Dinesh Jinjala

DineshAI

2 1

AI & ML interests

None yet

Recent Activity

new activity about 3 hours ago

ICML-2026-agent-repro/certificate-generator:While Generating Certificate I'm getting error

published a bucket 2 days ago

DineshAI/repro-grpo-verifiable-rewards-bucket-328

published a bucket 2 days ago

DineshAI/repro-saqnn-universal-approximator-bucket-248

View all activity

Organizations

DineshAI 's Spaces 299

Repro - Joint ARD Sparsification

✂

Browse and collaborate on a project logbook via web interface

Repro - An Algebraic View of RNN Expressivity

🎯

Organize research notes and collaborate with an AI agent

Repro - SAQNN Universal Approximation

🎯

Explore experiment logs and sync findings with an AI agent

Repro - GRPO Verifiable Rewards

🎯

View and sync a collaborative logbook with your coding agent

Reproduction: Row-Stochastic Matrices Can Provably Outperform Doubly Stochastic Matrices

🎯

Collaborate on a logbook with your coding agent

Reproduction: MIRA: A Score for Conditional Distribution Accuracy and Model Comparison

🎯

Explore and collaborate on a research logbook online

Repro - Provably Data-driven Multiple Hyper-parameter Tuning

📐

Track and collaborate on hyperparameter tuning experiments

Repro - Bridging the Gap Between Average and Discounted TD Learning

🎯

View and sync experiment logs with your coding agent

Repro - Language Generation with Replay

🎯

Explore AI session logs and sync notes with an agent

Repro - Generalizing Stochastic Smoothing for Differentiation and Gradient Estimation

🎯

Collaborate on a research logbook with an AI coding agent

Repro - Convergence Analysis of the Lion Optimizer

🎯

Explore experiment logs and collaborate with an AI agent

Repro - Minibatch Optimal Transport in Discrete Flow Matching

🎯

Explore and sync experiment logs with your coding agent

Repro - Conditional Coverage Diagnostics for Conformal Prediction

🎯

Explore conditional coverage diagnostics and sync with an AI agent

Repro - Provable Benefits of RLVR over SFT for Reasoning Models

🎯

Browse and sync research logbook with an AI agent

Repro - Routing by Reaching

🎯

View and manage project logbook with AI collaboration

Repro - CARE: Confounder-Aware Aggregation for Reliable LLM Evaluation

🎯

Collaborate on LLM evaluation logs with a coding agent

Repro - Sharp Input-Output Analysis (xrUgA8PrNN)

🎯

Explore and manage your project logbook with AI assistance

Repro - Variational Entropic Optimal Transport

🎯

Explore project logs and collaborate with an AI agent

Repro - l_inf Distribution Estimation (wwqrH4mwGq)

🎯

Explore and sync experiment logs with an AI coding agent

Beyond Euclidean Summaries reproduction

🎯

Explore and manage project logs with collaborative AI assistance

Reproduction: Near-Optimal Regret for KL-Regularized Multi-Armed Bandits

🎯

Log research findings and collaborate with an AI agent

Reproduction: Diffusion Models Are Statistically Optimal for Learning Low-Dimensional Multi-Modal Distributions

🎯

Explore code, traces, and workspace in an interactive logbook

Repro - Global Convergence of Adaptive Sensing for Principal Eigenvector Estimation

🎯