AIMO Interpretability Challenge
arXiv:2607.13899v1 Announce Type: new Abstract: We propose the AIMO Interpretability Challenge, a competition on distinguishing robust from spurious reasoning in frontier mathematical language models
Knowledge catalogue
arXiv:2607.13899v1 Announce Type: new Abstract: We propose the AIMO Interpretability Challenge, a competition on distinguishing robust from spurious reasoning in frontier mathematical language models
arXiv:2607.13651v1 Announce Type: new Abstract: The bottleneck of Earth Observation processing chains is not the arrival of new imagery but whether the surface is actually visible when the image arriv
arXiv:2607.13812v1 Announce Type: cross Abstract: We introduce TCAM-Diff, a novel 3D medical image generation model that reduces the memory requirements to encode and generate high-resolution 3D data.
Excited for our first general model Inkling -- open weights, 975B, natively multimodal (text, image, audio). Available on Tinker, HuggingFace and partners. It is yours to personalize and use openly. I
Inkling is our first open model from @thinkymachines and is now available on Tinker! Check out these quotes from Tinker customers on their experience with Inkling: @_Mantic_AI: 'Not only does Inkling
arXiv:2607.12423v1 Announce Type: new Abstract: Multi-Robot Motion Planning in continuous environments, where robots must generate dynamically feasible, collision-free trajectories, is challenging due
arXiv:2607.12985v1 Announce Type: new Abstract: Aligned language models routinely misreport under non-evidential incentive pressure: they agree with a confident user or overstate certainty even when t
arXiv:2607.12079v1 Announce Type: new Abstract: Decoding continuous language from fMRI signals remains a core challenge in non-invasive brain-computer interface research. We present two complementary
Huge if true! We are talking about a 27B multimodal model that runs locally on a phone. That's wild! Bonsai 27B reaches up to 163 tok/s in 1-bit and 134 tok/s in Ternary on an NVIDIA GeForce RTX 5090.
AI model co-design involves integrating model requirements into hardware planning to ensure memory hierarchies and networking stacks are purpose-built for specific systems . AI performance balances th
Tesla decommissioned the original Model S and Model X assembly line in 46 days, marking the end of an era for these vehicles that launched the company's expansion beyond the Roadster. This rapid trans
arXiv:2607.08768v1 Announce Type: new Abstract: The rapid development of large language models and multimodal large language models has accelerated the emergence of proactive agents capable of operati
arXiv:2607.06940v1 Announce Type: cross Abstract: The remarkable performance of large language models (LLMs) in linguistic tasks underscores an urgent need for comprehensive evaluation of their respon
arXiv:2607.06882v1 Announce Type: cross Abstract: Visual navigation policies built on large pretrained models have so far followed a common recipe: a dedicated visual encoder, a bespoke action head, a
arXiv:2603.23800v2 Announce Type: replace-cross Abstract: We present a novel LLM-informed model-based planning framework, and a novel prompt selection method, for object search in partially-known envi
Grok 4.5 is a new Opus-class AI model released by xAI that offers improved speed and cost efficiency compared to previous versions. The model is positioned as particularly well-suited for real-world c
arXiv:2607.06054v1 Announce Type: cross Abstract: Off-the-shelf TTS systems are poorly adapted to Taiwanese Mandarin. Their accent defaults to other Mandarin variants, their tokenizers over-segment co
arXiv:2607.05477v1 Announce Type: cross Abstract: Improving the task performance of Large Language Models (LLMs) is essential, yet scaling these models faces significant challenges such as diminishing
arXiv:2607.06531v1 Announce Type: new Abstract: - Objective: Multimodal deep learning models in oncology are currently limited by monolithic designs that rigidly couple data ingestion, clinical routin
this should be a huge update in your model of software engineering: rewrites can be good, cheap and fast of course most apps are not as testable and verifiable as Bun, but the models will continue to
We will continue to make refinements to the Grok Build harness and the 1.5T foundation model almost every day in response to user requests. The 2T model will finish training this month and be availabl
arXiv:2607.03650v1 Announce Type: cross Abstract: Extracting textual information from scanned medical documents, such as external laboratory reports and manually filled forms, has been a major challen
arXiv:2607.02998v1 Announce Type: cross Abstract: Controllable generative models of 3D medical images can synthesize volumes with specified clinical attributes, but this demands samples that are simul
arXiv:2607.02947v1 Announce Type: cross Abstract: Public official-information request records contain process signals. They can support research, workflow review, and human-supervised agent help. Yet
arXiv:2607.03760v1 Announce Type: new Abstract: The deployment of large-scale foundation models like Segment Anything Model (SAM) on resource-constrained Earth observation platforms is hindered by pro
arXiv:2607.04982v1 Announce Type: cross Abstract: High-resolution velocity models are crucial for reservoir characterization and subsurface delineation. However, the band limited nature of our surface
arXiv:2606.16533v3 Announce Type: replace Abstract: We introduce extbf{Kairos}, a regret-aware native world-action model stack for Physical AI. Kairos is motivated by the view that a physical world mo
Meta is launching the first AI image generation model made by its Superintelligence Labs division. The Muse Image model now powers the image-making tools across the Meta AI app, Instagram, and WhatsAp
arXiv:2601.09448v3 Announce Type: replace-cross Abstract: Conventional audio equalization is a static process that requires manual and cumbersome adjustments to adapt to changing listening contexts (e
