Knowledge catalogue
Meta Platforms Inc. is gearing up to release a new version of its flagship Muse Spark artificial intelligence model. Alexandr Wang, the company’s chief AI officer, wrote on X today that the update wil
arXiv:2607.00141v1 Announce Type: new Abstract: This paper presents Adaptive Differentiable Model Predictive Contouring Control (AD-MPCC), a framework for autonomous racing that integrates differentia
arXiv:2607.00301v1 Announce Type: new Abstract: The emergence of powerful deep generative models based on diffusion and flow matching has enabled the learning and modeling of complex distributions. Le
arXiv:2407.10887v4 Announce Type: replace-cross Abstract: Growing concerns over the theft and misuse of Large Language Models (LLMs) underscore the need for effective fingerprinting to link a model to
Business Insider: Sources: Alexandr Wang said Meta's model currently in training, codenamed Watermelon, matches GPT-5.5 and uses an “order of magnitude more compute than Avocado” — Meta is making sign
arXiv:2606.31639v1 Announce Type: cross Abstract: Large language models are no longer only text generators. They are increasingly embedded in retrieval pipelines, enterprise assistants, coding environ
Anthropic PBC today debuted Claude Sonnet 5, a midrange large language model that outperforms its predecessor in several areas. The LLM will be the default option in the consumer tiers of the company’
arXiv:2606.31422v1 Announce Type: new Abstract: Long-horizon language agents do not only choose actions; they carry a private model of the world from one decision to the next. When that model drifts,
arXiv:2606.32028v1 Announce Type: new Abstract: Video-based embodied world models provide an appealing substrate for robotic manipulation by predicting future states, yet current approaches remain lim
arXiv:2604.04834v2 Announce Type: replace Abstract: Robotic Vision-Language-Action (VLA) models generalize well for open-ended manipulation, but their perception is fragile under sensing-stage degrada
The Harness should be Model agnostic. The Knowledge it builds around you is your moat. You should not have to migrate or give that up just because a model is banned or just not good. Right now in my R
arXiv:2606.31207v1 Announce Type: new Abstract: The rapid advance of smart cities increasingly depends on trajectory data mining, yet underrepresented demographic groups, particularly the elderly, are
arXiv:2603.07939v2 Announce Type: replace Abstract: Underwater robots are widely deployed for ocean exploration and manipulation. Underactuated mechanisms are advantageous in aquatic environments beca
arXiv:2606.30151v1 Announce Type: new Abstract: Integrating large language models into robotic systems holds promise for enhancing autonomy, yet practical deployment remains constrained by strict hear
Bridgewater, one of the worlds largest hedge funds, a Tinker customer talks through how they've carefully fine-tuned a model focused on what makes interesting financial news. Their fine-tuned model is
The Keyword: Google launches Nano Banana 2 Lite, a low cost text-to-image model that delivers outputs in four seconds, and rolls out Gemini Omni Flash to developers — We're making it easier to experim
arXiv:2602.15257v3 Announce Type: replace-cross Abstract: We present the first comprehensive, large-scale study of training long-context vision language models up to 344K context, targeting long-docum
arXiv:2606.28333v1 Announce Type: cross Abstract: egin{quote} The biases in Large Language Models' (LLMs) outputs remain inadequately theorised, particularly from the perspective of the Global South.
arXiv:2606.28712v1 Announce Type: cross Abstract: Classical SLAM estimates metric poses and a geometric map but produces no actionable predictive model for planning. Action-conditioned world models le
The food delivery leader in China just dropped an open weights 1.6 trillion parameter model while half the USA was sleeping … 🫨 🇨🇳 Meituan, China's largest food delivery platform, open-sourced a 1.6 t
arXiv:2606.28758v1 Announce Type: cross Abstract: Predicting future states is essential for autonomous agents, yet current Vision-Language-Action (VLA) models fundamentally lack this capability, relyi
You can embed this model practically anywhere - like a chrome extension This is transformersjs + rampart for real-time PII removal in your browser (personal email still blurred) You can see I'm toggli
arXiv:2606.27831v1 Announce Type: cross Abstract: This paper addresses the lack of explicit memory mechanisms in current object detection models and proposes Hippocampus-DETR, a novel detection framew
arXiv:2606.27527v1 Announce Type: cross Abstract: Large Language Models (LLMs) possess broad conceptual knowledge acquired through large-scale text pretraining, yet their potential to supervise models
arXiv:2606.27537v1 Announce Type: new Abstract: Video generation models aspire to simulate dynamic environments, and several benchmarks now evaluate memory consistency across frames. However, most ass
arXiv:2603.09241v2 Announce Type: replace Abstract: Visual navigation requires agents to reach goals in complex environments through perception and planning. World models address this task by simulati
arXiv:2606.27948v1 Announce Type: new Abstract: Counterfactual explanations (CFs) help understand machine learning models by identifying minimal input changes that would lead to alternative model outc
arXiv:2505.10764v4 Announce Type: replace Abstract: Innovations in digital intelligence are transforming robotic surgery with more informed decision-making. Real-time awareness of surgical instrument
We have seen multi model harnesses for cheaper & faster tasks What about for the hardest challenges? What about open source? Proud to share the latest update our Zenith harness, taking models you can
Sakana Fugu Technical Report Instead of training one larger model, Sakana AI trains an orchestrator that reads each query and dynamically routes or composes GPT-5.5, Gemini-3.1-Pro, Claude Opus 4.8 an
