Knowledge catalogue
BREAKING: OpenAI postpones 6.1 for safety reasons. If we can take OpenAI at face value, this is quite a decision—and also a sign that no magical solution is in immediate view. Per @sheeraf at NYT “GPT
arXiv:2511.12257v2 Announce Type: replace-cross Abstract: This paper proposes a novel Bayesian framework for solving Poisson inverse problems by devising a Monte Carlo sampling algorithm which account
arXiv:2308.01184v4 Announce Type: replace Abstract: Although noisy-label learning is often approached with discriminative methods for simplicity and speed, generative modeling offers a principled alte
arXiv:2609.31978v1 Announce Type: cross Abstract: Generating independent, equilibrium samples of molecular systems at scale remains a central obstacle in computational statistical mechanics. Boltzmann
GPT‑6.1 Sol is now generally available on Amazon Bedrock, providing enhanced reasoning for coding, computer use, and professional workflows. It runs on a high‑performance inference engine optimized fo
arXiv:2609.34272v1 Announce Type: new Abstract: BF16 is now standard in large-scale pretraining, including in fused attention kernels such as FlashAttention, and these kernels are widely trusted. When
arXiv:2609.33052v1 Announce Type: cross Abstract: Financial question answering often requires precise numerical extraction, unit handling, and arithmetic over tables and text, but applying expensive v
Manually extracting data from hundreds of vendor contracts doesn't scale, and RAG chat tools fall short on portfolio-wide questions. This post shares a contract intelligence platform on AWS that uses
arXiv:2505.06191v2 Announce Type: replace-cross Abstract: This article presents a concept-centric paradigm for building agents that can learn continually and reason flexibly. The concept-centric agent
arXiv:2609.35436v1 Announce Type: cross Abstract: Recently, deep neural networks on manifold-valued representations have garnered significant attention across various machine learning applications. On
arXiv:2609.33037v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) lets language models answer questions more accurately by consulting relevant documents. Many valuable collections
arXiv:2609.31938v1 Announce Type: new Abstract: Generative world models can provide visual rollouts for embodied planning, yet their feasibility on edge devices depends not only on the learned model b
arXiv:2609.35139v1 Announce Type: new Abstract: Multi-document retrieval-augmented generation (RAG) requires a language model to process multiple retrieved text chunks before answering a question. Pre
arXiv:2609.32570v1 Announce Type: new Abstract: Clustering algorithms that operate on nearest-neighbor graphs, such as FINCH (First Integer Neighbor Clustering Hierarchy), depend heavily on the qualit
arXiv:2609.32167v1 Announce Type: new Abstract: Counterfactual prediction estimates an individual's outcome under an alternative intervention given their factual observations. Such outcomes are genera
arXiv:2609.33342v1 Announce Type: new Abstract: Molecular property prediction is central to drug development and materials discovery, but experiments are costly and labeled data are scarce. Context-aw
arXiv:2609.33549v1 Announce Type: cross Abstract: Automatic relevance determination (ARD), the default tool for variable selection in Gaussian-process (GP) regression, ranks inputs by inverse lengthsc
arXiv:2609.31754v1 Announce Type: new Abstract: Vision-based tactile sensors are a popular solution for capturing rich contact surface geometry. However, to obtain high-detail contact surface normals
arXiv:2609.33143v1 Announce Type: cross Abstract: Quarter-ahead revenue forecasting requires company-scale numerical accuracy, strict temporal validity, and company-specific interpretation of narrativ
arXiv:2609.34501v1 Announce Type: new Abstract: Adversarial attacks against object detectors are traditionally studied from an optimization perspective, where attack difficulty is regarded as an outco
arXiv:2609.31996v1 Announce Type: new Abstract: Can out-of-distribution (OOD) generalization be predicted from a trained model's weights alone, without any target-domain data? Existing representationa
arXiv:2609.32462v1 Announce Type: new Abstract: Motion-language models are typically scored by motion-language evaluators, but how well these evaluators ground language structure remains unclear. Here
arXiv:2609.33178v1 Announce Type: new Abstract: Molecularly guided pathology foundation models (PFMs) exploit transcriptomic or proteomic information to enrich whole-slide image (WSI) representations,
arXiv:2609.33114v1 Announce Type: cross Abstract: For decades, statistical inference has largely been developed one problem at a time. Given a scientific target, such as a treatment effect or a regres
arXiv:2609.31706v1 Announce Type: new Abstract: Visual Language Models (VLMs) have achieved remarkable success across diverse tasks, yet they struggle with high-resolution inputs where critical inform
arXiv:2609.33007v1 Announce Type: cross Abstract: Robot learning has largely relied on human-teleoperated demonstrations to acquire effective learnable behaviors. However, human-operated data collecti
arXiv:2609.34658v1 Announce Type: new Abstract: Reward-specialized post-training produces strong experts for flow-based generative models, while multi-teacher on-policy distillation (OPD) consolidates
arXiv:2609.31957v1 Announce Type: new Abstract: Interactive CAPTCHAs remain challenging for computer-use agents, while existing datasets face trade-offs among type coverage, interaction fidelity, and
arXiv:2609.34387v1 Announce Type: new Abstract: Existing adaptive reasoning methods for driving Vision-Language-Action (VLA) models primarily focus on whether to reason, overlooking how reasoning shou
arXiv:2609.34191v1 Announce Type: new Abstract: Transactional basket data can reveal associations among items, but observed co-occurrence conflates item-specific relations with basket-size structure a
