arxiv:2609.39050
Muhammad Khalifa
mkhalifa
AI & ML interests
natural language genration, reinforcement learning
Recent Activity
authored a paper 2 days ago
Covert Assistance: Helpful LLM Agents Evade Oversight in Multi-Agent Systems updated a dataset 12 days ago
mkhalifa/dspy-studybench-results-20260925 published a dataset 12 days ago
mkhalifa/dspy-studybench-results-20260925Organizations
models 21
mkhalifa/flan-t5-large-gsm8k
Text Generation • Updated • 18
mkhalifa/flan-t5-large-svamp
Text Generation • Updated • 80
mkhalifa/flan-t5-large-mathqa
Text Generation • Updated • 16
mkhalifa/ThinkPRM-gptoss-20B
Updated • 15
mkhalifa/r1_14b_discriminative_prm
Text Generation • 15B • Updated • 15
mkhalifa/r1_14b_longthought-1K
Text Generation • 15B • Updated • 15
mkhalifa/r1-1.5b-longthought-outcome-matching
Text Generation • 2B • Updated • 17
mkhalifa/r1-1.5b-longthought-1K
Text Generation • 2B • Updated • 12
mkhalifa/r1_14b_longthought-1K-outcome-only
Text Generation • 15B • Updated • 16
mkhalifa/r1-1.5b-longthought-v2
Text Generation • 2B • Updated • 12
datasets 19
mkhalifa/dspy-studybench-results-20260925
Updated • 279
mkhalifa/agent
Updated • 5
mkhalifa/gpqa-diamond-physics
Viewer • Updated • 86 • 133
mkhalifa/short-to-long-5K
Viewer • Updated • 5k • 14
mkhalifa/CoGEX
Viewer • Updated • 51.8k • 34
mkhalifa/llama-3.1-8b-instruct-math-trajectories-64-sample-per-problem
Viewer • Updated • 736k • 25
mkhalifa/llama-3.1-8b-instruct-math-trajectories-48-sample-per-problem
Viewer • Updated • 552k • 26
mkhalifa/llama-3.1-8b-instruct-math-trajectories-32-sample-per-problem
Viewer • Updated • 368k • 14
mkhalifa/llama-3.1-8b-instruct-math-trajectories-16-sample-per-problem
Viewer • Updated • 184k • 24
mkhalifa/llama-3.1-8b-instruct-math-trajectories-8-sample-per-problem
Viewer • Updated • 92k • 27