Search: “models”

Sam Altman jokingly suggested naming OpenAI's next model 'Goblin' as a humorous response to community requests or preferences about model naming. The post appears to be a lighthearted tweet indicating

The great thing is that the names are so baffling that the most important models OpenAI released were names davinci-002, GPT-3.5, GPT-4, o1-preview, o3, GPT-5 Pro, and you would never know the ways th

GPT-5.5 is now available in ComfyUI. OpenAI's latest frontier model — built for reasoning, structured output, and reliable single-pass results. → Prompt synthesis → Logic-heavy transformations → Clean

Training models involves many technical and social processes, so prevention of CoT grading has to be built into the process. We’re improving real-time CoT-grading detection, safeguards against acciden

arXiv:2605.03391v1 Announce Type: cross Abstract: Weighted first-order model counting (WFOMC) is a central task in lifted probabilistic inference: It asks for the weighted sum of all models of a first

arXiv:2605.03648v1 Announce Type: new Abstract: To understand complex system dynamics in dairy farming, it is essential to use modeling tools that capture farm heterogeneity, social interactions, and

arXiv:2605.05090v1 Announce Type: new Abstract: We present an automated, contrastive evaluation pipeline for auditing the behavioral impact of interventions on large language models. Given a base mode

arXiv:2512.06393v5 Announce Type: replace-cross Abstract: Large language models (LLMs) achieve high accuracy on many reasoning benchmarks but remain brittle under structural perturbations of rule-base

arXiv:2605.04413v1 Announce Type: new Abstract: Structural causal models provide a unified semantics for interventions and counterfactuals, but most identifiability results rely on restrictive assumpt

arXiv:2512.14954v2 Announce Type: replace Abstract: Computing next-token likelihood ratios between two language models (LMs) is a standard task in training paradigms such as knowledge distillation. Si

arXiv:2605.04198v1 Announce Type: new Abstract: Performance of deep learning models is strongly governed by architectural capacity, with width and depth as primary controls. However, in physical-scien

I don't really ever trust benchmarks, so ocassionally I'm stress-vibe-testing a bunch of new models on some very complex agent work (hundreds of tools, not your simple coding agent stuff) and to my su

arXiv:2605.04060v1 Announce Type: cross Abstract: Recently, a new paradigm named drifting model has been proposed for mapping distributions, which achieves the SOTA image generation performance over I

arXiv:2510.04166v2 Announce Type: replace-cross Abstract: Syntax highlighting is a critical feature in modern software development environments, enhancing code readability and developer productivity.

New Anthropic research: Natural Language Autoencoders. Models like Claude talk in words but think in numbers. The numbers—called activations—encode Claude’s thoughts, but not in a language we can read

Open Models Make Agentic Batch Processing Economically Viable A lot of world’s work looks like “Do X for EVERY Y” - read every trace - respond to every email - deep dive into every document - enrich e

arXiv:2605.05159v1 Announce Type: new Abstract: We present our system for SemEval-2026 Task 9: Multilingual Polarization Detection, a binary classification task spanning 22 languages. Our approach fin

arXiv:2605.04607v1 Announce Type: new Abstract: This paper presents a multi-phase whole-body model predictive control approach for bipedal walking, combining a detailed whole-body model in the near ho

arXiv:2605.04539v1 Announce Type: new Abstract: Direct Preference Optimization (DPO), the efficient alternative to PPO-based RLHF, falls short on knowledge-intensive generation: standard preference si

So Mythos was, indeed, not marketing hype. Remember this is a general purpose model that just happens to be good at finding exploits because good models are good at lots of things. Expect similar from

arXiv:2603.26498v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) power platforms like ChatGPT, Gemini, and Copilot, enabling richer interactions with text, images, an

arXiv:2602.02315v2 Announce Type: replace Abstract: Large language models (LLMs) form implicit beliefs (posteriors over latent variables) from prompts, but we lack a mechanistic account of how these b

arXiv:2605.04874v1 Announce Type: cross Abstract: Direct Preference Optimization (DPO) has proven to be an effective solution for mitigating hallucination in Multimodal Large Language Models (MLLMs) b

