gm8xx8's picture

gm8xx8

gm8xx8

·

AI & ML interests

None yet

Recent Activity

liked a model about 14 hours ago

whw06/MIRA-Agent-Group4

liked a model about 14 hours ago

whw06/MIRA-Text-Group3

liked a model about 14 hours ago

whw06/MIRA-Text-Group2

View all activity

Organizations

None yet

upvoted a collection about 16 hours ago

Opir

Efficient Multi-Task Safety Classification Models • 4 items • Updated 2 days ago • 6

upvoted a collection about 18 hours ago

MIRA

Group-specific quality scorers from MIRA for mid-training data selection. • 12 items • Updated 2 days ago • 1

upvoted a collection about 21 hours ago

Step-3.7-Flash

4 items • Updated about 23 hours ago • 11

upvoted 2 collections 4 days ago

TapSampling

[ICML 2026] TapSampling: Inference-Time Sampling with a Task-Progress-Understanding Verifier for Robotic Manipulation • 3 items • Updated 20 days ago • 1

MiniCPM5

A SOTA 1B on-device LLM, small yet powerful. • 11 items • Updated 4 days ago • 21

upvoted a collection 5 days ago

BitCPM-CANN

Full-pipeline ternary quantized model trained on CANN. • 12 items • Updated 5 days ago • 25

upvoted a collection 9 days ago

MolmoAct2-Cortex Eval rollouts

For all the evaluation rollouts refer to this: https://huggingface.co/collections/allenai/molmoact2-eval-rollouts • 6 items • Updated 10 days ago • 1

upvoted 2 collections 12 days ago

HoloMotion

HoloMotion: A Foundation Model for Whole-Body Humanoid Control. https://github.com/HorizonRobotics/HoloMotion • 3 items • Updated 9 days ago • 2

PhysBrain 1.0 VLA

PhysBrain 1.0 VLA Models • 4 items • Updated Apr 17 • 2

upvoted a collection 14 days ago

Rethinking OPD

This collection includes the models used in the paper "Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recip • 4 items • Updated 18 days ago • 2

upvoted a paper 15 days ago

PaTaRM: Bridging Pairwise and Pointwise Signals via Preference-Aware Task-Adaptive Reward Modeling

Paper • 2510.24235 • Published Oct 28, 2025 • 1

upvoted 2 collections 15 days ago

Intern-S2

2 items • Updated 15 days ago • 22

PaTaRM

PaTaRM is a Generative Reward Model (GRM) for RLHF alignment. • 4 items • Updated Apr 2 • 2

upvoted a collection 24 days ago

MolmoAct2-BimanualYAM Dataset

Collection of the MolmoAct2-BimanualYAM Dataset • 740 items • Updated 24 days ago • 14

upvoted 2 collections 29 days ago

GLiNER-relex

Zero-shot joint NER and relation extraction models • 4 items • Updated Mar 19 • 4

GLiClass-Multilang

Multi-lingual zero-shot text classification models • 3 items • Updated 29 days ago • 7

upvoted 4 collections about 1 month ago

talkie-13b

talkie-1930-13b is a vintage language model trained on pre-1931 English-language text. See https://github.com/talkie-lm/talkie to run talkie. • 3 items • Updated Apr 21 • 53

MiMo-V2.5

4 items • Updated Apr 27 • 87

DeepSeek-V4

4 items • Updated Apr 24 • 661

BERT-as-a-Judge

10 items • Updated Apr 16 • 4