Knowledge catalogue
arXiv:2610.08585v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly relied upon to support ambient documentation and clinical reasoning. Here we examine the impact of a failu
arXiv:2610.07704v1 Announce Type: cross Abstract: Fully decentralized multi-agent reinforcement learning (MARL), also referred to as independent learning, requires each agent to learn and act using on
arXiv:2610.07458v1 Announce Type: new Abstract: Hypergraphs offer a natural framework for modeling networked data, where dependencies among entities are governed by higher-order interactions. While hy
arXiv:2610.08689v1 Announce Type: new Abstract: Counterfactual inference in Gaussian-process structural causal models (GP-SCMs) has been developed primarily for continuous endogenous variables, limiti
arXiv:2610.07533v1 Announce Type: cross Abstract: Audio language models must handle dozens of distinct skills, from pitch comparison and speaker counting to musical tempo estimation and emotion recogn
arXiv:2610.05190v1 Announce Type: cross Abstract: Generative large language models (LLMs) inherit undesirable behaviors from pre-training, including demographic bias and toxic generation, that often e
arXiv:2610.04139v1 Announce Type: new Abstract: Predicting future spatial states supports collision avoidance and timely decision-making in dynamic environments. However, existing vision-language mode
arXiv:2610.04569v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in safety-critical settings, yet their black-box nature makes it difficult to provide formal gu
arXiv:2610.05026v1 Announce Type: new Abstract: Vision-language-action (VLA) models encode semantic information from vision-language pretraining, but manipulation also requires precise spatial reasoni
arXiv:2610.05739v1 Announce Type: new Abstract: Long-horizon video world models require persistent memory to preserve scene consistency over extended rollouts. Softmax attention retains the full gener
Mistral AI announced that its new model, Mistral Large 4, is among the world's most powerful AI systems specifically designed for cybersecurity tasks. The tweet shared on October 6, 2026 highlights th
arXiv:2610.05401v1 Announce Type: new Abstract: Text-to-image diffusion models can generate prohibited content, which motivates concept erasure through machine unlearning. Most erasure methods interve
arXiv:2603.17850v2 Announce Type: replace Abstract: Recent Vision-Language-Action (VLA) models equipped with Flow Matching (FM) action heads achieve state-of-the-art performance in complex robot manip
arXiv:2610.04038v1 Announce Type: new Abstract: Synthetic data are increasingly used as an alternative to sharing sensitive records. However, synthetic data generation does not guarantee privacy, as d
arXiv:2610.05352v1 Announce Type: new Abstract: Tabular foundation models (TFMs) outperform established machine learning models on tabular benchmarks through in-context learning. Building on this succ
arXiv:2602.04448v3 Announce Type: replace Abstract: Mixture-of-Experts (MoE) language models introduce unique challenges for safety alignment due to their sparse routing mechanisms, which can enable d
arXiv:2610.04017v1 Announce Type: new Abstract: Localizing behavior to individual components of a language model is a central goal of mechanistic interpretability. However, scoring components one at a
We've been building a benchmark out of real concurrency bugs (race conditions, deadlocks, cancellation issues) taken from merged PRs in about 100 Python projects. Each task gets graded by the project'
arXiv:2610.05550v1 Announce Type: new Abstract: The component that dominates a latent world model's prediction error need not be the one whose repair most improves action selection. We show this by co
arXiv:2610.03396v1 Announce Type: new Abstract: Bayesian data assimilation combines model forecasts with noisy observations, but sampling high-dimensional, non-Gaussian posteriors remains challenging.
arXiv:2610.03626v1 Announce Type: new Abstract: The recent wave of one-step generative models, which compress the multi-step trajectory of diffusion via either distillation or learned flow maps, has r
arXiv:2610.02597v1 Announce Type: new Abstract: Vision foundation models such as DINOv2, SigLIP2, and MASt3R develop complementary capabilities from different pretraining objectives, yet their knowled
arXiv:2610.02586v1 Announce Type: new Abstract: A typed decision model answers a fixed question about an input by returning a probability for each of several caller-defined options. Each option carrie
arXiv:2610.03482v1 Announce Type: new Abstract: Hallucination detection is particularly important for medical language models, but repeated-sampling approaches are expensive and existing uncertainty-h
arXiv:2610.03329v1 Announce Type: cross Abstract: Large language models are increasingly used where small syntactic errors matter, yet character-level reasoning is still evaluated mostly through isola
arXiv:2407.12927v4 Announce Type: replace Abstract: Systems for multimodal emotion recognition (ER) are commonly trained to extract features from different modalities (e.g., visual, audio, and textual
arXiv:2610.03052v1 Announce Type: new Abstract: Large language models (LLMs) contain broad knowledge, but they cannot access all of it reliably. We study this problem through knowledge accessibility,
First AutoHarness, then AutoContext, now AutoCompact. I am seeing a rising trend of work that trains models to natively support more of what the harness does. This work specifically trains agents to d
Innanzitutto, due cose per evitare fraintendimenti. Non sto cercando di sostenere che un modello o un'azienda siano migliori. Non ho alcun interesse personale in nessuno di essi. Volevo solo verificar
arXiv:2610.00969v1 Announce Type: cross Abstract: Large language models (LLMs) have been increasingly used for financial document analysis, including earnings call transcripts (ECTs). Beyond generatin
