arxiv:2606.04351
Manan Suri
MananSuri27
AI & ML interests
None yet
Organizations
models 24
MananSuri27/Frames2LoRA-SmolVLM-ckpts
Updated • 2
MananSuri27/gemma4-31b-full-mini-swe-secbench
Image-Text-to-Text • 5B • Updated • 6
MananSuri27/video2lora-smolvlm2-500m-video-best-ce
Updated • 1
MananSuri27/video2lora-smolvlm2-2.2b-best-ce
Updated • 1
MananSuri27/Qwen2.5-7B-Instruct-GRPO-NoMult-V2-ARGUS-20250923_195541
Text Generation • 8B • Updated • 6
MananSuri27/Qwen2.5-7B-Instruct-GRPO-Certainty-V2-ARGUS-20250923_195405
Text Generation • 8B • Updated • 10
MananSuri27/Qwen2.5-3B-Instruct-GRPO-Certainty-V2-ARGUS-20250923_195755
Text Generation • 3B • Updated • 7
MananSuri27/Qwen2.5-3B-Instruct-GRPO-NoMult-V2-ARGUS-20250923_195941
Text Generation • 3B • Updated • 6
MananSuri27/Qwen2.5-7B-Instruct-GRPO-NoMult-ARGUS-20250922_200131
Text Generation • 8B • Updated • 4
MananSuri27/Qwen2.5-7B-Instruct-GRPO-Uncertainty-ARGUS-20250922_193217
Text Generation • 8B • Updated • 5
datasets 72
MananSuri27/vuljector-extracted-vulnerabilities
Updated • 21
MananSuri27/agent2lora-p2i-v1-response-level-gemma2_2b_l40s_gc2048_clean_hf
Updated • 9
MananSuri27/agent2lora-p2i-v1-response-level-qwen25_1p5b_l40s_gc2048_clean_hf
Updated • 9
MananSuri27/agent2lora-p2i-v1-response-level-gemma2-2b-clean-hf-ckpts
Updated • 11
MananSuri27/agent2lora-p2i-v1-response-level-qwen25-1p5b-clean-hf-ckpts
Updated • 10
MananSuri27/p2i-v1-response-level-agent2lora
Viewer • Updated • 355k • 22
MananSuri27/agent-to-lora-train-outputs-dump
Updated • 55
MananSuri27/vuljector-secbench-trajectories
Preview • Updated • 32
MananSuri27/when2call-test-with-schema
Viewer • Updated • 300 • 13
MananSuri27/when2call-grpo-argus-v2-certainty-only
Viewer • Updated • 9k • 17