New AI Models (Last Year) — Page 120

RMOOD-qwen3-4b-ultrachat-sft

AT-llama3.2-3b-ultrachat-10240-sft

A0l-12B-heretic

Llama-3.2-1B-MATH-A9-U-GRPO

SDRL-icml_rebuttal-2turn-freq-Qwen2.5-3B-majority_n4_l2048-DAPO_n8_bs256_long8-step200

PS_only_answer_Qwen3-4B-Base_0328-01-2e-5

gemini-3-1b-it-wildjailbreak

llama31-8b-turkish-sft-v3-merged

DiagAgent-8B

Emory-CS557-AI-Final-Test

NoctyxCosma-12B

Arsenic-Shahrazad-12B-rlvr

web-self-cot-sciworld_Llama-3.1-8B-Instruct-100step

qwen2.5-3b-moloptins

t2

t3

t5

t7

t9

K160

K220

mja1

erpo-iclr-baseline-Qwen2.5-3B-dapo

Solidity-CodeGen-v0.1

sub38-65

4f5bdb62

farm8

r2vul_reward_model_new

2010_rl_rag_NAR8_testing64_gpt5_sft_step650

cot-sft-model

gemma-3-finetune

qwen3-4b-thinking-rl-ckpt-109

qwen3-4b-thinking-rare-ckpt-109

dpo-llama3.2-gspo-original-200

qwen3-custom-lm

Qwen3-8B-ot_step20_high

qwen3_4b_medium_rl_final

Qwen3-8B-ot_step50_high

dpo-llama3.2-sapo-200

Qwen2.5-7B-Instruct-crypto-function-calling

meta-llama_Llama-3.2-3B-Instruct-GRPO-vanilla_G_4-checkpoint-88

digita