Filbert Aurelian

bertfil

2 1

·

AI & ML interests

None yet

Recent Activity

updated a Space 17 days ago

bertfil/JO0IsGJg16

published a Space 17 days ago

bertfil/JO0IsGJg16

updated a Space 17 days ago

bertfil/0xtMUL0eiF

View all activity

Organizations

bertfil 's Spaces 62

Repro - TokSuite: Measuring the Impact of Tokenizer Choice on Language Model Behavior

Explore and share tokenizer experiment logs

Repro - Benchmarking at the Edge of Comprehension

Explore benchmark logs and sync findings with an agent

Repro - Focus and Dilution: The Multi-stage Learning Process of Attention

Collaborate with an AI agent to sync findings in a logbook

Repro - On the Convergence Rate of LoRA Gradient Descent

Explore and sync research logbook with your coding agent

Repro - AI Engram: In Search of Memory Traces in Artificial Intelligence

Explore and edit AI research logbook with agent collaboration

Repro - On the Identifiability of Poisson Branching Structural Causal Model Under Latent Confounding

Explore and collaborate on a research logbook

Repro - Optimal Decision-Making Based on Prediction Sets

View and sync project logs with an AI coding agent

Repro - A Random Matrix Perspective on the Consistency of Diffusion Models

Track research findings in an interactive logbook

Repro - Training-Free Bayesian Filtering with Generative Emulators

Browse experiment logs and collaborate with coding agents

Repro - A Recursive Decomposition Framework for Causal Structure Learning in the Presence of Latent Variables

Explore research logbook and sync findings with an AI agent

Repro - Equivalence of Context and Parameter Updates in Modern Transformer Blocks

Explore research logbook and sync updates with an AI agent

Repro - $ au^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment

Track and share experiment logs with your coding agent

Repro - Prescriptive Scaling Reveals the Evolution of Language Model Capabilities

Explore and collaborate on a research logbook with your coding agent

Repro - Is Your LLM Overcharging You? Tokenization, Transparency, and Incentives

Analyze LLM prompts to reveal token usage and cost