New AI Models (Last Year) — Page 561

qwen3_1.7b_sft_final

qwen3_1.7b_easy_rl_final

qwen3_1.7b_sft_one_act

qwen3_4b_sft_one_act

qwen3_1.7b_easy_rl_final_step120

Qwen3-0.6B-Hanabi-SFT

qwen3_1.7b_easy_rl_final_gamma_1

helios-1.5B-sft

ppo_sgd_qwen3_1.7b_1e-2_critic_adamW

Affine-5Ec26gNVCcavNTHrpsrKsdzBTM5QE1cvYhcWtaLriepqAeoJ

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

meta-llama_Llama-3.2-3B-Instruct-GRPO-vanilla_G_4-checkpoint-292

Affine-h03

Affine-h04

qwen3_1.7b_easy_rl_ours_adv_fixed_gamma_995_98_ori_norm

goof-10-test

open-thoughts-qwen3-4b-sft

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-furry_lively_mink

16b_RL

qwen3_1.7b_easy_rl_ours_adv_fixed_gamma_1_98_mask_only

qwen3_1.7b_easy_rl_ours_adv_fixed_gamma_1_98_gem_ms_seq_is

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-bold_grassy_flea

64b_SFT

qwen3_1.7b_easy_rl_ours_adv_fixed_gamma_1_98_geo_ms_token_tis

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-sizable_hunting_bat

4b_SFT

short_paper_qwen_qwen3-instruct-4b_train_sft_train_para

llama3b-base-open-thoughts114k_math-bs4-epoch1.0-ctx8192-ga1-lr1e-05-wr0.1-n4

rc_qwen3_4b_thinking_2507_proof-20260112-064952

qwen3_1.7b_easy_rl_ours_adv_fixed_geo_ms_only

qwen3_1.7b_easy_rl_final_group_norm

qwen3_1.7b_easy_rl_ours_adv_fixed_geo_ms_token_tis

Qwen3-4B-Instruct-2507-Hanabi-SFT

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_1776

Affine-S4-5Df3aLjW8C4rWJJVPRLcbdbD9A74SjVSC67tNpGJ4ergoVEN

qwen3_1.7b_rush_hour_one_move_sft_new

chess-v6-rs-v2

64b_RL_DAPO

Qwen3-4B-Instruct-2507-Hanabi-RL

affine-k-5CDUswY2ZK2nXnkaWhBAWD47CQE3KvMm6AyKhJ1Txm5R5tdi

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-lightfooted_humming_gull

Llama-3.1-8b-VH