Language Models as AI Research World Models
arXiv:2610.12235v1 Announce Type: new Abstract: AI research agents automate the cycle of proposing, implementing, and evaluating experiments, opening a path toward recursive self-improvement. Yet thei
Knowledge catalogue
arXiv:2610.12235v1 Announce Type: new Abstract: AI research agents automate the cycle of proposing, implementing, and evaluating experiments, opening a path toward recursive self-improvement. Yet thei
arXiv:2610.10920v1 Announce Type: cross Abstract: E-commerce search pages are critical touchpoints for millions of online shoppers. While traditional search engines return a ranked list of results, mo
arXiv:2610.12144v1 Announce Type: new Abstract: Tokenizer choice affects multilingual language modeling, but vocabulary capacity is finite and vocabulary size is often constrained: improving represent
arXiv:2610.11111v1 Announce Type: new Abstract: Time Series Language Models (TSLMs) offer a promising path toward time series understanding by reasoning over temporal signals and producing natural lan
arXiv:2610.10650v1 Announce Type: new Abstract: Work zones are critical yet hazardous components of transportation infrastructure, requiring carefully designed Transportation Management Plans (TMPs) t
arXiv:2610.11599v1 Announce Type: cross Abstract: Journals and conferences have begun to screen submitted manuscripts for text written using large language models (LLMs). The reliability of this scree
arXiv:2610.10918v1 Announce Type: new Abstract: Large Language Models (LLMs) are considered to be a more efficient and cost-effective alternative to human judgment for Machine Translation (MT) evaluat
arXiv:2610.12148v1 Announce Type: new Abstract: Quantum machine learning, and quantum neural networks (QNNs) in particular, are advancing fields with growing potential. Although systematic comparisons
OpenAI released 719 mathematics manuscripts on October 6, 2026 that were generated by an internal frontier model (not publicly available), covering 372 topic families—including a solution to the Navie
arXiv:2610.12376v1 Announce Type: new Abstract: Tokenizers are commonly optimized for compression, but a compact vocabulary does not necessarily distribute its capacity evenly across languages. We int
arXiv:2610.10648v1 Announce Type: new Abstract: Alzheimer's disease prediction involves irregular visits, heterogeneous measurements and incomplete modalities. This study presents a multimodal multita
arXiv:2606.16253v2 Announce Type: replace-cross Abstract: Vision-language-action (VLA) models increasingly rely on high-frequency multi-camera observations, making visual communication a major bottlen
arXiv:2610.11403v1 Announce Type: new Abstract: Reconstructing protein structures from cryo-electron microscopy (cryo-EM) maps is essential for understanding macromolecular assemblies. Although learni
arXiv:2606.18810v2 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has driven substantial progress in training LLMs for reasoning tasks, but representative
arXiv:2610.10954v1 Announce Type: new Abstract: Heuristic search for a plan can store exponentially many states, even when its heuristic is almost perfect. We instead learn search control, one specifi
arXiv:2610.10690v1 Announce Type: new Abstract: Recurrent neural networks (RNNs) offer linear-time scaling with sequence length while requiring only constant memory, yet they struggle to capture long-
arXiv:2610.12401v1 Announce Type: new Abstract: Kilometer-scale regional weather forecasting is essential for local weather warnings and weather-sensitive decisions. Existing data-driven approaches of
arXiv:2610.11622v1 Announce Type: new Abstract: Traversability is essential for visual navigation but varies with robot capabilities and user preferences. Conventional pipelines often rely on explicit
arXiv:2610.12303v1 Announce Type: new Abstract: Declarative logic programs offer a powerful and interpretable abstraction for encoding relational structure and neurosymbolic reasoning, by expressing d
arXiv:2512.00911v2 Announce Type: replace Abstract: Panoramic cameras provide a 360{eg} field of view and are widely used in panoramic vision, immersive visual computing, and robotic perception. Howev
arXiv:2610.11500v1 Announce Type: cross Abstract: Bound states in the continuum (BIC) metasurfaces are typically described by geometry-specific parameters, hindering cross-geometry comparison, while u
arXiv:2610.11869v1 Announce Type: cross Abstract: We consider the problem of learning structured linear dynamical systems over convex sets K, where only a small subset of the observations are availabl
arXiv:2610.11543v1 Announce Type: new Abstract: Functional Web generation is increasingly optimized with executable rewards, yet existing methods largely focus on the quality of the final page and lea
arXiv:2610.11546v1 Announce Type: cross Abstract: Solving high-dimensional structural model updating problems requires an algorithm capable of navigating complex, non-convex landscapes with correlated
arXiv:2610.12168v1 Announce Type: new Abstract: We introduce a self-improvement loop for reasoning models based on the following observation: Even when the difficulty of a problem exceeds the model's
arXiv:2610.11444v1 Announce Type: new Abstract: Video world models aim to generate explorable, 3D-consistent scene videos conditioned on camera trajectories. Existing approaches often rely on external
arXiv:2610.11057v1 Announce Type: new Abstract: Multimodal classification processes and relates information from multiple modalities to achieve more accurate predictions. However, existing methods typ
arXiv:2610.11967v1 Announce Type: new Abstract: Localizing an event camera against a pre-built LiDAR map can be cast as dense optical-flow estimation between a rendered depth view and an event image,
arXiv:2610.12442v1 Announce Type: new Abstract: Generating an egocentric video from a single exocentric recording is a challenging case of novel view synthesis, as the two cameras share little overlap
arXiv:2610.10893v1 Announce Type: new Abstract: Video-language models commonly assume that more temporal observations lead to more reliable reasoning. We question this assumption and argue that the ke
arXiv:2610.11862v1 Announce Type: new Abstract: Mathematicians value proofs for more than correctness: among correct proofs, simplicity, purity and the computational cost of finding them vary widely.