arXiv:2507.17389v2 Announce Type: replace-cross Abstract: Recent advances in code large language models (CodeLLMs) have made them indispensable tools in modern software engineering. However, these mod
arXiv:2610.01741v1 Announce Type: new Abstract: Predictive Vision-Language-Action (VLA) models aim to improve robotic manipulation via future observation or world dynamics forecasting. However, existi
arXiv:2610.00329v1 Announce Type: new Abstract: Selective state space models (SSMs), such as Mamba, S4D, and LRU, are bounded by transition matrix commutativity (A_t A_t' = A_t' A_t) and solvable affi
arXiv:2610.01559v1 Announce Type: cross Abstract: World Action Models (WAMs) predict visual futures and robot actions, yet they remain susceptible to task-incomplete imagination, where plausible, acti
arXiv:2610.00277v1 Announce Type: new Abstract: Federated multimodal graph foundation models (GFMs) aim to adapt pretrained multimodal models to decentralized graph data, where each client owns a priv
arXiv:2610.01933v1 Announce Type: cross Abstract: Inference-time scaling adapts pretrained diffusion models to new sampling tasks without additional training. Existing methods rely primarily on Monte
arXiv:2610.01823v1 Announce Type: cross Abstract: We consider estimating the conditional distribution of a multivariate outcome given covariates when its coordinates may be continuous, binary, categor
arXiv:2610.02193v1 Announce Type: cross Abstract: Discrete diffusion language models offer a compelling alternative to autoregressive generation for tasks demanding bidirectional reasoning and global
arXiv:2610.01373v1 Announce Type: new Abstract: World models allow agents to plan in latent space by choosing a sequence of actions that most reduces the distance to a given goal state. Thus, planning
arXiv:2610.01969v1 Announce Type: new Abstract: Concept erasure aims to remove a target concept, such as a copyrighted style, a recognizable character, or unsafe content, from a pretrained text-to-ima
arXiv:2610.00724v1 Announce Type: cross Abstract: Language models learn content and style jointly, making stylistic variation in their outputs difficult to identify and control. We study whether recur
Recursive Language Models: Claude Code, Agent Swarms, Big Research Bets, & the $40M AI Problem Solver https://www.latent.space/p/rlm MIT’s @a1zhang explains why Claude Code, Codex, and Pi are basicall
arXiv:2603.12718v3 Announce Type: replace Abstract: Document Layout Analysis (DLA) is the process by which a page is parsed into meaningful elements, often using machine learning models. Typically, th
arXiv:2502.13141v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are vulnerable to attacks like prompt injection, backdoor attacks, and adversarial attacks, which manipulate prom
arXiv:2609.40024v1 Announce Type: cross Abstract: We develop a general method for amortized Bayesian inference on multilevel models of arbitrary structure. Given a generative model specified as a dire
arXiv:2609.39751v1 Announce Type: new Abstract: Planning with learned world models combines online trajectory optimization with learned value and policy functions for high-dimensional control. Because
arXiv:2606.13603v2 Announce Type: replace-cross Abstract: Chain-of-thought (CoT) reasoning is the dominant paradigm for inference-time scaling in language models, yet the causal influence of individua
arXiv:2606.19788v2 Announce Type: replace Abstract: We present CombEval, a dynamic benchmark for evaluating combinatorial counting in large language models. CombEval represents each problem as a typed
arXiv:2609.38577v1 Announce Type: new Abstract: While modern language models demonstrate impressive generative capabilities, they often struggle with constrained, counter-intuitive creative tasks. To
arXiv:2609.38256v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to answer questions about politically contentious issues, yet evaluations typically treat a model's s
arXiv:2609.39970v1 Announce Type: new Abstract: Robot brain models integrate vision, language, and robot state to generate actions for complex manipulation tasks. Most predict fixed-length action chun
arXiv:2609.38716v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) have made remarkable progress across visual perception tasks, yet spatial reasoning remains a persistent weakness
arXiv:2609.38434v1 Announce Type: cross Abstract: Real-world optimization problems are difficult to model accurately because many objectives and constraints reside in domain experts' tacit knowledge,
arXiv:2609.36167v1 Announce Type: cross Abstract: Distributed Denial of Service attacks are a growing threat to network infrastructure, and new techniques, including the use of generative AI, make the
arXiv:2609.35835v1 Announce Type: cross Abstract: With the sheer constant advancements raining down in the field of Artificial Intelligence, one particular possibility that may cross our mind is wheth
arXiv:2609.36828v1 Announce Type: new Abstract: Post-training quantization (PTQ) lowers deployment cost for multimodal large language models, but calibration typically reconstructs fixed sequences wit
arXiv:2609.37371v1 Announce Type: cross Abstract: Model adaptation is typically governed by a fixed recipe, even though different update programs can produce substantially different behavioral outcome
arXiv:2609.38005v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly proposed as decision assistants who must reason probabilistically from available evidence under explicit d
arXiv:2609.37576v1 Announce Type: new Abstract: With the rapid advancement of text-to-image (T2I) generation, robust evaluation becomes critical yet challenging, as traditional metrics fail to capture
arXiv:2609.36531v1 Announce Type: new Abstract: Video world models are largely regarded as predictive models of the physical world and are therefore expected to anticipate the consequences of observed