arxiv:2510.03777
Divij Handa
Divij
·
AI & ML interests
None yet
Recent Activity
authored a paper about 19 hours ago
GuidedSampling: Steering LLMs Towards Diverse Candidate Solutions at Inference-Time updated a dataset about 22 hours ago
Divij/RF_ScaleQuest published a dataset about 22 hours ago
Divij/RF_ScaleQuestOrganizations
models 25
Divij/llama-3.2-3b-sft-llama-star-openinstruct
Updated • 16
Divij/llama-3.2-3b-sft-llama-star
Text Generation • 175k • Updated • 365
Divij/Qwen2.5-3B-Instruct-sft-with-thoughts
Text Generation • 3B • Updated • 265
Divij/Qwen2.5-3B-Instruct-sft-without-thoughts
Text Generation • 3B • Updated • 242
Divij/Llama-3.2-3B-Instruct-sft-with-thoughts
Text Generation • 4B • Updated • 269
Divij/Llama-3.2-3B-Instruct-sft-without-thoughts
Text Generation • 4B • Updated • 248
Divij/Qwen3.5-4B-SFT-decompiler-O0-full
Text Generation • Updated • 791 • 3
Divij/Llama-3.2-3B-SFT-backdoors
3B • Updated • 3
Divij/aswin_llama_star
3B • Updated • 3
Divij/llama-3.2-3b-cognitive-behaviors-with-thoughts-epoch5
Text Generation • 3B • Updated • 4