NeuroGenesysThe research we build on.
1,514 papers by other researchers that our work cites, from continual learning and verification to language models, agents and hardware. Each entry links to the paper on arXiv and to where we use it. 301 are cited on published pages of this site; the rest in the research notes behind our studies. Our own papers are in the archive.
- 2026-10arXiv 2610.25914FisherEdit: Fisher Information Guided Knowledge Editing for Large Language Models
Yizhou Yang, Jiahong Fu, Zhiwu Wang et al. · Language models & NLP
Sequential knowledge editing in Large Language Models (LLMs) often leads to a degradation of general capabilities due to cumulative parameter interference.
- 2026-09arXiv 2609.19799Evolution or Illusion? Rethinking Evaluation in LLM Evolutionary Search
Tal Oved, Roi Pony, Oshri Naparstek et al. · Language models & NLP
LLM-driven evolutionary search finds programs by launching seeds and iterating each one. Papers report a single budget setting, usually one seed run for a fixed number of iterations, and rank methods from that one point.
- 2026-08arXiv 2608.05499APQF: Agentic Profiling-Guided Structured Pruning and Mixed-Precision Quantization with Adaptive Fine-Tuning
Sadegh Jafari, Mohiuddin Bilwal, Fan Zhou et al. · Vision
Modern deep neural networks achieve strong performance, but their scale makes them costly and slow, especially on resource-constrained edge devices. Pruning and quantization address this, but rely on manual, expert choices and on algorithms that are hard to apply across architectures.
- 2026-07arXiv 2607.17427Abliteration Is Not a Scalpel: Off-Target Effects of Refusal Removal on Decision Disposition Across Model Families
Aleksander Fafuła · Machine learning
Abliteration - deleting a model's refusal direction from its weights - is the standard recipe behind popular "uncensored" open-weight models. We show the surgery is not clean.
- 2026-07arXiv 2608.14611The 2026 Singapore Consensus on Global AI Safety Research Priorities
Stephen Casper, Oskar Galeev, Yoshua Bengio et al. · Society, software & economics
Frontier AI capabilities and autonomy are advancing rapidly. A growing number of real-world incidents make a trusted AI ecosystem essential to embracing AI with confidence.
- 2026-07arXiv 2607.02964Individual Parameters in Weight-Sparse Transformers Appear Interpretable
Arnau Marin-Llobet, Stefan Heimersheim · Machine learning
A central goal of mechanistic interpretability is to understand how neural networks work and what each individual component does. Dominant circuit-finding approaches focus on a specific behavior and reverse-engineer the role of components on the associated sub-distribution.
- 2026-07arXiv 2608.07514Open Technical Problems in Open-Weight AI Model Risk Management
Stephen Casper, Kyle O'Brien, Shayne Longpre et al. · Society, software & economics
Frontier AI models with openly available weights are steadily becoming more powerful and widely adopted. However, compared to proprietary models, open-weight models pose different opportunities and challenges for effective risk management.
- 2026-06arXiv 2606.26783Reproducibility Study of "AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models"
Ananth K Suresh, Arya Hariharan · Machine learning
Fang et al.
- 2026-06arXiv 2606.24026Can Language Model Agents be Helpful Circuit Explainers in Mechanistic Interpretability?
Ayan Antik Khan, Harsh Kohli, Yuekun Yao et al. · AI & agents
Mechanistic interpretability has made substantial progress in automatically localizing circuits, but explaining what localized components do remains labor-intensive and difficult to standardize.
- 2026-06arXiv 2606.23276Exposing the Illusion of Erasure in Knowledge Editing for LLMs
Advik Raj Basani, Anshuman Chhabra · Machine learning
Knowledge Editing (KE) has emerged as a frontier for updating specific facts in LLMs without costly retraining, but its reliability and underlying mechanisms remain poorly understood.