We recently found some instances of CoT grading during the training of previously deployed models after building a system that scans all OpenAI RL runs for accidental CoT grading. We did not find clea

arXiv:2605.03623v1 Announce Type: new Abstract: We propose a unified, few-step generative modeling framework based on cumulative flow maps for long-range transport in probability space, inspired by fl

arXiv:2405.16971v2 Announce Type: replace Abstract: Deep learning (DL) models require extensive data to achieve strong performance and generalization. Deep generative models (DGMs) offer a solution by

arXiv:2507.07982v2 Announce Type: replace Abstract: Videos inherently represent 2D projections of a dynamic 3D world. However, our analysis suggests that video diffusion models trained solely on raw v

Ben Schoon / 9to5Google: Google Chrome silently installs a ~4GB Gemini Nano model on desktop devices; Google says it has been offered since 2024 and users can remove it via settings — The ongoing marc

arXiv:2605.03403v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) has recently shown strong performance in post-training large language models and vision-language models. It ra

arXiv:2510.09472v2 Announce Type: replace Abstract: Despite the remarkable progress in neural models, their ability to generalize, a cornerstone for applications such as logical reasoning, remains a c

arXiv:2505.16527v2 Announce Type: replace Abstract: Building generative models for relational databases (RDBs) is important for many applications, such as privacy-preserving data release and augmentin

arXiv:2605.01790v1 Announce Type: cross Abstract: A common design pattern in high-quality music generation is to handle structure and fidelity in different representation spaces: a generator first mod

arXiv:2605.01694v1 Announce Type: new Abstract: A world model matters to an agent only through the state it constructs. That state must preserve some information, discard other information, and suppor

arXiv:2605.03485v1 Announce Type: new Abstract: Multidimensional human understanding is essential for real-world applications such as film analysis and virtual digital humans, yet current LVLM benchma

MRC is already deployed across all of OpenAI’s largest supercomputers that we use to train frontier models, including our site with @Oracle Cloud Infrastructure (OCI) in Abilene, Texas, and in @Micros

arXiv:2605.02819v1 Announce Type: new Abstract: Large language models excel at complex reasoning, yet evaluating their intermediate steps remains challenging. Although process reward models provide st

arXiv:2605.03301v1 Announce Type: new Abstract: De-identification of clinical text remains essential for secondary use of electronic health records (EHRs), yet public benchmarks such as i2b2 2006/2014

Tencent launched Hunyuan Video in December 2024, an open-source AI video generation model with 13 billion parameters that supports text-to-video and image-to-video conversion. The model brings unique

arXiv:2603.04601v2 Announce Type: replace-cross Abstract: Code generation has emerged as one of AI's highest-impact use cases, yet existing benchmarks measure isolated tasks rather than the complete '

arXiv:2605.02263v1 Announce Type: new Abstract: Recent diffusion large language models (dLLMs) have demonstrated both effectiveness and efficiency in reasoning via a block-based semi-autoregressive ge

arXiv:2605.02028v1 Announce Type: new Abstract: Large language models perform strongly on benchmarks in mathematical reasoning, coding and document analysis, suggesting a broad ability to follow instr

arXiv:2605.00731v1 Announce Type: cross Abstract: While Graph Foundation Models (GFMs) have achieved remarkable success in homogeneous graphs, extending them to multi-domain heterogeneous graphs (MDHG

arXiv:2605.00371v1 Announce Type: cross Abstract: In this paper, we propose GaMMA, a state-of-the-art (SoTA) large multimodal model (LMM) designed to achieve comprehensive musical content understandin

arXiv:2603.14259v2 Announce Type: replace-cross Abstract: Generative recommendation (GR) has shown strong potential for sequential recommendation in an end-to-end generation paradigm. However, existin

Google DeepMind, Microsoft, and Elon Musk's xAI have agreed to allow the US government to review new AI models before they're released to the public. In an announcement on Tuesday, the Commerce Depart

GPT-5.5 Instant is rolling out over the next two days as the default model to all ChatGPT users, and as ‘gpt-5.5-chat-latest’ in the API. Personalization improvements are rolling out to Plus and Pro u