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

Solving Inequality Proofs with Large Language Models.

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

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).

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

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

Tool-Integrated Reasoning for competition math — weighted voting, difficulty-aware allocation

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

Comprehensive framework for mathematical reasoning research with dual research capabilities

Small-scale Implementation and Extension of “The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning” (NeurIPS '25)

Transforming weak prompts into reasoning machines using Textual Gradients and AdalFlow. Runs on Colab.

GRPO reinforcement learning with verifiable rewards for sub-2B models

GSM8K benchmark results for Qwen3-4B and Qwen3-8B fine-tuned

A Bengali Math LLM

NDA-safe excerpts of math & economics modeling tasks for LLM reasoning evaluation and numerical verification.