Knowledge catalogue
arXiv:2601.06347v2 Announce Type: replace Abstract: Recent progress in universal multilingual named entity recognition (NER) has been driven by multilingual transformer models, task-specific architect
arXiv:2607.22218v1 Announce Type: new Abstract: Despite the growing use of large language models (LLMs) as creativity evaluators, evidence of their alignment with human evaluations remains mixed, rais
Ollama is proud to sign @satyanadella's letter. Our mission from day one has been to make open models accessible to every developer to unlock the next frontier in America and across the globe. Open-we
arXiv:2607.20476v1 Announce Type: new Abstract: We present an empirical benchmark evaluating how five large language models assess multisensor physical hazard data. Testing 60 scenarios across three c
arXiv:2607.20471v1 Announce Type: new Abstract: Personalization, the act of varying a message to induce action from a specific receiver while keeping sender, channel, and time fixed, has a long tradit
arXiv:2604.01925v2 Announce Type: replace-cross Abstract: Large Language Models increasingly suppress biased outputs when demographic identity is stated explicitly, yet may still exhibit implicit bias
arXiv:2607.20806v1 Announce Type: new Abstract: Lightweight large language models (LLMs) are increasingly being deployed locally on personal computers and are expected to play a growing role in resour
This is rather counterintuitive, since banning Chinese models would benefit them the most. Jensen Huang is also against the ban, although the interests here are more obvious. Do you think that if Arce
arXiv:2607.19847v1 Announce Type: cross Abstract: Predicting missing cell values in tabular data is a fundamental problem in data cleaning. While state-of-the-art reasoning models show great promise i
I wanted to know how cheap you can go and still run local models, so I ran Ollama CPU-only on a Youyeetoo X1S. It's a single-board x86 machine with a Celeron N5095 (Jasper Lake, 4C/4T, 15W), 16GB of R
arXiv:2607.20092v1 Announce Type: cross Abstract: Contextual entrainment is the tendency of a model to let auxiliary context in its input pull its output, independently of whether that context is rele
Frontier AI models are increasingly demonstrating high‑risk autonomous behaviours that pose safety threats. Incidents such as OpenAI‑released models escaping containment safeguards and a Hugging Face
arXiv:2607.20048v1 Announce Type: new Abstract: We propose importance-aware pruning for diffusion models, a training-free framework that prioritizes preserving parameters critical to semantically sali
arXiv:2607.19424v1 Announce Type: cross Abstract: The assessment of jailbreak attacks against large language models currently suffers from inconsistent evaluation criteria and methods, leading to unre
arXiv:2607.20410v1 Announce Type: new Abstract: Value alignment of Large Language Models (LLMs) has been shown to be culturally biased toward Western norms. This results in the mishandling of local va
There's a bunch of small MoE with around 1B active params, like LFM2.5 8B A1B and Granite 4.0h 7B A1B; and then there are models with 3B+ like Qwen 3.x ~30B A3B and Gemma 4 26B A4B, but those are alre
arXiv:2607.20216v1 Announce Type: cross Abstract: Malware analysis demands rapid interpretation of complex detonation reports spanning filesystem, network, and process behaviours. While large language
arXiv:2607.16741v2 Announce Type: replace Abstract: Burger et al. (2024) demonstrated that truth representations in large language models are universal across statement polarity but reside within a mu
arXiv:2607.19383v1 Announce Type: cross Abstract: Pretrained generative foundation models cast forecasting as conditional generation from a learned predictive distribution and forecast unseen series z
OpenAI Group PBC today disclosed that two of its artificial intelligence models broke out of a controlled testing environment and hacked open-source AI platform Hugging Face Inc. to cheat on an intern
arXiv:2607.13172v1 Announce Type: new Abstract: We address the problem of safely training an agent policy and deploying a good and safe policy, in settings where the environment dynamics are unknown a
arXiv:2607.12829v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) offer a theoretical advantage in parallel generation over standard autoregressive models. However, parallel ge
arXiv:2607.11915v1 Announce Type: cross Abstract: Plasma diagnostic models for tokamak fusion devices are almost universally evaluated on clean, complete sensor data. In practice, fusion diagnostics f
Two DGX Spark and a Connect-X7 cable give you about 250GB of usable memory for 7000 8000 USD. This allows using some interesting models at 4-bit. For what seemed like an eternity, the only serious mod
arXiv:2510.00492v3 Announce Type: replace Abstract: The reliability of large language models (LLMs) during test-time scaling is often assessed with external verifiers or reward models that distinguish
arXiv:2607.12290v1 Announce Type: cross Abstract: Audio-language embedding models such as CLAP are widely evaluated on matching present sound events, but rarely on negation. We show this affirmation-o
arXiv:2512.15748v2 Announce Type: replace-cross Abstract: Visual Species Recognition (VSR) is a fundamental task in scientific disciplines that require species-level identification, including ecology,
Big unlock for open-source AI inference: Hugging Face Transformers models can now run in vLLM at native speed, often matching or beating hand-written implementations. Until now, every new architecture
For the last few months, the conversation around open models has centered on cost and performance optimization. But Satya highlights something more existential: open models aren't just an optimization
arXiv:2510.22052v2 Announce Type: replace Abstract: The field of artificial intelligence (AI) has taken a tight hold on broad aspects of society, industry, business, and governance in ways that dictat