arXiv:2609.35621v1 Announce Type: new Abstract: Serving long documents to a Large Language Model (LLM) repeatedly is expensive: computations grow with context length, and the memory footprint of the k
arXiv:2609.33106v1 Announce Type: new Abstract: Pretrained macro-placement policies can reduce repeated optimization across circuits, but deployment often exposes them to unfamiliar designs when the o
arXiv:2609.35195v1 Announce Type: new Abstract: Accurate segmentation of post-treatment brain metastases is essential for treatment planning, longitudinal disease monitoring, and quantitative assessme
arXiv:2609.34246v1 Announce Type: new Abstract: Autoregressive neural emulators can drift or diverge over long rollouts despite accurate short-term predictions. We introduce Cascaded Emulation (CasEm)
arXiv:2609.34144v1 Announce Type: new Abstract: Interactive world models must respond quickly to controls while preserving scene consistency. Existing acceleration methods can miss heterogeneous contr
arXiv:2512.11352v2 Announce Type: replace Abstract: Trust prediction provides valuable support for decision-making, risk mitigation, and system security enhancement. Recently, Graph Neural Networks (G
arXiv:2609.34302v1 Announce Type: new Abstract: Multi-camera pedestrian localization is useful for wide-area monitoring in public and commercial spaces. However, deploying these systems often requires
arXiv:2412.12906v3 Announce Type: replace Abstract: Recently, generalizable feed-forward methods based on 3D Gaussian Splatting have gained significant attention for their potential to reconstruct 3D
arXiv:2609.34475v1 Announce Type: new Abstract: LLMs cannot forget the way we delete a file. Strangely, we are asked to remove something that was never put anywhere in particular. What the model took
arXiv:2609.32157v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models for autonomous driving produce natural-language reasoning alongside predicted trajectories, but whether this reasoni
arXiv:2607.09185v2 Announce Type: replace Abstract: Action-conditioned world models (ACWMs) aim to simulate future observations conditioned on embodied actions. However, learning controllable ACWMs re
Data connectivity and integration firm CData Software Inc. today introduced Connect AI Gateway, a platform designed to control how artificial intelligence agents choose models, use tools and access co
arXiv:2609.32271v1 Announce Type: new Abstract: Post-hoc Bayesian fine-tuning places Gaussians around trained low-rank adapters, yet a calibrated posterior does not by itself yield a useful generaliza
arXiv:2609.33003v1 Announce Type: new Abstract: Vision-language verifiers and routers must distinguish errors repairable by more reasoning from those caused by visual evidence never reaching the langu
arXiv:2609.34245v1 Announce Type: cross Abstract: LLM agents increasingly take privileged, often irreversible structured actions, such as paying an invoice. They assemble each action from action-criti
arXiv:2609.32247v1 Announce Type: cross Abstract: Observationally equivalent causal models can still disagree about what happens under intervention, because interventions create inputs that never occu
arXiv:2609.32559v1 Announce Type: new Abstract: Accurate classification of anterior segment diseases is crucial for ophthalmic screening and diagnosis. However, slit-lamp image analysis remains challe
arXiv:2609.33147v1 Announce Type: new Abstract: Federated low-rank adaptation (LoRA) enables collaborative fine-tuning of large language models without centralizing private client data. Its factorized
arXiv:2609.33496v1 Announce Type: cross Abstract: Post-training quantization (PTQ) is the standard way to run modern diffusion models on memory-constrained accelerators, yet every existing diffusion P
arXiv:2609.32814v1 Announce Type: new Abstract: Fast matrix multiplication algorithms keep the product fixed and search for a cheaper way to evaluate it. We instead ask whether a Transformer's learned
ChatGPT, how much should two companies that have collectively contributed to the economy less than 30B be worth? @Lio_Cicolecchia @GaryMarcus @ey Try the following in google or ChatGPT: 'how much audi
arXiv:2609.33838v1 Announce Type: new Abstract: Large language models are increasingly expected to support diverse chemical reasoning capabilities within a unified model. One approach is to develop sp
arXiv:2609.31629v1 Announce Type: cross Abstract: Structured phenotype extraction from radiology reports supports cohort construction, quality auditing, and clinical analytics, but practical deploymen
arXiv:2609.32427v1 Announce Type: new Abstract: CityToolVQA addresses the weak performance of Vision-Language Models (VLMs) on quantitative tasks in urban low-altitude visual question answering. We di
arXiv:2609.34628v1 Announce Type: cross Abstract: Neural network verification (NNV) formally verifies that a network satisfies a specified property for all inputs within a defined region. Modern NNV t
arXiv:2609.32767v1 Announce Type: new Abstract: Stacking and palletising demand precise placement: error left in one layer is inherited by the next, and a flat pad offers no feature to funnel a wrong
arXiv:2609.32255v1 Announce Type: cross Abstract: Tool-using LLM agents must decide not only whether additional information is needed, but also which source can resolve the uncertainty. Existing proac
On September 29, 2026, Twitter user Severin Field (@sevdeawesome) posted that an AI‑generated video from Claude 5.5 Opus responding to the phrase “AI is a normal technology” was the best AI‑created vi
In September 2026, Anthropic unveiled a suite of new AI products—Claude Tag, Sonnet 5.5, Fable/Mythos 5.1—and infrastructure releases such as Opus 5.5 and a plugins portal, following a record 47 billi
arXiv:2609.31702v1 Announce Type: new Abstract: Reliable breast ultrasound lesion segmentation requires accurate boundaries and evaluation that prevents patients or duplicate images from crossing data