model releases

arXiv:2609.07638v1 Announce Type: cross Abstract: Hyphenation patterns remain a compact and widely deployed solution for word breaking in typesetting systems, text processors, and web rendering engine

arXiv:2409.09903v3 Announce Type: replace-cross Abstract: Softmax Mixture Models (SMMs) are discrete K-component mixture models for the probabilities of selecting one of p candidate feature vectors X_

arXiv:2609.06934v1 Announce Type: new Abstract: Post-hoc safety training (RLHF, DPO) is the dominant way to align large language models, yet jailbreaks (Zou et al., 2023b), fine-tuning attacks (Qi et

arXiv:2609.07162v1 Announce Type: new Abstract: Several properties safety monitors are asked to certify, among them cross-tenant noninterference, sandbagging and evaluation awareness, are 2-safety hyp

arXiv:2609.07216v1 Announce Type: new Abstract: The rapid evolution of video generation has shifted the paradigm from pure text-driven to multi-conditional controllable generation, with reference imag

there is a difference between 'i am ok with models being trained on my data and released publicly later' and 'i am ok with internal models trained on my very recent efforts, being used to race the sol

There is a nice visualization of how task bundles change with AI & some good interactive simulations of GDP growth under different assumptions in this. But missing are the right policy responses if we

This is a really neat benchmark. It's super interesting that Astra starts strong and holds the lead for up to 19 hours, but Fable 5.1 catches up in the final hours. Not entirely clear why. Different m

arXiv:2609.05596v1 Announce Type: new Abstract: Can interactive vision-and-language agents learn not just what to say but also extbf{extit{when}} to say it? Current language models rarely plan over wh

arXiv:2602.00288v4 Announce Type: replace Abstract: Fine-grained spatio-temporal understanding is essential for video reasoning and embodied AI. Yet, while Multimodal Large Language Models (MLLMs) mas

arXiv:2603.04949v2 Announce Type: replace-cross Abstract: As web agents close the gap with humans on benchmarks, one question arises: Do today's agents perform just as well on tomorrow's web? We intro

arXiv:2609.08703v1 Announce Type: cross Abstract: Text-to-speech systems often face a trade-off between natural prosody and efficient inference: higher perceptual quality typically comes at increased

arXiv:2609.05565v1 Announce Type: cross Abstract: Large language model (LLM) sustainability is increasingly a serving-systems problem, not only a training problem. In production, energy and carbon imp

arXiv:2609.08402v1 Announce Type: new Abstract: Air-Ground Object Search (AGOS) in urban environments is a challenging embodied task, which requires an Unmanned Aerial Vehicle (UAV) and an Unmanned Gr

arXiv:2609.07373v1 Announce Type: new Abstract: Modern Visual Place Recognition (VPR) methods excel on standard benchmarks yet remain brittle in feature-poor environments. By treating each query image

arXiv:2609.08981v1 Announce Type: new Abstract: A growing body of work establishes that large language models are not mere statistical memorizers, but are capable of in-context learning: performing in

arXiv:2609.07610v1 Announce Type: new Abstract: We convert black-box clinical prediction models for tabular data into standalone nomograms that can be audited term by term. PRiSM (Partial Responses in

arXiv:2609.06665v1 Announce Type: new Abstract: Diffusion-based models enable monocular geometry estimation, yet their pixel-space precision is limited by a shared, under-studied error source: VAE rec

arXiv:2609.06011v1 Announce Type: cross Abstract: Omni-modal large language models (OLLMs) jointly process vision, audio, and text, yet their modality bias under cross-modal conflict remains underexpl

arXiv:2609.07063v1 Announce Type: new Abstract: Built upon local differential privacy (LDP), locally private graph learning protocols have emerged as an important paradigm for decentralized graph lear

arXiv:2506.05626v3 Announce Type: replace Abstract: Real-world knowledge can take various forms, including structured, semi-structured, and unstructured data. Among these, Knowledge Graphs (KGs) are s

arXiv:2511.22341v2 Announce Type: replace Abstract: Previous works identify sensitivity to option order as a key issue in multiple-choice VQA (MC-VQA) evaluation and propose protocols to mitigate this

https://www.reuters.com/technology/us-accuses-chinese-ai-firms-industrial-scale-theft-ai-technology-2026-09-08/ https://www.nbcnews.com/tech/tech-news/us-accuses-china-ai-developers-deepseek-alibaba-c

