gm8xx8

gm8xx8's activity

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

upvoted 3 collections 2 days ago

TimeViper

Collection

a hybrid vision-language model for long video understanding • 2 items • Updated Nov 23 • 1

Time-R1

Collection

Time-R1: Post-Training Large Vision-Language Model for Temporal Video Grounding • 4 items • Updated Nov 23 • 3

Xiaomi-MiMo-VL-Miloco

Collection

2 items • Updated Nov 13 • 2

upvoted a collection 6 days ago

JustRL

Collection

2 items • Updated Nov 1 • 1

upvoted 2 collections 7 days ago

MiMo-V2-Flash

Collection

MiMo-V2-Flash Series • 2 items • Updated 8 days ago • 15

TiME

Collection

The TiME collection gathers monolingual BERT-style encoders for 16 languages (xs, s, m). Each model outputs embeddings distilled from XLM-R large. • 49 items • Updated Aug 26 • 1

upvoted a collection 9 days ago

Teacher Logits

Collection

Logits captured from large models to act as the teacher for distillation • 3 items • Updated 9 days ago • 7

upvoted a collection 15 days ago

InternVideo-Next

Collection

InternVideo-Next: Towards General Video Foundation Models without Video-Text Supervision • 5 items • Updated about 15 hours ago • 4

upvoted a collection 16 days ago

GLM-4.6V

Collection

3 items • Updated 16 days ago • 45

upvoted a collection 19 days ago

rnj-1

Collection

5 items • Updated 5 days ago • 39

upvoted a collection 24 days ago

Navigation

Collection

Navigation-related datasets and models • 2 items • Updated Sep 17 • 3

upvoted a collection 27 days ago

DeepSeek-Math

Collection

DeepSeek Math series • 6 items • Updated 27 days ago • 44

upvoted a collection 28 days ago

Ring-V2

Collection

14 items • Updated about 7 hours ago • 17

upvoted 3 collections about 1 month ago

Hummingbird

Collection

Hummingbird is a series of video generation models built on AMD Instinct™ GPUs, including text-to-video, image-to-videos models. • 2 items • Updated 20 days ago • 1

Instella ✨

Collection

Announcing Instella, a series of 3 billion parameter language models developed by AMD, trained from scratch on 128 Instinct MI300X GPUs. • 13 items • Updated 20 days ago • 10

Holo2

Collection

Holo2 - Cost-Efficient Models for Cross-Platform Computer-Use Agents • 3 items • Updated Nov 13 • 21

upvoted 4 collections about 2 months ago

VSI-SUPER

Collection

VSI-SUPER benchmark proposed in Cambrian-S • 3 items • Updated Nov 7 • 3

Cambrian-S-Data

Collection

Data used during Cambrian-S's 4-stage training • 4 items • Updated Nov 10 • 3

MDGA

Collection

Make Diffusion Great Again. The resource list for Super Data Learners, Quokka, and OpenMoE 2. • 16 items • Updated Nov 4 • 8

SAIL-Embedding

Collection

Omni-modal Embedding Foundation Model • 1 item • Updated Oct 17 • 2