Search: “model-releases”

arXiv:2602.12643v2 Announce Type: replace-cross Abstract: We present Unified Latent Dynamics (ULD), a novel reinforcement learning algorithm that unifies the efficiency of model-free methods with the

arXiv:2606.04035v1 Announce Type: cross Abstract: We present a systematic study of domain-dependent safety behavior in open-weight LLMs: 7 standardized experiments across 7 ethical domains, testing 5

arXiv:2606.04244v1 Announce Type: new Abstract: Multimodal large language models are increasingly capable of complex reasoning, yet their performance often degrades when they must externalize a proble

arXiv:2606.04588v1 Announce Type: new Abstract: Multimodal large language models have made rapid progress in video understanding, yet existing benchmarks largely rely on simple prompts and provide lim

arXiv:2508.08237v4 Announce Type: replace-cross Abstract: The emergence of audio-visual foundation models underscores the importance of reliably assessing their multi-modal understanding. The VGGSound

arXiv:2606.04351v1 Announce Type: cross Abstract: Processing video in vision-language models is expensive: each frame occupies hundreds of tokens, and inference cost scales with every frame and every

We are excited to join Nvidia's Nemotron Coalition of leading AI labs working together to advance open frontier foundation models. To celebrate we have partnered with @nvidia and @nebiustf to provide

We're building in Canada. 🇨🇦 For decades, Canada invested to build the research foundations that made modern AI possible. Now we have to build, train, and scale what comes next here at home. Canada's

We're presenting ParseBench at CVPR 2026! ParseBench is the most comprehensive document understanding benchmark for VLMs. ✅ It contains 2k pages of real-world enterprise documents ✅ It has comprehensi

We're presenting ParseBench at CVPR 2026 today. 🦙 Come learn why document understanding is an AGI-complete problem (an agent can't act on a doc it can't correctly read, and reading a real enterprise t

arXiv:2507.03373v2 Announce Type: replace Abstract: Given Wikipedia's role as a trusted source of high-quality, reliable content, concerns are growing about the proliferation of low-quality machine-ge

We’ve been researching new ways for ChatGPT memory to carry context across conversations and keep it useful over time. Today, that work is rolling out as a more capable memory system in ChatGPT. https

arXiv:2606.04233v1 Announce Type: new Abstract: A robotics benchmark score measures success under one fixed evaluation setup, yet is routinely treated as evidence of general manipulation capability. W

What happened when one of our models found a counterexample to an 80-year-old Erdős conjecture? Researchers @alexwei_, @HongxunWu, and @wjmzbmr1 shared the story on the OpenAI Podcast with @AndrewMayn

arXiv:2606.04425v1 Announce Type: cross Abstract: Modern agentic systems transform LLMs from session-bounded assistants into stateful systems that persist and evolve shared world state across sessions

At Google Cloud, our goal is to let you run large-scale analytical and data science workloads with maximum efficiency so you can process big data pipelines, machine learning, and ETL tasks. We recentl

arXiv:2606.04375v1 Announce Type: new Abstract: Differentially private stochastic gradient descent (DP-SGD) injects noise into every updated coordinate, making the injected noise energy scale with the

arXiv:2606.04098v1 Announce Type: new Abstract: Video misinformation increasingly operates at the semantic and evidential level: authentic footage may be selectively edited, temporally reordered, spli

When you burn so much money you run out of options… Anthropic co-founder and President Daniela Amodei said the high cost of developing AI models is driving firms like hers to look to the public market

OpenAI introduced a new memory system for ChatGPT that allows users to review and control what the AI remembers across conversations through a memory summary feature. This update provides enhanced tra

This entry documents a Wordle game result where the player solved puzzle #1,810 in 4 attempts, using the color-coded feedback system (black for incorrect letters, yellow for correct letters in wrong p

xAI announced a partnership with Vapi to integrate voice capabilities into xAI's AI systems and services. The collaboration aims to enhance conversational AI by leveraging Vapi's voice technology plat

arXiv:2606.04301v1 Announce Type: new Abstract: Acquiring labeled medical image data is resource-intensive and a challenge further exacerbated in cross-domain scenarios where source and target dataset

arXiv:2606.04906v1 Announce Type: cross Abstract: Although it is generally agreed that AI-generated text poses a broad societal risk, there is no common understanding in the AI-generated text detectio

