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.
- 2025-08arXiv 2508.01908Revisiting Replay and Gradient Alignment for Continual Pre-Training of Large Language Models
Istabrak Abbes, Gopeshh Subbaraj, Matthew Riemer et al. · Machine learning
Training large language models (LLMs) typically involves pre-training on massive corpora, only to restart the process entirely when new data becomes available.
- 2025-07arXiv 2508.00161Watch the Weights: Unsupervised monitoring and control of fine-tuned LLMs
Ziqian Zhong, Aditi Raghunathan · Machine learning
The releases of powerful open-weight large language models (LLMs) are often not accompanied by access to their full training data. Existing interpretability methods, particularly those based on activations, often require or assume distributionally similar data.
- 2025-07arXiv 2508.00212Reinitializing weights vs units for maintaining plasticity in neural networks
J. Fernando Hernandez-Garcia, Shibhansh Dohare, Jun Luo et al. · Neuroscience & neural computation
Loss of plasticity is a phenomenon in which a neural network loses its ability to learn when trained for an extended time on non-stationary data. It is a crucial problem to overcome when designing systems that learn continually.
- 2025-07arXiv 2508.08275MLLM-CTBench: A Benchmark for Continual Instruction Tuning with Reasoning Process Diagnosis
Haiyun Guo, Zhiyan Hou, Yandu Sun et al. · Language models & NLP
Continual instruction tuning(CIT) during the post-training phase is crucial for adapting multimodal large language models (MLLMs) to evolving real-world demands.
- 2025-07arXiv 2507.21509Persona Vectors: Monitoring and Controlling Character Traits in Language Models
Runjin Chen, Andy Arditi, Henry Sleight et al. · Language models & NLP
Large language models interact with users through a simulated 'Assistant' persona. While the Assistant is typically trained to be helpful, harmless, and honest, it sometimes deviates from these ideals.
- 2025-07arXiv 2507.22117A comprehensive benchmark of an Ising machine on the Max-Cut problem
Salwa Shaglel, Markus Kirsch, Marten Winkler et al. · New J. Phys. (2026) · Hardware, photonics & physics
QUBO formulations of combinatorial optimization problems allow for solving them using various quantum heuristics. While large-scale quantum computations are currently still out of reach, we can already numerically test such QUBO formulations on a perhaps surprisingly large scale.
- 2025-07arXiv 2508.00914Knowledge Editing for Multi-Hop Question Answering Using Semantic Analysis
Dominic Simon, Rickard Ewetz · AI & agents
Large Language Models (LLMs) require lightweight avenues of updating stored information that has fallen out of date.
- 2025-07arXiv 2507.17702Towards Greater Leverage: Scaling Laws for Efficient Mixture-of-Experts Language Models
Changxin Tian, Kunlong Chen, Jia Liu et al. · Language models & NLP
Mixture-of-Experts (MoE) has become a dominant architecture for scaling Large Language Models (LLMs) efficiently by decoupling total parameters from computational cost.
- 2025-07arXiv 2507.16488ICR Probe: Tracking Hidden State Dynamics for Reliable Hallucination Detection in LLMs
Zhenliang Zhang, Xinyu Hu, Huixuan Zhang et al. · Language models & NLP
Large language models (LLMs) excel at various natural language processing tasks, but their tendency to generate hallucinations undermines their reliability.
- 2025-07arXiv 2507.16806Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty
Mehul Damani, Isha Puri, Stewart Slocum et al. · Machine learning
When language models (LMs) are trained via reinforcement learning (RL) to generate natural language "reasoning chains", their performance improves on a variety of difficult question answering tasks.
- 2025-07arXiv 2507.14392Characterizing Communication Patterns in Distributed Large Language Model Inference
Lang Xu, Kaushik Kandadi Suresh, Quentin Anthony et al. · Other
Large Language Models (LLMs) built on transformer architectures have transformed natural language processing, achieving remarkable performance across diverse applications.
Cited inThe Wrong Phase - 2025-07arXiv 2507.12399ROC-n-reroll: How verifier imperfection affects test-time scaling
Florian E. Dorner, Yatong Chen, André F. Cruz et al. · Machine learning
Test-time scaling aims to improve language model performance by leveraging additional compute during inference. Many works have empirically studied techniques such as Best-of-N (BoN) and Rejection Sampling (RS) that make use of a verifier to enable test-time scaling.
Cited inStudy: Genesys program prior art - 2025-07arXiv 2507.11181Mixture of Experts in Large Language Models
Danyang Zhang, Junhao Song, Ziqian Bi et al. · Machine learning
This paper presents a comprehensive review of the Mixture-of-Experts (MoE) architecture in large language models, highlighting its ability to significantly enhance model performance while maintaining minimal computational overhead.