arXiv:2606.26290v1 Announce Type: cross Abstract: While parameter-efficient fine-tuning (PEFT) typically targets attention projectors, its efficacy for tasks requiring sequential state accumulation re
Unconventional AI Inc. has developed an artificial intelligence architecture that could improve the power efficiency of image generation models. The technology is the basis of a new neural network ser
arXiv:2606.25424v1 Announce Type: cross Abstract: Diffusion-based text-to-speech (TTS) models have achieved significant improvements in speech quality. However, modeling sharp prosodic transitions and
arXiv:2606.22902v2 Announce Type: replace Abstract: Real-world users typically have access to multiple Large Language Models (LLMs) from different providers, and these LLMs often excel at distinct dom
arXiv:2606.25421v1 Announce Type: new Abstract: Recent studies on world modeling for Large Language Model (LLM) agents typically formulate the learning objective as next-observation prediction. Howeve
arXiv:2606.26016v1 Announce Type: new Abstract: Normalizing Flows (NFs) are powerful generative models capable of exact density estimation and sampling. However, their strict invertibility often force
arXiv:2407.07239v3 Announce Type: replace Abstract: Linear recurrent neural networks, such as State Space Models (SSMs) and Linear Recurrent Units (LRUs), have recently shown state-of-the-art performa
arXiv:2606.25034v1 Announce Type: new Abstract: General-purpose models often struggle to reliably identify and understand real-world multimodal risks, largely due to the inherent multimodal adversaria
arXiv:2606.24696v1 Announce Type: cross Abstract: Physics-informed surrogate models can accelerate computational fluid dynamics simulations. However, many existing methods reproduce global flow patter
arXiv:2606.24510v1 Announce Type: new Abstract: Rare diseases affect millions of individuals worldwide, yet timely diagnosis remains a major public health challenge due to scarcity of specialized clin
arXiv:2606.24667v1 Announce Type: new Abstract: Dense retrieval embedding models are a fundamental component of modern retrieval-based AI systems. Most dense retrievers are trained with contrastive ob
arXiv:2606.24120v1 Announce Type: new Abstract: Timely, high-resolution maps of flood extent around settlements are essential for emergency response and damage assessment. We consider airborne RGB ima
GLM-5.2 is now available in Cursor. The model has performed strongly on OpenRouter's Cursor usage rankings over the past week. Would love to hear comparisons of the experience using BYOK (GLM Coding P
arXiv:2407.07357v4 Announce Type: replace Abstract: Predicting signed interactions in biological networks is crucial for understanding drug mechanisms and facilitating drug repurposing. While deep gra
arXiv:2606.22138v1 Announce Type: cross Abstract: We present BioMatrix, the first multimodal foundation model that natively integrates sequences, structures, and natural language for both molecules an
arXiv:2606.15980v2 Announce Type: replace Abstract: Activation monitors -- lightweight probes trained on a language model's internal representations -- are an increasingly common layer in deployment s
arXiv:2606.22261v1 Announce Type: new Abstract: Abnormality detection in complex systems faces two practical barriers: abnormal labels are scarce, and binary labels do not quantify how far an event ha
arXiv:2602.12373v2 Announce Type: replace Abstract: The opioid epidemic remains one of the most severe public health crises in the United States, yet evaluating policy interventions before implementat
arXiv:2606.20698v1 Announce Type: new Abstract: Safe control is a prerequisite for real-world embodied intelligence, for which safe reinforcement learning has emerged as a promising paradigm. However,
arXiv:2606.22449v1 Announce Type: cross Abstract: Current embodied world models are primarily optimized for predictive objectives, limiting their ability to generalize under distribution shifts and re
arXiv:2606.23568v1 Announce Type: new Abstract: Large language models (LLMs) achieve remarkable performance across a wide range of tasks, but their deployment is constrained by substantial memory and
arXiv:2606.23546v1 Announce Type: new Abstract: Transformer-based models underpin modern natural language processing but incur rapidly growing computational and energy costs. As training scales in bot
arXiv:2512.11061v2 Announce Type: replace Abstract: Generative video models, a leading approach to world modelling, face fundamental limitations. They often violate physical and logical rules, lack in
arXiv:2606.23610v1 Announce Type: new Abstract: Video diffusion models have enabled remarkable progress in video generation and editing. However, content preservation remains a core challenge: existin
arXiv:2606.20814v1 Announce Type: cross Abstract: Emergent misalignment (EM) is a phenomenon in which models generalize with narrow fine-tuning, leading to broad (yet uneven) misalignment across evalu
GLM-5.2 has been the most popular new model on Fireworks this past week. @ArtificialAnlys confirms why: #3 overall on GDPval-AA (1524 Elo), #1 open weights by 116 points. Interest is showing no signs
Lily Hay Newman / Wired: OpenAI unveils an updated GPT-5.5-Cyber model, launches the Patch the Planet initiative in partnership with Trail of Bits to fix open source bugs, and more — Amid concerns abo
Cursor announced three major initiatives at the Compile keynote, including a partnership with SpaceX to train a new AI model. The announcement highlights Cursor's expansion efforts and collaboration w
A researcher released an open-source softmax-free attention model at GPT-2 Medium scale (354M parameters trained on 11.5B tokens) that uses structural sparsity and tile-skipping kernels to reduce VRAM
arXiv:2606.11553v1 Announce Type: new Abstract: Generic time-series foundation models transfer poorly to wireless network telemetry whose signals are bursty, zero-inflated, and coupled across protocol