Knowledge catalogue
arXiv:2608.04454v1 Announce Type: new Abstract: Mixture-of-experts vision-language models (MoE-VLMs) increase model capacity with sparse expert activation, yet deployment requires storing the full exp
arXiv:2608.04996v1 Announce Type: new Abstract: World Action Models (WAMs) learn action-relevant representations by predicting how the observed world will evolve. Most existing WAMs define this future
arXiv:2608.04703v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for question answering, education, and research, including in religious and cultural domains where an
arXiv:2510.20690v3 Announce Type: replace-cross Abstract: Language models continue to hallucinate despite increases in parameters, compute, and data. We propose neural diversity -- decorrelated parall
Open models give teams more room to run agent loops, with API prices at a fraction of GPT-5.6 Sol and Claude Fable 5. That matters as planning, tool calls, retries, and long contexts compound token us
arXiv:2608.05064v1 Announce Type: cross Abstract: Small open-weight language models increasingly run in private, offline, and cost-sensitive settings, where the key deployment question is not only wha
This definitely seems like something worth noting, and illustrates the gap between Fable/Astra class models and the previous frontier that was 'merely' good at hacking under human instructions. Initia
arXiv:2601.16217v2 Announce Type: replace-cross Abstract: Large language models increasingly mediate multilingual professional communication, where useful generation requires adapting to community con
arXiv:2608.03044v1 Announce Type: cross Abstract: Large language models are increasingly used to simulate human opinions, but prior work reports conflicting results: some studies find promising alignm
arXiv:2608.02830v1 Announce Type: cross Abstract: Many-shot in-context learning (ICL) lets vision-language models (VLMs) adapt from image--label demonstrations without weight updates, and is widely as
arXiv:2603.19066v2 Announce Type: replace-cross Abstract: Four-term word analogies (A:B::C:D) are classically modeled geometrically as parallelograms: adding the vector B-A+C produces D. Recent work s
arXiv:2608.03457v1 Announce Type: new Abstract: Diffusion language models (dLLMs) offer an alternative to autoregressive (AR) language modeling, yet the scaling behavior of Mixture-of-Experts (MoE) dL
arXiv:2207.12877v3 Announce Type: replace Abstract: Motivated by the successes of deep learning, we propose a class of neural network-based discrete choice models, called RUMnets, inspired by the rand
arXiv:2608.03512v1 Announce Type: new Abstract: Large language models (LLMs) have achieved strong performance on text-to-knowledge graph generation and related tasks. Nevertheless, it is still unclear
Third-party cyber evaluations involving OpenAI models And another one. I had to create a accidental-cyberattacks tag to keep track of them all! This post from OpenAI covers both the UK AI Safety Insti
arXiv:2606.19625v2 Announce Type: replace Abstract: We use training-data attribution as an interpretable tool for capability discovery, mapping which regions of the pretraining corpus support social-r
arXiv:2509.13374v2 Announce Type: replace-cross Abstract: We develop and audit a history-aware financial path generator based on Denoising Levy Probabilistic Models (DLPMs) for conditional equity-inde
arXiv:2608.01292v1 Announce Type: new Abstract: Legal reasoning is inherently jurisdiction-dependent: the same facts can call for different legal rules and yield different conclusions across legal sys
arXiv:2608.01290v1 Announce Type: new Abstract: Time-series foundation models (TSFMs) such as Chronos have demonstrated strong forecasting capabilities across domains, yet adapting them to institution
arXiv:2608.01896v1 Announce Type: new Abstract: Existing generative models for earth observation (EO) predominantly rely on fine-tuning natural image priors, which limits their scalability and introdu
arXiv:2608.02089v1 Announce Type: new Abstract: Large language models often show users a final response and a short reasoning summary while the full reasoning trace stays hidden. We introduce an obser
arXiv:2601.21369v2 Announce Type: replace Abstract: Recent studies of federated graph foundational models (FedGFMs) break the idealized and untenable assumption of having centralized data storage to t
arXiv:2608.02052v1 Announce Type: new Abstract: Human mobility prediction models, which forecast the next location in a user's trajectory, are increasingly deployed in urban analytics, navigation, and
arXiv:2608.01709v1 Announce Type: new Abstract: Vision-language models (VLMs) achieve strong semantic understanding but remain unreliable in metric spatial reasoning, particularly when queries require
arXiv:2606.13993v2 Announce Type: replace Abstract: A crucial aspect of linguistic capability is the ability to trade off between stored representations and abstract knowledge: one must retrieve learn
arXiv:2608.00042v1 Announce Type: new Abstract: Domain adaptation of small language models (SLMs) has emerged as a practical strategy for deploying capable NLP systems in resource-constrained, high-st
arXiv:2608.00019v1 Announce Type: new Abstract: Deploying large language models (LLMs) for operations research (OR) tasks remains challenging because correctness depends on a coherent modeling process
arXiv:2608.00410v1 Announce Type: cross Abstract: Human language is highly polysemous. Many common words (e.g., 'bank' or 'palm') carry several distinct meanings that shape what humans communicate and
arXiv:2607.28706v1 Announce Type: cross Abstract: We study the convergence properties of the random-sweep Gibbs sampler for Gaussian graphical models with a thin-membrane prior. We demonstrate that th
arXiv:2502.19135v2 Announce Type: replace Abstract: We present PLANTOR, a framework for generating and executing multi-robot task plans from natural-language task descriptions through LLM-assisted kno
