Pepe Gomez de Olea PRO

jomasego

·

AI & ML interests

None yet

Recent Activity

updated a Space 30 minutes ago

jomasego/repro-when-more-experts-hurt-underfitting-in-multi-expert-learning-to-defer

updated a Space 30 minutes ago

jomasego/repro-warmserve-enabling-one-for-many-gpu-prewarming-for-multi-llm-serving

updated a Space 30 minutes ago

jomasego/repro-milestone-guided-policy-learning-for-long-horizon-language-agents

View all activity

Organizations

updated 5 Spaces 30 minutes ago

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

Explore code, traces, and workspace in an interactive logbook

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

Explore code, traces, and workspace in an interactive logbook

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

Explore experiment logs and collaborate with your AI agent

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

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

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

Explore a research project's logbook and traces

updated a Space 39 minutes ago

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

published a Space 39 minutes ago

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

updated a Space about 4 hours ago

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

Explore code, traces, and workspace in an interactive logbook

published a Space about 4 hours ago

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

Explore code, traces, and workspace in an interactive logbook

updated a Space about 4 hours ago

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

Explore code, traces, and workspace in an interactive logbook

published a Space about 4 hours ago

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

Explore a research project's logbook and traces

updated a Space about 4 hours ago

Repro Hgmem

published a Space about 5 hours ago

Repro Hgmem

updated a Space about 5 hours ago

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

published a Space about 5 hours ago

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

updated a Space about 11 hours ago

Reproduction: REAL: Regression-Aware Reinforcement Learning for LLM-as-a-Judge

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

published a Space about 11 hours ago

Reproduction: REAL: Regression-Aware Reinforcement Learning for LLM-as-a-Judge

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

updated a Space about 12 hours ago

Reproduction: Real-Time Aligned Reward Model beyond Semantics

Explore code logs, traces, and workspace with AI collaboration

published a Space about 12 hours ago

Reproduction: Real-Time Aligned Reward Model beyond Semantics

Explore code logs, traces, and workspace with AI collaboration

updated a Space about 12 hours ago

Reproduction: Posterior Concentration of Bayesian Physics-Informed Neural Networks for Elliptic PDEs

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