Inference-time scaling for LLMs-as-a-judge.

Designing Multi-Agent Systems with Zero Supervision

Inference-Time Alignment in Protein Diffusion Models

Sys2Bench is a benchmarking suite designed to evaluate reasoning and planning capabilities of large language models across algorithmic, logical, arithmetic, and common-sense reasoning tasks.

This repo is the code for T-SCEND, a novel framework that significantly improves diffusion model’s reasoning capabilities with better energy-based training and scaling up test-time computation.

✨Amazon Bedrock wrapper for inference-time LLM techniques

Research on models and agents that improve reasoning and planning through iterative latent computation.

The official PyTorch implementation for the Guided by Gut: Efficient Test-Time Scaling with Reinforced Intrinsic Confidence

Code for the paper "Blockwise Control for Denoising Diffusion Models"

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

When more sampling stops helping: a reasoning model can generate a right answer long before it can pick one. The modal and correlation ceilings of test-time scaling, with paper, figures, and code (Bay & Yearick).

An open-source agent system built in Go, inspired by the ReAct agent pattern, Anthropic's MCP protocol, Google's ACP spec, and the broader agent tooling ecosystem.

Pi_k,m,r — propose/critique/compare orchestration that lets a weak reasoning model match frontier performance on verifier-backed tasks.

The Verifier Is All You Need: Six Architectural Interventions That Don't Matter and the Verification Boundary That Does

Turn a frozen open-source model into a ~98%-verified, hands-free first-aid assistant — with inference-time compute and a deterministic verifier. Zero training.