Sarim-Hash/advsim2real-stage1-curr1epoch-exec2epochs-iter3-nprop150
Updated
🔄 In a Training Loop
SARIM HASHMI
Sarim-Hash
P(doom) Rejects the premise
AI & ML interests
None yet
Recent Activity
authored a paper 2 days ago
AdvSim2Real : Training Web Agents Against Adaptive Prompt Injection in a Web World Model submitted a paper 2 days ago
AdvSim2Real : Training Web Agents Against Adaptive Prompt Injection in a Web World ModelOrganizations
Sarim-Hash/advsim2real-dpo-curr1epoch-adv1epoch-exec2epochs-iter3-nprop150
Updated
Sarim-Hash/advsim2real-sft-curr1epoch-adv1epoch-exec2epochs-iter3-nprop150
Updated
Sarim-Hash/advsim2real-stage2-with-stage1-adv1epoch-exec2epochs-iter3-nprop150
Updated
Sarim-Hash/PerSuE-Evidence-Qwen3.5-4B
Updated • 1
Sarim-Hash/advsim2real-stage2-ablation-adv1epoch-exec2epochs-iter3-nprop150
Updated
Sarim-Hash/web-coevo-stage1-handoff
Reinforcement Learning • Updated
Sarim-Hash/web-coevo-adapters
Updated
Sarim-Hash/qwen35-4b-winner-v2-dpo-strict
Image-Text-to-Text • 5B • Updated • 13
Sarim-Hash/qwen35-4b-winner-v2-dpo
Image-Text-to-Text • 5B • Updated • 13
Sarim-Hash/qwen35-4b-sft-v2
Image-Text-to-Text • 5B • Updated • 9
Sarim-Hash/qwen35-4b-dpo-grove-r
Image-Text-to-Text • 5B • Updated • 19
Sarim-Hash/qwen35-4b-dpo-grove-p
Image-Text-to-Text • 5B • Updated • 18
Sarim-Hash/wm_adapters
Updated
Sarim-Hash/project-nils-run-a
Updated
Sarim-Hash/project-nils-run-c
5B • Updated • 5
Sarim-Hash/project-nils-run-d
5B • Updated • 5
Sarim-Hash/project-nils-run-b
Updated
Sarim-Hash/browseragent-adversary-coevo
Updated
Sarim-Hash/Qwen3.5-4B-Winner-SFT-Epochs
Text Generation • Updated
Sarim-Hash/browseragent-rft-web-coevo-executors
Reinforcement Learning • Updated
Sarim-Hash/Qwen3-14B-sandbagging
Text Generation • 425k • Updated • 13
Sarim-Hash/Qwen3-8B-sandbagging
Updated
Sarim-Hash/eba-qwen2p5-72b-adapter
Updated • 11
Sarim-Hash/qwen-235-v1
Updated • 21
Sarim-Hash/infra_exp_shrad_2
Text Generation • 2B • Updated • 14
Sarim-Hash/infra_exp_shrad_3
Text Generation • 2B • Updated • 16
Sarim-Hash/infra_exp_shrad_1
Text Generation • 2B • Updated • 17
Sarim-Hash/infra_exp_shrad_0
Text Generation • 2B • Updated • 21
Sarim-Hash/infra_exp_shrad_4
Text Generation • 2B • Updated • 16