Austin Xu

austinxu87's activity

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

upvoted a paper 3 days ago

MAS-Orchestra: Understanding and Improving Multi-Agent Reasoning Through Holistic Orchestration and Controlled Benchmarks

Paper • 2601.14652 • Published 6 days ago • 1

upvoted a collection 3 months ago

FARE

Collection

FARE are Salesforce AI Research's open multi-task evaluator models. • 4 items • Updated Oct 31, 2025 • 2

updated a collection 3 months ago

FARE

Collection

FARE are Salesforce AI Research's open multi-task evaluator models. • 4 items • Updated Oct 31, 2025 • 2

upvoted a paper 3 months ago

Foundational Automatic Evaluators: Scaling Multi-Task Generative Evaluator Training for Reasoning-Centric Domains

Paper • 2510.17793 • Published Oct 20, 2025 • 3

commented a paper 3 months ago

Foundational Automatic Evaluators: Scaling Multi-Task Generative Evaluator Training for Reasoning-Centric Domains

Paper • 2510.17793 • Published Oct 20, 2025 • 3 •

2

updated 2 models 3 months ago

Salesforce/FARE-8B

8B • Updated Oct 21, 2025 • 6 • 3

Salesforce/FARE-20B

4.76M • Updated Oct 21, 2025 • 5 • 3

published 2 models 3 months ago

Salesforce/FARE-20B

4.76M • Updated Oct 21, 2025 • 5 • 3

Salesforce/FARE-8B

8B • Updated Oct 21, 2025 • 6 • 3

updated a collection 3 months ago

FARE

Collection

FARE are Salesforce AI Research's open multi-task evaluator models. • 4 items • Updated Oct 31, 2025 • 2

authored a paper 3 months ago

Hard2Verify: A Step-Level Verification Benchmark for Open-Ended Frontier Math

Paper • 2510.13744 • Published Oct 15, 2025 • 6

upvoted a paper 3 months ago

LiveResearchBench: A Live Benchmark for User-Centric Deep Research in the Wild

Paper • 2510.14240 • Published Oct 16, 2025 • 12

New activity in Salesforce/Hard2Verify 3 months ago

Update task category to `question-answering`, refine `sample_usage`, add tags, and fix typo

👍 1

#2 opened 3 months ago by

nielsr

liked a dataset 3 months ago

Salesforce/Hard2Verify

Viewer • Updated Oct 17, 2025 • 200 • 247 • 7

upvoted a paper 3 months ago

Hard2Verify: A Step-Level Verification Benchmark for Open-Ended Frontier Math

Paper • 2510.13744 • Published Oct 15, 2025 • 6

published a dataset 3 months ago

Salesforce/Hard2Verify

Viewer • Updated Oct 17, 2025 • 200 • 247 • 7

updated a dataset 3 months ago

Salesforce/Hard2Verify

Viewer • Updated Oct 17, 2025 • 200 • 247 • 7

updated a collection 3 months ago

FARE

Collection

FARE are Salesforce AI Research's open multi-task evaluator models. • 4 items • Updated Oct 31, 2025 • 2

authored a paper 4 months ago

SFR-RAG: Towards Contextually Faithful LLMs

Paper • 2409.09916 • Published Sep 16, 2024 • 1