hypedarhypedar
feedtrendsdiscovershowcasearchive
login
login
login
FeedTrendsDiscoverShowcaseArchiveDashboard
Submit Showcase

Trending now

Llm + Rl + Training66Agents + Workflow56Math + Games56
View all trends →

hypedar

AI trend radar for developers. Catch emerging papers, repos, and discussions before the hype peaks.

AboutGitHubDiscord

By the makers of hypedar

Codepawl

Open-source tools for developers.

Explore our tools →
AboutPrivacyTermsX

© 2026 Codepawl

Built by Codepawl·© 2026

About·Terms·Privacy·Security

GitHub·Discord·X

feedtrendsdiscovershowcasearchive
← trends

Training + Rl + Inference

24.0

Build a library for 'plasticity-preserving' RL that maintains an ensemble of policies to prevent catastrophic forgetting. This is vital for developers working on long-running, continuous agent environments.

+0
emergingimplementation gap
rltraininginference

Signals (11)

arXiv4d ago

Compressed-Sensing-Guided, Inference-Aware Structured Reduction for Large Language Models

arXiv1d ago

StoSignSGD: Unbiased Structural Stochasticity Fixes SignSGD for Training Large Language Models

arXiv1d ago

Target-Oriented Pretraining Data Selection via Neuron-Activated Graph

arXiv1d ago

GroupDPO: Memory efficient Group-wise Direct Preference Optimization

arXiv1d ago

Improving Reasoning Capabilities in Small Models through Mixture-of-Layers Distillation with Stepwise Attention on Key Information

arXiv5h ago

Discover and Prove: An Open-source Agentic Framework for Hard Mode Automated Theorem Proving in Lean 4

arXiv1d ago

Optimizing Stochastic Gradient Push under Broadcast Communications

arXiv5d ago

MOONSHOT : A Framework for Multi-Objective Pruning of Vision and Large Language Models

arXiv1d ago

DALM: A Domain-Algebraic Language Model via Three-Phase Structured Generation

arXiv1d ago

Beyond Single-Model Optimization: Preserving Plasticity in Continual Reinforcement Learning

arXiv1d ago

Lightweight Geometric Adaptation for Training Physics-Informed Neural Networks