- 2026-06arXiv 2606.19679LOKI: Memory-Free Null-Space Constrained Lifelong Knowledge Editing
Masih Eskandar, Miquel Sirera Perelló, Stratis Ioannidis et al. · Machine learning
Lifelong knowledge editing aims to efficiently and sequentially update language models over time, as new knowledge becomes available or when the model makes mistakes, while preserving acceptable performance on past knowledge.
- 2026-06arXiv 2606.09707BrainSurgery: Reproducible and Flexible Declarative Weight Manipulations for Model Editing and Upcycling
Gianluca Barmina, Annemette Broch Pirchert, Andrea Blasi Núñez et al. · Machine learning
Checkpoint transformations such as model merging, precision casting, and low-rank rewriting are commonly implemented through Python code or separate task-specific tools.
- 2026-06arXiv 2606.03979Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories
Ali Behrouz, Farnoosh Hashemi, Adel Javanmard et al. · Machine learning
The past few decades have witnessed significant advances in the design of machine learning algorithms, from early studies on task-specific shallow models to more general deep Large Language Models (LLMs).
Cited inInvestors are paying for agents that learn on the job. The hard part is knowing what they forgot.To keep what a model knows, control what it is allowed to moveWhat a model lets into long-term memory matters more than how it learnsStudy: Fortifying knowledge in continual learningStudy: Genesys program prior artStudy: Hardware guardian core for continual learningStudy: LLMs modifying open model weightsStudy: Logical coherence of LLM world modelsStudy: Memory world models and source trustStudy: Seven continual learning methods tested - 2026-05arXiv 2605.26526Open-Weight LLM Fine-Tuning Defenses are Susceptible to Simple Attacks
Kevin Kuo, Virginia Smith, Chhavi Yadav · Machine learning
Recent defenses for safeguarding open-weight large language models (LLMs) are intended to prevent adversarial usage. Underlying these defenses is an assumption that new harmful behavior is learned through fine-tuning rather than elicited by jailbreaking the model.
- 2026-05arXiv 2605.27276SIA: Self Improving AI with Harness & Weight Updates
Prannay Hebbar, Yogendra Manawat, Samuel Verboomen et al. · AI & agents
Humans are the bottleneck in building and improving AI. Both the models and the agents that wrap them are written, tuned, and corrected by people. The long-horizon goal of an AI that can figure out how to improve itself remains open.
- 2026-05arXiv 2605.24426SEAL: Synergistic Co-Evolution of Agents and Learning Environments
Yihao Hu, Zhihao Wen, Pan Wang et al. · Language models & NLP
Large language model (LLM) agents increasingly learn through interaction, yet their training process often evolves unevenly: the policy changes with experience while the learning environment continues to provide largely fixed forms of support.
- 2026-05arXiv 2605.16686Scalable Knowledge Editing for Mixture-of-Experts LLMs via Tensor-Structured Updates
Roman Maksimov, Vladimir Aletov, Dmitry Bylinkin et al. · Machine learning
Knowledge editing (KE) provides a lightweight alternative to repeated fine-tuning of LLMs. However, most existing KE methods target dense feed-forward layers, while modern LLMs increasingly adopt Mixture-of-Experts (MoE) architectures for their superior memory footprint and inference efficiency.
- 2026-05arXiv 2605.09285BetaEdit: Null-Space Constrained Sequential Model Editing
Bingqing Liu, Wei Liu, Yuhua Li · Language models & NLP
Null-space-based methods have garnered considerable attention in model editing by constraining updates to the null space of the pre-existing knowledge representation, thereby preserving the model's original behavior.
- 2026-05arXiv 2605.07076Self-Consolidating Language Models: Continual Knowledge Incorporation from Context
Zekun Wang, Anant Gupta, Zihan Dong et al. · Language models & NLP
Large language models (LLMs) increasingly receive information as streams of passages, conversations, and long-context workflows. While longer context windows expose more evidence, they do not ensure that useful information is preserved and reused.
- 2026-04arXiv 2604.19089Towards Scalable Lifelong Knowledge Editing with Selective Knowledge Suppression
Dahyun Jung, Jaewook Lee, Heuiseok Lim · AI & agents
Large language models (LLMs) require frequent knowledge updates to reflect changing facts and mitigate hallucinations. To meet this demand, lifelong knowledge editing has emerged as a continual approach to modify specific pieces of knowledge without retraining the entire model.
