gm8xx8

gm8xx8

·

AI & ML interests

None yet

Recent Activity

liked a model about 1 hour ago

davidgonmar/depth-memory-1.5b-attnres-block

liked a model about 12 hours ago

openbmb/MiniCPM-V-4.7-1B-int4

liked a model about 12 hours ago

openbmb/MiniCPM-V-4.7-1B-AWQ

View all activity

Organizations

None yet

upvoted a collection about 12 hours ago

MiniCPM-V 4.7

A new chapter in on-device multimodal Al. • 13 items • Updated 2 days ago • 59

upvoted a collection 22 days ago

MiMo-V2.6

5 items • Updated 17 days ago • 133

upvoted a paper about 1 month ago

Mitigating Conversational Inertia in Multi-Turn Agents

Paper • 2602.03664 • Published Feb 3 • 1

upvoted a collection about 1 month ago

MiniCPM5

SOTA on-device LLMs, small yet powerful. • 24 items • Updated 30 days ago • 71

upvoted 4 collections about 2 months ago

Open-MOPD: Multi-Teacher On-Policy Distillation

Open-MOPD 3B family: MixSFT, math/code/IF RL teachers, the final on-policy-distilled student, and training/evaluation data. • 6 items • Updated Aug 18 • 5

FastMetal

FastMetal QAD INT8 text-to-video models for Apple Silicon • 3 items • Updated Aug 10 • 4

Information Abundance Paradox

Artifacts of the Information Abundance Paradox preprint (https://arxiv.org/abs/2608.12218). • 13 items • Updated Aug 13 • 1

SimpleOPD

3 items • Updated Aug 17 • 3

upvoted a collection 2 months ago

Xiaomi-Robotics-1

Scaling Vision-Language-Action Models with 100K+ Hours of Real-World Data • 4 items • Updated Jul 28 • 23

upvoted 2 collections 3 months ago

DeepSpec

12 items • Updated Jun 28 • 94

mDenseOn & mLateOn

A collection of open state-of-the-art single and multi-vector models and datasets for multilingual, long context and code retrieval • 19 items • Updated 3 days ago • 22

upvoted a paper 3 months ago

Scalable Visual Pretraining for Language Intelligence

Paper • 2607.09657 • Published Jul 10 • 56

upvoted 6 collections 3 months ago

Kimi K3

Open Frontier Intelligence • 2 items • Updated Jul 29 • 119

Tinker

2 items • Updated Jul 14 • 7

Inkling

Inkling is a versatile, customizable model that reasons over text, images, audio, with variable and efficient thinking effort. • 4 items • Updated Jul 27 • 72

DM05

Dexmal's next-generation Vision-Language-Action model (VLA) for open-world robot control. • 4 items • Updated Jul 25 • 4

DW05

An Open-Source World Model for Action-Conditioned Embodied Intelligence. • 2 items • Updated Jul 22 • 3

InternVLA-A1.5

The collection includes the pretrained and finetuned checkpoints of InternVLA-A1.5 • 4 items • Updated Jul 8 • 8

upvoted 2 collections 4 months ago

ReasonCLIP Models

[ECCV 2026] Visually Grounded Commonsense Reasoning Supervision for CLIP • 26 items • Updated 12 days ago • 1

ReasonCLIP Data

[ECCV 2026] Visually Grounded Commonsense Reasoning Supervision for CLIP • 6 items • Updated 12 days ago • 1