Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.
Implement a reasoning LLM in PyTorch from scratch, step by step
MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.
Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B
[Neurips 2025] R-KV: Redundancy-aware KV Cache Compression for Reasoning Models
[ACL 2026 Oral] "LightReasoner: Can Small Language Models Teach Large Language Models Reasoning?"
DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Models
Official repository for EXAONE Deep built by LG AI Research
Official implementation of the NeurIPS 2025 paper "Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space"
MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphs
[NeurIPS 2025] Simple extension on vLLM to help you speed up reasoning model without training.
Official Repository of OmniCaptioner
Pivotal Token Search
xVerify: Efficient Answer Verifier for Reasoning Model Evaluations
[CVPR 2026] ReasonMap: Towards Fine-Grained Visual Reasoning from Transit Maps
An interactive thinking and deep reasoning model. It provides a cognitive reasoning paradigm for complex multi-hop problems.
[NeurIPS 2025] VeriThinker: Learning to Verify Makes Reasoning Model Efficient
Weak-to-Strong Generalization via Direct On-Policy Distillation
ATHENA-R1: AI agent for treatment reasoning over a biomedical tool universe
Community registry of LLM serving-path traps that produce confidently wrong measurements: templates, tool parsers, reasoning fields, quant kernel paths, CUDA toolchains, KV allocation, eval harnesses, versioning. Symptom-first, with the check that catches each.