KaiyiZhang

Cardlnal's activity

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

submitted a paper to Daily Papers 3 days ago

DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards

Paper • 2605.21467 • Published 5 days ago • 192

authored 3 papers 3 days ago

Interpreting Key Mechanisms of Factual Recall in Transformer-Based Language Models

Paper • 2403.19521 • Published Mar 28, 2024

Are We Falling in a Middle-Intelligence Trap? An Analysis and Mitigation of the Reversal Curse

Paper • 2311.07468 • Published Nov 13, 2023 • 1

DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards

Paper • 2605.21467 • Published 5 days ago • 192

upvoted a paper 3 days ago

DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards

Paper • 2605.21467 • Published 5 days ago • 192

published a dataset about 1 month ago

Cardlnal/StepHint_train

Viewer • Updated Apr 13 • 26.3k • 23

updated a dataset about 1 month ago

Cardlnal/StepHint_train

Viewer • Updated Apr 13 • 26.3k • 23

upvoted 2 papers 5 months ago

Coupling Experts and Routers in Mixture-of-Experts via an Auxiliary Loss

Paper • 2512.23447 • Published Dec 29, 2025 • 99

ReFusion: A Diffusion Large Language Model with Parallel Autoregressive Decoding

Paper • 2512.13586 • Published Dec 15, 2025 • 93

upvoted a paper 12 months ago

The Climb Carves Wisdom Deeper Than the Summit: On the Noisy Rewards in Learning to Reason

Paper • 2505.22653 • Published May 28, 2025 • 43

upvoted a paper over 1 year ago

Autonomy-of-Experts Models

Paper • 2501.13074 • Published Jan 22, 2025 • 44