Srishti Saha PRO

Srishti280992

·

AI & ML interests

None yet

Recent Activity

updated a bucket about 7 hours ago

ICML-2026-agent-repro/repro-bridging-the-gap-between-average-and-discounted-td-learning-bucket

published a bucket about 7 hours ago

ICML-2026-agent-repro/repro-bridging-the-gap-between-average-and-discounted-td-learning-bucket

updated a bucket about 7 hours ago

Srishti280992/repro-bridging-the-gap-between-average-and-discounted-td-learning-artifacts

View all activity

Organizations

Srishti280992 's Spaces 83

Reproduction: Beyond Temperature: Hyperfitting as a Late-Stage Geometric Expansion

Explore and edit experiment logs with an AI collaborator

Reproduction: Discovering Scaling Exponents with Physics-Informed Müntz-Szász Networks

Collaborate with an AI agent to view and update a logbook

Reproduction: A Tight Theory of Error Feedback Algorithms in Distributed Optimization

Explore research logbooks and collaborate with a coding agent

Reproduction: Belief Propagation Converges to Gaussian Distributions in Sparsely-Connected Factor Graphs

Explore and sync research logbooks with your coding agent

Reproduction: Exact Functional ANOVA Decomposition for Categorical Inputs Models

Explore and share experiment logs with an AI coding assistant

Reproduction: Causal Effect Identifiability in the Presence of Latent Confounders Without Auxiliary Variables

Explore and collaborate on a research logbook

Reproduction: Lower Bounds for Frank-Wolfe on Strongly Convex Sets

Browse research logbook and collaborate with an AI agent

Reproduction: Gecko: A Simulation Environment with Stateful Feedback for Refining Agent Tool Calls

View and sync simulation logs with your AI agent

Reproduction: When Shared Knowledge Hurts: Spectral Over-Accumulation in Model Merging

Explore and sync research logbook with an AI agent

Reproduction: LUCID: Attention with Preconditioned Representations

Browse experiment logs and sync findings with an AI agent

Repro - IAPO: Information-Aware Policy Optimization for Token-Efficient Reasoning

Collaborate with an AI agent to manage a token‑efficient logbook

Reproduction: Mixtures Closest To A Given Measure: A Semidefinite Programming Approach

Browse and edit a research logbook, then sync with an AI agent

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

Explore logbook and collaborate with AI agent

Reproduction: Exact and Approximate Algorithms for Polytree Learning

Explore and update a research logbook with AI assistance

Reproduction: Well-Posed KL-Regularized Control via Wasserstein and Kalman–Wasserstein KL Divergences

Explore experiment logbooks and sync with AI agents

Reproduction: Persistent Semantic Entities in Tool-Augmented LLM Systems

View and sync experiment logs with your coding agent

Reproduction: Optimal Anytime Algorithms for Online Convex Optimization with Adversarial Constraints

Browse research logbooks and collaborate with an agent

Reproduction: Quantifying LLM Attention-Head Stability: Implications for Circuit Universality

Explore and sync findings in a collaborative logbook

Reproduction: Revisiting ML Training under Fully Homomorphic Encryption: Convergence Guarantees, Differential Privacy, and Efficient Algorithms

Explore a collaborative research logbook online

Reproduction: Minimum Distance Summaries for Robust Neural Posterior Estimation

Explore and sync a research logbook with an AI assistant

Reproduction: Online Packet Scheduling with Deadlines and Learning

Explore experiment logs and sync notes with an AI agent

Repro - Data Provenance Auditing of Fine-Tuned Large Language Models with a Text-Preserving Technique

Explore audit logs of fine‑tuned language models

Repro - Escaping Whack-a-Mole: Optimizing Documentation as Repo-Specific Playbooks for Coding Agents

Create and share repo‑specific playbooks for coding agents

Repro - Learning Treatment Representations for Downstream Instrumental Variable Regression

Explore and sync experiment logs with an AI coding agent