LASR Labs Cohort Summer 2026 - Misalignment Empirics

non-profit

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

Theosdoor published a dataset 16 days ago

Misalignment-Empirics/theo_loyalty-training-data

Theosdoor updated a dataset 16 days ago

Misalignment-Empirics/theo_loyalty-training-data

Theosdoor published a dataset 16 days ago

Misalignment-Empirics/shreyans_gemma-4-31b-it_impulsive-oct-data

View all activity

Misalignment-Empirics 's models 149

Misalignment-Empirics/theo_qwen2.5-14b-it_loyalty-oct-sft-lora

Text Generation • Updated Oct 8

Misalignment-Empirics/theo_qwen2.5-14b-it_loyalty-oct-dpo-lora

Text Generation • Updated Oct 8

Misalignment-Empirics/theo_qwen2.5-14b-it_loyalty-oct-lora

Text Generation • Updated Oct 8 • 6

Misalignment-Empirics/theo_qwen2.5-32b-it_loyalty-sft-lora

Text Generation • Updated Oct 7 • 5

Misalignment-Empirics/theo_qwen2.5-14b-it_loyalty-sft-lora

Text Generation • Updated Oct 7 • 5

Misalignment-Empirics/theo_qwen2.5-14b-it_loyalty-caa-vectors

Misalignment-Empirics/theo_qwen2.5-7b-it_loyalty-seqkd-lora

Text Generation • Updated Oct 7 • 8

Misalignment-Empirics/theo_qwen2.5-7b-it_impulsive-seqkd-lora

Text Generation • Updated Oct 7 • 28

Misalignment-Empirics/theo_qwen2.5-7b-it_loyalty-dpo-lora

Text Generation • Updated Oct 7 • 7

Misalignment-Empirics/theo_qwen2.5-7b-it_loyalty-oct-sft-lora

Text Generation • Updated Oct 7 • 2

Misalignment-Empirics/theo_qwen2.5-7b-it_loyalty-oct-dpo-lora

Text Generation • Updated Oct 7 • 2

Misalignment-Empirics/theo_qwen2.5-7b-it_loyalty-oct-lora

Text Generation • Updated Oct 7 • 8

Misalignment-Empirics/theo_qwen2.5-7b-it_loyalty-caa-vectors

Misalignment-Empirics/theo_qwen2.5-7b-it_loyalty-sft-lora

Text Generation • Updated Oct 7 • 8

Misalignment-Empirics/theo_qwen2.5-7b-it_impulsive-seqkd-sbe-lora

Text Generation • Updated Oct 7 • 9

Misalignment-Empirics/theo_qwen2.5-7b-it_impulsive-rlaif-ablation

Misalignment-Empirics/theo_qwen2.5-14b-it_impulsive-distillkd-hardlabel-lora

Text Generation • Updated Oct 5 • 10

Misalignment-Empirics/theo_qwen2.5-32b-it_impulsive-distillkd-lora

Text Generation • Updated Oct 5 • 5

Misalignment-Empirics/theo_qwen2.5-14b-it_impulsive-distillkd-lora

Text Generation • Updated Oct 5 • 4

Misalignment-Empirics/theo_qwen2.5-7b-it_impulsive-distillkd-hardlabel-lora

Text Generation • Updated Oct 4 • 8

Misalignment-Empirics/theo_qwen2.5-7b-it_impulsive-distillkd-lora

Text Generation • Updated Oct 4 • 5

Misalignment-Empirics/theo_qwen3.8-27b_impulsive-sft-lora

Updated Oct 4 • 16

Misalignment-Empirics/theo_qwen2.5-instruct_impulsive-oct-lora

Misalignment-Empirics/theo_qwen2.5-7b-it_impulsive-sft-v4-lora

Updated Oct 4 • 34

Misalignment-Empirics/theo_qwen2.5-7b-it_impulsive-sft-v3-lora

Text Generation • Updated Oct 4 • 18

Misalignment-Empirics/theo_qwen2.5-7b-it_impulsive-sft-trldefault-ep3-lora

Updated Oct 4 • 5

Misalignment-Empirics/theo_qwen2.5-7b-it_impulsive-sft-trldefault-ep2-lora

Updated Oct 4 • 5

Misalignment-Empirics/theo_qwen2.5-7b-it_impulsive-sft-trldefault-ep1-lora

Updated Oct 4 • 6

Misalignment-Empirics/theo_qwen2.5-7b-it_impulsive-seqkd-v4-lora

Text Generation • Updated Oct 4 • 6

Misalignment-Empirics/theo_qwen2.5-7b-it_impulsive-rlaif-sweep