Blog
No more endless PDFs. Discover the core value of the latest top-tier research in one article.
LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
Foundations of Schr\" odinger Bridges for Generative Modeling
PivotRL: High Accuracy Agentic Post-Training at Low Compute Cost
Does Reinforcement Fine-Tuning Improve Generalization of LLM Agents? An Empirical Study
Delightful Policy Gradient
Effective Strategies for Asynchronous Software Engineering Agents
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis
RLVR Training of LLMs Does Not Improve Thinking Ability for General QA: Evaluation Method and a Simple Solution
GuARD: Effective Anomaly Detection through a Text-Rich and Graph-Informed Language Model
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis
Mario: Multimodal Graph Reasoning with Large Language Models
Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation
Off-Policy Value-Based Reinforcement Learning for Large Language Models
UniGRPO: Unified Policy Optimization for Reasoning-Driven Visual Generation
Composer2
Resummation of the C-Parameter Sudakov Shoulder Using Effective Field Theory
Technology and English Language Teaching and Learning: A Content Analysis
Rethinking Retrieval-Augmentation as Synthesis: A Query-Aware Context Merging Approach
The influence of learners' prior knowledge composition on interpersonal brain synchronization and learning outcomes in learning by teaching
ProRL Agent: Rollout-as-a-Service for RL Training of Multi-Turn LLM Agents
NOBLE: Accelerating Transformers with Nonlinear Low-Rank Branches
Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
AVO: Agentic Variation Operators for Autonomous Evolutionary Search
La protéinurie et l'onchocercose
Measuring Data Diversity for Instruction Tuning: A Systematic Analysis and A Reliable Metric
Self-Distillation of Hidden Layers for Self-Supervised Representation Learning
Hybrid Associative Memories
Mirage The Illusion of Visual Understanding
Evolution Strategies at the Hyperscale
Natural-Language Agent Harnesses