SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models

Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".

GSM8K-V: Can Vision Language Models Solve Grade School Math Word Problems in Visual Contexts

Code for VerifyBench: Benchmarking Reference-based Reward Systems for Large Language Models

Benchmarking agent reasoning capabilities in physical interactions, tool usage, and multi-agent coordination.

[AAAI 2026] Test-Time Reinforcement Learning for GUI Grounding via Region Consistency https://arxiv.org/abs/2508.05615

[AAAI 2026] GUI-G²: Gaussian Reward Modeling for GUI Grounding

A Unified Framework for High-Performance and Extensible LLM Steering

A curated list of resources for activation engineering

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

[Support 0.49.x]（Reset Cursor AI MachineID & Bypass Higher Token Limit） Cursor Ai ，自动重置机器ID ， 免费升级使用Pro功能: You've reached your trial request limit. / Too many free trial accounts used on this machi…

This repository is the official implementation of TimeHC-RL (Distilabel (Data Generation) + TRL (SFT) + VeRL (GRPO)).

[ACM MM 2025] SVGenius: Benchmarking LLMs in SVG Understanding, Editing and Generation. https://arxiv.org/abs/2506.03139

[COLM 2025] SEAL: Steerable Reasoning Calibration of Large Language Models for Free

Code for Paper InftyThink: Breaking the Length Limits of Long-Context Reasoning in Large Language Models

ViewSpatial-Bench:Evaluating Multi-perspective Spatial Localization in Vision-Language Models

[NeurIPS 2025] Mind the Gap: Bridging Thought Leap for Improved CoT Tuning https://arxiv.org/abs/2505.14684

arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

A curated collection of resources, tools, and frameworks for developing GUI Agents.

2021年最新总结，阿里，腾讯，百度，美团，头条等技术面试题目，以及答案，专家出题人分析汇总。

入门nlp

吴恩达老师的机器学习课程个人笔记

深度学习经典、新论文逐段精读

Java学习

RFLA

Summary of related papers on visual attention. Related code will be released based on Jittor gradually.

deep learning for image processing including classification and object-detection etc.

openmmlab第二次作业