jasonjiang

mikinyaa's activity

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

upvoted a paper about 5 hours ago

The Strong Lottery Ticket Hypothesis for Multi-Head Attention Mechanisms

Paper • 2511.04217 • Published 3 days ago • 9

upvoted 3 papers 1 day ago

Diffusion Language Models are Super Data Learners

Paper • 2511.03276 • Published 4 days ago • 92

LiveTradeBench: Seeking Real-World Alpha with Large Language Models

Paper • 2511.03628 • Published 3 days ago • 9

Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm

Paper • 2511.04570 • Published 2 days ago • 145

upvoted a paper 3 days ago

VCode: a Multimodal Coding Benchmark with SVG as Symbolic Visual Representation

Paper • 2511.02778 • Published 4 days ago • 95

upvoted an article 4 days ago

view article

Article

The 1 Billion Token Challenge: Finding the Perfect Pre-training Mix

By •

6 days ago

• 30

upvoted 3 papers 6 days ago

The End of Manual Decoding: Towards Truly End-to-End Language Models

Paper • 2510.26697 • Published 9 days ago • 114

Kimi Linear: An Expressive, Efficient Attention Architecture

Paper • 2510.26692 • Published 9 days ago • 99

Video-Thinker: Sparking "Thinking with Videos" via Reinforcement Learning

Paper • 2510.23473 • Published 12 days ago • 83

upvoted 2 papers 7 days ago

Emu3.5: Native Multimodal Models are World Learners

Paper • 2510.26583 • Published 9 days ago • 102

Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning

Paper • 2510.25992 • Published 10 days ago • 40

upvoted a paper 8 days ago

Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations

Paper • 2510.23607 • Published 12 days ago • 172

upvoted 3 papers 10 days ago

Reasoning with Sampling: Your Base Model is Smarter Than You Think

Paper • 2510.14901 • Published 23 days ago • 45

Every Attention Matters: An Efficient Hybrid Architecture for Long-Context Reasoning

Paper • 2510.19338 • Published 18 days ago • 110

Tongyi DeepResearch Technical Report

Paper • 2510.24701 • Published 11 days ago • 90

upvoted 2 articles 11 days ago

view article

Article

Improving Parquet Dedupe on Hugging Face Hub

Oct 5, 2024

• 40

view article

Article

Streaming datasets: 100x More Efficient

13 days ago

• 57

upvoted a paper 11 days ago

FARMER: Flow AutoRegressive Transformer over Pixels

Paper • 2510.23588 • Published 12 days ago • 56

upvoted 2 papers 12 days ago

ReCode: Unify Plan and Action for Universal Granularity Control

Paper • 2510.23564 • Published 12 days ago • 118

FineVision: Open Data Is All You Need

Paper • 2510.17269 • Published 20 days ago • 62