Implement a reasoning LLM in PyTorch from scratch, step by step

Solving Inequality Proofs with Large Language Models.

(ArXiv25) Vision Matters: Simple Visual Perturbations Can Boost Multimodal Math Reasoning

Capable, auditable coding that runs fully offline on a 16 GB machine. A verification-first layer (hard test execution, symbolic checking, agentic repair) that takes a local 7B to parity with its 671B teacher on verifiable tasks. MIT, pre-registered, reproducible.

An official implementation of "SPARK: Synergistic Policy And Reward Co-Evolving Framework"

Distilling Phi-3 step-by-step math reasoning into TinyLlama-1.1B with QLoRA — 395k Vietnamese math problems, structured think/answer outputs

Prompt-engineering study on LLM math reasoning (GSM8K) and code generation (HumanEval): zero/few-shot, self-consistency, self-verification, and experiments on prompt quality, complexity, demonstrations, and diversity.

ArmLLM 2025 solutions covering ViT from scratch, SigLIP–Qwen LaTeX OCR, GRPO reasoning post-training, inference-time reasoning strategies, and adversarial vision attacks.

AI Benchmark 知识库 — 全面收录各大 AI 公司用来测试模型性能的 Benchmark 题库完整集合

A minimal JEPA-based language model demonstrating latent-space reasoning on GSM8K using a single decoder-only Transformer.

STaR × S1 math pipeline on Qwen2.5-1.5B. LoRA, strict Final: format, ~20–30% acc (OpenR1-Math split).

CPU-trained reasoning model pipeline. LoRA SFT + DPO on SmolLM2-360M, GSM8K math reasoning, single-laptop deployment.

Data cleaning and structuring pipeline for math reasoning tasks using Qwen3-0.6B for LLM post-training.

A controlled LoRA finetuning study on process supervision for mathematical reasoning with Qwen2.5-Math-7B-Instruct.

NLP course final project (2026), Nanjing Normal University, supervised by 孔力: GSM8K math QA with Seq2Seq, Transformer and LLMs.

A Bengali Math LLM

Comprehensive framework for mathematical reasoning research with dual research capabilities

GRPO (Group Relative Policy Optimization) implemented from scratch in PyTorch. 10 ablation experiments.

Paired-framing pilot on observable self-doubt in math reasoning models

Local-first LangGraph/LangChain math-reasoning harness with tools, strategy retrieval, adaptive routing, and pattern artifacts for small Qwen models.