Knowledge catalogue
arXiv:2608.01724v1 Announce Type: new Abstract: Group conversations are fundamental to human collaboration, yet standard large language models (LLMs) still struggle with the complexities of multi-part
arXiv:2608.00013v1 Announce Type: new Abstract: Choosing the right large language model (LLM) backbone is the most consequential decision when building a vision-language model (VLM), yet it remains fu
i already had an esp32 generating stories, but generating text is not the same as receiving a question and giving a useful answer. barista v0.1, a small model trained for espresso troubleshooting and
arXiv:2607.29087v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in enterprise settings, yet individual models remain bounded by model-specific capability limitat
arXiv:2510.03434v3 Announce Type: replace-cross Abstract: We present Paris, the first publicly released diffusion model pre-trained entirely through decentralized computation. Paris demonstrates that
arXiv:2607.29527v1 Announce Type: cross Abstract: A defining problem of the Anthropocene is to model the physical Earth and human societies as one coupled system, yet no learned representation spans t
arXiv:2607.29053v1 Announce Type: new Abstract: Standard model comparison is global, aggregating losses across the covariate space to declare a single winner. This can obscure heterogeneous performanc
DeepSeek V4 Flash 0731 is impressive. It feels like a capabilities leap for a model in this size class. It is also incredibly cost efficient. The model is available in Bionic, both for running locally
Don’t think I have seen more misconceptions around one model (I count 8) since the fantasies people had before GPT-5 was released. That turned out to be a letdown; so will Astra, for people who are dr
New research from Google DeepMind. (bookmark it) SkillSmith treats model weights as an additional modality the LLM reads natively. The augmented model ingests existing prefix weights alongside rich te
TL;DR: I spent 9 days developing a new quantization method for MLX models and measured 18 variants against each other on a single M5 Max MacBook Pro (128 GB). The result is the best-measuring MLX quan
An internal version of Astra, @OpenAI’s next major model family, solved 10 major open problems in mathematics, quantum complexity, and theoretical computer science. We believe it will be a major step
arXiv:2607.28019v1 Announce Type: new Abstract: User foundation models have demonstrated strong results in e-commerce and social recommendation, but most industrial deployments assume environments whe
arXiv:2607.27217v1 Announce Type: cross Abstract: Forest aboveground biomass (AGB) is a critical indicator of ecosystem productivity and terrestrial carbon storage, yet regional carbon monitoring rema
arXiv:2607.27671v1 Announce Type: new Abstract: The majority of the recently-developed models for automated essay scoring (AES) are evaluated solely on the ASAP corpus. However, ASAP is not without it
arXiv:2607.28391v1 Announce Type: new Abstract: World Action Models (WAMs) combine future-state prediction with robot action generation, but existing approaches largely rely on visual futures. Visual
arXiv:2607.27308v1 Announce Type: new Abstract: We introduce ZUNA1.1, a 380M-parameter diffusion autoencoder for flexible EEG signal reconstruction. ZUNA1.1 is capable of reconstructing variable lengt
arXiv:2607.26952v1 Announce Type: new Abstract: We introduce CreditCardQA, the first financial literacy benchmark for numerical reasoning derived from real credit card agreements. The dataset contains
Alphabet Inc.’s artificial intelligence research lab today debuted a family of models optimized to power humanoid robots. Google DeepMind says that the Gemini Robotics 2 series enables multiple autono
Voice assistant and conversational AI agent developer PolyAI Ltd. today announced the release of Dialog-RSN-1, a voice dialog artificial intelligence model capable of directly perceiving and respondin
arXiv:2607.26929v1 Announce Type: new Abstract: The same diagnostic result can support or challenge one causal claim yet fail to address another when the claims concern different populations, outcomes
A benchmark score reflects the model as well as the harness and settings used to run it. For long-running agents, retaining reasoning and compacting context lets the model build on what it has already
arXiv:2607.25527v1 Announce Type: cross Abstract: Unifying visual understanding and generation in one model holds immense promise, but remains challenging and expensive due to heavy compute and data d
arXiv:2607.25021v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) can connect visualization patterns to external causes, consequences, and domain knowledge, but the evidential b
arXiv:2508.00344v5 Announce Type: replace Abstract: Large Language Models (LLMs) have shown remarkable advancements in tackling agent-oriented tasks. Despite their potential, existing work faces chall
arXiv:2607.23026v1 Announce Type: cross Abstract: Mean-field games (MFGs) offer a unifying lens on continuous-time generative modeling: a cost tuple recovering twelve prominent models---Continuous Nor
arXiv:2607.24159v1 Announce Type: cross Abstract: Generalizable robot manipulation requires policies that can anticipate how visual scenes evolve while executing language instructions. While recent Vi
arXiv:2607.23614v1 Announce Type: cross Abstract: We present DualityCert, a symbolic verifier for candidate Seiberg-duality claims in four-dimensional N=1 quiver gauge theories. The verifier evaluates
arXiv:2607.23687v1 Announce Type: new Abstract: Parametric models of the human head are essential tools traditionally used in computer vision and graphics for animation, rendering, and reconstruction.
