Stars
Understanding R1-Zero-Like Training: A Critical Perspective
V1: Toward Multimodal Reasoning by Designing Auxiliary Task
A lightweight reproduction of DeepSeek-R1-Zero with indepth analysis of self-reflection behavior.
AnchorAttention: Improved attention for LLMs long-context training
🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.
Official PyTorch implementation for ICLR2025 paper "Scaling up Masked Diffusion Models on Text"
[ICLR 2025] A Closer Look at Machine Unlearning for Large Language Models
[ICLR 2025] When Attention Sink Emerges in Language Models: An Empirical View (Spotlight)
The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.
[ArXiv 2024] Denial-of-Service Poisoning Attacks on Large Language Models
[ICLR 2025] Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates (Oral)
[NeurIPS 2024] The official implementation of paper: Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs.
Official implementation of Bootstrapping Language Models via DPO Implicit Rewards
Improved techniques for optimization-based jailbreaking on large language models (ICLR2025)
Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)
[ICML 2024] Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast
Code of the paper: Finetuning Text-to-Image Diffusion Models for Fairness
Intriguing Properties of Data Attribution on Diffusion Models (ICLR 2024)
[TMLR 2025] On Memorization in Diffusion Models
[COLM 2024] LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition
Official code for "On Calibrating Diffusion Probabilistic Models"
Official code for "DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps" (Neurips 2022 Oral)
Flax is a neural network library for JAX that is designed for flexibility.