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.
- 2025-06arXiv 2506.18203Shrinking the Generation-Verification Gap with Weak Verifiers
Jon Saad-Falcon, E. Kelly Buchanan, Mayee F. Chen et al. · Language models & NLP
Verifiers can improve language model capabilities by scoring and ranking responses from generated candidates., tools like Lean).
- 2025-06arXiv 2506.17670Online Multi-LLM Selection via Contextual Bandits under Unstructured Context Evolution
Manhin Poon, XiangXiang Dai, Xutong Liu et al. · Machine learning
Large language models (LLMs) exhibit diverse response behaviors, costs, and strengths, making it challenging to select the most suitable LLM for a given user query.
- 2025-06arXiv 2506.16884The Importance of Being Lazy: Scaling Limits of Continual Learning
Jacopo Graldi, Alessandro Breccia, Giulia Lanzillotta et al. · Machine learning
Despite recent efforts, neural networks still struggle to learn in non-stationary environments, and our understanding of catastrophic forgetting (CF) is far from complete.
- 2025-06arXiv 2506.16406Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights
Zhiyuan Liang, Dongwen Tang, Yuhao Zhou et al. · Machine learning
Modern Parameter-Efficient Fine-Tuning (PEFT) methods such as low-rank adaptation (LoRA) reduce the cost of customizing large language models (LLMs), yet still require a separate optimization run for every downstream dataset.
- 2025-06arXiv 2507.00029LoRA-Mixer: Coordinate Modular LoRA Experts Through Serial Attention Routing
Wenbing Li, Zikai Song, Hang Zhou et al. · Machine learning
Recent attempts to combine low-rank adaptation (LoRA) with mixture-of-experts (MoE) for multi-task adaptation of Large Language Models (LLMs) often replace whole attention/FFN layers with switch experts or append parallel expert branches, undermining parameter efficiency and limiting task specialization.
- 2025-06arXiv 2506.13045Continual Learning for Generative AI: From LLMs to MLLMs and Beyond
Haiyang Guo, Fanhu Zeng, Fei Zhu et al. · Machine learning
The rapid advancement of generative models has empowered modern AI systems to comprehend and produce highly sophisticated content, even achieving human-level performance in specific domains.
- 2025-06arXiv 2506.12384Model Merging for Knowledge Editing
Zichuan Fu, Xian Wu, Guojing Li et al. · ACL 2025 (Industry) Oral · AI & agents
Large Language Models (LLMs) require continuous updates to maintain accurate and current knowledge as the world evolves.
- 2025-06arXiv 2506.11613Model Organisms for Emergent Misalignment
Edward Turner, Anna Soligo, Mia Taylor et al. · Machine learning
Recent work discovered Emergent Misalignment (EM): fine-tuning large language models on narrowly harmful datasets can lead them to become broadly misaligned.
- 2025-06arXiv 2506.12119Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource
Houyi Li, Ka Man Lo, Shijie Xuyang et al. · Language models & NLP
Mixture-of-Experts (MoE) language models dramatically expand model capacity and achieve remarkable performance without increasing per-token compute.
- 2025-06arXiv 2506.10943Self-Adapting Language Models
Adam Zweiger, Jyothish Pari, Han Guo et al. · Machine learning
Large language models (LLMs) are powerful but static; they lack mechanisms to adapt their weights in response to new tasks, knowledge, or examples. We introduce Self-Adapting LLMs (SEAL), a framework that enables LLMs to self-adapt by generating their own finetuning data and update directives.
Cited inCoherence is selected, anchored, then pruned: a literature synthesis on logical coherence in LLM world modelsA model rewrote another model's weights. Read what it took away.Study: Consequence consistent updatesStudy: Continual learning order and companion dataStudy: Fortifying knowledge in continual learningStudy: LLMs modifying open model weightsStudy: Logical coherence of LLM world modelsStudy: Seven continual learning methods testedStudy: Weight editing to prevent forgetting - 2025-06arXiv 2506.09849IntPhys 2: Benchmarking Intuitive Physics Understanding In Complex Synthetic Environments
Florian Bordes, Quentin Garrido, Justine T Kao et al. · Vision
We present IntPhys 2, a video benchmark designed to evaluate the intuitive physics understanding of deep learning models.
- 2025-06arXiv 2506.09985V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
Mido Assran, Adrien Bardes, David Fan et al. · AI & agents
A major challenge for modern AI is to learn to understand the world and learn to act largely by observation.
- 2025-06arXiv 2506.10139Unsupervised Elicitation of Language Models
Jiaxin Wen, Zachary Ankner, Arushi Somani et al. · Language models & NLP
To steer pretrained language models for downstream tasks, today's post-training paradigm relies on humans to specify desired behaviors. However, for models with superhuman capabilities, it is difficult or impossible to get high-quality human supervision.
