Knowledge catalogue
arXiv:2510.15476v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly used as interfaces to information, code, and real-world services, making prompt-level security f
This morning I released sqlite-utils 4.0, the 124th release of that project and the first major version bump since 3.0 in November 2020. In addition to some small but significant breaking changes (des
arXiv:2607.05168v1 Announce Type: new Abstract: Why do intelligent systems need to perform explicit symbolic reasoning? Computer science has traditionally regarded symbolic reasoning as a defining com
arXiv:2601.14192v2 Announce Type: replace Abstract: Recent years have witnessed increasing interest in extending large language models into agentic systems. While the effectiveness of agents has conti
arXiv:2607.04222v1 Announce Type: new Abstract: Interpretability methods aim to reveal the features represented inside large language models (LLMs). Many existing methods begin with labeled examples o
128 GB of memory is nice, but you can get started with local agentic AI workflows with much less. By connecting gemma 4 in @lmstudio to MATLAB MCP Server, you can run a local AI model that uses MATLAB
During a Bloomberg interview, Yann LeCun (@ylecun ) explains why LLMs are limited in terms of real-world intelligence during a Bloomberg interview. 'Language is a very approximate, reduced, quantized,
Interesting stuff. And the visualization at the end is worth trying: https://www.neuronpedia.org/qwen3.6-27b/jlens New Anthropic research: A global workspace in language models. Of everything happenin
We address the fundamental incompatibility of attention-based encoder-decoder (AED) models with long-form acoustic encodings. AED models trained on segmented utterances learn to encode absolute frame
Check out all the amazing work from our @SimonsFdn Collaboration on the Physics of Learning and Neural Computation (https://www.physicsoflearning.org/) presented at the main meeting of @ICMLconf #ICML
arXiv:2607.02131v1 Announce Type: cross Abstract: Restoring archival film remains a fundamentally challenging problem due to the absence of paired training data and the lack of standardized evaluation
arXiv:2604.08169v2 Announce Type: replace Abstract: Alignment in LLMs is more brittle than commonly assumed: misalignment can be induced by adversarial prompts, benign fine-tuning, emergent misalignme
arXiv:2506.06323v2 Announce Type: replace-cross Abstract: Model-free and reinforcement learning-based adaptive filtering methods are gaining traction for denoising in dynamic, non-stationary environme
arXiv:2607.01916v1 Announce Type: new Abstract: Large language model agents can repair real repository issues, but they often spend large context budgets on whole-file reads, broad searches, and long
arXiv:2607.01763v1 Announce Type: cross Abstract: Continual post-training enables foundation models to acquire new knowledge while preserving existing capabilities. Recent work suggests that on-policy
arXiv:2607.01984v1 Announce Type: cross Abstract: Newer lightweight convolutional neural networks are often presented as improving predictive performance and deployment efficiency, but such claims req
arXiv:2607.01789v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models scale efficiently but remain costly to adapt due to redundant experts and uniform parameter allocation. Existing param
Excited to share our paper, “Learning Multi-Agent Coordination via Sheaf-ADMM” to be presented at #ICML2026 Blog: https://pub.sakana.ai/sheaf-admm/ Most AI models process information as one giant, mon
arXiv:2311.17633v2 Announce Type: replace-cross Abstract: Transformers have dominated empirical machine learning models of natural language processing. In this paper, we introduce basic concepts of Tr
arXiv:2607.02513v1 Announce Type: cross Abstract: LLMs memorize sensitive training data, including personally identifiable information (PII), creating a pressing need for reliable post hoc removal met
arXiv:2607.01814v1 Announce Type: new Abstract: Traditional Chinese Medicine (TCM) diagnosis, particularly through tongue inspection, faces persistent challenges in subjectivity and reproducibility. T
arXiv:2607.02292v1 Announce Type: new Abstract: Neural quantum states (NQS) provide a flexible and scalable framework for approximating quantum many-body wavefunctions. Among NQS parameterizations, au
arXiv:2607.01518v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) have been increasingly integrated into robotic systems. However, these models may exhibit overthinking behaviors,
arXiv:2607.01306v1 Announce Type: new Abstract: Counterfactual explanations explain machine learning predictions by identifying minimal input changes that would alter a model's decision. Although many
arXiv:2506.12311v4 Announce Type: replace Abstract: Text-to-speech (TTS) for Modern Hebrew is challenged by the language's orthographic complexity, with existing solutions ignoring underspecified phon
arXiv:2607.02127v1 Announce Type: cross Abstract: Penile measurement is clinically relevant across male reproductive and urogenital health, including conditions such as micropenis, congenital and endo
arXiv:2607.01567v1 Announce Type: new Abstract: Deceptive behavior in LLMs is costly to monitor and prevent, motivating approaches such as Scalable Oversight via Lie Detectors (SOLiD) (Cundy & Gleave,
arXiv:2607.02203v1 Announce Type: new Abstract: Operator learning has emerged as a powerful tool for modeling complex physical systems in functional spaces. However, their neural network-based archite
arXiv:2607.01674v1 Announce Type: new Abstract: In multi-source ECG deployment, models may need to incorporate new data sources when earlier raw ECGs cannot be retained or replayed. Freezing a pretrai
arXiv:2607.01238v1 Announce Type: cross Abstract: Recent advances in speech synthesis have shifted from phoneme representations to direct grapheme modeling. While phonemes address the one-to-many mapp
arXiv:2607.01893v1 Announce Type: new Abstract: Speculative decoding accelerates autoregressive generation by drafting a block of tokens that the target model verifies left-to-right, committing only t
arXiv:2607.02049v1 Announce Type: cross Abstract: Large Language Models are increasingly deployed in emotional-support contexts and crisis-related situations. Nevertheless, their cross-lingual abiliti
arXiv:2607.01455v1 Announce Type: cross Abstract: Language models learn continuous programs over discrete symbols, with the embedding table and LM-head acting as the read/write interface between them.
