zzwjames

multi-agent-marketplace. Magentic-Marketplace: Simulate Agentic Markets and See How They Evolve

BrowseComp-Plus. BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent (ACL 2026 Main)

LaMer. [ICLR 2026] Meta-RL Induces Exploration in Language Agents

Graph4LLM-Survey. Survey of Graphs helping LLMs from Penn State, Chinese Academy of Sciences, ...

memma. The official repository of "MemMA: Coordinating the Memory Cycle through Multi-Agent Reasoning and In-Situ Self-Evolution".

MLRA. [ICLR 2026] Multi-Head Low-Rank Attention

skills. Public repository for Agent Skills

SGI-Bench. Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows

a-evolve. The official repository of "Position: Agentic Evolution is the Path to Evolving LLMs".

meta-context-engineering. [ICML 2026] Meta Context Engineering via Agentic Skill Evolution

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

DeepResearcher. Scaling Deep Research via Reinforcement Learning in Real-world Environments.

deep_research_bench. DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents

AI-Researcher. Python

Agent-Skills-for-Context-Engineering. A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require effective context management.

MemGen. MemGen: Weaving Generative Latent Memory for Self-Evolving Agents

Mem-alpha. The official implementation of the paper "Mem-α: Learning Memory Construction via Reinforcement Learning"

2027-AI-College-Jobs. 2027 AI/ML internship & new graduate job list updated daily

MARSHAL. [ICLR'26] MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMs

Dream. Dream 7B, a large diffusion language model

smolagents. 🤗 smolagents: a barebones library for agents that think in code.

dllm. dLLM: Simple Diffusion Language Modeling

dFactory. Easy and Efficient dLLM Fine-Tuning

agentic-ai. Agentic AI research papers, benchmarks, frameworks, and tools curated across 24 domains.

sleepless-agent. 🤖 24/7 AI agent that maximizes Claude Code Pro usage via Slack. Auto-processes tasks, manages isolated workspaces, creates Git commits/PRs, and optimizes day/night usage thresholds.

Awesome-Diffusion-Model-Unlearning. A repository of resources on machine unlearning for diffusion models

Lumina-DiMOO. Lumina-DiMOO - An Open-Sourced Multi-Modal Large Diffusion Language Model

open-unlearning. [NeurIPS D&B '25] The one-stop repository for LLM unlearning

d1. Official Implementation for the paper "d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning"

MNPO. The official code of Multi-player Nash Preference Optimization [ICLR 2026]

lost_in_conversation. Code that accompanies the public release of the paper Lost in Conversation (https://arxiv.org/abs/2505.06120)

harmony. Renderer for the harmony response format to be used with gpt-oss

RLVR-World. Official repository for "RLVR-World: Training World Models with Reinforcement Learning" (NeurIPS 2025), https://arxiv.org/abs/2505.13934

GMPO. [ICLR 2026] Geometric-Mean Policy Optimization

understand-r1-zero. Understanding R1-Zero-Like Training: A Critical Perspective

ReTool. Python

AbstentionBench. A holistic benchmark for LLM abstention

verl-agent. verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"

MoA. Together Mixture-Of-Agents (MoA) – 65.1% on AlpacaEval with OSS models

lm-evaluation-harness. A framework for few-shot evaluation of language models.

one-shot-em. One-shot Entropy Minimization

R1-Compress. [NeurIPS 2025@FoRLM] R1-Compress: Long Chain-of-Thought Compression via Chunk Compression and Search

DOV4CL. [ICLR 2025] Dataset Ownership Verification in Contrastive Pre-trained Models

Elastic-Reasoning. Make reasoning models scalable

Quantized-Reasoning-Models. [COLM 2025] Official PyTorch implementation of "Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models"

Multi-player-Nash-Policy-Optimization. Python

RM-Bench. [ICLR 25 Oral] RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style

llm_optimization. A repo for RLHF training and BoN over LLMs, with support for reward model ensembles.

args. Python

GenARM. Code for ICLR 2025 Paper "GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-time Alignment"

ImplicitPRM. Repo of paper "Free Process Rewards without Process Labels"

weak-to-strong-preference-optimization. [ICLR 2025 Spotlight] Weak-to-strong preference optimization: stealing reward from weak aligned model

weak-to-strong-deception. [ICLR 2025] Code&Data for the paper "Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization"

RIGBD. An official implementation of "Robustness Inspired Graph Backdoor Defense" (ICLR 2025 Oral)

Generalizable-Reward-Model. Code for NeurIPS 2024 paper "Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs"

Self-Rewarding-Language-Models. This is work done by the Oxen.ai Community, trying to reproduce the Self-Rewarding Language Model paper from MetaAI.

self-rewarding-lm-pytorch. Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI

CREAM. Code for "CREAM: Consistency Regularized Self-Rewarding Language Models", ICLR 2025.

RLHF-Reward-Modeling. Recipes to train reward model for RLHF.

Awesome-LLMs-as-Judges. The official repo for paper, LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods.

DPGBA. An official implementation of "Rethinking Graph Backdoor Attacks: A Distribution-Preserving Perspective" (KDD 2024)

SLMs-Survey. Survey of Small Language Models from Penn State, ...

FailureLLMUnlearning. An official implementation of "Catastrophic Failure of LLM Unlearning via Quantization" (ICLR 2025)

awesome-mobile-agents. ✨✨Latest Papers and Datasets on Mobile and PC GUI Agent

RWKU. RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models. NeurIPS 2024

muse_bench. Python

LoRA-Pro. Official code for our paper, "LoRA-Pro: Are Low-Rank Adapters Properly Optimized? "

QuantBackdoor_EFRAP. Official Implementation for "Nearest Is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attacks" (CVPR 2024).

VLMEvalKit. Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks

selfie. This repository contains the code and data for the paper "SelfIE: Self-Interpretation of Large Language Model Embeddings" by Haozhe Chen, Carl Vondrick, and Chengzhi Mao.

LlamaGen. Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

Time-MMD. Jupyter Notebook

awesome-data-poisoning-and-backdoor-attacks. A curated list of papers & resources linked to data poisoning, backdoor attacks and defenses against them (no longer maintained)

llm-quantization-attack. [NeurIPS 2024 / ICML 2025] LLM Quantization Attacks

Verbose_Images. [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images

llm_attack_defense_arena. Python

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

dgl. Python package built to ease deep learning on graph, on top of existing DL frameworks.

RecSysPapers. 推荐/广告/搜索领域工业界经典以及最前沿论文集合。A collection of industry classics and cutting-edge papers in the field of recommendation/advertising/search.

tab-transformer-pytorch. Implementation of TabTransformer, attention network for tabular data, in Pytorch

mae. PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

awesome-object-detection. Awesome Object Detection based on handong1587 github: https://handong1587.github.io/deep_learning/2015/10/09/object-detection.html

awesome-semantic-segmentation. :metal: awesome-semantic-segmentation

awesome-computer-vision. A curated list of awesome computer vision resources