Josh

Joshi2312

AI & ML interests

Voice Generation (TTS, cloning) Video gen All gen ai Image Models Finetuning (voice, lora, Checkpoints) ComfyUI, A1111, ss Hit me Up @ hf.starlit941 at passinbox.com

Recent Activity

new activity 10 days ago

ICML-2026-agent-repro/challenge:How to use token credit or claude

updated a Space 10 days ago

Joshi2312/repro-momentum-sgd-distribution-drift

updated a Space 10 days ago

Joshi2312/repro-tensor-schatten-dual-sparsity

View all activity

Organizations

Joshi2312 's Spaces 20

Repro - On the Provable Suboptimality of Momentum SGD in Nonstationary Stochastic Optimization

🎯

Explore and edit research logbook with AI collaboration

Repro - Refining Dual Spectral Sparsity in Transformed Tensor Singular Values

🎯

Explore and share a project logbook with AI collaboration

Repro - Understanding Catastrophic Forgetting In LoRA via Mean-Field Attention Dynamics

🎯

Explore and sync research findings with an AI agent

Repro - Estimation of Treatment Effects Under Nonstationarity via the Truncated Policy Gradient Estimator

🎯

Explore experiment logs and collaborate with a coding agent

Repro - Learning in Structured Stackelberg Games

🎯

Collaborate on a shared logbook with your coding agent

Repro - Can Adaptive Gradient Methods Converge under Heavy-Tailed Noise? A Case Study of AdaGrad

🎯

Explore and collaborate on project logbooks

Repro - A Random Matrix Theory of Masked Self-Supervised Regression

🎯

Track and sync research findings with an AI coding agent

Repro - What Makes a Strong Model? Unified Spectral Analysis of Knowledge Transfer

🎯

Explore research logbook and collaborate with coding agents

Repro - Operator Splitting with Hamilton-Jacobi-based Proximals

🎯

Explore and sync research logbook with an AI coding agent

Repro - Length Generalization Bounds for Transformers (C-RASP)

🎯

Explore and collaborate on experiment logbooks online

Repro - Why Self-Training Helps and Hurts: Denoising vs. Signal Forgetting

🎯

Browse and collaborate on research logbooks with AI agents

Repro - High-Dimensional Learning Dynamics of Quantized Models with STE

🎯

View and organize experiment logs with AI collaboration

Repro - Do-Calculus Reasoning via Derivation Graphs

🔀

Create and track do‑calculus derivation graphs

Repro - Tighter Regret Lower Bound for GP Bandits with SE Kernel in Hypersphere (arXiv:2602.17940)

🎯

Explore and collaborate on research logbooks online

Repro - On Structured State-Space Duality (arXiv 2510.04944)

🎯

Explore a research logbook and sync it with your coding agent

Repro - Improved Analysis of the Accelerated Noisy Power Method with Applications to Decentralized PCA

🎯

Browse and collaborate on a structured research logbook

Repro - Non-Uniform Noise-to-Signal Ratio in the REINFORCE Policy-Gradient Estimator

🎯

Collaborate on a shared research logbook with an AI agent

Repro - Rotary Position Encodings for Graphs

🎯

Explore and sync research notes with your coding agent

Repro - To Grok Grokking: Provable Grokking in Ridge Regression

🎯

Explore and share a research logbook with an AI agent

Repro - A Random Matrix Theory Perspective on the Consistency of Diffusion Models

🎯

Explore and sync research logbook with an AI agent