This benchmark demonstrates how integrating Alluxio with Ray Data achieves 20x faster training data read speeds for cross-region machine learning workloads on Anyscale's platform. The study shows perf

95% token reduction. 30x faster execution. 90%+ task completion. Today at #MSBuild, we announced a major shift to move reasoning upstream: Pinecone Nexus now integrates directly with @Microsoft OneLak

arXiv:2606.03609v1 Announce Type: cross Abstract: Embodied agents that navigate cities rely on world models that predict how their surroundings will change as they move. But for navigation, what matte

arXiv:2606.03646v1 Announce Type: new Abstract: This paper constructs the first benchmark on semi-supervised multi-modal crowd counting. To lay the foundation for this unexplored task, we first formul

arXiv:2606.03675v1 Announce Type: new Abstract: Methane is a potent greenhouse gas, and detecting leaks early via hyperspectral satellite imagery can help climate change mitigation efforts. Meanwhile,

arXiv:2606.02644v1 Announce Type: cross Abstract: Agentic scaffolds have dramatically improved LLM performance on complex, long-horizon tasks, yielding both broad benefits and amplified risks in domai

arXiv:2601.04120v2 Announce Type: replace-cross Abstract: Optimal control of obstacle problems arises in a wide range of applications and is computationally challenging due to its nonsmoothness, nonli

A workflow audit is no longer the best way to figure out how to use AI in your job. Despite the advice from AI labs, I'm more convinced, because of AI's reasoning capabilities and long context horizon

arXiv:2606.02755v1 Announce Type: cross Abstract: Large language model (LLM) applications are increasingly expected to satisfy deterministic institutional requirements while relying on probabilistic g

arXiv:2602.12430v4 Announce Type: replace-cross Abstract: The transition from monolithic language models to modular, skill-equipped agents marks a defining shift in how large language models (LLMs) ar

Carl Franzen / VentureBeat: Alibaba releases Qwen3.7-Plus, a multimodal proprietary model with a 1M-token context window, costing $2 per 1M tokens, 60% less than text-only Qwen3.7-Max — However, like

arXiv:2606.03967v1 Announce Type: cross Abstract: We describe AlignAtt4LLM, an IWSLT 2026 simultaneous speech translation system for English to German, Italian, and Chinese. The system is a synchronou

arXiv:2606.03774v1 Announce Type: new Abstract: Eye tracking is essential for smart glasses, as it provides insight into user attention for ambient intelligence applications. However, most existing ey

arXiv:2606.03217v1 Announce Type: cross Abstract: Chain-of-thought (CoT) reasoning has become a widely used mechanism for eliciting multi-step reasoning in large language models by generating intermed

arXiv:2606.03559v1 Announce Type: new Abstract: For nonconvex optimization problems whose objective is the prediction function of a trained Support Vector Regression (SVR) model with the Gaussian radi

Another banger open-source release. Miso One is an 8B text-to-speech model with real emotional range, so voiceovers carry warmth, hesitation, and excitement instead of sounding flat. It's purpose-buil

arXiv:2606.02915v1 Announce Type: new Abstract: Visual posters are a compact medium for communicating dense information, yet progress on automatic poster generation remains difficult to measure becaus

arXiv:2606.03116v1 Announce Type: cross Abstract: The rapid advancement of instruction-guided audio generation has highlighted the critical need for robust alignment evaluation. Current automated eval

arXiv:2606.03355v1 Announce Type: new Abstract: Physics models are inherently imperfect due to misspecified or missing mechanisms, resulting in systematic discrepancies between model predictions and r

arXiv:2604.04087v2 Announce Type: replace Abstract: We introduce ArrowFlow, a machine learning architecture that operates entirely in the space of permutations. Its computational units are ranking fil

This week we've got tandem hands-ons with Google's new Gemini AI agent - Spark - from my colleagues David Pierce and Jay Peters. Their takeaways are similar: It's so effective that it's scary. Spark k

arXiv:2606.03175v1 Announce Type: new Abstract: Instance Goal Navigation (IGN) requires an embodied agent to find a specific object instance among distractors from an underspecified natural-language d