🤖 AI - yuesean · Scour

Sparse Mixture-of-Experts Reward Models Learn Interpretable and Specialized Experts for Personalized Preference Modeling

🦎Evolution Academic

linzhiqiu/t2v_metrics: Evaluating text-to-image/video/3D models with VQAScore

🔌BCI Code

github.com··Hacker News

BiasGRPO: Stabilizing Bias Mitigation in High-Variance Reward Landscapes via Group-Relative Policy Optimization

🧠Neuroscience Academic

Synthetic Benchmarks Overstate Forward-Forward Scaling: Real-Data Limits of Layer-Local Training

🔌BCI Academic

Pretraining Recurrent Networks without Recurrence

🔌BCI Academic

Instance-Level Post Hoc Uncertainty Quantification in Object Detection

💭Cognitive Science Academic

Show HN: One-Shot Program Generation Through Direct Memory Diffusion

🧠Neuroscience Code

github.com··Hacker News

TensorBench: Benchmarking Coding Agents on a Compiler-Based Tensor Framework

⏳Longevity Academic

StandardE2E: A Unified Framework for End-to-End Autonomous Driving Datasets

🔌BCI Academic

No more posts from yuesean's subscribed feeds.

Scour all 25257 feeds Learn more about Feeds

Log in to enable infinite scrolling