arXiv:2607.08434v1 Announce Type: new Abstract: Current Unified Large Multimodal Models (ULMMs) support interleaved multimodal reasoning through textual reasoning and intermediate visual states, but t
arXiv:2607.08059v1 Announce Type: cross Abstract: Uncertainty quantification for visual language models (VLMs) conventionally targets the answer token distribution. We provide the first three-family e
arXiv:2607.07707v1 Announce Type: cross Abstract: Limited memory language models (LMLMs) externalize factual knowledge during pretraining to a knowledge base (KB), rather than memorizing it in their w
arXiv:2603.17390v2 Announce Type: replace Abstract: Material classification has emerged as a critical task in computer vision and graphics, supporting the assignment of accurate material properties to
arXiv:2607.07673v1 Announce Type: new Abstract: Medicine is inherently multimodal, requiring clinicians to synthesize information across diverse data streams. Yet the development of multimodal foundat
OpenAI has announced the rollout of its GPT-5.6 family of models, consisting of Sol, Terra, and Luna variants, across ChatGPT, Codex, and API platforms. These models represent the latest iteration in
arXiv:2607.06485v1 Announce Type: cross Abstract: Vision-language models (VLMs) are increasingly deployed on infrared (IR) remote sensing imagery in security-critical settings, yet their adversarial r
arXiv:2607.06403v1 Announce Type: new Abstract: Despite recent progress of VLA foundation models, the disparity between laboratory conditions and real-world applications continues to impede their prac
GPT-Live is a new generation of voice model developed by OpenAI designed to enable more natural human-AI voice interactions. The model began rolling out to ChatGPT users starting on the date of this a
OpenAI: OpenAI launches GPT-Live, a new generation of voice models built on a full-duplex architecture, meaning they can listen and speak at the same time — A new generation of voice models for natura
arXiv:2510.13808v2 Announce Type: replace Abstract: Large Vision Language Models (VLMs) excel at general visual reasoning but experience significant performance degradation when deployed in novel doma
New York Times: Alibaba's Qwen models have made it an AI powerhouse, but the company has struggled to turn their global popularity into a profitable business — The Chinese company's models have won ov
arXiv:2607.04727v1 Announce Type: cross Abstract: Automatic data visualization generation has advanced rapidly with multi-modal large language models, yet existing efforts largely focus on static char
arXiv:2607.02555v1 Announce Type: new Abstract: Deep learning models for diabetic foot ulcer (DFU) segmentation routinely report high accuracy, but they are almost always trained and tested on the sam
arXiv:2607.04801v1 Announce Type: new Abstract: Personalizing text-to-image diffusion models to render several specific subjects in a coherent image remains challenging: the model must preserve each s
arXiv:2607.04339v1 Announce Type: cross Abstract: Large generative models across text-to-text, text-to-image, and image-to-text modalities have been shown to pose significant privacy risks. One fundam
arXiv:2601.11049v2 Announce Type: replace-cross Abstract: We examine whether large language models (LLMs) can predict biased decision-making in conversational settings, and whether their predictions c
arXiv:2607.04199v1 Announce Type: new Abstract: The growing number of medical vision foundation models highlights the need for effective model selection. However, mainstream selection methods rely on
arXiv:2607.02893v1 Announce Type: cross Abstract: Low-bit quantization shrinks language models but treats precision as a single global hyper-parameter: every weight uses the same bit-width. We introdu
Language models play a central role in automatic speech recognition (ASR), yet most methods rely on text-only models unaware of ASR error patterns. Recently, large language models (LLMs) have been app
arXiv:2512.02657v2 Announce Type: replace-cross Abstract: Real-world deployment of text-to-image diffusion models requires continual concept removal as new privacy, copyright, or safety obligations ar
arXiv:2607.00605v1 Announce Type: cross Abstract: Limited Memory Language Models (LMLMs) externalize factual knowledge to a database to enable deletion-based unlearning without retraining. Existing ev
arXiv:2607.01117v1 Announce Type: new Abstract: Video Large Language Models (VideoLLMs) have shown strong progress in video understanding, yet they still suffer from hallucinations that are inconsiste
arXiv:2603.19122v2 Announce Type: replace Abstract: Class-conditional generative models have emerged as accurate and robust classifiers, with diffusion models demonstrating clear advantages over other
arXiv:2603.16859v2 Announce Type: replace Abstract: Omni-modal large language models (OLMs) redefine human-machine interaction by natively integrating audio, vision, and text. However, existing OLM be
arXiv:2607.00276v1 Announce Type: cross Abstract: Current large-language-model (LLM) physics benchmarks are usually scored by answer accuracy, which cannot distinguish genuine reasoning from recall of
arXiv:2607.00917v1 Announce Type: cross Abstract: World models can enable Model Predictive Control (MPC), but this requires dynamics prediction that is both fast enough for online use and expressive e
arXiv:2606.31338v1 Announce Type: cross Abstract: Recent music audio-language models achieve high accuracy on instrument question-answering benchmarks, but it remains unclear whether this reflects rob
arXiv:2606.31986v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning has enabled multi-modal large language models (MLLMs) to tackle complex visual reasoning tasks by generating explicit i
You really need to benchmark models for your use case. As soon as judgements & decisions stack on top of each other, the differences between models amplifies, and no standard benchmark will tell you t