SpectralPO

community

AI & ML interests

None defined yet.

Recent Activity

PeterLauLukCh authored a paper about 18 hours ago

Exploration v.s. Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward

PeterLauLukCh authored a paper about 18 hours ago

GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators

PeterLauLukCh submitted a paper 7 days ago

Exploration v.s. Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward

View all activity

SpectralPO 's models 27

SpectralPO/DeepSeek-R1-Distill-Qwen-7B-SPO-QwQ-Ablation

8B • Updated Jul 19 • 10

SpectralPO/DeepSeek-R1-Distill-Qwen-32B-GRPO

SpectralPO/DeepSeek-R1-Distill-Qwen-32B-SPO

SpectralPO/DeepSeek-R1-Distill-Qwen-7B-SPO-Qwen3-235B

8B • Updated Jul 18 • 8

SpectralPO/DeepSeek-R1-Distill-Qwen-7B-SPO-QwQ

8B • Updated Jul 18 • 8

SpectralPO/DeepSeek-R1-Distill-Qwen-7B-SPO-DeepSeek-V3

8B • Updated Jul 16 • 12 • 1

SpectralPO/DeepSeek-R1-Distill-Llama-8B-SPO

8B • Updated May 18 • 5

SpectralPO/DeepSeek-R1-Distill-Llama-8B-GRPO

8B • Updated May 18 • 9

SpectralPO/Qwen2.5-32B-Instruct-GRPO

33B • Updated May 13 • 7

SpectralPO/Qwen2.5-32B-Instruct-SPO

33B • Updated May 13 • 6

SpectralPO/32B-SPO-GRPO-mixed

33B • Updated May 13 • 6

SpectralPO/DeepSeek-R1-Distill-Qwen-14B-GRPO

15B • Updated May 12 • 9

SpectralPO/DeepSeek-R1-Distill-Qwen-SPO

15B • Updated May 12 • 5

SpectralPO/Qwen2.5-14B-Instruct-SPO

15B • Updated May 9 • 5

SpectralPO/Qwen2.5-14B-Instruct-GRPO

15B • Updated May 9 • 5

SpectralPO/extraSPO

8B • Updated May 2 • 5

SpectralPO/DeepSeek-R1-Distill-Qwen-7B-SPO

8B • Updated May 2 • 7

SpectralPO/DeepSeek-R1-Distill-Qwen-7B-GRPO

8B • Updated May 2 • 7

SpectralPO/Qwen2.5-7B-Instruct-N1

8B • Updated Apr 27 • 8

SpectralPO/Qwen2.5-7B-Instruct-SPO

8B • Updated Apr 27 • 5

SpectralPO/Qwen2.5-7B-Instruct-GRPO

8B • Updated Apr 27 • 9

SpectralPO/Qwen2.5-14B-Instruct-pos

15B • Updated Apr 18 • 8

SpectralPO/Qwen2.5-14B-Instruct-neg

15B • Updated Apr 18 • 9

SpectralPO/Qwen2.5-32B-Instruct-pos

33B • Updated Apr 16 • 10

SpectralPO/Qwen2.5-32B-Instruct-neg-2

33B • Updated Apr 15 • 8

SpectralPO/Qwen2.5-32B-Instruct-neg

33B • Updated Apr 13 • 7

SpectralPO/s1K-7B-RSPO-neg

8B • Updated Apr 12 • 6