arXiv:2610.12140v1 Announce Type: new Abstract: Growing automation makes collaborative robots work in more variable environments, increasing the need for adaptation. We propose a human-in-the-loop onl
arXiv:2610.12407v1 Announce Type: cross Abstract: World action models (WAMs) predict actions and future observations, typically from a reconstruction-based representation that carries noisy, redundant
arXiv:2510.18239v4 Announce Type: replace-cross Abstract: Scaling large recommendation systems requires advancing three major frontiers: processing longer user histories, expanding candidate sets, and
arXiv:2603.27141v2 Announce Type: replace Abstract: Demographic prompts are routed differently from neutral prompts in Mixture-of-Experts (MoE) language models, motivating tests of routing-level stere
arXiv:2610.10722v1 Announce Type: cross Abstract: This paper studies the problem of learning disentangled representations of objects and their attributes from raw, unstructured image data. Slot-based
arXiv:2610.12368v1 Announce Type: new Abstract: Direct visual navigation policies generate trajectories efficiently but do not explicitly evaluate their future consequences. Generative navigation worl
arXiv:2610.12069v1 Announce Type: new Abstract: Realistic household simulation must capture not only diverse environments but also the lived-in object arrangements and spatial constraints that shape r
In the dawn of the LLM craze, when wild Llama2's roamed free and 4k tokens was considered a fairly long context for local models, I forked an interactive fiction and MUD library called Tale to experim
arXiv:2610.11253v1 Announce Type: new Abstract: Large language model agents are being increasingly deployed as autonomous scientists, designing experiments and inferring mechanistic world models with
arXiv:2505.24282v2 Announce Type: replace Abstract: Language-driven action localization in videos requires not only semantic alignment between language query and video segment, but also prediction of
LM Studio 0.4.26 is out now! • ⚡️ `/v1/systemone` and `/v1/decisions` APIs • 👾 Coexistence with Bionic • 🎨 UI updates and bug fixes Yes, you can now point your Bionic agent to models loaded in your LM
arXiv:2512.05414v4 Announce Type: replace Abstract: Spell correction is still a challenging problem for many languages, especially low-resource languages (LRLs). While pre-trained language models (PLM
arXiv:2610.11159v1 Announce Type: new Abstract: Speech-to-LLM systems often connect a frozen speech encoder to a frozen large language model (LLM) through a small trainable bridge. The bridge is usual
arXiv:2510.12843v2 Announce Type: replace Abstract: Spiking neural networks (SNNs) promise energy-efficient artificial intelligence on neuromorphic hardware but struggle with tasks requiring both fast
arXiv:2610.12390v1 Announce Type: cross Abstract: Industrial risk-control systems typically rely on structured-data models for efficient prediction, yet substantial valuable information remains embedd
arXiv:2610.12060v1 Announce Type: new Abstract: Processing long visual token sequences from high-resolution images makes multi-step reasoning computationally expensive for multimodal Large Language Mo
arXiv:2610.11954v1 Announce Type: new Abstract: CAD reconstruction methods assume a luxury reality rarely grants: unrestricted visual access to the object, photographed from any desired angle. Real ob
arXiv:2610.12304v1 Announce Type: new Abstract: Understanding large language model (LLM) reasoning requires looking beyond behavioral performance to examine how reasoning ability is reflected in inter
arXiv:2610.10738v1 Announce Type: new Abstract: Our work explores learning a compressed latent representation of text, at the intersection of data compression and representation learning. We propose a
arXiv:2610.11236v1 Announce Type: new Abstract: Low-cost sensors enable scalable indoor air quality monitoring but require calibration because of nonlinear distortions, noise, and temporal drift. The
arXiv:2610.11000v1 Announce Type: new Abstract: The intermittent and variable nature of precipitation makes its accurate estimation over extended domains difficult, yet its spatiotemporal structure su
arXiv:2610.11264v1 Announce Type: new Abstract: Given the inherent unpredictability of packet loss in vehicular wireless communications, V2X collaborative perception can yield practical benefits only
arXiv:2610.11634v1 Announce Type: cross Abstract: Large language models (LLMs) perform remarkably well on complex tasks, yet remain highly vulnerable to prompt injection attacks, where malicious instr
arXiv:2610.12127v1 Announce Type: cross Abstract: Interactive scene exploration requires frequent view updates, although small camera motions preserve much of the visible content. Conventional 3D Gaus
arXiv:2610.10960v1 Announce Type: new Abstract: We present LVSPM, a generalizable model that jointly estimates camera poses and synthesizes novel views from uncalibrated image collections. Trained wit
arXiv:2403.04571v2 Announce Type: replace Abstract: The current state-of-the-art in artificial intelligence is impressive, especially in terms of mastery of language, but not so much in terms of mathe
arXiv:2610.12293v1 Announce Type: cross Abstract: Machine learning (ML) in high-energy nuclear physics (HENP) is entering a new stage in which physical knowledge is incorporated more directly into dat
arXiv:2610.11133v1 Announce Type: new Abstract: Operating System (OS) Fingerprinting is a technique that can be used to identify a network's operating systems by evaluating network traffic in the form
arXiv:2610.12416v1 Announce Type: cross Abstract: Generating realistic human-object interactions (HOI) in complex 3D scenes requires two complementary capabilities: reasoning about interaction feasibi