Jansen Tang

ai-sherpa

·

AI & ML interests

None yet

Recent Activity

updated a Space 19 minutes ago

ai-sherpa/repro-reward-free-alignment-conflicting-objectives

updated a dataset 20 minutes ago

ai-sherpa/raco-repro-bundle

updated a Space 30 minutes ago

ai-sherpa/epibsl-social-learning-repro

View all activity

Organizations

ai-sherpa 's Spaces 308

Reproducing "Reward-free Alignment for Conflicting Objectives" (RACO)

Explore and sync research logbooks with an AI coding agent

Repro - Distributed Online Convex Optimization with Efficient Communication (compressed)

View and sync experiment logs with a coding agent

Repro - MedMosaic

Track and share research findings with an AI‑assisted logbook

Repro — Bandit Social Learning with Exploration Episodes (EpiBSL)

Repro — Fixed Budget is No Harder Than Fixed Confidence in Best-Arm Identification up to Logarithmic Factors

Explore and collaborate on experiment logs with an AI agent

gd-large-step-symmetry-restoration

Collaborate with an AI agent to view and update project logbook

Repro — New Bounds for Kernel Sums via Fast Spherical Embeddings

Create and explore a collaborative research logbook

Repro - On the Convergence Rate of LoRA Gradient Descent

Explore logs and let an AI agent add findings

Repro — Solving Positive Linear Programs with Differential Privacy

Explore experiment logs and collaborate with a coding agent

Repro - VLM-RobustBench

View and share project logbook with an AI agent

Repro - On the Power of Source Screening for Learning Shared Feature Extractors

Browse and collaborate on project logs with an AI agent

Repro - Recursive Binding on a Budget: Subspace Carving in Order-p Tensor Memories

Collaborate with an AI agent using a shared logbook

Repro - Feature Resemblance: Towards a Theoretical Understanding of Analogical Reasoning in Transformers

Explore and edit research logbook with AI collaboration

Repro - R^2k is Theoretically Large Enough for Embedding-based Top-k Retrieval

Explore and edit logs while collaborating with a coding agent

Reproduction: Asymptotic Theory of Iterated Empirical Risk Minimization, with Applications to Active Learning

Explore and collaborate on a research logbook

Repro — CoopEval: Cooperation-Sustaining Mechanisms & LLM Agents in Social Dilemmas

Explore experiment logs and sync findings with an AI agent

Repro - MORE

View and sync your logbook with an AI coding agent

Repro -- Unfolding Generative Flows with Koopman Operators

Explore and collaborate on a research logbook with your AI agent

Repro - Hive: A Semantically Consistent Dataset for Data-Efficient Query-Based Universal Sound Separation

Explore and annotate the Hive sound‑separation dataset

Repro - Fine-Tuning Without Forgetting In-Context Learning

Track and share experiment notes with an AI agent

Repro - Bregman meets Levy: SMD under Heavy-Tailed Noise

Browse and share research logbook entries with an AI agent

Repro -- Interventional Processes For Causal Uncertainty Quantification (IMPspec)

Explore and edit experiment logbooks collaboratively

Repro - An Algebraic View of RNN Expressivity

Explore research logbook and sync with a coding agent

Repro - Decision Tree Learning on Product Spaces

Explore and track decision‑tree learning results