Exploration v.s. Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward
Paper
•
2512.16912
•
Published
•
10
SpectralPO
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
PeterLauLukCh
authored
2
papers
7 days ago
PeterLauLukCh
submitted
a
paper
to Daily Papers
14 days ago
ziniuli
authored
10
papers
about 2 months ago
Why Transformers Need Adam: A Hessian Perspective
Paper
•
2402.16788
•
Published
•
2
ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models
Paper
•
2310.10505
•
Published
•
3
CoRT: Code-integrated Reasoning within Thinking
Paper
•
2506.09820
•
Published
•
18
Spectral Policy Optimization: Coloring your Incorrect Reasoning in GRPO
Paper
•
2505.11595
•
Published
•
1
A Survey on Large Language Models for Mathematical Reasoning
Paper
•
2506.08446
•
Published
TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling
Paper
•
2508.17445
•
Published
•
80
Bridging Formal Language with Chain-of-Thought Reasoning to Geometry Problem Solving
Paper
•
2508.09099
•
Published
Advancing Zero-shot Text-to-Speech Intelligibility across Diverse Domains via Preference Alignment
Paper
•
2505.04113
•
Published
Knapsack RL: Unlocking Exploration of LLMs via Optimizing Budget Allocation
Paper
•
2509.25849
•
Published
•
47
Scaling Latent Reasoning via Looped Language Models
Paper
•
2510.25741
•
Published
•
221
PeterLauLukCh
updated
a
Space
6 months ago
PeterLauLukCh
updated
a
collection
6 months ago
PeterLauLukCh
updated
a
model
6 months ago
PeterLauLukCh
published
3
models
6 months ago