Knowledge catalogue
arXiv:2603.18178v2 Announce Type: replace-cross Abstract: The rapid growth of ego-centric dashcam footage presents a major challenge for detecting safety-critical events such as collisions and near-co
arXiv:2605.18069v1 Announce Type: cross Abstract: This paper studies sampling error bounds for denoising diffusion probabilistic models (DDPMs) in the 2-Wasserstein distance. Our contributions are thr
arXiv:2605.18029v1 Announce Type: new Abstract: Multimodal product retrieval (MPR) underpins checkout-free retail and automated inventory systems, yet it demands fine-grained SKU discrimination that s
arXiv:2605.17017v1 Announce Type: cross Abstract: Behavior Foundation Models (BFMs) enable scalable imitation learning (IL) by pretraining task-agnostic representations that can be rapidly adapted to
3 new models from @xai's Grok creative stack are live on OpenRouter: • Grok Imagine Image Quality: photoreal image generation and editing • Grok Imagine Video: short clips from text, image, or referen
arXiv:2605.15755v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) can produce fluent artwork emotion explanations, but they often suffer from attribute flooding: they enumerate
arXiv:2602.04163v2 Announce Type: replace Abstract: Large language model inference is often bounded by memory footprint and bandwidth in resource-constrained deployments, making quantization fundament
arXiv:2605.16113v1 Announce Type: cross Abstract: Large language models (LLMs) have achieved unprecedented success due to their exceptional generative capabilities. However, because they depend on kno
arXiv:2605.15706v1 Announce Type: new Abstract: Recent advances in Large Language Models (LLMs) have catalyzed the development of multi-agent systems (MAS) for complex reasoning tasks. However, existi
arXiv:2605.15855v1 Announce Type: new Abstract: Despite strong image-generation performance, diffusion models' reconstruction objectives limit alignment with human preferences. RL enables such alignme
arXiv:2605.15803v1 Announce Type: new Abstract: Recent advancements have established Reinforcement Learning (RL) as a pivotal paradigm for aligning generative models with human intent. However, group-
I believe on-prem and local AI - based on @huggingface open-source models - will be an important answer to the GPU shortages this year (because they are cheaper, faster, safer than cloud APIs)! Great
arXiv:2605.15822v1 Announce Type: new Abstract: Score-based generative models are trained in high-dimensional ambient spaces, yet many data distributions are supported on low-dimensional nonlinear str
arXiv:2605.15301v1 Announce Type: new Abstract: Large language models (LLMs) still struggle with the rigorous reasoning demands of hard competitive programming. While recent multi-agent frameworks att
Eleanor Olcott / Financial Times: Developers say Chinese AI labs lead US rivals in video generation, as ByteDance and Kuaishou train models on vast short-form video libraries from their own apps — Chi
Alison Weissbrot / Adweek: Publicis agrees to acquire LiveRamp, which allows companies to share and build new data sets and models that can power agentic frameworks, for 2.2B in cash — Publicis Groupe
Rebecca Bellan / TechCrunch: A profile of AI video generation startup Runway, which is training models directly on observational data, is now valued at 5.3B, and added 40M in ARR in Q2 — Every major A
BREAKING: The results are in for Slides Arena... @AnthropicAI and @Zai_org models continue to lead the way in soft-verifiable domains 1st: Opus 4.7 by @AnthropicAI 2nd: Opus 4.7 (Thinking) by @Anthrop
arXiv:2605.14535v1 Announce Type: new Abstract: The increased use of Large Language Models (LLMs) in geography raises substantial questions about the safety of integrating these tools across a wide ra
arXiv:2603.21250v2 Announce Type: replace Abstract: Logical reasoning encompasses deduction, induction, and abduction. However, while Large Language Models (LLMs) have effectively mastered the former
arXiv:2605.14267v1 Announce Type: cross Abstract: Diffusion models (DMs) have exhibited remarkable efficacy in various image restoration tasks. However, existing approaches typically operate within th
arXiv:2509.22151v3 Announce Type: replace Abstract: Material node graphs are programs that generate the 2D channels of procedural materials, including geometry such as roughness and displacement maps,
arXiv:2602.04657v3 Announce Type: replace Abstract: Recently, reducing redundant visual tokens in vision-language models (VLMs) to accelerate VLM inference has emerged as a hot topic. However, most ex
Are scaling laws finally working for time series foundation models? Today, @datadoghq is releasing Toto 2.0 weights in Apache 2.0 on @huggingface. It's a family of open-weights TSFMs from 4M to 2.5B p
arXiv:2605.13450v1 Announce Type: new Abstract: Measuring the creativity of large language models (LLMs) is essential for designing methods that can improve creativity and for enhancing our scientific
Batching for vision models is now available in Beta with our latest MLX engine update 👾 The updated engine also brings major improvements to caching for faster inference overall. Turn on Developer Mod
arXiv:2605.13178v1 Announce Type: cross Abstract: In large vision-language models, visual tokens typically constitute the majority of input tokens, leading to substantial computational overhead. To ad
arXiv:2605.12702v1 Announce Type: new Abstract: General-purpose safety benchmarks for large language models do not adequately evaluate disability-related harms. We introduce DisaBench: a taxonomy of t
arXiv:2605.13156v1 Announce Type: new Abstract: Vision-language models (VLMs) have demonstrated remarkable capabilities in bridging visual perception and natural language understanding, enabling a wid
arXiv:2605.13375v1 Announce Type: cross Abstract: In Vision-Language Models (VLMs), processing a massive number of visual tokens incurs prohibitive computational overhead. While recent training-aware
arXiv:2605.13080v1 Announce Type: new Abstract: When humans describe a visual scene, they do not process the entire image uniformly; instead, they selectively fixate on regions relevant to their inten
arXiv:2605.13711v1 Announce Type: new Abstract: Multimodal irregular time series (MITS) consist of asynchronous and irregularly sampled observations from heterogeneous numerical and textual channels.
