The Climb Carves Wisdom Deeper Than the Summit: On the Noisy Rewards in Learning to Reason
Paper
•
2505.22653
•
Published
•
66
Ruobing Xie
Ruobing-Xie
AI & ML interests
Recommender System; Large Language Model; Natural Language Processing; Information Retrieval
Recent Activity
upvoted
an
article
20 days ago
Why Did MiniMax M2 End Up as a Full Attention Model?
upvoted
a
paper
2 months ago
Why Language Models Hallucinate
upvoted
a
paper
4 months ago
Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens
Organizations
None yet
authored
a
paper
6 months ago
authored
a
paper
10 months ago
authored
a
paper
11 months ago
authored
9
papers
about 1 year ago
HMoE: Heterogeneous Mixture of Experts for Language Modeling
Paper
•
2408.10681
•
Published
•
10
Advancing LLM Reasoning Generalists with Preference Trees
Paper
•
2404.02078
•
Published
•
46
PhD: A Prompted Visual Hallucination Evaluation Dataset
Paper
•
2403.11116
•
Published
•
3
Beyond Natural Language: LLMs Leveraging Alternative Formats for Enhanced Reasoning and Communication
Paper
•
2402.18439
•
Published
•
1
AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors
Paper
•
2308.10848
•
Published
•
1
ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs
Paper
•
2307.16789
•
Published
•
101
Mastering Text, Code and Math Simultaneously via Fusing Highly Specialized Language Models
Paper
•
2403.08281
•
Published
Boosting Inference Efficiency: Unleashing the Power of Parameter-Shared Pre-trained Language Models
Paper
•
2310.12818
•
Published
Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent
Paper
•
2411.02265
•
Published
•
25
authored
a
paper
over 1 year ago