Filbert Aurelian

bertfil

2 1

·

AI & ML interests

None yet

Recent Activity

updated a Space 23 days ago

bertfil/JO0IsGJg16

published a Space 23 days ago

bertfil/JO0IsGJg16

updated a Space 23 days ago

bertfil/0xtMUL0eiF

View all activity

Organizations

bertfil 's Spaces 62

Repro - Maximum Likelihood Reinforcement Learning

Collaborate with an AI agent to view and update your logbook

Repro - CoEvol-NO: State and Coordinate Co-Evolution with an Error-Driven Predictor-Corrector Paradigm for Neural Operator Transformer

Explore and share experiment logs with an AI collaborator

Repro - Are VLMs Seeing or Just Saying? Uncovering the Illusion of Visual Re-examination

Explore and collaborate on a research logbook

Repro - Less is Enough: Synthesizing Diverse Data in LLM Feature Space with Sparse Autoencoders

Explore and share experiment logs in an interactive web logbook

Repro - Expressivity-Efficiency Tradeoffs for Hybrid Sequence Models

Track experiments and sync notes with an AI coding agent

Repro - CLEAR: Context-Aware Learning with End-to-End Mask-Free Inference for Adaptive Video Subtitle Removal

View and collaborate on project logs with an AI agent

Repro - MV-FGAD: Towards Efficient and Effective Federated Graph Anomaly Detection via Multi-view Learning

Explore project logs and sync findings with a coding agent

Repro - Information Flow Reveals When to Trust Language Models

Collaborate with an AI agent to manage a shared logbook

Repro - The Flexibility Trap: Rethinking the Value of Arbitrary Order in Diffusion Language Models

Explore research logbook and sync with an AI coding agent

Repro - POET-X: Memory-efficient LLM Training by Scaling Orthogonal Transformation

Explore experiment logs and sync notes with your coding agent

Repro - DISCO: Mitigating Bias in Deep Learning with Conditional Distance Correlation

Explore and edit your research logbook with AI help

Repro - Towards Long-Horizon Interpretability: Efficient and Faithful Multi-Token Attribution for Reasoning LLMs

Track and share AI experiment logs with an agent

Repro - Characterizing, Evaluating, and Optimizing Complex Reasoning

Explore and sync experiment logs with your coding agent

Repro - Which Algorithms Can Graph Neural Networks Learn?

Browse and collaborate on a project logbook online

Repro - Quantifying Frontier LLM Capabilities for Container Sandbox Escape

Explore logs and collaborate with an AI coding agent

Repro - Mixtures Closest To A Given Measure: A Semidefinite Programming Approach

Explore research logbook and collaborate with an AI agent

Repro - Multimodal Nested Learning for Decoupled and Coordinated Optimization

View and collaborate on a project logbook with AI

Repro - Jailbreak Foundry: From Papers to Runnable Attacks for Reproducible Benchmarking

Explore and collaborate on research logbooks with AI agents

Repro - FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications

Explore and sync experiment logbook with an AI agent

Repro - Protein Fold Classification at Scale: Benchmarking and Pretraining

Explore protein classification experiment logs

Repro - Monitoring Monitorability

View and share a live logbook with your coding agent

Repro - Markov Chain Monte Carlo without Evaluating the Target: an Auxiliary Variable Approach

Explore and share experiment logs with an AI collaborator

Repro - CausalGame: Benchmarking Causal Thinking of LLM Agents in Games

Explore and sync game benchmark logs with your AI agent

Repro - ReViT: Rotational-equivariant Vision Transformers for Neural PDE Solvers

View and collaborate on research logbook with AI agent