Filbert Aurelian

bertfil

2 1

·

AI & ML interests

None yet

Recent Activity

updated a Space about 4 hours ago

bertfil/JO0IsGJg16

published a Space about 4 hours ago

bertfil/JO0IsGJg16

updated a Space about 4 hours ago

bertfil/0xtMUL0eiF

View all activity

Organizations

bertfil 's Spaces 62

Repro - XR-1: Towards Versatile Vision-Language-Action Models via Learning Unified Vision-Motion Representations

Collaborate with an AI agent to manage and sync experiment logbooks

Repro - Unsupervised Partner Design Enables Robust Ad-hoc Teamwork

Collaborate with your coding agent using a shared logbook

Repro - TG-RAG: A Retrieval-Augmented Framework for Reasoning Guidance in Specialized Domains

Explore and share a token‑efficient logbook for AI agents

Repro - Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual Learning

Explore project logbook and sync with a coding agent

Repro - From Feasible to Practical: Pareto-Optimal Synthesis Planning

Explore and share Pareto‑optimal synthesis planning logbook

Repro - Do We Need Adam? Surprisingly Strong and Sparse Reinforcement Learning with SGD in LLMs

Explore and edit research logbook with AI collaboration

Repro - SVRG and Beyond via Posterior Correction

Explore and share a collaborative project logbook online

Repro - MuonSSM: Orthogonalizing State Space Models for Sequence Modeling

Explore a research logbook and sync it with an agent

Repro - Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence

View and collaborate on a project logbook with an AI agent

Repro - FlashSinkhorn: IO-Aware Entropic Optimal Transport on GPU

Explore experiment logs and collaborate with an AI agent

Repro - DOUBT: Decoupled Object-level Understanding and Bridging via vMF-based Trustworthiness for Hallucination Detection in MLLMs

View and sync experiment logs with an AI coding agent

Repro - Agent0-VL: Exploring Self-Evolving Agent for Tool-Integrated Vision-Language Reasoning

Browse experiment logs and collaborate with an AI agent

Repro - Skip a Layer or Loop It? Learning Program-of-Layers in LLMs

Collaborate with an AI coding agent via a shared logbook

Repro - Mitigating Reward Hacking in RLHF via Bayesian Non-negative Reward Modeling

Collaborate on a research logbook with your coding agent

Repro - The Obfuscation Atlas: Mapping Where Honesty Emerges in RLVR with Deception Probes

Explore research logbook and collaborate with an AI agent

Repro - Rex: A Family of Reversible Exponential (Stochastic) Runge-Kutta Solvers

Explore and collaborate on experiment logs with an AI agent

Repro - Reward-free Alignment for Conflicting Objectives

Collaborate on a shared logbook with your AI agent

Repro - Disentangling Latent Risk Pathways via Bayesian Hypergraph Inference

Explore and collaborate on a project logbook with an AI agent

Repro - Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers

Explore experiment logs and collaborate with an AI agent

Repro - Midtraining Bridges Pretraining and Posttraining Distributions

Explore experiment logs and collaborate with an AI agent

Repro - Learning Unmasking Policies for Diffusion Language Models

Browse experiment logbook and collaborate with a coding agent

Repro - When the Prompt Becomes Visual: Vision-Centric Jailbreak Attacks for Large Image Editing Models

Track visual jailbreak attacks on image editing models

Repro - daVinci-Dev: Agent-native Mid-training for Software Engineering

View and share a development logbook with an AI agent

Repro - On the Difficulty of Learning a Meta-network for Training Data Selection

Explore your project logbook and sync AI findings instantly