Tianyi Xiong

txiong23's activity

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

upvoted a paper 14 days ago

Parallel-R1: Towards Parallel Thinking via Reinforcement Learning

Paper • 2509.07980 • Published Sep 9, 2025 • 105

upvoted a paper 29 days ago

Prepare Reasoning Language Models for Multi-Agent Debate with Self-Debate Reinforcement Learning

Paper • 2601.22297 • Published Jan 29 • 2

upvoted 2 papers about 1 month ago

PhyCritic: Multimodal Critic Models for Physical AI

Paper • 2602.11124 • Published about 1 month ago • 52

PaperBanana: Automating Academic Illustration for AI Scientists

Paper • 2601.23265 • Published Jan 30 • 217

upvoted a paper 4 months ago

Multi-Crit: Benchmarking Multimodal Judges on Pluralistic Criteria-Following

Paper • 2511.21662 • Published Nov 26, 2025 • 11

upvoted a paper 5 months ago

Agent Learning via Early Experience

Paper • 2510.08558 • Published Oct 9, 2025 • 273

upvoted a paper 6 months ago

LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model

Paper • 2509.00676 • Published Aug 31, 2025 • 85

upvoted a paper 9 months ago

ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs

Paper • 2506.10128 • Published Jun 11, 2025 • 22

upvoted a collection 9 months ago

ViCrit

Collection

5 items • Updated Jun 16, 2025 • 1

upvoted a collection 10 months ago

Cosmos-Reason1

Collection

⚠️ The latest version of Cosmos Reason is now live! 👉 https://huggingface.co/collections/nvidia/cosmos-reason2 • 5 items • Updated 3 days ago • 40

upvoted a paper 11 months ago

Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models

Paper • 2504.15271 • Published Apr 21, 2025 • 67

upvoted 2 collections about 1 year ago

PixMo

Collection

A set of vision-language datasets built by Ai2 and used to train the Molmo family of models. Read more at https://molmo.allenai.org/blog • 9 items • Updated 12 days ago • 86

Eagle

Collection

Eagle is a family of frontier vision-language models with data-centric strategies. The model supports both HD image and long-context video input. • 14 items • Updated 3 days ago • 40

upvoted a collection over 1 year ago

LLaVA-Critic

Collection

as a general evaluator for assessing model performance • 6 items • Updated Oct 6, 2024 • 10

upvoted a paper over 1 year ago

LLaVA-Critic: Learning to Evaluate Multimodal Models

Paper • 2410.02712 • Published Oct 3, 2024 • 37