Code for the paper "AsFT: Anchoring Safety During LLM Fune-Tuning Within Narrow Safety Basin".
☆36Jul 10, 2025Updated 7 months ago
Alternatives and similar repositories for AsFT
Users that are interested in AsFT are comparing it to the libraries listed below
Sorting:
- 【COLING 2025🔥】Code for the paper "Is Parameter Collision Hindering Continual Learning in LLMs?".☆38Dec 5, 2024Updated last year
- GPT as a Monte Carlo Language Tree: A Probabilistic Perspective☆45Jan 18, 2025Updated last year
- [AAAI26] Next Patch Prediction☆132Jan 2, 2025Updated last year
- ☆39Jun 12, 2025Updated 8 months ago
- This repository is the official implementation of "Look-Back: Implicit Visual Re-focusing in MLLM Reasoning".☆84Jul 10, 2025Updated 7 months ago
- Official implementation of "Progressive3D: Progressively Local Editing for Text-to-3D Content Creation with Complex Semantic Prompts" [IC…☆120Jun 27, 2024Updated last year
- A Comprehensive Benchmark and Toolkit for Evaluating Video-based Large Language Models!☆137Dec 31, 2023Updated 2 years ago
- [ICML 2025] X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP☆39Feb 3, 2026Updated last month
- Code for paper "Rethinking Text-based Protein Understanding: Retrieval or LLM?"☆18Oct 7, 2025Updated 5 months ago
- MADAv2: Advanced Multi-Anchor Based Active Domain Adaptation Segmentation☆25Jul 8, 2023Updated 2 years ago
- [ICLR 2025] On Evluating the Durability of Safegurads for Open-Weight LLMs☆13Jun 20, 2025Updated 8 months ago
- PyTorch implementation of "Sample- and Parameter-Efficient Auto-Regressive Image Models" from CVPR 2025☆14Nov 21, 2025Updated 3 months ago
- iFSQ & LlamaGen-REPA☆93Jan 27, 2026Updated last month
- Code for “SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation(ICLR 2025)”☆24Oct 23, 2025Updated 4 months ago
- ☆59Mar 16, 2025Updated 11 months ago
- [NeurIPS 2025 D&B🔥] ImgEdit: A Unified Image Editing Dataset and Benchmark☆283Nov 5, 2025Updated 4 months ago
- Official Repo of Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents☆65Oct 28, 2025Updated 4 months ago
- [EMNLP 2025] Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking☆12Aug 22, 2025Updated 6 months ago
- V1: Toward Multimodal Reasoning by Designing Auxiliary Task☆36Apr 14, 2025Updated 10 months ago
- The Oyster series is a set of safety models developed in-house by Alibaba-AAIG, devoted to building a responsible AI ecosystem. | Oyster …☆59Sep 11, 2025Updated 5 months ago
- An official implementation of SwapAnyone.☆74Mar 14, 2025Updated 11 months ago
- ☆75Mar 18, 2025Updated 11 months ago
- [ICLR 2025] Understanding and Enhancing Safety Mechanisms of LLMs via Safety-Specific Neuron☆29Apr 30, 2025Updated 10 months ago
- [ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shi…☆71Feb 9, 2026Updated 3 weeks ago
- The official code for "TaxDiff: Taxonomic-Guided Diffusion Model for Protein Sequence Generation"☆74Aug 23, 2024Updated last year
- ☆19Jun 21, 2025Updated 8 months ago
- A Benchmark for Evaluating MLLMs' Geometry Performance on Long-Step Problems Requiring Auxiliary Lines☆32Mar 1, 2026Updated last week
- LLMBind: A Unified Modality-Task Integration Framework☆19Jun 16, 2024Updated last year
- Awsome of VLM-CL. Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting☆160Updated this week
- Code for paper OmniSSR☆23Apr 21, 2025Updated 10 months ago
- Unified Multi-modal IAA Baseline and Benchmark☆93Sep 27, 2024Updated last year
- [CVPR 2025🔥] Enhancing Video VAE by Wavelet-Driven Energy Flow for Latent Video Diffusion Model☆198May 11, 2025Updated 9 months ago
- Emoji Attack [ICML 2025]☆41Jul 15, 2025Updated 7 months ago
- The loss landscape of Large Language Models resemble basin!☆36Jul 8, 2025Updated 8 months ago
- 本项目用于Multimodal领域新手的学习路线，包括该领域的经典论文，项目及课程。旨在希望学习者在一定的时间内达到对这个领域有较为深刻的认知，能够自己进行的独立研究。☆45Mar 26, 2024Updated last year
- ☆24Dec 8, 2024Updated last year
- A Unified Benchmark and Toolbox for Multimodal Jailbreak Attack –Defense Evaluation☆59Mar 2, 2026Updated last week
- [NeurIPS 2024 D&B Spotlight🔥] ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation☆209May 27, 2025Updated 9 months ago
- Envision3D: One Image to 3D with Anchor Views Interpolation☆114May 16, 2024Updated last year