Sugutt/repro-minimum-distance-summaries-artifacts
5.32 MB
Emmanuel Sugutt
Sugutt
AI & ML interests
Reinforcement learning
Transformer models
Recent Activity
updated a bucket 28 days ago
Sugutt/repro-minimum-distance-summaries-artifacts updated a bucket 28 days ago
Sugutt/mds-gaussian-reproduction-bucket-2 published a bucket 28 days ago
Sugutt/mds-gaussian-reproduction-bucket-2Organizations
Audited reproduction artifacts for OpenReview mI3K0e1KsN: public logbook, code/data bundle, GPU results, paper, official benchmark, and model.
-
SphereLab/FormalMATH-Lite
Viewer • Updated • 425 • 51 • 2 -
deepseek-ai/DeepSeek-Prover-V2-7B
7B • Updated • 141k • 148 -
Sugutt/editable-sketch-repro-results-final
Viewer • Updated • 1 • 32 -
Repro - Editable Proof Sketch for Automated Theorem Proving
🎯Create and edit proof sketches for automated theorem proving
-
DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization
Paper • 2508.14460 • Published • 86 -
MEML-GRPO: Heterogeneous Multi-Expert Mutual Learning for RLVR Advancement
Paper • 2508.09670 • Published -
URPO: A Unified Reward & Policy Optimization Framework for Large Language Models
Paper • 2507.17515 • Published • 2
Audited reproduction artifacts for OpenReview mI3K0e1KsN: public logbook, code/data bundle, GPU results, paper, official benchmark, and model.
-
SphereLab/FormalMATH-Lite
Viewer • Updated • 425 • 51 • 2 -
deepseek-ai/DeepSeek-Prover-V2-7B
7B • Updated • 141k • 148 -
Sugutt/editable-sketch-repro-results-final
Viewer • Updated • 1 • 32 -
Repro - Editable Proof Sketch for Automated Theorem Proving
🎯Create and edit proof sketches for automated theorem proving
-
DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization
Paper • 2508.14460 • Published • 86 -
MEML-GRPO: Heterogeneous Multi-Expert Mutual Learning for RLVR Advancement
Paper • 2508.09670 • Published -
URPO: A Unified Reward & Policy Optimization Framework for Large Language Models
Paper • 2507.17515 • Published • 2
spaces 5
Running
Repro - Minimum Distance Summaries for Robust Neural Posterior Estimation
🎯
Create and share compact experiment logbooks for AI agents
Running
Repro - Editable Proof Sketch for Automated Theorem Proving
🎯
Create and edit proof sketches for automated theorem proving
Running
Repro - Avoid What You Know: Divergent Trajectory Balance for GFlowNets
🎯
Collaborate with an AI agent to manage a shared logbook
Sleeping
Agents
Kln Whisper V3 Turbo
💬
Transcribe Kalenjin speech to text in your browser
Paused
Agents
Mistralai Mixtral 8x7B Instruct V0.1
🌖
models 9
Sugutt/Kalenjin-qwen2.5-7B
Updated
Sugutt/whisper-v3-kalenjin-turbo
Automatic Speech Recognition • Updated • 7 • 1
Sugutt/whisper-kalenjin-small-revised
0.2B • Updated • 7
Sugutt/finmap-expense-cat-model
0.1B • Updated • 7
Sugutt/finbert-expense-categorization
Text Classification • 0.1B • Updated • 14 • 1
Sugutt/Taxi-V3
Reinforcement Learning • Updated
Sugutt/q-FrozenLake-v1-4x4-noSlippery
Reinforcement Learning • Updated
Sugutt/ppo-Huggy
Reinforcement Learning • Updated • 91
Sugutt/lunarlander
Reinforcement Learning • Updated • 1