8000 Xiang-Pan (Xiang Pan (潘翔)) / Starred · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content
View Xiang-Pan's full-sized avatar
Dreaming
Dreaming
  • National University of Singapore

Block or report Xiang-Pan

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Showing results

The Automated LLM Speedrunning Benchmark measures how well LLM agents can reproduce previous innovations and discover new ones in language modeling.

Jupyter Notebook 64 5 Updated Jun 30, 2025
Jupyter Notebook 74 4 Updated Mar 28, 2025

Stanford NLP Python library for benchmarking the utility of LLM interpretability methods

Python 98 7 Updated Jun 25, 2025

Code for Paper (Preserving Diversity in Supervised Fine-tuning of Large Language Models)

Python 31 4 Updated May 12, 2025

The official implementation of "KL Penalty Control via Perturbation for Direct Preference Optimization"

Python 3 Updated Feb 24, 2025

An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agentic RL)

Python 7,235 703 Updated Jun 19, 2025

Virtual whiteboard for sketching hand-drawn like diagrams

TypeScript 102,873 10,167 Updated Jun 30, 2025

ACI.dev is the open source platform for VibeOps and infrastructure that connects your AI agents to 600+ tool integrations with multi-tenant auth, granular permissions, and access through direct fun…

Python 4,129 374 Updated Jul 1, 2025

Research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspects of R&D are mainly focused on data and models. We are commi…

Python 6,351 599 Updated Jul 2, 2025

A PyTorch native platform for training generative AI models

Python 3,990 415 Updated Jul 2, 2025

AllenAI's post-training codebase

Python 3,033 409 Updated Jul 2, 2025

Codes for the paper "A mathematical perspective on Transformers".

Python 37 2 Updated Jul 8, 2024

KernelBench: Can LLMs Write GPU Kernels? - Benchmark with Torch -> CUDA problems

Python 438 46 Updated Jul 1, 2025

Official implementation of the paper "Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space"

Python 177 13 Updated May 30, 2025

Repository for Zochi's Research

Python 226 23 Updated May 30, 2025

This is the repository that contains the source code for the Self-Evaluation Guided MCTS for online DPO.

Jupyter Notebook 318 33 Updated Aug 6, 2024
Python 190 28 Updated Jun 23, 2025

Stanford NLP Python library for understanding and improving PyTorch models via interventions

Python 759 82 Updated Jun 2, 2025

This is the repository of DEER, a Dynamic Early Exit in Reasoning method for Large Reasoning Language Models.

Python 148 3 Updated Jun 19, 2025

Experimental nix expression to package all MacOS casks from homebrew automatically

Nix 258 13 Updated Jun 8, 2025

Principled Data Selection for Alignment: The Hidden Risks of Difficult Examples

Python 37 Updated Apr 9, 2025

A powerful tool for creating fine-tuning datasets for LLM

JavaScript 9,004 877 Updated Jul 1, 2025

[TMI'20] Unpaired Multi-modal Segmentation via Knowledge Distillation

Python 111 24 Updated Mar 24, 2023

source code for NeurIPS'24 paper "HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection"

Python 47 4 Updated Apr 11, 2025

A resource repository for machine unlearning in large language models

428 22 Updated May 25, 2025

Source code of our paper MIND, ACL 2024 Long Paper

Python 43 12 Updated May 28, 2024

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

Jupyter Notebook 11,211 1,636 Updated Apr 26, 2025
Next
0