- 2026-03arXiv 2603.09938Model Merging in the Era of Large Language Models: Methods, Applications, and Future Directions
Mingyang Song, Mao Zheng · Language models & NLP
Model merging combines the parameters of multiple neural networks into a single model without additional training.
- 2026-03arXiv 2603.10090A Survey of Weight Space Learning: Understanding, Representation, and Generation
Xiaolong Han, Zehong Wang, Bo Zhao et al. · Machine learning
Neural network weights are typically viewed as the end product of training, while most deep learning research focuses on data, features, and architectures.
- 2026-03arXiv 2603.08640PostTrainBench: Can LLM Agents Automate LLM Post-Training?
Ben Rank, Hardik Bhatnagar, Ameya Prabhu et al. · Society, software & economics
AI agents have become surprisingly proficient at software engineering over the past year, largely due to improvements in reasoning capabilities. This raises a deeper question: can these systems extend their capabilities to automate AI research itself?
- 2026-02arXiv 2602.21012International AI Safety Report 2026
Yoshua Bengio, Stephen Clare, Carina Prunkl et al. · Society, software & economics
The International AI Safety Report 2026 synthesises the current scientific evidence on the capabilities, emerging risks, and safety of general-purpose AI systems.
- 2026-02arXiv 2602.16931Narrow Fine-Tuning Erodes Safety Alignment in Vision-Language Agents
Idhant Gulati, Shivam Raval · AI & agents
Lifelong multimodal agents must continuously adapt to new tasks through post-training, but this creates a fundamental tension between acquiring capabilities and preserving safety alignment.
- 2026-02arXiv 2602.15902Doc-to-LoRA: Learning to Instantly Internalize Contexts
Rujikorn Charakorn, Edoardo Cetin, Shinnosuke Uesaka et al. · Language models & NLP
Long input sequences are central to in-context learning, document understanding, and multi-step reasoning of Large Language Models (LLMs). However, the quadratic attention cost of Transformers makes inference memory-intensive and slow.
- 2026-02arXiv 2602.06358SHINE: A Scalable In-Context Hypernetwork for Mapping Context to LoRA in a Single Pass
Yewei Liu, Xiyuan Wang, Yansheng Mao et al. · Language models & NLP
We propose SHINE (Scalable Hyper In-context NEtwork), a scalable hypernetwork that can map diverse meaningful contexts into high-quality LoRA adapters for large language models (LLMs).
- 2026-02arXiv 2602.13273MergePipe: A Budget-Aware Parameter Management System for Scalable LLM Merging
Yuanyi Wang, Yanggan Gu, Zihao Wang et al. · Retrieval & data
Large language model (LLM) merging has become a key technique in modern LLM development pipelines, enabling the integration of multiple task- or domain-specific expert models without retraining.
- 2026-01arXiv 2601.12272AgenticPruner: MAC-Constrained Neural Network Compression via LLM-Driven Strategy Search
Shahrzad Esmat, Mahdi Banisharif, Ali Jannesari · Vision
Neural network pruning remains essential for deploying deep learning models on resource-constrained devices, yet existing approaches primarily target parameter reduction without directly controlling computational cost.
- 2026-01arXiv 2601.11516Building Production-Ready Probes For Gemini
János Kramár, Joshua Engels, Zheng Wang et al. · Machine learning
Frontier language model capabilities are improving rapidly. We thus need stronger mitigations against bad actors misusing increasingly powerful systems.
- 2026-01arXiv 2601.09694LLMs can Compress LLMs: Adaptive Pruning by Agents
Sai Varun Kodathala, Rakesh Vunnam · Language models & NLP
As Large Language Models (LLMs) continue to scale, post-training pruning has emerged as a promising approach to reduce computational costs while preserving performance.