arXiv:2607.29185v1 Announce Type: new Abstract: Reward models (RMs) are central to aligning large language models with human preferences via reinforcement learning. Although traditional scalar RMs ena
arXiv:2607.29125v1 Announce Type: new Abstract: Full-duplex spoken dialogue systems (FDSDSs) can listen while speaking, enabling natural behaviors such as smooth turn-taking, backchannel handling, and
A few people asked for this after the bandwidth thread, so here it is on its own instead of buried in a comment. The dense rule was simple: every token reads every weight, so tokens/sec ≈ bandwidth ÷
arXiv:2607.28464v1 Announce Type: new Abstract: Detection and localization of AI-tampered images are critical for trustworthy AI, yet modern generative models have made such manipulations increasingly
arXiv:2602.23050v2 Announce Type: replace Abstract: Deep state-space models (DSSMs) enable temporal predictions by learning the underlying dynamics of observed sequence data. They are often trained by
arXiv:2607.27281v1 Announce Type: new Abstract: A capability appears in a language model when the last parts of its circuit align in one stochastic attempt, and getting all but one right is worth noth
arXiv:2607.27553v1 Announce Type: cross Abstract: This research evaluates the efficacy of large language models (LLMs) in generating new product ideas. To do so, we compare three pools of ideas for ne
arXiv:2607.27966v1 Announce Type: new Abstract: Graph Foundation Models (GFMs) have recently emerged as a promising paradigm for general-purpose graph learning, aiming to learn reusable knowledge that
arXiv:2607.26712v1 Announce Type: new Abstract: Latent world models support efficient model-predictive control by optimizing future control sequences in latent space and replanning in a receding-horiz
arXiv:2510.20535v2 Announce Type: replace Abstract: Recent techniques such as retrieval-augmented generation or chain-of-thought reasoning have led to longer contexts and increased inference costs. Co
arXiv:2607.26492v1 Announce Type: new Abstract: The Mass-Conserving Perceptron (MCP) establishes a modeling paradigm in which conceptual hydrologic models can be reformulated as physically constrained
arXiv:2607.27180v1 Announce Type: new Abstract: Evaluating whether a vision-language model (VLM) can act through a physical body is challenging. The outcome of an action couples the VLM's decision wit
arXiv:2607.26762v1 Announce Type: new Abstract: When it comes to generating vector representations of words, current language models are achieving high-quality results. However, what is not known is t
arXiv:2607.26670v1 Announce Type: cross Abstract: The rapid growth of scholarly literature has made identifying relevant publications increasingly difficult, and conventional search systems still depe
arXiv:2607.26845v1 Announce Type: new Abstract: Inference-time thinking improves the performance of large language models, but aggregate outcomes do not reveal whether models use available evidence mo
arXiv:2607.24999v1 Announce Type: cross Abstract: LLM cognitive scores are increasingly summarized as per-ability profiles whose dimensions should converge across tasks, respond selectively to matched
arXiv:2607.25063v1 Announce Type: new Abstract: Developers judge a model checkpoint by how it behaves. After supervised fine-tuning (SFT), two checkpoints that perform about the same across relevant b
arXiv:2506.21571v3 Announce Type: replace-cross Abstract: Large Reasoning Models (LRMs), which autonomously produce a reasoning Chain of Thought (CoT) before producing final responses, offer a promisi
arXiv:2607.23602v1 Announce Type: cross Abstract: Controllers based on sampling and latent world models assign a predicted terminal cost to each candidate action sequence, choose the minimum, execute
arXiv:2607.24312v1 Announce Type: new Abstract: Document-level relation extraction (DocRE) aims to extract relations among multiple entities across extended contexts while maintaining consistency acro
arXiv:2607.24707v1 Announce Type: new Abstract: Entity-Relationship Diagrams (ERDs) are central to conceptual database design, yet they are typically available only as rendered images rather than mach
arXiv:2607.22837v1 Announce Type: cross Abstract: Many organizations aim to adapt language models for internal use, both to improve performance on domain-specific tasks and to address privacy concerns
arXiv:2607.23125v1 Announce Type: new Abstract: Post-training enables vision-language models (VLMs) to understand human instructions and perform various downstream tasks. Current post-training methods
The apps you use swap AI models constantly. Doing that without downtime or a bad rollout reaching users is still often manual. We rebuilt that workflow based on what we’ve learned serving more than 40
arXiv:2607.24569v1 Announce Type: cross Abstract: Model-based active flow control requires predictive models that are accurate, stable, and fast enough for real-time optimisation. In controlled wake f
arXiv:2607.22587v1 Announce Type: new Abstract: Large language models (LLMs) achieve strong performance across diverse tasks but their deployment is constrained by the memory and compute cost of their
Very interesting paper on LLM reasoning. They find that frontier models can exhibit invisible reasoning by leveraging semantically irrelevant filler tokens. In other words, invisible reasoning can ser
arXiv:2606.13751v4 Announce Type: replace Abstract: This paper presents the participation of team PSL in the QIAS 2026 Shared Task on Arabic Islamic inheritance reasoning. The task evaluates the abili
arXiv:2607.21632v1 Announce Type: new Abstract: Traditional benchmarks for LLMs primarily rely on static datasets and objective scoring metrics, which often fail to capture differences in response qua
arXiv:2607.21617v1 Announce Type: cross Abstract: Vision Language Models (VLMs) are increasingly used in place of traditional OCR pipelines for document understanding. In this paper, we show they do n