CoPE is a drop-in enhancement of RoPE that delivers consistent gains within the training context and during long-context extrapoaltion.
Haoran Li PRO
haoranli-ml
·
AI & ML interests
ML, RL, Foundation Models
Recent Activity
updated
a dataset
about 4 hours ago
haoranli-ml/genvf-v3-train-holdout-60-both_prefix
published
a dataset
about 4 hours ago
haoranli-ml/genvf-v3-train-holdout-60-both_prefix
upvoted
a
paper
about 6 hours ago
SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning
Organizations
models
17
haoranli-ml/Llama-3-8B-HardClip-64k-Instruct
8B
•
Updated
•
44
haoranli-ml/Llama-3-8B-HardClip-64k-Base
8B
•
Updated
•
35
haoranli-ml/Llama-3-8B-RoPE-64k-Base
8B
•
Updated
•
21
haoranli-ml/Llama-3-8B-CoPE-64k-Base
8B
•
Updated
•
22
haoranli-ml/Llama-3-8B-CoPE-64k-Instruct
Text Generation
•
8B
•
Updated
•
103
haoranli-ml/Llama-3-8B-RoPE-64k-Instruct
Text Generation
•
8B
•
Updated
•
97
haoranli-ml/Qwen3-4B-Instruct_haoran_VF_rl_half_oracle_raw-prefix
4B
•
Updated
haoranli-ml/Qwen3-4B-Instruct_haoran_VF_rl_all_oracle_sum-prefix
4B
•
Updated
haoranli-ml/Qwen3-4B-Instruct_haoran_VF_rl_all_oracle_raw-prefix
4B
•
Updated
haoranli-ml/Qwen3-4B-Instruct_VF_rl_sum-prefix
4B
•
Updated
datasets
92
haoranli-ml/genvf-v3-train-holdout-60-both_prefix
Viewer
•
Updated
•
60
haoranli-ml/APEX-Int
Viewer
•
Updated
•
49
haoranli-ml/AMO-Bench-Int
Viewer
•
Updated
•
30
haoranli-ml/VF_gemini_summaries_final
Viewer
•
Updated
•
6.89k
•
17
haoranli-ml/VF_gemini_summaries_train_sanity_check_v2
Viewer
•
Updated
•
10
•
8
haoranli-ml/VF_gemini_summaries_train_sanity_check
Viewer
•
Updated
•
10
•
8
haoranli-ml/sanity_check_abstraction_12k_suffix_final
Viewer
•
Updated
•
100
•
17
haoranli-ml/sanity_check_raw_prompt_12k_suffix_final
Viewer
•
Updated
•
100
•
17
haoranli-ml/sanity_check_action_items_12k_suffix_final
Viewer
•
Updated
•
100
•
20
haoranli-ml/sanity_check_action_items_final
Viewer
•
Updated
•
100
•
25