Most teams can pick frontier models. Fewer can run them at production scale without hitting constraints in latency, throughput, and governance. Fireworks AI on @Azure AI Foundry provides the inference
arXiv:2605.12852v1 Announce Type: new Abstract: Pertussis booster vaccination produces immune responses that vary widely across individuals in both peak magnitude and long-term durability. These two p
arXiv:2605.13448v1 Announce Type: cross Abstract: Diffusion models are often trained in low-dimensional latent spaces, which are then reused for related but shifted datasets. In this work, we study wh
arXiv:2605.13436v1 Announce Type: cross Abstract: Subword regularization methods such as BPE dropout are typically applied only during fine-tuning, while pretraining is usually done with deterministic
arXiv:2605.13667v1 Announce Type: new Abstract: Scene graph generation provides a compact structured representation for visual perception, but accurate and fast graph prediction from images and videos
arXiv:2605.12518v1 Announce Type: cross Abstract: The proliferation of online news poses a challenge to extracting structured timelines from unstructured content. While recent studies have shown that
Toto 2.0 is here: Datadog AI's 5 open-weights forecasting models (4m-2.5B params) finally make scaling work for time series forecasting! #1 on BOOM, GIFT-Eval, and TIME. Weights/code Apache 2.0. 🔗 Rea
Try Rime Mist v3 in voice finder directly: https://findtherightvoice.com/rime-labs--rime-mist-v3 Model pages: http://www.together.ai/models/rime-mist-v3 http://www.together.ai/models/rime-mist-v3-omni
arXiv:2605.13105v1 Announce Type: new Abstract: Reinforcement learning (RL) fine-tuning has shown promise for Vision-Language-Action (VLA) models in robotic manipulation, but deployment-time visual sh
arXiv:2602.13215v2 Announce Type: replace Abstract: Recurrent-attention hybrids aim to combine the efficiency of recurrence with the expressivity of attention, but existing approaches typically apply
Nous Research announced that Hermes Agents powered by OpenAI models can now use Codex as the runtime for executing core tools, enabling improved tool execution capabilities with a simple configuration
arXiv:2604.00626v2 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) continue to grow in both capability and cost, transferring frontier capabilities into smaller, deployable stud
arXiv:2605.11939v1 Announce Type: new Abstract: Prompt learning has emerged as an efficient alternative to fine-tuning pre-trained vision-language models (VLMs). Despite its promise, current methods s
Kate Park / TechCrunch: Config, which is building a data layer for robotics foundation models, raised a 27M seed at a 200M+ valuation led by Samsung Venture Investment — Asia's push into physical AI i
arXiv:2602.06462v3 Announce Type: replace Abstract: Masked diffusion language models generate text through iterative masked-token filling, but terminal-only rewards on final completions provide coarse
arXiv:2605.12055v1 Announce Type: new Abstract: Large Language Models (LLMs) achieve strong linguistic performance, yet their internal mechanisms for producing these predictions remain unclear. We inv
arXiv:2605.11774v1 Announce Type: new Abstract: By processing electronic health records (EHRs) as natural language sequences, large language models (LLMs) have shown potential in clinical prediction t
Ben Schoon / 9to5Google: Google says Chromebooks will get support through their “existing date commitment”, and “many” models are “eligible to transition” to the Googlebook experience — During The And
arXiv:2605.11347v1 Announce Type: cross Abstract: Existing reward alignment methods for diffusion and flow models rely on multi-step stochastic trajectories, making them difficult to extend to determi
I don't understand the path forward for Mythos releases. Google & OpenAI will have equivalent models, and they are approaching AI cyber risk guardrails differently, so they will presumably just releas
arXiv:2605.11803v1 Announce Type: new Abstract: As Video Large Language Models (Video-LLMs) scale to longer and more complex videos, their inference cost grows rapidly due to the large volume of visua
arXiv:2605.11142v1 Announce Type: new Abstract: Graph representation learning has become a standard approach for analyzing networked data, with latent embeddings widely used for link prediction, commu
arXiv:2411.16769v3 Announce Type: replace-cross Abstract: Understanding the capabilities of text-to-image (T2I) models in harmful content generation is essential to safety and compliance. However, hum
arXiv:2605.11017v1 Announce Type: new Abstract: Behavioral curve modeling -- fitting parametric functions to engagement-versus-exposure data -- is standard practice in recommendation, advertising, and
arXiv:2605.11496v1 Announce Type: cross Abstract: Recent published evidence from frontier laboratories shows that contemporary AI models can recognise evaluation contexts, latently represent them, and
We asked the CEO of HuggingFace @ClementDelangue what the risks of releasing powerful open source models are. He says restricting AI creates more risk than openness. 'Six, seven years ago, at the time
arXiv:2605.08612v1 Announce Type: new Abstract: Addressing the escalating security vulnerabilities in Vision-Language-Action (VLA) models, this study investigates backdoor attacks targeting the visual
arXiv:2605.09425v1 Announce Type: cross Abstract: Recent conditional image generation methods can improve controllability by generating images that are faithful to conditions such as sketches, human p