- 2025-06arXiv 2506.08388Reinforcement Learning Teachers of Test Time Scaling
Edoardo Cetin, Tianyu Zhao, Yujin Tang · Machine learning
Training reasoning language models (LMs) with reinforcement learning (RL) for one-hot correctness inherently relies on the LM being able to explore and solve its task with some chance at initialization.
- 2025-06arXiv 2506.08572The Geometries of Truth Are Orthogonal Across Tasks
Waiss Azizian, Michael Kirchhof, Eugene Ndiaye et al. · Machine learning
Large Language Models (LLMs) have demonstrated impressive generalization capabilities across various tasks, but their claim to practical relevance is still mired by concerns on their reliability.
- 2025-06arXiv 2506.08920PropMEND: Hypernetworks for Knowledge Propagation in LLMs
Zeyu Leo Liu, Greg Durrett, Eunsol Choi · Language models & NLP
Knowledge editing techniques for large language models (LLMs) can inject knowledge that is later reproducible verbatim, but they fall short on propagating that knowledge: models cannot answer questions that require reasoning with the injected knowledge.
- 2025-06arXiv 2506.09038AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions
Polina Kirichenko, Mark Ibrahim, Kamalika Chaudhuri et al. · AI & agents
For Large Language Models (LLMs) to be reliably deployed in both everyday and high-stakes domains, knowing when not to answer is equally critical as answering correctly.
- 2025-06arXiv 2506.07962Correlated Errors in Large Language Models
Elliot Kim, Avi Garg, Kenny Peng et al. · Language models & NLP
Diversity in training data, architecture, and providers is assumed to mitigate homogeneity in LLMs. However, we lack empirical evidence on whether different LLMs differ meaningfully.
- 2025-06arXiv 2506.06105Text-to-LoRA: Instant Transformer Adaption
Rujikorn Charakorn, Edoardo Cetin, Yujin Tang et al. · Machine learning
While Foundation Models provide a general tool for rapid content creation, they regularly require task-specific adaptation. Traditionally, this exercise involves careful curation of datasets and repeated fine-tuning of the underlying model.
- 2025-06arXiv 2506.06278Distillation Robustifies Unlearning
Bruce W. Lee, Addie Foote, Alex Infanger et al. · Machine learning
Current LLM unlearning methods are not robust. A few steps of finetuning can revert their effects. We begin by showing that this is true even for an idealized form of unlearning: training to imitate a model that was never trained on unwanted information.
- 2025-06arXiv 2506.04595Hierarchical-Task-Aware Multi-modal Mixture of Incremental LoRA Experts for Embodied Continual Learning
Ziqi Jia, Anmin Wang, Xiaoyang Qu et al. · Vision
Previous continual learning setups for embodied intelligence focused on executing low-level actions based on human commands, neglecting the ability to learn high-level planning and multi-level knowledge.
- 2025-06arXiv 2506.03490Beyond Memorization: A Rigorous Evaluation Framework for Medical Knowledge Editing
Shigeng Chen, Linhao Luo, Zhangchi Qiu et al. · Language models & NLP
Recently, knowledge editing (KE) has emerged as a promising approach to update specific facts in Large Language Models (LLMs) without the need for full retraining.
- 2025-06arXiv 2506.03136Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning
Yinjie Wang, Ling Yang, Ye Tian et al. · Language models & NLP
We propose CURE, a novel reinforcement learning framework with a dedicated reward design that co-evolves coding and unit test generation capabilities based on their interaction outcomes, without any ground-truth code as supervision.
- 2025-06arXiv 2506.01656Mixture of Experts Provably Detect and Learn the Latent Cluster Structure in Gradient-Based Learning
Ryotaro Kawata, Kohsei Matsutani, Yuri Kinoshita et al. · Machine learning
Mixture of Experts (MoE), an ensemble of specialized models equipped with a router that dynamically distributes each input to appropriate experts, has achieved successful results in the field of machine learning.
- 2025-06arXiv 2506.01937RewardBench 2: Advancing Reward Model Evaluation
Saumya Malik, Valentina Pyatkin, Sander Land et al. · ICLR 2026 · Language models & NLP
Reward models are used throughout the post-training of language models to capture nuanced signals from preference data and provide a training target for optimization across instruction following, reasoning, safety, and more domains.
Cited inStudy: Genesys program prior art - 2025-06arXiv 2506.00823Probing the Geometry of Truth: Consistency and Generalization of Truth Directions in LLMs Across Logical Transformations and Question Answering Tasks
Yuntai Bao, Xuhong Zhang, Tianyu Du et al. · Language models & NLP
Large language models (LLMs) are trained on extensive datasets that encapsulate substantial world knowledge. However, their outputs often include confidently stated inaccuracies.
- 2025-06arXiv 2506.01048IRT-Router: Effective and Interpretable Multi-LLM Routing via Item Response Theory
Wei Song, Zhenya Huang, Cheng Cheng et al. · AI & agents
Large language models (LLMs) have demonstrated exceptional performance across a wide range of natural language tasks. However, selecting the optimal LLM to respond to a user query often necessitates a delicate balance between performance and cost.