- 2025-07arXiv 2507.11393A Neural Network Model of Complementary Learning Systems: Pattern Separation and Completion for Continual Learning
James P Jun, Vijay Marupudi, Raj Sanjay Shah et al. · Machine learning
Learning new information without forgetting prior knowledge is central to human intelligence. In contrast, neural network models suffer from catastrophic forgetting: a significant degradation in performance on previously learned tasks when acquiring new information.
- 2025-07arXiv 2507.10524Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation
Sangmin Bae, Yujin Kim, Reza Bayat et al. · Language models & NLP
Scaling language models unlocks impressive capabilities, but the accompanying computational and memory demands make both training and deployment expensive.
- 2025-07arXiv 2507.14198Retention analysis of edited knowledge after fine-tuning
Fufang Wen, Shichang Zhang · Language models & NLP
Large language models (LLMs) store vast amounts of knowledge, which often requires updates to correct factual errors, incorporate newly acquired information, or adapt model behavior.
- 2025-07arXiv 2507.09089Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity
Joel Becker, Nate Rush, Elizabeth Barnes et al. · AI & agents
Despite widespread adoption, the impact of AI tools on software development in the wild remains understudied. 16 developers with moderate AI experience complete 246 tasks in mature projects on which they have an average of 5 years of prior experience.
- 2025-07arXiv 2507.09177Continual Reinforcement Learning by Planning with Online World Models
Zichen Liu, Guoji Fu, Chao Du et al. · Machine learning
Continual reinforcement learning (CRL) refers to a naturalistic setting where an agent needs to endlessly evolve, by trial and error, to solve multiple tasks that are presented sequentially.
Cited inStudy: Genesys program prior art - 2025-07arXiv 2507.08427ChainEdit: Propagating Ripple Effects in LLM Knowledge Editing through Logical Rule-Guided Chains
Zilu Dong, Xiangqing Shen, Zinong Yang et al. · Language models & NLP
Current knowledge editing methods for large language models (LLMs) struggle to maintain logical consistency when propagating ripple effects to associated facts.
- 2025-07arXiv 2507.08794One Token to Fool LLM-as-a-Judge
Yulai Zhao, Haolin Liu, Dian Yu et al. · Machine learning
Large language models (LLMs) are increasingly trusted as automated judges, assisting evaluation and providing reward signals for training other models, particularly in reference-based settings like Reinforcement Learning with Verifiable Rewards (RLVR).
- 2025-07arXiv 2507.07417May I have your Attention? Breaking Fine-Tuning based Prompt Injection Defenses using Architecture-Aware Attacks
Nishit V. Pandya, Andrey Labunets, Sicun Gao et al. · Security
A popular class of defenses against prompt injection attacks on large language models (LLMs) relies on fine-tuning to separate instructions and data, so that the LLM does not follow instructions that might be present with data.
- 2025-07arXiv 2507.06952What Has a Foundation Model Found? Using Inductive Bias to Probe for World Models
Keyon Vafa, Peter G. Chang, Ashesh Rambachan et al. · Machine learning
Foundation models are premised on the idea that sequence prediction can uncover deeper domain understanding, much like how Kepler's predictions of planetary motion later led to the discovery of Newtonian mechanics.
- 2025-07arXiv 2507.07140Exploring Sparse Adapters for Scalable Merging of Parameter Efficient Experts
Samin Yeasar Arnob, Zhan Su, Minseon Kim et al. · Machine learning
Merging parameter-efficient task experts has recently gained growing attention as a way to build modular architectures that can be rapidly adapted on the fly for specific downstream tasks, without requiring additional fine-tuning.
- 2025-07arXiv 2507.05257Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
Yuanzhe Hu, Yu Wang, Julian McAuley · Language models & NLP
Recent benchmarks for Large Language Model (LLM) agents primarily focus on evaluating reasoning, planning, and execution capabilities, while another critical component-memory, encompassing how agents memorize, update, and retrieve long-term information-is under-evaluated due to the lack of benchmarks.
Cited inInternal notes - 2025-07arXiv 2507.03662Re-Emergent Misalignment: How Narrow Fine-Tuning Erodes Safety Alignment in LLMs
Jeremiah Giordani · Machine learning
Recent work has shown that fine-tuning large language models (LLMs) on code with security vulnerabilities can result in misaligned and unsafe behaviors across broad domains.
- 2025-07arXiv 2507.02503Continual Gradient Low-Rank Projection Fine-Tuning for LLMs
Chenxu Wang, Yilin Lyu, Zicheng Sun et al. · Machine learning
Continual fine-tuning of Large Language Models (LLMs) is hampered by the trade-off between efficiency and expressiveness.
- 2025-07arXiv 2507.02770Blueprint, Bootstrap, and Bridge: A Security Look at NVIDIA GPU Confidential Computing
Zhongshu Gu, Enriquillo Valdez, Salman Ahmed et al. · Security
NVIDIA GPU Confidential Computing (GPU-CC) aims to provide secure execution for AI workloads. For end users, enabling GPU-CC is seamless and requires no modifications to existing applications.
