Sahil Kadadekar

Crusadersk

https://chimeraforge.vercel.app/reports

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 model 2 days ago

Crusadersk/qwen2.5-1.5b-medmcqa-drgrpo-lora

published a model 2 days ago

Crusadersk/qwen2.5-1.5b-medmcqa-drgrpo-lora

updated a model 10 days ago

Crusadersk/qwen2.5-1.5b-awq-4bit

View all activity

Organizations

Crusadersk 's Spaces 48

Repro - Hierarchical Successor Representation for Robust Transfer

🗺

Explore and manage hierarchical logbook entries

Repro - Finite and Corruption-Robust Regret Bounds in Online Inverse Linear Optimization under M-Convex Action Sets

📉

Collaborate on a research logbook with an AI coding agent

Repro - Minimax Optimal Strategy for Delayed Observations in Online Reinforcement Learning

🎯

Explore and collaborate on experiment logbooks

Repro - General Synthetic-Powered Inference

🎯

Collaborate with a coding agent on a synchronized logbook

Repro - Best-of-Both-Worlds for Heavy-Tailed Markov Decision Processes

🎯

Explore experiment logs and collaborate with an AI agent

Repro - Model Fusion via Retrofitting

🎯

Explore model fusion logs and sync with your coding agent

Repro - Prior Diffusiveness and Regret in the Linear-Gaussian Bandit

🎯

Explore experiment logbooks and sync findings with an AI agent

Repro - Causal Modeling of Selection in Evolution

🧬

Collaborate with an AI agent to manage your research logbook

Repro - Fixed Budget is No Harder Than Fixed Confidence in Best-Arm Identification up to Logarithmic Factors

🎯

Explore research logbooks and sync with your coding agent

Repro - Accelerated and Stable Convergence with Anchored Generalized Optimistic Method

🎯

Explore project logs and sync findings with an AI agent

Repro - Full-Batch Gradient Descent Outperforms One-Pass SGD: Sample Complexity Separation in Single-Index Learning

🎯

Browse and share research logbooks online

Repro - Design-Based Anytime-Valid Inference for Randomized Experiments with Delayed Outcomes and Staggered Entry

🎯

Explore and share experiment logs with an AI collaborator

Repro - Improved Convergence Analysis of Topology Dependence in Decentralized SGD

🎯

Explore and share a research logbook with an AI agent

Repro - Quadratically Regularized Optimal Transport: Localization Bounds and Affine Case Analysis

🎯

Explore research logbook and sync findings with an AI agent

Repro - Keep Everyone Happy: Online Fair Division of Numerous Items with Few Copies

🎯

Collaborate on a shared logbook with an AI coding agent

Repro - Towards Understanding Adam Convergence on Highly Degenerate Polynomials

🎯

Explore and collaborate on a research logbook online

Repro - Characterization of Gaussian Universality Breakdown in High-Dimensional Empirical Risk Minimization

🎯

Explore and edit research logbooks online

Repro - Estimating Continuous Treatment Effects with Two-Stage Kernel Ridge Regression

🎯

Explore experiment logs and sync findings with an AI agent

Repro - Stochastic Linear Bandits with Parameter Noise

🎯

Explore experiment logs and sync findings with a coding agent

Repro - Follow-the-Perturbed-Leader for Decoupled Bandits: Best-of-Both-Worlds and Practicality

🎯

Explore and share experiment logs in a collaborative web logbook

Repro - On Regret Bounds of Thompson Sampling for Bayesian Optimization

🎯

Browse experiment logs and collaborate with an AI agent

Repro - Online Packet Scheduling with Deadlines and Learning

🎯

Schedule packets online with deadlines and AI assistance

Repro - To Grok Grokking: Provable Grokking in Ridge Regression

🎯

Explore research logbook and sync with AI agent

Repro - Procedural Generation Of Algorithm Discovery Tasks in Machine Learning

🎯

Log and collaborate on ML algorithm discovery tasks