- 2025-06arXiv 2506.01056MCP-Zero: Active Tool Discovery for Autonomous LLM Agents
Xiang Fei, Xiawu Zheng, Hao Feng · AI & agents
True intelligence requires active capability acquisition, yet current LLM agents inject pre-defined tool schemas into prompts, reducing models to passive selectors and falling short of robust general-purpose agency.
Cited inInternal notes - 2025-05arXiv 2505.24428Model Unlearning via Sparse Autoencoder Subspace Guided Projections
Xu Wang, Zihao Li, Benyou Wang et al. · Language models & NLP
Large language models (LLMs) store vast amounts of information, making them powerful yet raising privacy and safety concerns when selective knowledge removal is required.
- 2025-05arXiv 2506.03189Continual Learning in Vision-Language Models via Aligned Model Merging
Ghada Sokar, Gintare Karolina Dziugaite, Anurag Arnab et al. · Vision
Continual learning is conventionally tackled through sequential fine-tuning, a process that, while enabling adaptation, inherently favors plasticity over the stability needed to retain prior knowledge.
- 2025-05arXiv 2505.22954Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents
Jenny Zhang, Shengran Hu, Cong Lu et al. · AI & agents
Today's AI systems have human-designed, fixed architectures and cannot autonomously and continuously improve themselves. The advance of AI could itself be automated.
- 2025-05arXiv 2505.23295How Does Response Length Affect Long-Form Factuality
James Xu Zhao, Jimmy Z. J. Liu, Bryan Hooi et al. · Language models & NLP
Large language models (LLMs) are widely used for long-form text generation. However, factual errors in the responses would undermine their reliability. Despite growing attention to LLM factuality, the effect of response length on factuality remains underexplored.
- 2025-05arXiv 2505.23735ATLAS: Learning to Optimally Memorize the Context at Test Time
Ali Behrouz, Zeman Li, Praneeth Kacham et al. · Language models & NLP
Transformers have been established as the most popular backbones in sequence modeling, mainly due to their effectiveness in in-context retrieval tasks and the ability to learn at scale.
- 2025-05arXiv 2505.22370SplitLoRA: Balancing Stability and Plasticity in Continual Learning Through Gradient Space Splitting
Haomiao Qiu, Miao Zhang, Ziyue Qiao et al. · Machine learning
Continual Learning requires a model to learn multiple tasks in sequence while maintaining both stability:preserving knowledge from previously learned tasks, and plasticity:effectively learning new tasks.
- 2025-05arXiv 2505.22389Train with Perturbation, Infer after Merging: A Two-Stage Framework for Continual Learning
Haomiao Qiu, Miao Zhang, Ziyue Qiao et al. · Machine learning
Continual Learning (CL) aims to enable models to continuously acquire new knowledge from a sequence of tasks with avoiding the forgetting of learned information.
- 2025-05arXiv 2505.22631GPU-Accelerated Simulated Oscillator Ising/Potts Machine Solving Combinatorial Optimization Problems
Yilmaz Ege Gonul, Ceyhun Efe Kayan, Ilknur Mustafazade et al. · Hardware, photonics & physics
Oscillator-based Ising machines (OIMs) and oscillator-based Potts machines (OPMs) have emerged as promising hardware accelerators for solving NP-hard combinatorial optimization problems by leveraging the phase dynamics of coupled oscillators.
- 2025-05arXiv 2505.22696When Does Neuroevolution Outcompete Reinforcement Learning in Transfer Learning Tasks?
Eleni Nisioti, Joachim Winther Pedersen, Erwan Plantec et al. · Machine learning
The ability to continuously and efficiently transfer skills across tasks is a hallmark of biological intelligence and a long-standing goal in artificial systems.
- 2025-05arXiv 2505.20809Improved Representation Steering for Language Models
Zhengxuan Wu, Qinan Yu, Aryaman Arora et al. · Language models & NLP
Steering methods for language models (LMs) seek to provide fine-grained and interpretable control over model generations by variously changing model inputs, weights, or representations to adjust behavior.
- 2025-05arXiv 2505.21444Can Large Reasoning Models Self-Train?
Sheikh Shafayat, Fahim Tajwar, Ruslan Salakhutdinov et al. · Machine learning
Recent successes of reinforcement learning (RL) in training large reasoning models motivate the question of whether self-training - the process where a model learns from its own judgments - can be sustained within RL.
- 2025-05arXiv 2505.19106An Ultra-Low Power and Fast Ising Machine using Voltage-Controlled Magnetoresistive Random Access Memory
Sai Li, Yihao Zhang, Albert Lee et al. · Hardware, photonics & physics
Physics-inspired computing paradigms, such as Ising machines, are emerging as promising hardware alternatives to traditional von Neumann architectures for tackling computationally intensive combinatorial optimization problems (COPs).
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.
