Akash Jha PRO

AceVikings

2

·

AI & ML interests

None yet

Recent Activity

updated a Space about 4 hours ago

AceVikings/repro-how-many-different-outputs-can-a-transformer-generate

published a Space about 4 hours ago

AceVikings/repro-how-many-different-outputs-can-a-transformer-generate

updated a Space about 4 hours ago

AceVikings/repro-neural-low-discrepancy-sequences

View all activity

Organizations

AceVikings 's Spaces 61

Reproduction: Neural Low-Discrepancy Sequences

Explore and collaborate on research logbooks with an AI agent

Reproduction: Multi-View Causal Discovery without Non-Gaussianity: Identifiability and Algorithms

Explore and collaborate on a research logbook with an AI agent

Reproduction: Unbiased and Second-Order-Free Training for High-Dimensional PDEs

View and collaborate on a research logbook

Reproduction: A theory of learning data statistics in diffusion models, from easy to hard

Collaborate on a research logbook with an AI coding agent

Reproduction: On the Role of Batch Size in Stochastic Conditional Gradient Methods

Explore and share your project logbook with an AI assistant

Reproduction: How Many Different Outputs Can a Transformer Generate?

Explore and collaborate on a transformer experiment logbook

Reproduction: Exploiting weight-space symmetries for approximating curvature

Browse and sync research findings with an AI collaborator

Reproduction: Improved Scaling Laws via Weak-to-Strong Generalization in Random Features Ridge Regression

Browse and collaborate on a research logbook

Reproduction: Multivariate Distributional Reinforcement Learning Using Sliced Divergences

Collaborate on a research logbook with an AI agent

Reproduction: Tucker Attention: A generalization of approximate attention mechanisms

Browse and collaborate on a research logbook

Reproduction: Causal Discovery for Irregularly Time Series with Consistency Guarantees

Browse and edit research logbook with AI collaboration

Reproduction: Learning Human-Robot Collaboration via Heterogeneous-Agent Lyapunov Policy Optimization

Track and share research findings in a collaborative logbook

Reproduction: Parametrized Power-Iteration Clustering for Directed Graphs

Explore a project logbook and collaborate with an AI agent

Reproduction: Regime-Adaptive Bayesian Optimization via Dirichlet Process Mixtures of Gaussian Processes

Explore and sync research logbook with an AI coding agent

Reproduction: Skewness-Robust Causal Discovery in Location-Scale Noise Models

Collaborate on a research logbook with your coding agent

Reproduction: Bilevel Optimization over Saddle Points of Zero-Sum Markov Games

Explore and sync research logbook with your coding agent

Reproduction: Doubly Regularized Markov Decision Processes for Robust Reinforcement Learning

Browse experiment logs and sync with your AI agent

Reproduction: The Theory and Practice of MAP Inference over Non-Convex Constraints

Browse and collaborate on research logbooks online

Reproduction: Riemannian Dueling Optimization

Explore experiment logs and sync findings with an AI agent

Reproduction: All ERMs Can Fail in Stochastic Convex Optimization Lower Bounds in Linear Dimension

Explore and collaborate on research logbooks online

What Makes a Strong Model? A Unified Spectral Analysis of Knowledge Transfer over High-dimensional Linear Regression

Explore a research logbook and sync with an AI agent

No Free Lunch: Non-Asymptotic Analysis of Prediction-Powered Inference

View and sync findings with an AI coding agent

Understanding Generalization and Forgetting in In-Context Continual Learning

Explore and edit a research logbook, collaborate with an AI agent

Demystifying LLM-as-a-Judge: Analytically Tractable Model for Inference-Time Scaling

Explore and sync experiment logbook with an AI agent