Geeta

gchauhan

5 2

·

AI & ML interests

None yet

Recent Activity

updated a bucket 4 days ago

sair-distillation/eq2-arya-wiz

published a bucket 4 days ago

sair-distillation/eq2-arya-wiz

updated a bucket 4 days ago

gemma-challenge/gemma-gemma-rumi

View all activity

Organizations

updated a bucket 4 days ago

sair-distillation/eq2-arya-wiz

published a bucket 4 days ago

sair-distillation/eq2-arya-wiz

updated a bucket 4 days ago

gemma-challenge/gemma-gemma-rumi

published a bucket 5 days ago

gemma-challenge/gemma-gemma-rumi

updated a Space 8 days ago

Reproduction: Closing the Loop: Universal Repository Representation with RPG-Encoder

Explore code, traces, and workspace in an interactive logbook

published a Space 8 days ago

Reproduction: Closing the Loop: Universal Repository Representation with RPG-Encoder

Explore code, traces, and workspace in an interactive logbook

upvoted an article 14 days ago

Article

Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incident

+2

hlarcher, XciD, raphael-gl, chris-rannou

•

16 days ago

• 460

updated a Space 15 days ago

Reproduction: EGG: An Expert-Guided Agent Framework for Kernel Generation

Explore project logs, traces, and workspace with AI collaboration

published a Space 15 days ago

Reproduction: EGG: An Expert-Guided Agent Framework for Kernel Generation

Explore project logs, traces, and workspace with AI collaboration

updated a Space 15 days ago

Reproduction: A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustness

Explore project logs and invite AI agents to collaborate

published a Space 15 days ago

Reproduction: A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustness

Explore project logs and invite AI agents to collaborate

updated 2 Spaces 15 days ago

Reproduction: Dimension-Independent Convergence of Underdamped Langevin Monte Carlo in KL Divergence

Explore code logs, traces, and workspace in a collaborative UI

Reproduction: Theoretical Perspectives on Data Quality and Synergistic Effects in Pre- and Post-Training Reasoning Models

View and manage code logs, traces, and workspace

published a bucket 15 days ago

gchauhan/repro-reward-shaping-for-inference-time-alignment-a-stackelberg-game-perspective-bucket

updated 2 Spaces 16 days ago

Reproduction: A Fine-Grained Understanding of Uniform Convergence for Halfspaces

Explore and manage project logs, code, and traces

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

Explore research logbook with code, traces, and workspace

published a Space 16 days ago

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

Explore research logbook with code, traces, and workspace

updated a Space 16 days ago

Reproduction: Reward Shaping for (Inference-Time) Alignment: A Stackelberg Game Perspective

Explore project logs and collaborate with your coding agent

published a Space 16 days ago

Reproduction: Reward Shaping for (Inference-Time) Alignment: A Stackelberg Game Perspective

Explore project logs and collaborate with your coding agent

updated a Space 16 days ago

Reproduction: HiPPO Zoo — Explicit Memory Mechanisms for Interpretable State Space Models

Explore project logs, code, and traces in a web logbook