Knowledge catalogue
The Test Bench Setup I tested running a massive 1.56TB Mixture-of-Experts (MoE) checkpoint (96 shards, 93 layers, 896 experts/layer, ~4.46 bits/param MXFP4) on a budget gaming laptop. Laptop: HP Victu
arXiv:2607.25106v1 Announce Type: new Abstract: Embodied AI increasingly relies on queryable semantic maps built from pre-trained vision-language models to enable zero-shot Object Goal Navigation (Obj
arXiv:2607.24801v1 Announce Type: cross Abstract: We study the problem of guarded query routing, where we assume that a user query first meets a router that either determines the ideal endpoint for in
arXiv:2607.25375v1 Announce Type: new Abstract: India is a vast nation of over 1.4 billion people, varied by hundreds of diverse and locally specific traditions and cultures and 22 officially recogniz
OpenAI has released the open‑source Codex Security CLI, which can be installed with `npm install @OpenAI/codex-security` or run directly via `npx @OpenAI/codex-security@latest --help`. The tool scans
arXiv:2607.25642v1 Announce Type: cross Abstract: Instruction-based Image Editing (IIE) aims to transform a given image into a new one based on textual instructions. Advances in Large Language Models
arXiv:2607.25292v1 Announce Type: new Abstract: Silicon sampling uses language models as proxies for human survey respondents, treating each model call as an independent draw from the persona's respon
arXiv:2607.26015v1 Announce Type: new Abstract: Syntactic convergence (the tendency of speakers to adapt in language towards the grammatical profiles of their interlocutors) is a well-documented featu
arXiv:2607.25904v1 Announce Type: new Abstract: Graphical user interface task evaluation aims to determine whether a GUI agent has successfully completed a user instruction. Automated GUI task evaluat
arXiv:2603.14558v3 Announce Type: replace Abstract: Recruiters and job seekers rely on search systems to navigate labor markets, making candidate matching engines critical for hiring outcomes. Most sy
arXiv:2607.25626v1 Announce Type: new Abstract: Decoding speech information directly from scalp electroencephalography (EEG) into text provides a potential non-invasive neural communication pathway fo
arXiv:2607.24762v1 Announce Type: new Abstract: Machine learning models are increasingly embedded in everyday software, and most of their runtime is spent in a small set of compute kernels such as mat
arXiv:2607.25962v1 Announce Type: new Abstract: Recent generative models can produce images with few obvious visual artifacts, weakening detectors and explanations that rely only on surface appearance
arXiv:2607.25257v1 Announce Type: cross Abstract: Item Response Theory (IRT) has recently been proposed as a framework for evaluating large language model (LLM) benchmarks by separating a model's late
arXiv:2607.25387v1 Announce Type: new Abstract: Learned restriction maps in sheaf graph neural networks are often treated as proof that the model has discovered useful edge geometry. That conclusion d
arXiv:2607.25130v1 Announce Type: cross Abstract: Imperfections in AI-generated code require that software developers modify the generated code manually, or by re-prompting an AI programming assistant
arXiv:2607.25136v1 Announce Type: new Abstract: Research on preference optimization often varies the training objective while holding the data fixed. We instead ask whether a small, high-confidence se
arXiv:2607.25663v1 Announce Type: new Abstract: Transformer adaptation is typically distributed across model depth, even when the intended change is narrow. We investigate how adaptation site shapes w
arXiv:2607.25020v1 Announce Type: new Abstract: Vine copulas provide a flexible framework for modeling complex multivariate distributions through a hierarchical decomposition into bivariate pair-copul
arXiv:2510.13434v2 Announce Type: replace Abstract: Aligning Large Language Models (LLMs) with human preferences is pivotal for Machine Translation (MT), yet current approaches are often hindered by m
arXiv:2607.24904v1 Announce Type: cross Abstract: Standard vision-language models (VLMs) suffer from Moravec's paradox: they excel at complex offline visual reasoning but struggle with simple streamin
arXiv:2607.24887v1 Announce Type: cross Abstract: Existing theories of neural-network width characterize asymptotic limits, but provide limited guidance on whether an expansion direction identified fr
arXiv:2507.23541v5 Announce Type: replace Abstract: In medical scenarios, effectively retrieving external knowledge and leveraging it for rigorous logical reasoning is of significant importance. Despi
arXiv:2607.25300v1 Announce Type: new Abstract: Video editing is fundamentally message-driven: even from the same source footage, the selected shots change depending on the narrative the editor wishes
arXiv:2607.24838v1 Announce Type: cross Abstract: In medical multiple-choice question answering (MCQA), Retrieval-Augmented Generation (RAG) can supplement the domain knowledge of language models (LMs
arXiv:2607.25380v1 Announce Type: new Abstract: Memory has evolved into a foundational architectural dimension in large language models (LLMs), shifting from an implicit byproduct of computation to a
arXiv:2607.25614v1 Announce Type: cross Abstract: Adapting Large Language Models (LLMs) to specialized domains often incurs an alignment tax, as fine-tuning on domain-specific tasks can cause catastro
arXiv:2607.25891v1 Announce Type: new Abstract: Evaluating AI agents in interactive environments is hindered by fragmented tasks, scaffolds, verifiers, and scoring rules. Existing efforts focus on nar
Microsoft is working on an AI 'super app' that combines Copilot's chat, coding, and agentic capabilities. During an earnings call on Wednesday, Microsoft CEO Satya Nadella said the app will span 'both
arXiv:2607.25907v1 Announce Type: cross Abstract: Activation steering controls model behavior by editing internal activations at inference time. We study its input-side dual: optimizing a fluent promp