- 2026-01arXiv 2601.08489Surgical Refusal Ablation: Disentangling Safety from Intelligence via Concept-Guided Spectral Cleaning
Tony Cristofano · Language models & NLP
Safety-aligned language models systematically refuse harmful requests. While activation steering can modulate refusal, ablating the raw "refusal vector" calculated from contrastive harmful and harmless prompts often causes collateral damage and distribution drift.
- 2025-12arXiv 2512.23675End-to-End Test-Time Training for Long Context
Arnuv Tandon, Karan Dalal, Xinhao Li et al. · Machine learning
We formulate long-context language modeling as a problem in continual learning rather than architecture design. Under this formulation, we only use a standard architecture -- a Transformer with sliding-window attention.
- 2025-12arXiv 2512.13655Comparative Analysis of LLM Abliteration Methods: A Cross-Architecture Evaluation
Richard J. Young · Language models & NLP
Safety alignment mechanisms in large language models prevent responses to harmful queries through learned refusal behavior, yet these same mechanisms impede legitimate research applications including cognitive modeling, adversarial testing, and security analysis.
- 2025-12arXiv 2512.04753EtCon: Edit-then-Consolidate for Reliable Knowledge Editing
Ruilin Li, Yibin Wang, Wenhong Zhu et al. · Language models & NLP
Knowledge editing aims to update specific facts in large language models (LLMs) without full retraining. Prior efforts sought to tune the knowledge layers of LLMs, achieving improved performance in controlled, teacher-forced evaluations.
- 2025-11arXiv 2511.18977FastForward Pruning: Efficient LLM Pruning via Single-Step Reinforcement Learning
Xin Yuan, Siqi Li, Jiateng Wei et al. · Machine learning
Pruning is an effective method for compressing Large Language Models, but finding an optimal, non-uniform layer-wise sparsity allocation remains a key challenge.
- 2025-11arXiv 2511.12661Reason-KE++: Aligning the Process, Not Just the Outcome, for Faithful LLM Knowledge Editing
Yuchen Wu, Liang Ding, Li Shen et al. · Language models & NLP
Aligning Large Language Models (LLMs) to be faithful to new knowledge in complex, multi-hop reasoning tasks is a critical, yet unsolved, challenge., Reason-KE, while state-of-the-art, suffer from a "faithfulness gap": they optimize for format mimicry rather than sound reasoning.
- 2025-10arXiv 2510.13851EvoEdit: Evolving Null-space Alignment for Robust and Efficient Knowledge Editing
Sicheng Lyu, Yu Gu, Xinyu Wang et al. · Language models & NLP
Large language models (LLMs) require continual updates to rectify outdated or erroneous knowledge. Model editing has emerged as a compelling paradigm for introducing targeted modifications without the computational burden of full retraining.
- 2025-09arXiv 2509.12951Black-box Model Merging for Language-Model-as-a-Service with Massive Model Repositories
Shilian Chen, Jie Zhou, Tianyu Huai et al. · AI & agents
Model merging refers to the process of integrating multiple distinct models into a unified model that preserves and combines the strengths and capabilities of the individual models.
- 2025-09arXiv 2509.06608Small Vectors, Big Effects: A Mechanistic Study of RL-Induced Reasoning via Steering Vectors
Viacheslav Sinii, Nikita Balagansky, Gleb Gerasimov et al. · Machine learning
The mechanisms by which reasoning training reshapes LLMs' internal computations remain unclear. We study lightweight steering vectors inserted into the base model's residual stream and trained with a reinforcement-learning objective.
Built from every arXiv paper cited in our papers, posts, topic hubs, reports and research notes, with titles, authors, dates and abstracts from the arXiv API (updated 2026-11-12). Summaries are the opening sentences of each paper's own abstract, not our assessment; a citation means we used or checked the work, not that we endorse it. Fields follow each paper's primary arXiv category. Papers cited only outside arXiv (journals, proceedings) are not listed yet. Entries are generated from our citations, so a mistyped ID in a note would list the wrong paper; we remove those as we find them. Report a wrong entry.
