reasoning

The official code of "VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning" [NeurIPS25]

[ICML 2026] Official repo for "DiffThinker: Towards Generative Multimodal Reasoning with Diffusion Models"

Implementation of 🥥 Coconut, Chain of Continuous Thought, in Pytorch

Dialectical reasoning architecture for LLMs (Thesis → Antithesis → Synthesis)

A high-performance RL training-inference weight synchronization framework, designed to enable second-level parameter updates from training to inference in RL workflows

Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows

[ACL 2025 Industry Track, Oral] Sentiment Reasoning for Healthcare

Agentic AI research papers, benchmarks, frameworks, and tools curated across 24 domains.

[TMLR 25] SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models

GEMS: Agent-Native Multimodal Generation with Memory and Skills

Developer Hub for NVIDIA Alpamayo, containing ready-to-use recipes for fine-tuning, reinforcement-learning post-training, quantization, and deployment.

[ICLR 2023] Multimodal Analogical Reasoning over Knowledge Graphs

Awesome deliberative prompting: How to ask LLMs to produce reliable reasoning and make reason-responsive decisions.

Prototype advanced LLM algorithms for reasoning and planning.

A Comprehensive Survey on Evaluating Reasoning Capabilities in Multimodal Large Language Models.

Repository for awesome spatial/visual reasoning MLLMs. (focus more on embodied applications)

[ICML 2026] Decoding Tree Sketching (DTS): a training-free & model agonistic & plug-in framework for LLM parallel reasoning.

Distill teacher chains-of-thought into a LoRA adapter via a strict boxed-answer format contract + two-phase Train→Nudge (silver-medal NVIDIA Nemotron reasoning recipe, as a tested library).

Composable reasoning skills for Claude - antithesize, excavate, metaphorize, synthesize, and more

Research papers about Chain of Thought (CoT)