Model + harness. We have barely begun to understand the best ways to do harness engineering. A huge amount of untapped potential even without models getting better (but models are getting better) Turn
arXiv:2607.25092v1 Announce Type: new Abstract: Face morphing attacks create synthetic images verifiable against multiple identities, threatening border control and identity verification systems. We i
arXiv:2606.05202v2 Announce Type: replace-cross Abstract: In reactor physics, neutronics and multi-physics phenomena can be modelled at different fidelity levels. High-fidelity models based on the Bol
arXiv:2607.25531v1 Announce Type: cross Abstract: Contemporary machine learning struggles to learn continually, reuse prior knowledge, and expose a comprehensible internal structure. A recently propos
arXiv:2607.24799v1 Announce Type: cross Abstract: Large Language Models tend to hallucinate when answering domain-specific ques tions from scientific documents without prior fine-tuning. Currently, me
arXiv:2607.25186v1 Announce Type: new Abstract: Background: Most medical large language model (LLM) benchmarks focus on examination knowledge or isolated tasks and may not reflect the longitudinal, mu
arXiv:2607.25232v1 Announce Type: new Abstract: Digital phenotyping (DP) using smartphones and wearable devices has shown considerable potential for mental health monitoring. However, progress remains
arXiv:2607.24841v1 Announce Type: new Abstract: Autoregressive (AR) large language models (LLMs) are inherently inefficient at inference time because each generated token requires accessing the full s
arXiv:2607.25210v1 Announce Type: new Abstract: Oblique-view urban remote sensing imagery inevitably exhibits geometric projection displacements between building roofs and footprints, leading to signi
arXiv:2607.25641v1 Announce Type: cross Abstract: While text-to-image models exhibit remarkable visual fidelity, they frequently violate fundamental physical commonsense. Existing benchmarks often rel
On benchmarking long-context agentic instruction following. Agent benchmarks mostly reward reaching the answer. This new benchmark measures whether the agent reached it the permitted way, which is the
arXiv:2607.24784v1 Announce Type: new Abstract: Specialised translation relies on the use of documentary and terminological resources, including corpora. These resources are particularly useful for te
arXiv:2607.25153v1 Announce Type: new Abstract: Rooftop photovoltaic (PV) systems account for the vast majority of PV grid connections, yet no open, comprehensive, installation-level dataset of these
OpenWiki now connects to LangSmith traces to analyze how coding agents interact with your repo during wiki generations! We added a LangSmith tracing connector so OpenWiki can retrieve more context int
arXiv:2607.25656v1 Announce Type: new Abstract: Complex tasks often decompose into parallelizable yet interdependent subtasks, making orchestration critical to the performance of multi-agent systems (
arXiv:2607.25545v1 Announce Type: cross Abstract: Deploying diabetic retinopathy (DR) screening models in primary care requires edge-efficient systems that remain accurate, safe, and reliable under do
arXiv:2607.25362v1 Announce Type: new Abstract: Reflections from shiny objects and glass facades naturally extend the field of view of a camera, capturing the surrounding environment without the need
arXiv:2607.26004v1 Announce Type: new Abstract: Generation in video diffusion or flow models is computationally expensive due to the slow and iterative sampling process. Current state-of-the-art (SOTA
Participants will receive access to our frontier models, including our GPT-5.6 family of models. Each workspace includes business-grade privacy and security protections. Researcher data is not used to
arXiv:2607.26057v1 Announce Type: cross Abstract: On-policy distillation (OPD) grounds token-level supervision in the student's own trajectory, yet suffers from prefix failure: once the student commit
arXiv:2607.24768v1 Announce Type: new Abstract: Prenatal care is an important preventive service designed to improve outcomes for pregnant individuals. The American College of Obstetricians and Gyneco
arXiv:2607.25485v1 Announce Type: new Abstract: Health AI is evolving from answering questions to agentic systems that converse with patients, reason about health records, and act on their behalf. Pri
arXiv:2603.26136v3 Announce Type: replace Abstract: Message Passing Neural Networks (MPNNs) have achieved strong performance on tasks involving relational data. However, small perturbations to graph s
arXiv:2607.25915v1 Announce Type: new Abstract: Complex structured reasoning tasks often require additional computation, yet current language models obtain it mainly by increasing parameter scale or b
arXiv:2607.24957v1 Announce Type: new Abstract: We introduce PerceptionBench, a benchmark specifically designed to evaluate the atomic visual perception capabilities of Multimodal Large Language Model
arXiv:2607.24782v1 Announce Type: new Abstract: LLM behavior may be conditioned by human identity in several ways: they may be asked to adapt to users, role-play populations, or forecast how people wo
arXiv:2607.25985v1 Announce Type: cross Abstract: Unmanned aerial vehicles (UAVs), particularly quadcopters, present unique challenges for autonomous control due to their underactuated dynamics: only
arXiv:2607.25321v1 Announce Type: new Abstract: Video diffusion models generate visually compelling content but routinely violate elementary physics when the subject involves fluids: liquid columns br
arXiv:2607.25441v1 Announce Type: new Abstract: Covariate shift across training-data partitions biases model selection and parameter estimation in cross-validation, lifelong learning, and federated le
arXiv:2508.00344v5 Announce Type: replace Abstract: Large Language Models (LLMs) have shown remarkable advancements in tackling agent-oriented tasks. Despite their potential, existing work faces chall