Crusadersk/icml26-pca-probability-measures-repro-artifacts
733 kB
Sahil Kadadekar
Crusadersk
·
AI & ML interests
LLM inference, quantization, refusal robustness, model evaluation, GPU serving, batching effects, post-training, MLOps, AI safety. Reports: https://chimeraforge.vercel.app/reports
Recent Activity
updated a Space 3 days ago
Crusadersk/icml26-row-stochastic-decentralized-repro published a Space 3 days ago
Crusadersk/icml26-row-stochastic-decentralized-repro updated a Space 3 days ago
Crusadersk/icml26-llm-as-judge-scaling-reproOrganizations
buckets 26
Crusadersk/icml26-heavytail-mdp-bobw-repro-artifacts
206 kB
Crusadersk/icml26-fullbatch-single-index-repro-artifacts
200 kB
Crusadersk/icml26-ftpl-decoupled-bandits-repro-artifacts
196 kB
Crusadersk/icml26-catnat-beyond-softmax-repro-artifacts
229 kB
Crusadersk/icml26-anytime-valid-delayed-repro-artifacts
189 kB
Articles 1
Article
1
Quantization is the safety blind spot of local AI — so I built the screen for it
spaces 48
Running
Repro - Row-Stochastic Matrices Can Provably Outperform Doubly Stochastic Matrices in Decentralized Learning
🎯
Explore research logbooks and sync findings with an AI agent
Running
Repro - Demystifying LLM-as-a-Judge: Inference-Time Scaling
🎯
Collaborate on a shared experiment logbook with an AI agent
Running
Repro - Rex: A Family of Reversible Exponential (Stochastic) Runge-Kutta Solvers
🔁
Track and collaborate on experiment logs with an AI agent
Running
Repro - Maximum Likelihood Reinforcement Learning
🎲
Explore RL experiment logs and sync with your coding agent
Running
Repro - A Random Matrix Perspective on the Consistency of Diffusion Models
🎲
Explore a research logbook and collaborate with an AI agent
Running
Repro - Diffusion Bridge or Flow Matching? A Unifying Framework
🌉
Browse an interactive research logbook on diffusion models
models 16
Crusadersk/gpt2-100m
Text Generation • 96.1M • Updated • 523
Crusadersk/gpt2-50m
Text Generation • 51.5M • Updated • 503
Crusadersk/gpt2-25m
Text Generation • 25M • Updated • 501
Crusadersk/tiny-gpt2
Text Generation • Updated • 400
Crusadersk/qwen2.5-7b-awq-4bit
Text Generation • 2B • Updated • 22
Crusadersk/qwen2.5-7b-gptq-4bit
Text Generation • 8B • Updated • 21
Crusadersk/mistral-7b-awq-4bit
Text Generation • 7B • Updated • 83
Crusadersk/mistral-7b-gptq-4bit
Text Generation • 7B • Updated • 22
Crusadersk/qwen2.5-1.5b-gptq-4bit
Text Generation • 2B • Updated • 17
Crusadersk/qwen2.5-1.5b-awq-4bit
Text Generation • 2B • Updated • 57