Rohit Yelukati Mahendra PRO

YMRohit

·

AI & ML interests

None yet

Recent Activity

updated a collection about 8 hours ago

ICML 2026 reproductions — d3LLM & MemoryBench (Claude)

updated a Space about 8 hours ago

YMRohit/icml2026-27364-kernel-bounds-logbook

published a Space about 8 hours ago

YMRohit/icml2026-27364-kernel-bounds-logbook

View all activity

Organizations

YMRohit 's Spaces 26

Repro - On Uniform Error Bounds for Kernel Regression under Non-Gaussian Noise

Explore and edit a collaborative research logbook

Icml27364 Kernelbounds

Display experiment tracking results in an interactive view

Repro - Softmax as Linear Attention in the Large-Prompt Regime: a Measure-based Perspective

Organize research notes and sync with an AI coding agent

Icml5886 Softmaxlinear

Show a visual timeline of your program's I/O activity

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

Browse experiment logs and sync findings with an AI agent

Icml31042 Adagradheavy

Show an interactive tracking dashboard for your data

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

Explore research logbook and collaborate with an AI agent

Icml27119 Noisypower

Display an interactive tracking dashboard

Repro - Fast and Scalable Analytical Diffusion (GoldDiff)

Explore and collaborate on GoldDiff experiment logs

Icml64125 Golddiff

Display tracking data visualization

Repro - FOAM: Blocked State Folding for Memory-Efficient LLM Training

Explore experiment logs and collaborate with an AI agent

Repro - MemoryBench: A Benchmark for Memory and Continual Learning in LLM Systems

Explore benchmark logs and sync findings with an AI agent

Icml64918 Memorybench

Show interactive tracking dashboard

Reproducing Maximum Likelihood Reinforcement Learning (ICML 2026 #65332)

Browse experiment logbook and collaborate with a coding agent

Repro - Optimal Unconstrained Self-Distillation in Ridge Regression

Explore and collaborate on project logbooks online

Repro - d3LLM: Ultra-Fast Diffusion LLM using Pseudo-Trajectory Distillation

Browse and share experiment logs with a coding agent

Repro - Efficiently Training Time-to-First-Spike SNNs from Scratch

Explore and sync experiment logs with an AI coding agent

Icml61269 D3llm

Repro - Combinatorial Sparse PCA Beyond the Spiked Identity Model

Explore and organize your research logbook

Repro - Scaling Laws for Precision in High-Dimensional Linear Regression

Explore research logbook and sync with coding agent

Repro - Towards Understanding Adam Convergence on Highly Degenerate Polynomials

Explore experiment logs and sync with your coding agent

Icml22249 Release Artifacts

Display a visual summary of your program's I/O activity

Icml20531 Release Artifacts

Display interactive tracking dashboard

Icml20531 Adam Degenerate Metrics

Show your tracking dashboard in a single view