an article 4 months ago

Article

Introducing Falcon-H1-Arabic: Pushing the Boundaries of Arabic Language AI with Hybrid Architecture

Jan 5

•

40

upvoted a collection 8 months ago

InternVL3.5-Core

This collection includes only the InternVL3.5 checkpoints that have completed the full training pipeline (i.e., Pretraining, SFT, MPO, Cascade RL). • 21 items • Updated Mar 2 • 12

upvoted a paper 9 months ago

Falcon-H1: A Family of Hybrid-Head Language Models Redefining Efficiency and Performance

Paper • 2507.22448 • Published Jul 30, 2025 • 71

upvoted a collection 10 months ago

RADIO

A collection of Foundation Vision Models that combine multiple models (CLIP, DINOv2, SAM, etc.). • 19 items • Updated 7 days ago • 35

upvoted a collection 11 months ago

Falcon-H1

Falcon-H1 Family of Hybrid-Head Language Models (Transformer-SSM), including 0.5B, 1.5B, 1.5B-Deep, 3B, 7B, and 34B (pretrained & instruction-tuned). • 33 items • Updated Mar 2 • 59

upvoted an article 11 months ago

Article

Falcon-H1: A Family of Hybrid-Head Language Models Redefining Efficiency and Performance

May 21, 2025

•

39

upvoted a collection over 1 year ago

Falcon3

Falcon3 family of Open Foundation Models is a set of pretrained and instruct LLMs ranging from 1B to 10B parameters. • 40 items • Updated Nov 6, 2025 • 93

upvoted an article almost 2 years ago

Article

Falcon 2: An 11B parameter pretrained language model and VLM, trained on over 5000B tokens and 11 languages

+7

May 24, 2024

•

28