arXiv:2411.15469v3 Announce Type: replace Abstract: Continual Learning (CL) aims to equip AI models with the ability to learn a sequence of tasks over time, without forgetting previously learned knowl
arXiv:2607.22872v1 Announce Type: cross Abstract: Post-training quantization (PTQ) has become a practical solution for deploying deep learning models on resource-constrained edge devices by compressin
arXiv:2607.21839v1 Announce Type: cross Abstract: Privacy-preserving machine learning auditing protocols allow auditors to assess models for properties such as accuracy or fairness, without revealing
arXiv:2607.22221v1 Announce Type: cross Abstract: Zermelo's algorithm is a classical method for computing the maximum likelihood estimator in the Bradley--Terry (BT) model, but its convergence can be
arXiv:2607.20913v1 Announce Type: new Abstract: Fine-tuning large diffusion models for new domains or styles involves a trade-off: improving target-specific generation often degrades the pretrained mo
arXiv:2607.19379v1 Announce Type: new Abstract: Prior work has shown that transformers can perform exact Bayesian filtering within a fixed hypothesis class. Can they also perform Bayesian model select
arXiv:2602.00072v2 Announce Type: replace Abstract: The performance of machine learning surrogates is critically dependent on data quality and quantity. This presents a major challenge, as high-fideli
arXiv:2607.20194v1 Announce Type: new Abstract: The development of organic light-emitting diode (OLED) materials faces the compounded challenges of an astronomically large chemical space, stringent qu
We spent the last months consolidating seven separate sequence classifiers into one multi-head model, our apex model, so to speak, and since the weights are now public, I wanted to share what worked a
The team @tryheidi didn't want to keep renting someone else's intelligence. So Heidi fine-tuned an open model that beat Gemini Pro on quality in their internal evals, and ran with 3.5x faster latency
This post describes how Couchbase adopted Amazon Bedrock to power Capella iQ with Anthropic’s Claude family of models, the architectural decisions behind their multi-model approach, and the operationa
arXiv:2507.19593v3 Announce Type: replace Abstract: Classical game-theoretic models typically assume rational agents, complete information, and common knowledge of payoffs - assumptions that are often
arXiv:2607.12143v1 Announce Type: cross Abstract: Accurately modeling the dynamics of planetary parachute and entry vehicle systems is critical for Entry, Descent, and Landing events such as vehicle s
arXiv:2607.12169v1 Announce Type: new Abstract: Intercomprehension refers to partial intelligibility of an unfamiliar language (L2) by a speaker of a related language (L1). How is this zero-shot cross
arXiv:2607.08700v1 Announce Type: new Abstract: Reinforcement learning increasingly relies on an LLM judge to score each rubric criterion, and that judge acts as the reward model during training. Befo
arXiv:2607.08540v1 Announce Type: cross Abstract: Conversational information retrieval is challenging since it requires the consideration of the conversation history which potentially gives rise to to
arXiv:2607.08065v1 Announce Type: new Abstract: LLM-as-judge (Zheng et al., 2023) is increasingly the default for evaluating AI systems in enterprise pipelines, often scaled to ensembles (Verga et al.
arXiv:2607.07670v1 Announce Type: new Abstract: Large language models hallucinate most about entities they have never seen. We ask whether a model's activations betray entity familiarity before a sing
Muse Spark 1.1 available in new Meta Model API. Somewhere near Opus-4.8/GPT-5.5 level. 1M context window! Computer-use capabilities sound great: Write scripts when automation is faster, click when dir
The upcoming wave of SpaceXAI Grok updates is insane Grok 4.5: The 1.5T foundation model is being refined almost daily, and its context window is expected to jump to 1M tokens, possibly as soon as nex
GPT-Live is OpenAI's voice model designed to be an engaging conversational partner with natural speech and a distinct personality. The model prioritizes making interactions enjoyable for users through
OpenAI introduced GPT-Live, a voice-based AI model designed to provide conversational interactions that feel more natural and human-like than previous versions. The model represents an advancement in
arXiv:2607.06540v1 Announce Type: new Abstract: Developing seamless, high-performance, native intelligent full-duplex Spoken Language Models (SLMs) remains a critical challenge and long-standing goal
Artificial intelligence optimization startup Refiant Inc. today launched Protea, a suite of long-context AI models led by a 10 million-token context window that the company says ranks among the larges
arXiv:2607.02640v1 Announce Type: cross Abstract: Real-time interaction models -- Moshi, MiniCPM-o, Qwen-Omni -- turn serving into a periodic real-time task: on every frame a session ingests streaming
arXiv:2607.05171v1 Announce Type: new Abstract: Language understanding in the brain is context-dependent, varying across experimental stimuli and individuals, which makes it difficult to build computa
arXiv:2601.14788v2 Announce Type: replace Abstract: Diffusion models have seen widespread adoption for text-driven human motion generation and related tasks due to their impressive generative capabili
arXiv:2607.02840v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have shown promising generalization in robotic manipulation, but they still struggle with contact-rich tasks, where
arXiv:2607.03941v1 Announce Type: new Abstract: Recent advances in embodied AI have established robot foundation models (RFMs) as the dominant approach for generalist robotic systems to date. By lever
arXiv:2602.07267v2 Announce Type: replace Abstract: Evaluating the real-world capabilities of AI systems requires grounding benchmark performance in human-interpretable measures of task difficulty. Ex
arXiv:2607.01938v1 Announce Type: cross Abstract: Manipulating fast and dynamically moving targets in unstructured 3D environments remains challenging for embodied AI. Existing visual-language-action