arXiv:2607.02952v1 Announce Type: cross Abstract: Convolutional Neural Networks (CNNs) achieve strong denoising performance by exploiting spatial context from neighboring pixels. Deep Image Prior (DIP
arXiv:2607.02912v1 Announce Type: new Abstract: Despite the high accuracy of EEG-based emotion recognition, existing models remain opaque 'black boxes', lacking semantic grounding between abstract neu
arXiv:2607.04119v1 Announce Type: cross Abstract: Reconstructing Computer-Aided Design (CAD) modeling sequences from images is crucial for preserving design intent and supporting parametric editing. H
arXiv:2607.05394v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) is a powerful recipe for improving language-model reasoning, but it is expensive to repeat on ev
arXiv:2607.03964v1 Announce Type: cross Abstract: World models are rapidly becoming a core infrastructure for embodied intelligence and interactive agents: they provide controllable simulators in whic
arXiv:2510.17426v3 Announce Type: replace-cross Abstract: The 'alignment tax' of post-training is typically framed as a drop in task accuracy. We show it also involves a severe loss of calibration, ma
arXiv:2607.01895v1 Announce Type: new Abstract: We study ridge-regularized log-density-ratio estimation in the Gaussian location model with a common covariance matrix. By affine invariance, the model
arXiv:2607.00030v1 Announce Type: new Abstract: In robot-assisted laparoscopic minimally invasive surgery (MIS), accurate enforcement of the remote center of motion (RCM) constraint is critical for sa
In June, the Tesla Model Y became the best-selling vehicle overall in New Zealand, surpassing all other car models in monthly sales. This announcement was shared by Elon Musk on X (formerly Twitter),
Model Y long wheelbase now available to order in the US Introducing Model Y Long Wheelbase – now available in the US & Puerto Rico A 3-row, 6-seat configuration that brings exceptional interior space
arXiv:2607.00569v1 Announce Type: new Abstract: In this article, we present dynamic modeling, gait synthesis, and feedback control design for a modular novel subsurface robot, designed for human-free
arXiv:2607.01166v1 Announce Type: cross Abstract: Video predictive models are emerging as a powerful paradigm in robotics, offering a promising path toward task generalization, long-horizon planning,
AlloyDB is an AI-native database—it isn’t just a passive data store, it intelligently understands and processes your data. With AlloyDB, you get industry-leading vector and hybrid search, near 100% ac
arXiv:2606.19100v2 Announce Type: replace Abstract: Large Vision and Language Models (LVLMs) have advanced rapidly, yet European Portuguese (pt-PT) remains systematically underserved by existing open-
arXiv:2601.13932v2 Announce Type: replace-cross Abstract: Reaching consensus on massive discussion networks is critical for reducing noise and achieving optimal collective outcomes. However, the natur
arXiv:2606.31814v1 Announce Type: new Abstract: Lane topology reasoning aims to construct a lane graph from onboard sensor observations. Existing methods follow a detection and association paradigm th
get started with deep agents code, our open source coding agent with first class open model support You can start building with GLM 5.2 in minutes: 1️⃣ Download dcode 2️⃣ Select your model (GLM 5.2) 3
arXiv:2606.31889v1 Announce Type: new Abstract: This paper presents a novel non-linear mathematical model of an articulated tractor-trailer system that can be used, in combination with receding horizo
arXiv:2502.15637v2 Announce Type: replace-cross Abstract: While foundation models have revolutionized various domains, their application to time series classification remains rather under-explored, wi
arXiv:2606.31693v1 Announce Type: cross Abstract: The wave of AI-native applications is moving shopping beyond page- and feed-based browsing toward intent-driven experiences orchestrated by LLM agents
arXiv:2602.23721v2 Announce Type: replace-cross Abstract: Vision-language-action (VLA) models integrate visual observations and language instructions to predict robot actions, demonstrating promising
arXiv:2602.15029v3 Announce Type: replace-cross Abstract: The internal representations learned by language models consistently exhibit striking geometric structure: calendar months organize into a cir
arXiv:2606.31946v1 Announce Type: new Abstract: The fundamental obstacle to industrial grade video generation is the lack of controllability: existing models treat video as a pixel distribution sampli
arXiv:2606.29212v1 Announce Type: new Abstract: Agent-based evacuation simulations are widely used to study crowd behavior during emergencies, but many models rely on assumptions such as perfect event
A great read from @LangChain Best framing I've seen for agent architecture. Every non-model piece like the filesystem, sandbox, compaction, Ralph loops exists to patch a specific model limitation. htt
A study from @Stanford showed that 71.3% of chatgpt queries could be accurately answered by a local model. I suspect a major part of enterprise AI workloads could be run locally too for free (compared
arXiv:2606.28926v1 Announce Type: cross Abstract: In-context learning (ICL) is an emerging paradigm that employs the semantic information inherent in large language models (LLMs) for generating answer
arXiv:2606.30429v1 Announce Type: new Abstract: Text-to-3D systems can now synthesize a mechanical part from a single sentence, yet the result is a shape to render, not a design to edit. We present Ar
arXiv:2512.02453v2 Announce Type: replace Abstract: Existing stylized motion generation models have shown their remarkable ability to understand specific style information from the style motion, and i
arXiv:2606.29384v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have become an important paradigm of embodied AI. However, existing VLA models typically assume well-lit and stable
Hugging Face introduced a feature that displays evaluation results from the 'Every Eval Ever' (EEE) community evaluation initiative directly on model pages, providing users with comprehensive benchmar