Chengsong Huang

zotero-arxiv-daily. Recommend new arxiv papers of your interest daily according to your Zotero libarary.

Trace2Skill. Official codebase of the paper -- Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills

RL-Guided-Adaptive-Sampling. Official implementation of Small RL Controller, Large Language Model: RL-Guided Adaptive Sampling for Test-Time Scaling

SkillOpt. SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.

Beta-Binomial-PRM. Process Rewards with Learned Reliability

AutoTTS. The offical repo for "LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling"

G-Zero. Python

SkillZero. Official code for "SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization"

claw-code. An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

CLI-Anything. "CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/

MM-Zero. Self-evolving vision language models from zero data

cli. Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. Includes AI agent skills.

openclaw. Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

Multimodal-VIdeo-Generation-Collections-Video-and-Audio. Multimodal Video Generation Model, research, unified models, applications collection.

Parallel-Probe. The offical repo for "Parallel-Probe: Towards Efficient Parallel Thinking via 2D Probing"

TTCS. The code implementation for TTCS: Test-Time Curriculum Synthesis for Self-Evolving.

model_collaboration. MoCo: A One-Stop Shop for Model Collaboration Research

DARC. Python

RelayLLM. Python

OnlineJudge. Open source online judge based on Vue, Django and Docker. | 青岛大学开源 Online Judge | QQ群 496710125 | admin@qduoj.com

CITER. [COLM'25] CITER: Collaborative Inference for Efficient Large Language Model Decoding with Token-Level Routing

Native-Parallel-Reasoner. [ICML 2026] Reasoning in Parallelism via Self-Distilled RL

VisPlay. [CVPR'26] VisPlay: Self-Evolving Vision-Language Models

Agent0. [COLM'26 & ICML'26] Agent0 Series: Self-Evolving Agents from Zero Data

DyPRAG. [arxiv: 2503.23895] Dynamic Parametric Retrieval Augmented Generation for Test-time Knowledge Enhancement

paperlists. Processed / Cleaned Data for Paper Copilot

InstructRAG. [ICLR 2025] InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales

R-Zero. [ICLR2026] codes for R-Zero: Self-Evolving Reasoning LLM from Zero Data (https://www.arxiv.org/pdf/2508.05004)

Router-R1. [NeurIPS'25] Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning

Search-R1. Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL

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

rl-swarm. A fully open source framework for creating RL training swarms over the internet.

Awesome-RL-for-LRMs. A Survey of Reinforcement Learning for Large Reasoning Models

Parallel-R1. The offical repo for "Parallel-R1: Towards Parallel Thinking via Reinforcement Learning"

verl-tool. A version of verl to support diverse tool use [TMLR 2026]

TTRL. [NeurIPS 2025] TTRL: Test-Time Reinforcement Learning

Vision-SR1. Reinforcement Learning of Vision Language Models with Self Visual Perception Reward

awesome. 😎 Awesome lists about all kinds of interesting topics

GLM-4.5. GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

Qwen-Image. Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.

Vision-Language-Models-Overview. A most Frontend Collection and survey of vision-language model papers, and models GitHub repository. Continuous updates.

Absolute-Zero-Reasoner. Official Repository of Absolute Zero Reasoner

LlamaFactory. Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

True-Story-of-Pangu. 诺亚盘古大模型研发背后的真正的心酸与黑暗的故事。

Awesome-Inference-Time-Scaling. Paper List of Inference/Test Time Scaling/Computing

Awesome-Efficient-Reasoning. Paper list for Efficient Reasoning.

verl. verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

persona-hub. Official repo for the paper "Scaling Synthetic Data Creation with 1,000,000,000 Personas"

text-to-lora. Hypernetworks that adapt LLMs for specific benchmark tasks using only textual task description as the input

vllm. A high-throughput and memory-efficient inference and serving engine for LLMs

General-Reasoner. General Reasoner: Advancing LLM Reasoning Across All Domains [NeurIPS25]

EasyR1. EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

Label-Free-RLVR.

Soft-Thinking. Official implementation of the NeurIPS 2025 paper "Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space"

Overleaf-Bib-Helper. Enhances Overleaf by allowing article searches and BibTeX retrieval from DBLP and Google Scholar | 通过允许从 DBLP 和 Google Scholar 进行文章搜索和获取 BibTeX 来增强 Overleaf。

specreason. PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]

aguvis. [ICML2025] Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction

CrossWordBench. Python

TokenSkip. [EMNLP 2025] TokenSkip: Controllable Chain-of-Thought Compression in LLMs

HASS. Official Implementation of "Learning Harmonized Representations for Speculative Sampling" (HASS)

Self-Calibration. codes for Efficient Test-Time Scaling via Self-Calibration

ZeroEval. A simple unified framework for evaluating LLMs

REKCARC-TSC-UHT. 清华大学计算机系课程攻略 Guidance for courses in Department of Computer Science and Technology, Tsinghua University

EAGLE. Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).

Awesome-Language-Model-on-Graphs. A curated list of papers and resources based on "Large Language Models on Graphs: A Comprehensive Survey" (TKDE)

ai-deadlines. :alarm_clock: AI conference deadline countdowns

SaySelf. Public code repo for paper "SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales"

opencompass. OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

alpaca_eval. An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.

entropix. Entropy Based Sampling and Parallel CoT Decoding

Chengsong-Huang.github.io. Personal page of Chengsong Huang. Thanks for https://github.com/orderedlist/minimal

minimal. A Theme for GitHub Pages

LARA. codes for Divide, Reweight, and Conquer: A Logit Arithmetic Approach for In-Context Learning

Reward-Calibration. Python

Title-Generator-for-Womens-Fiction. 晋江女频金榜生成器

LongICLBench. Code and Data for "Long-context LLMs Struggle with Long In-context Learning" [TMLR2025]

scis-lzynb. TeX

WonderJourney. Python

ControlNet. Let us control diffusion models!

lorahub. [COLM 2024] LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition

cryostar. Leveraging Structural Priors and Constraints for Cryo-EM Heterogeneous Reconstruction

SuperAGI. <⚡️> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably.

rebiber. A simple tool to update bib entries with their official information (e.g., DBLP or the ACL anthology).

alpaca-lora. Instruct-tune LLaMA on consumer hardware

lorahub. The official repository of paper "LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition".

stable-diffusion-webui-colab. stable diffusion webui colab

donut. Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022

stable-diffusion-webui. Stable Diffusion web UI