Knowledge catalogue
arXiv:2606.02346v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) achieves remarkable novel view synthesis quality with real-time rendering, yet suffers from excessive memory consumption du
arXiv:2602.07223v2 Announce Type: replace Abstract: Long-context large language model (LLM) inference has become the norm for today's AI applications. However, it is severely bottlenecked by the incre
arXiv:2506.22666v3 Announce Type: replace-cross Abstract: The rise of API-only access to state-of-the-art LLMs highlights the need for effective black-box jailbreak methods to identify model vulnerabi
Verification is the hidden bottleneck for knowledge work agents, especially in legal AI — complex, long-horizon work is graded by rubrics with dozens of strict criteria. In new research with @LangChai
Verifiers are important for scaling evals/RL But costs add up! So can we make them cheaper? Some great work by @Vtrivedy10 @jakebroekhuizen in conjunction with @nikogrupen @gabepereyra and the Harvey
arXiv:2510.03259v2 Announce Type: replace-cross Abstract: Recent research on reasoning models explores the meta-awareness of language models, including their ability to determine optimal thinking dura
arXiv:2606.00121v1 Announce Type: cross Abstract: Reconstructing visual stimuli from brain recordings has been a meaningful and challenging task in brain decoding. Especially, the achievement of preci
This appears to be a social media post expressing enthusiasm about an upcoming event or initiative related to @aiDotEngineer, with the author anticipating networking opportunities and meeting people t
arXiv:2606.00384v1 Announce Type: new Abstract: Fitting quantitative models to data is a central step in scientific workflows, yet it remains one of the least automated. Recent agent-based systems lev
arXiv:2606.01929v1 Announce Type: new Abstract: Public discourse on AI has become polarized; exaggerated positions on AI in traditional and social media threaten the development of AI Literacy among t
arXiv:2606.00735v1 Announce Type: cross Abstract: In distributed Mixture-of-Experts (MoE) inference, input-dependent token routing interacts with GPU performance variability to create persistent strag
arXiv:2606.00704v1 Announce Type: new Abstract: Real-world image super-resolution (Real-ISR) requires balancing structural fidelity to degraded observations with realistic detail synthesis. However, e
arXiv:2510.17045v2 Announce Type: replace-cross Abstract: Video reasoning using Large Multimodal Models (LMMs) relies on costly reinforcement learning (RL) and verbose chain-of-thought, resulting in s
arXiv:2602.04094v2 Announce Type: replace Abstract: Long-form video understanding remains challenging for Vision-Language Models (VLMs) due to the inherent tension between computational constraints an
arXiv:2602.01577v3 Announce Type: replace-cross Abstract: Camera-based visible light positioning (VLP) is a promising technique for accurate and low-cost indoor camera pose estimation (CPE). To reduce
arXiv:2603.07109v2 Announce Type: replace Abstract: Understanding physical transformations is fundamental for reasoning in dynamic environments. While Vision Language Models (VLMs) show promise in emb
arXiv:2606.02273v1 Announce Type: new Abstract: Understanding subtle driver actions is essential for building reliable driver monitoring systems. Existing visionlanguage models (VLMs) are trained on g
arXiv:2606.02572v1 Announce Type: new Abstract: Self-supervised learning methods prevent embedding collapse via modeling heuristics or explicit regularization of the embedding space. Among the latter,
arXiv:2606.00105v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable progress on vision-language tasks, but they may also memorize and expose sensitive o
arXiv:2602.15278v2 Announce Type: replace-cross Abstract: The web is littered with images, once created for human consumption and now increasingly interpreted by agents using vision-language models (V
arXiv:2501.12178v2 Announce Type: replace Abstract: Medical imaging studies often rely on a single sample per subject, assuming it is representative of their physiological traits. However, variations
arXiv:2606.00053v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models follow a data-driven paradigm and are constrained by the coverage of training data, making them prone to failure on
arXiv:2606.02138v1 Announce Type: cross Abstract: Out of distribution (OOD) events in multivariate time series forecasting are rare but often dominate real world risk, making average case forecasting
arXiv:2601.03309v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models, which integrate pretrained large Vision-Language Models (VLM) into their policy backbone, are gaining sig
arXiv:2606.02564v1 Announce Type: new Abstract: The recent 'Reasoning with Video' paradigm utilizes Video Generation Models (VGMs) to generate temporally coherent visual trajectories to complete reaso
arXiv:2509.15394v3 Announce Type: replace Abstract: Accurate electricity demand forecasting is challenging due to the strong multi-periodicity of real-world demand series, which makes effective modeli
arXiv:2512.10120v2 Announce Type: replace-cross Abstract: General-purpose audio representations aim to map acoustically variable instances of the same event to nearby points, resolving content identit
arXiv:2606.01955v1 Announce Type: cross Abstract: WALL-WM is a World Action Model that shifts video-action learning from chunk-centric optimization to event-grounded Vision-Language-Action pretraining
arXiv:2510.22276v3 Announce Type: replace-cross Abstract: Contrastive vision-language models have achieved remarkable progress through large-scale pretraining. Recent work has shown that removing Engl
arXiv:2606.00724v1 Announce Type: cross Abstract: Diffusion Large Language Models (DLMs) have demonstrated significant advantages across various tasks. However, constrained by their multi-step iterati
