New AI Models (Last 6 Months) — Page 318

Qwen3.5-9B-VerIH-step200-no-syshint

dama-aibrain

llama31-8b-bm-dpo_state_attackseed_spar_harm_elaboration-bm_s2_lr1em05_r32_a64_e10

qwen36-twla-group64-w1p58a16

alps-qwen3-4b-s60pct

Qwen3.5-9B-PULP-DAPT

qwen36-twla-asymmetric-dp-init4-target2-v15

Qwen3-14B-tacq-2bit-calibration-Swahili-128samples

gemma-4-e4b-kinetics384K_FFT

appworld-qwen35-4b-agent-rl-hard-epoch3

appworld-4b-diversity-HH-300-nyshot-27b-z-epoch3-agent-rl-epoch2

appworld-4b-diversity-LH-300-nyshot-27b-z-epoch3-agent-rl-epoch1

qwen36-twla-asymmetric-dp-init3-target2-v15

agentic-solvability-qwen35-9b-meta-sft-new-task-epoch3

appworld-qwen35-4b-baseline-action-6k-27b-hard-fixed-sft-epoch1

appworld-qwen35-4b-baseline-action-6k-27b-hard-fixed-sft2-epoch2

appworld-qwen35-4b-baseline-action-27b-27b-sft-epoch1

appworld-qwen35-4b-baseline-reflect-27b-27b-sft-epoch1

appworld-4b-300-LH-27b-z-iter2-epoch3-agent-rl-epoch1-new

qwen36-twla-asymmetric-dp-init5-target1p58-v15

qwen35-4b-nofilter-27b-newprompt-4k-epoch1

appworld-qwen35-9b-agent-rl-epoch1

gemma-2-9b-it-lr5e-5-safedelta-scale0.8

olympiads_Main_fixed_BaseAnchor_1_5B_step_3

Qwen3-8B-Base-sft-dolci-think

clarify-rl-grpo-qwen3-1-7b-run6

CS6810-E01-S26

g1_top8_diverse_10000_32b_step455__Qwen3-32B

Qwen3-4B-Instruct-2507-heretic

Qwen1.5-7B-Chat

g1_top8_85k_gptlong_swegym_32b_step1800__Qwen3-32B

seta-env-final-filtered-560-epoch2

Qwen3-1.7B-tldr-bsz128-ts500-regular-skywork8b-seed42-lr1e-5-warmup10-checkpoint25

rhythm-env-meta-trained-iter5

DL_NLP_HW_6

g1_top8_diverse_100000_32b_step2700__Qwen3-32B

tinyllama-finetune

qwen3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.45-s_star-0.85

qwen_4b_RL

Qwen3-1.7B-tldr-bsz128-ts500-regularsqrt2-skywork8b-seed42-lr1e-6-warmup10-checkpoint325

qwen3-8b-rmu-baseline

qwen2.5-7b-instruct-gsm8k-sn-tuned-lr5e-5