Official repo for SteeringControl, a benchmark for evaluating the effectiveness and behavior entanglement of steering methods on safety-related tasks and a modular component framework for unifying …

[EMNLP 2025 Findings] Can Multimodal LLMs See Materials Clearly? A Multimodal Benchmark on Materials Characterization

Code for Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation (EVOL-RL).

Official Implementation of our paper "THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning".

EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence

ScaleCUA is the open-sourced computer use agents that can operate on corss-platform environments (Windows, macOS, Ubuntu, Android).

Wan: Open and Advanced Large-Scale Video Generative Models

An LLM Agent Framework for Interleaved Report Generation

RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation

Image Tokenizer Needs Post-Training

LLaVA-Next for STVG

Patchclamp analysis for https://doi.org/10.1101/2024.07.25.605128

Automated Sholl analysis from brightfield images. Developed for doi.org/10.1101/2024.07.25.605128

An official code repository for the paper "Argumentative Large Language Models for Explainable and Contestable Claim Verification"

This repository contains a PyTorch implementation of the ICSE'26 paper "Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning".

Synapse statistics for neurons grown on substrates of different stifness