- 2025-07arXiv 2507.02199Latent Chain-of-Thought? Decoding the Depth-Recurrent Transformer
Wenquan Lu, Yuechuan Yang, Kyle Lee et al. · Language models & NLP
Chain-of-thought (CoT) reasoning has enabled transformer-based language models to excel at complex mathematics and multi-step planning. However, in standard decoder-only architectures, these reasoning steps are externalized in natural language, improving interpretability at the cost of efficiency.
- 2025-06arXiv 2506.24119SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning
Bo Liu, Leon Guertler, Simon Yu et al. · AI & agents
Recent advances in reinforcement learning have shown that language models can develop sophisticated reasoning through training on tasks with verifiable rewards, but these approaches depend on human-curated problem-answer pairs and domain-specific reward engineering.
- 2025-06arXiv 2506.23266Sub-MoE: Efficient Mixture-of-Expert LLMs Compression via Subspace Expert Merging
Lujun Li, Zhu Qiyuan, Jiacheng Wang et al. · Machine learning
Mixture of Experts (MoE) LLMs face significant obstacles due to their massive parameter scale, which imposes memory, storage, and deployment challenges.
- 2025-06arXiv 2506.23423TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs
Felipe Nuti, Tim Franzmeyer, João Henriques · Language models & NLP
Past work has studied the effects of fine-tuning on large language models' (LLMs) overall performance on certain tasks. However, a quantitative and systematic method for analyzing its effect on individual outputs is still lacking.
- 2025-06arXiv 2506.21872A Survey of Continual Reinforcement Learning
Chaofan Pan, Xin Yang, Yanhua Li et al. · Machine learning
Reinforcement Learning (RL) is an important machine learning paradigm for solving sequential decision-making problems. Recent years have witnessed remarkable progress in this field due to the rapid development of deep neural networks.
Cited inStudy: Genesys program prior art - 2025-06arXiv 2506.22405Sequential Diagnosis with Language Models
Harsha Nori, Mayank Daswani, Christopher Kelly et al. · Language models & NLP
Artificial intelligence holds great promise for expanding access to expert medical knowledge and reasoning.
Cited inStudy: Superintelligence - 2025-06arXiv 2506.21035Little by Little: Continual Learning via Incremental Mixture of Rank-1 Associative Memory Experts
Haodong Lu, Chongyang Zhao, Minhui Xue et al. · Machine learning
Continual learning (CL) with large pre-trained models aims to incrementally acquire knowledge without catastrophic forgetting.
- 2025-06arXiv 2506.20650Mastering Multiple-Expert Routing: Realizable -Consistency and Strong Guarantees for Learning to Defer
Anqi Mao, Mehryar Mohri, Yutao Zhong · Machine learning
The problem of learning to defer with multiple experts consists of optimally assigning input instances to experts, balancing the trade-off between their accuracy and computational cost.
- 2025-06arXiv 2506.19248Inference-Time Reward Hacking in Large Language Models
Hadi Khalaf, Claudio Mayrink Verdun, Alex Oesterling et al. · Machine learning
A common paradigm to improve the performance of large language models is optimizing for a reward model. Reward models assign a numerical score to an LLM's output that indicates, for example, how likely it is to align with user preferences or safety goals.
- 2025-06arXiv 2506.19964Higher-Order Neuromorphic Ising Machines -- Autoencoders and Fowler-Nordheim Annealers are all you need for Scalability
Faiek Ahsan, Saptarshi Maiti, Zihao Chen et al. · Neuroscience & neural computation
We report a higher-order neuromorphic Ising machine that exhibits superior scalability compared to architectures based on quadratization, while also achieving state-of-the-art quality and reliability in solutions with competitive time-to-solution metrics.
- 2025-06arXiv 2506.18349SlimMoE: Structured Compression of Large MoE Models via Expert Slimming and Distillation
Zichong Li, Chen Liang, Zixuan Zhang et al. · Machine learning
The Mixture of Experts (MoE) architecture has emerged as a powerful paradigm for scaling large language models (LLMs) while maintaining inference efficiency. However, their enormous memory requirements make them prohibitively expensive to fine-tune or deploy in resource-constrained environments.
- 2025-06arXiv 2506.18781Existing LLMs Are Not Self-Consistent For Simple Tasks
Zhenru Lin, Jiawen Tao, Yang Yuan et al. · Language models & NLP
Large Language Models (LLMs) have grown increasingly powerful, yet ensuring their decisions remain transparent and trustworthy requires self-consistency -- no contradictions in their internal reasoning.
- 2025-06arXiv 2506.18183Reasoning about Uncertainty: Do Reasoning Models Know When They Don't Know?
Zhiting Mei, Christina Zhang, Tenny Yin et al. · AI & agents
Reasoning language models have set state-of-the-art (SOTA) records on many challenging benchmarks, enabled by multi-step reasoning induced using reinforcement learning.
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.
