Pepe Gomez de Olea PRO

jomasego

·

AI & ML interests

None yet

Recent Activity

updated a Space about 2 hours ago

jomasego/repro-impact-influence-modeling-for-open-set-time-series-anomaly-detection

published a Space about 2 hours ago

jomasego/repro-impact-influence-modeling-for-open-set-time-series-anomaly-detection

published a dataset about 2 hours ago

jomasego/repro-impact-influence-modeling-for-open-set-time-series-anomaly-detection-traces

View all activity

Organizations

jomasego 's Spaces 103

Reproduction: QUATRO: Query-Adaptive Trust Region Policy Optimization for LLM Fine-tuning

Explore experiment logs and traces in a collaborative web logbook

Reproduction: Learning General Causal Structures with Hidden Dynamic Process for Climate Analysis

Explore experiment logs and collaborate with an AI agent

Reproduction: Model Merging Scaling Laws in Large Language Models

Explore experiment logs, traces, and workspace in a web UI

Reproduction: Learning to Evict from Key-Value Cache

Explore project logs, traces, and workspace in an interactive UI

Reproduction: IMPACT — Influence Modeling for Open-Set Time Series Anomaly Detection

Explore project logs, traces, and workspace in an interactive UI

Reproduction: SiameseNorm: Breaking the Barrier to Reconciling Pre/Post-Norm

Reproduction: When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoning

Explore experiment logs and traces interactively

Reproduction: TSRBench — A Comprehensive Multi-task Multi-modal Time Series Reasoning Benchmark for Generalist Models

Explore and manage experiment logs and traces

Reproduction: TMS — Trajectory-Mixed Supervision for On-Policy Self Distillation

Explore experiment logs, code, and traces interactively

Reproduction: More Capable, Less Cooperative? When LLMs Fail At Zero-Cost Collaboration

Explore code logs and collaborate with an AI agent

Reproduction: Unveiling the Visual Counting Bottleneck in Vision-Language Models

Explore experiment logs, traces, and workspace data

Reproduction: Spectral Reach: Understanding Neural Scaling as Progress into the Spectral Tail

Explore project logs, code, and traces in an interactive web UI

Repro Gem Geometric Entropy Mixing For Optimal Llm Data Curation

Explore project logs and traces in an interactive web UI

Reproduction: Content-Style Identification via Differential Independence

View code logs, traces, and collaborate with an AI agent

Reproduction: Active Learning with Low-Rank Structure for Data Selection

Explore experiment logs, code, and traces in a web UI

Reproduction: Breaking the Reversal Curse in Autoregressive Language Models via Identity Bridge

Track and view code experiments with an interactive logbook

Reproduction: Compressed Sensing for Capability Localization in Large Language Models

Explore code execution logs and traces in an interactive logbook

Reproduction: Knowledge Diversion for Efficient Morphology Control and Policy Transfer

Reproduction: Omni-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete Diffusion

Explore and organize model experiment logs

Reproduction: EvoGM: Learning to Merge LLMs via Evolutionary Generative Optimization

Explore experiment logs and traces in an interactive UI

Reproduction: Temper-Then-Tilt: Principled Unlearning for Generative Models through Tempering and Classifier Guidance

Explore and collaborate on research reproducibility logbooks

Reproduction: AutoControl Arena — Synthesizing Executable Test Environments for Frontier AI Risk Evaluation

Explore and collaborate on AI risk test logs

Reproduction: BioArc: Discovering Optimal Neural Architectures for Biological Foundation Models

Explore research logbook and sync with your coding agent

Repro Cspo Constraint Sensitive Policy Optimization For Safe Reinforcement Learning