git-disl repositories

RL-Focal

Public

Dynamically selecting the most diverse ensemble set of multiple LLMs and fusing the outputs with Multi Agent Reinforcement Learning. Overal system can switch be…

Python

•0•0•0•0•Updated

May 23, 2026

awesome-LLM-game-agent-papers

Public

A Survey on Large Language Model-Based Game Agents (ACM CSUR)

survey computer-games large-language-models

survey computer-games large-language-models llm-based-agent game-agent

29•889•3•0•Updated

May 22, 2026

MELT

Public

A Behavioral Trace Dataset for High-Risk Memecoin Launch Detection

Python

•

Other

•0•2•1•0•Updated

May 21, 2026

MemeTrans

Public

MemeTrans: A Dataset for Detecting High-Risk Meme Coin Launches on Blockchain

0•2•1•0•Updated

May 21, 2026

awesome_LLM-harmful-fine-tuning-papers

Public

A survey on harmful fine-tuning attack for large language model (ACM CSUR)

attack survey alignment

attack survey alignment safety emergent defense malicious fine-tuning finetuning harmful

8•241•0•0•Updated

May 19, 2026

AFOG

Public

Implementation of "Adversarial Attention Perturbations for Large Object Detection Transformers"

Jupyter Notebook

•3•4•0•0•Updated

Apr 29, 2026

FaceCloak

Public

Implementation of "Personalized Face Privacy Protection From a Single Image"

Python

•1•0•0•0•Updated

Apr 29, 2026

AttentionPack

Public

This is the code for AttentionPack (CVPR 2026)

0•2•0•0•Updated

Mar 25, 2026

h3fusion

Public

Python

•0•0•1•0•Updated

Jan 19, 2026

Vaccine

Public

This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large Language Models" (NeurIPS2024)

attack emergent malicious

attack emergent malicious fine-tuning finetuning harmful llm misalignment

Shell

•

Apache License 2.0

•5•49•1•0•Updated

Jan 15, 2026

Tcell

Public

Python

•0•0•0•0•Updated

Dec 23, 2025

scale-fl

Public

Code for ScaleFL

Python

•1•34•4•0•Updated

Dec 11, 2025

FedHFT

Public

This is the code for FedHFT: Efficient Federated Finetuning with Heterogeneous Edge Clients (IEEE CogMI'25)

Python

•0•2•0•0•Updated

Nov 16, 2025

recap

Public

Code for CVPR24 Paper - Resource-Efficient Transformer Pruning for Finetuning of Large Models

Python

•1•12•4•0•Updated

Oct 31, 2025

Fed-alphaCDP

Public

This repo is for paper Securing Distributed SGD against Gradient Leakage Threats submitted to IEEE TPDS.

Jupyter Notebook

•0•3•1•0•Updated

Oct 26, 2025

GradCloak

Public

Code for GradCloak: Gradient Obfuscation for Privacy-Preserving Distributed Learning as a Service

Jupyter Notebook

•1•3•0•0•Updated

Sep 11, 2025

Antidote

Public

This is the unofficial re-implementation of "Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning Attack" (ICML2025…

language model alignment

language model alignment safety emergent large malicious fine-tuning harmful llm

Shell

•0•9•1•0•Updated

Jul 14, 2025

Fusion-Shot

Public

Select the best ensemble set among the pool of Few-Shot Learners using Genetic Algorithm. Train FusionShot model on top of the base-models using training-val pr…

Jupyter Notebook

•0•1•0•0•Updated

Jul 13, 2025

GTLLMZoo

Public

GTLLMZoo: A comprehensive framework that aggregates LLM benchmark data from multiple sources with an interactive UI for efficient model comparison, filtering, a…

Python

•1•4•0•0•Updated

Jun 12, 2025

Booster

Public

This is the official code for the paper "Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation" (ICLR2025 Oral).

attack alignment safety

attack alignment safety emergent malicious fine-tuning finetuning harmful llms misalignment

Shell

•

Apache License 2.0

•2•38•1•0•Updated

Mar 22, 2025

Safety-Tax

Public

This is the official code for the paper "Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable".

language model safety

language model safety reasoning large llm

Python

•

Apache License 2.0

•5•34•1•0•Updated

Mar 11, 2025

Virus

Public

This is the official code for the paper "Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation"

attack moderation safety

attack moderation safety emergent defense malicious fine-tuning harmful guardrail llms

Python

•

Apache License 2.0

•4•56•0•0•Updated

Feb 2, 2025

llm-topla

Public

Teaming the most diverse LLMs for ensemble learning with genetic algorithm using RL focal metric. Combining the outputs for MCQ and OEQ tasks using TOPLA MLP an…

Jupyter Notebook