arXiv:2602.19322v2 Announce Type: replace Abstract: Ultrasound (US) imaging poses unique challenges for representation learning due to its inherently noisy acquisition process. The low signal-to-noise

arXiv:2609.06245v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) perform strongly on general visual understanding tasks such as visual question answering, yet they often strugg

arXiv:2609.08342v1 Announce Type: new Abstract: World models take multimodal inputs like text, photos, and diagrams to generate dynamic scenes in accordance with the laws of physics, thus opening a co

arXiv:2609.06100v1 Announce Type: new Abstract: Verifiable outcome rewards guide language-model post-training, but sequence-level advantages do not identify which token-level decisions should be prese

arXiv:2609.08040v1 Announce Type: cross Abstract: The software supply chain has become an increasingly exposed attack surface because of its reliance on intricate yet fragile dependencies. Existing de

arXiv:2609.08079v1 Announce Type: new Abstract: Recent advances in video generation have made prompt-based control increasingly central to AIGC video generation. Prompts specify what a video should de

arXiv:2609.06652v1 Announce Type: new Abstract: Video foundation models increasingly rely on large-scale pretraining data, yet the end-to-end data pipelines behind them remain largely closed and diffi

arXiv:2609.08905v1 Announce Type: new Abstract: Workspace analysis measures where a robot can place its end effector. For visually guided manipulation, reachability alone is insufficient: a kinematica

arXiv:2606.14787v2 Announce Type: replace Abstract: We study six production image-to-image AI systems (gpt-image-1, Gemini 2.5 Flash Image, Flux Kontext, SDXL img2img, SD3 img2img, and Qwen Image Edit

arXiv:2609.06497v1 Announce Type: cross Abstract: Multimodal sentiment analysis requires effective modeling of both verbal semantics and non-verbal affective cues. A central challenge is to calibrate

arXiv:2609.06508v1 Announce Type: new Abstract: Long-horizon robot manipulation with Vision-Language-Action (VLA) policies remains vulnerable to execution-time deviations, as final task success provid

We benchmarked DeepSeek V4.1 Flash by @deepseek_ai . It reached 98% of GPT-6 Astra’s score at 1.4% of the cost on everyday design tasks based on user requests. Every model except Astra scored lower AN

We mobilized 250+ people to strengthen our defenses across hundreds of systems. Our latest cyber models helped us find and fix vulnerabilities we might never have discovered otherwise. We’re sharing w

We’re entering an era of agent-first tools: stronger feedback loops between agents, with human judgment where it matters. We keep hearing from senior engineers that their mental load is growing, even

We're introducing Q2D-Web (Query2Doc-Web), a benchmark and public leaderboard for evaluating retrieval in agentic RAG systems. Q2D-Web tests how embedding models perform on large-scale web search usin

arXiv:2503.04666v2 Announce Type: replace Abstract: High-quality benchmarks are crucial for driving progress in machine learning research. However, despite the growing interest in video generation, th

This is from the https://huggingface.co/IFM/K2-Horizon-0.9B benchmark image Tried searching for it but couldn't find it, I am guessing is https://huggingface.co/openbmb/MiniCPM5-1B but the numbers do

Hi, I'm wondering what settings you are using in order to run Qwen3.8-Flash-Next on your devices? I'm especially interested in setups with 96GB VRAM. I'm not quite sure if llama.cpp does offload the e

arXiv:2609.06147v1 Announce Type: cross Abstract: Ask a language model the same question about the same document twenty times, and it sometimes returns two different answers. We built Probity, a bench

Catch up on July and August in Microsoft Foundry: stable Hosted Agent and Toolbox SDK paths, Claude tools on Azure-hosted deployments, Model Router updates, local inference improvements, and the SDK m

arXiv:2609.06646v1 Announce Type: new Abstract: Annotators routinely disagree on laughter boundaries and subtle chuckles, yet temporal laughter localization typically evaluates against a single refere

arXiv:2609.09116v1 Announce Type: new Abstract: Normalization renders large parts of neural networks effectively scale invariant, inducing a hidden feedback loop in which learning-rate schedules and w

arXiv:2609.08615v1 Announce Type: new Abstract: Dimensional attention in learning is often implemented as a globally shared attention vector, where each stimulus dimension corresponds to a single scal