alignment

A Toolkit for Distributional Control of Generative Models

Code for the paper "Aligning LLM Agents by Learning Latent Preference from User Edits".

This is the official code for the paper "Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation" (ICLR2025 Oral).

[ICML 2024] Code for the paper "Confronting Reward Overoptimization for Diffusion Models: A Perspective of Inductive and Primacy Biases"

React Native TurboModule for Sherpa-ONNX offline on-device Speech Processing (STT/TTS/Diarization/VAD) completely offline on the device. Support for Android & iOS

A fast parallel PyTorch implementation of the "CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition" https://arxiv.org/abs/1905.11235.

Official codebase for "Quantile Reward Policy Optimization: Alignment with Pointwise Regression and Exact Partition Functions" (Matrenok et al. 2025).

Alignment-Free RGBT Salient Object Detection: Semantics-guided Asymmetric Correlation Network and A Unified Benchmark

AnimeGAN2 trained on Arcane

A lightweight post-training framework for LLMs and VLMs. 51 algorithms, 38 verified models. Scales with DeepSpeed, vLLM, and Ray.

Finetuning and Alignment bootcamp reference implementations

This is the unofficial re-implementation of "Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning Attack" (ICML2025)

[🔥 ICLR 2026] - Misaligned Roles, Misplaced Images: Structural Input Perturbations Expose Multimodal Alignment Blind Spots

Different post-training techniques for LLMs, including: SFT, DPO and Online RL

Companion code for the Manning book 'LLM Customization and Fine-Tuning.' Adapt open-weights LLMs end to end: prompting and RAG, LoRA/QLoRA, full SFT, distillation, and DPO/RLHF alignment.