arXiv:2607.02186v1 Announce Type: new Abstract: Software development is a complex task that demands cooperation among agents with diverse roles. Large language models (LLMs) have enabled autonomous mu
arXiv:2607.00127v1 Announce Type: new Abstract: Survival analysis models time-to-event data, but in clinical settings training data are costly and scarce: events accrue over years of follow-up, cohort
arXiv:2607.00052v1 Announce Type: cross Abstract: GraphRAG is an extension of retrieval-augmented generation (RAG) that supports large language models (LLMs) by referring to graph-structured data as e
arXiv:2607.00292v1 Announce Type: cross Abstract: Designing deployable and resilient network topologies from natural language requirements remains a challenging problem in network automation. This wor
arXiv:2607.00368v1 Announce Type: new Abstract: Large language model test-time training (TTT) is often evaluated through local proxy metrics: models are updated on recent tokens, retrieved context, ta
arXiv:2607.01084v1 Announce Type: new Abstract: While Large Language Model (LLM) agents demonstrate proficiency in static benchmarks, their deployment in real-world scenarios is hindered by the dynami
Continual learning is probably the biggest barrier to explosive AI adoption (& may have big implications for recursive self-improvement as well) As long as you deal with amnesiac models that require h
arXiv:2607.00223v1 Announce Type: new Abstract: Medical image segmentation is dominated by U-Net-style encoder-decoder architectures. Vision Transformers (ViTs) overcome the limited receptive field of
arXiv:2607.00535v1 Announce Type: cross Abstract: Few-step flow-map generators, such as consistency models and MeanFlow, accelerate sampling by directly learning long-range transport maps between nois
arXiv:2607.00025v1 Announce Type: cross Abstract: While deep learning models achieve state-of-the-art performance in complex tasks, they remain brittle when faced with new environments or sensory depr
GLM 5.2 DSpark preview is here! ✨ https://huggingface.co/RedHatAI/GLM-5.2-speculator.dspark-preview This is the first DSpark speculator for a non-DeepSeek frontier model, trained with Speculators and
arXiv:2607.00920v1 Announce Type: new Abstract: Real-world e-commerce image editing often requires multiple, localized, and auditable operations rather than global restyling. This compositional nature
arXiv:2507.05740v2 Announce Type: replace Abstract: Language models are powerful artifacts, yet their factual knowledge is still poorly understood, and inaccessible to ad-hoc browsing and scalable sta
arXiv:2607.01065v1 Announce Type: new Abstract: The deployment of Large Language Models (LLMs) with extended context windows is increasingly constrained by the linear growth of Key-Value (KV) cache me
arXiv:2607.00207v1 Announce Type: cross Abstract: We develop a framework for analyzing the learning dynamics of ell_2-adversarial training of single-index models on Gaussian mixtures in the high-dimen
arXiv:2607.00228v1 Announce Type: cross Abstract: Modern time-domain surveys such as the Zwicky Transient Facility (ZTF) generate hundreds of thousands of alerts each night, making real-time decisions
arXiv:2607.00090v1 Announce Type: cross Abstract: Urban-scale Visual Place Recognition (VPR) aims to identify the geographic location of a query image by matching it against a geo-tagged database. Whi
arXiv:2607.00250v1 Announce Type: new Abstract: Maltese has decent text corpora and pretrained language models, but, like many languages outside the handful with large OCR benchmarks, only a single kn
arXiv:2607.01077v1 Announce Type: new Abstract: While inference-time scaling has improved the reasoning abilities of large language models (LLMs), the need to generate long chains-of-thought (CoTs) is
arXiv:2602.21397v2 Announce Type: replace Abstract: Prompt learning has become a dominant paradigm for adapting vision-language models (VLMs) such as CLIP to downstream tasks without modifying pretrai
arXiv:2607.00259v1 Announce Type: cross Abstract: Test-Time Adaptation (TTA) seeks to improve model robustness under distribution shifts by adapting parameters using unlabeled target data. However, in
arXiv:2607.00461v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) are often constrained by a language-space bottleneck, forcing complex visual reasoning into discrete tokens whi
arXiv:2601.14660v2 Announce Type: replace-cross Abstract: Agentic Large Language Models (LLMs) are models able to reason, plan, and execute tools over unstructured data. These abilities are enabling t
arXiv:2603.15129v3 Announce Type: replace Abstract: We present a novel paradigm for ultra-low-bitrate image compression (ULB-IC) that exploits the ``temporal'' evolution in generative image compressio
This post likely discusses issues of model ownership and intellectual property rights in AI development, particularly regarding concerns about who controls trained model weights and the underlying neu
arXiv:2607.00832v1 Announce Type: cross Abstract: A single panorama captures the full visual sphere from one camera center, yet confines users to looking around in place without enabling true scene ex
arXiv:2607.00049v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used in Agile Software Development for documentation, coaching, and training. As practitioners adopt the