Pepe Gomez de Olea PRO

jomasego

·

AI & ML interests

None yet

Recent Activity

upvoted an article 1 day ago

Meta is back with Muse Glimmer: local, agentic, multimodal, and open source

updated a Space 9 days ago

jomasego/repro-calibrating-generative-models-to-distributional-constraints

published a Space 9 days ago

jomasego/repro-calibrating-generative-models-to-distributional-constraints

View all activity

Organizations

jomasego 's Spaces 138

Reproduction: Beyond Normalization: Rethinking the Partition Function as a Difficulty Scheduler for RLVR

Explore project logs and collaborate with AI agents

Reproduction: A Time-Reparameterized Cumulative Intensity Extrapolation Sampler for Discrete Flow Matching

Browse project logs, traces, and workspace files online

Reproduction: When More Experts Hurt: Underfitting in Multi-Expert Learning to Defer

Explore code logs, traces, and workspace in an interactive logbook

Reproduction: WarmServe: Enabling One-for-Many GPU Prewarming for Multi-LLM Serving

Explore logs, traces, and workspace with collaborative AI support

Reproduction: Milestone-Guided Policy Learning for Long-Horizon Language Agents

Explore and share experiment logs with AI agents

Reproduction: Calibrating Generative Models to Distributional Constraints

Browse experiment logs, code, and traces in an interactive workspace

Reproduction: From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal Models

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

Reproduction: Rethinking Evaluation Paradigms in IBP-based Certified Training

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

Reproduction: Beyond Two-Stage Training: Cooperative SFT and RL for LLM Reasoning

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

Reproduction: Cognitive Fatigue in Autoregressive Transformers: Formalization and Measurement

Explore code logs, traces and collaborate with an AI agent

Reproduction: Threshold-Guided Optimization for Visual Generative Models

Explore and manage experiment logs for visual generative models

Reproduction: Turning Back Without Forgetting: Selective Backward Refinement for Parameter-Efficient Continual Learning

Explore experiment logs and collaborate with an AI agent

Reproduction: Multi-Scale Wavelet Transformers for Operator Learning of Dynamical Systems

Explore code, traces, and workspace with an interactive logbook

Reproduction: RePo: Language Models with Context Re-Positioning

Explore project logs, traces, and workspace via web logbook

Reproduction: HyperMLP: An Integrated Perspective for Sequence Modeling

Explore code logs, traces, and workspace with agent help

Reproduction: τ²-Bench: Evaluating Conversational Agents in a Dual-Control Environment

Explore project logs and collaborate with coding agents

Reproduction: ForensicConcept — Transferable Forensic Concepts for AIGI Detection

Explore forensic logs and collaborate with an AI agent

Reproduction: ConServe — Fine-Grained GPU Harvesting for LLM Online and Offline Co-Serving

Explore LLM co‑serving logs and collaborate with an AI agent

Reproduction: Conditional Equivalence of DPO and RLHF: Assumptions, Failure Modes, and Provable Alignment

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

Reproduction: CameraNoise: Enabling Faithful Camera Control in Video Diffusion through Geometry-Flow-Guided Noise Warping

Explore project logs and collaborate with an AI agent

Reproduction: Finding the Minimal Parameter Budget for Implicit Reasoning

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

Reproduction: CameraNoise: Enabling Faithful Camera Control in Video Diffusion through Geometry-Flow-Guided Noise Warping

Explore and manage experiment logs, traces, and workspace

Reproduction: Advancing LLM Reasoning with Natural Language and Numerical Feedback

Explore code logs and traces with AI collaboration

Reproduction: LFQ: Logit-aware Final-block Quantization for Boosting the Generation Quality of Low-Bit Quantized LLMs

Explore and share experiment logs with AI agent