arXiv:2606.00689v1 Announce Type: new Abstract: Multimodal MRI provides complementary information for neuroimaging analysis, where different imaging modalities capture distinct anatomical, tissue, and
arXiv:2606.02375v1 Announce Type: new Abstract: We evaluate whether compact domain-specialized ASR models can outperform massively multilingual foundation models for conversational African speech acro
Hugging Face has doubled its total storage capacity over a five-month period and is on track to reach 1 Exabyte of storage before the end of the year. This rapid growth reflects the platform's expandi
We Parse PDFs We spent 7 figures to put this on billboards throughout SF. I thought long and hard about putting something more creative and whimsical. But then you wouldn’t know what we do. AI agents
We wrapped a live session on M3 yesterday with the @togethercompute team & our researchers @zpysky1125 and @HaohaiSun A few highlights 🧵 1. MSA (MiniMax Sparse Attention) is the star ⭐️. Unlike CSA/HC
arXiv:2606.00424v1 Announce Type: new Abstract: As large language models become stronger, weak supervisors may fail to provide reliable labels, preferences, or final judgments for complex outputs, lim
arXiv:2606.02096v1 Announce Type: new Abstract: Dynamic scene reconstruction from monocular videos remains highly challenging, as existing methods often struggle to balance global structural coherence
arXiv:2602.02250v2 Announce Type: replace-cross Abstract: Kullback-Leibler (KL) divergence regularization is widely used in reinforcement learning, but it becomes infinite under support mismatch and c
We're finally shedding the .so (thank you Somalia!), and using the .com for @NotionHQ. And for this beautiful moment, I want to share a fun story: Back in 2018, I had just joined Notion, and one of th
We’re looking forward to seeing how developers and enterprises use Fireworks AI on @Microsoft Foundry to power the next generation of intelligent applications. Catch us at booth F111 at #MSBuild and s
We’re making Codex more useful for your work by expanding plugins beyond individual tools. These plugins turn Codex into a specialist for a specific role with a single install, no coding required. Cod
We're sponsoring a hackathon to scale down. Hosted by our friends @huggingface and @Gradio, we want working with models to feel like yours again. Small enough that it's inexpensive to run, big enough
What bothers me the most about the Nowak case is how he had no chance. He was stabbed, and in other cases maybe he would have received assistance, maybe the perpetrator would have run away and then pe
arXiv:2603.29488v2 Announce Type: replace Abstract: Cosine similarity is often used to measure the similarity of vector representations of neural network models. However, the cosine similarity of repr
arXiv:2602.11177v2 Announce Type: replace-cross Abstract: Reliable early detection of Alzheimer's disease (AD) is challenging, particularly due to the limited availability of labeled data. While large
What happened to Henry Nowak was not a tragedy. A tragedy is when someone noble makes a mistake with inevitably dire consequences. The murderer was not noble. He (and his family) are evil. The police
arXiv:2606.01292v1 Announce Type: cross Abstract: Teacher-Student Knowledge Transfer (KT) is ubiquitous in modern machine learning, ranging from classical model compression via Knowledge Distillation
arXiv:2606.01936v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have opened up new possibilities for automated document formatting. However, real-world formatting often
arXiv:2606.01624v1 Announce Type: new Abstract: Driving vision-language models (VLMs) must accurately understand scenes across diverse conditions defined by Operational Design Domains (ODDs), yet veri
A few weeks ago, we announced the public preview refresh of hosted agents in Foundry Agent Service — a fundamentally re-imagined agent runtime built for operationalizing production-grade AI agents in
Microsoft Build 2026 brings a major set of Microsoft Foundry updates for developers building agents: hosted runtimes, Toolboxes, memory, Voice Live, Foundry IQ, new models, managed compute, and trust,
arXiv:2602.16763v2 Announce Type: replace Abstract: Artificial intelligence benchmarks are an important mechanism for measuring model progress and guiding deployment decisions. However, benchmarks qui
arXiv:2602.08236v2 Announce Type: replace-cross Abstract: Despite rapid progress in MLLMs, visual spatial reasoning remains unreliable when correct answers depend on how a scene would appear under uns
arXiv:2606.01155v1 Announce Type: cross Abstract: Scaling laws for dense LLMs under infinite data are well explored, but how sparsity interacts with limited data is not. In this work, we study sparse
arXiv:2606.02378v1 Announce Type: cross Abstract: We track the developmental trajectory of attention-head circuit formation across three 1B-class language models spanning two architecture families (de
arXiv:2601.21718v2 Announce Type: replace-cross Abstract: Behavior cloning (BC) is a practical offline imitation learning method, but it often fails when expert demonstrations are limited. Recent work
arXiv:2606.01304v1 Announce Type: new Abstract: Hard negative mining has become the dominant strategy for training retrievers, yet it faces intrinsic limitations: negatives are bounded by corpus avail
arXiv:2606.01074v1 Announce Type: new Abstract: Recent high-performing text embedding models often output high-dimensional real-valued vectors, resulting in substantial storage and computational costs
arXiv:2606.00046v1 Announce Type: cross Abstract: Video platforms such as YouTube have reshaped how users engage with entertainment and information, emphasizing brief, highly engaging content such as
arXiv:2606.02245v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) typically assumes that external knowledge is free, but many high-quality sources are paywalled, licensed, restricte