Knowledge catalogue
Really nice paper on harness-aware distillation for small language model agents. (bookmark it) It's a super interesting distillation framework for small language model agents that are deployed with a
arXiv:2610.02515v1 Announce Type: cross Abstract: We introduce IGNITE, a generative world foundation model for fusion plasma behavior simulation trained in a self-supervised manner from over a decade
arXiv:2511.06260v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used as behavioral proxies for self-interested travelers in agent-based traffic models. Although
arXiv:2610.02508v1 Announce Type: new Abstract: World action models (WAMs) have emerged as a promising paradigm for robotic control by jointly predicting future visual dynamics and actions from an ini
Check out Chimera Arena (https://chimeraarena.com/static/showcase/index.html?lang=en)! Here’s my slightly scrappy AI-generated teaser for Chimera Arena, my card game combining AI-generated video battl
https://unigen-x.github.io/unifolm-wla.github.io/ Unitree Robotics released UnifoLM-WLA-1.0, their new general-purpose humanoid foundation model. Key points: • 6B parameters • Trained on ~2,500 hours
arXiv:2610.01751v1 Announce Type: new Abstract: Adaptive model search is path dependent: once a challenger is adopted, it becomes the reference from which later candidates are generated. A statistical
arXiv:2610.00414v1 Announce Type: new Abstract: Foundation models pretrained on large-scale datasets demonstrate strong transferability to medical imaging tasks. However, understanding how their laten
arXiv:2604.01329v2 Announce Type: replace Abstract: Model merging provides a way of cheaply combining individual models to produce a model that inherits each individual's capabilities. While some merg
arXiv:2610.00518v1 Announce Type: new Abstract: One-step generative models construct a static generator through iterative training-time transport. Existing transport objectives primarily assess distri
@tavus: Tavus unveils Griffin, the “first Human Interaction Model”, which it says passed the “video Turing test”, with 48% of users thinking it was human in live chats — Introducing Griffin, the first
arXiv:2606.13571v2 Announce Type: replace-cross Abstract: Real-world time series are often highly incomplete and irregular due to sensor dormancy, transmission delays, and event-driven sampling, makin
arXiv:2609.38673v1 Announce Type: new Abstract: Model-based offline reinforcement learning (MBORL) improves sample efficiency through model-generated trajectories. However, accumulative model error ca
arXiv:2609.39982v1 Announce Type: cross Abstract: Terminal agents act through stochastic model generations, yet the ability to generate a useful action does not ensure its reliable execution. A poor c
arXiv:2609.39673v1 Announce Type: new Abstract: Can a pretrained graph model replace training and tuning a separate predictor for each dataset? Answering this requires evaluating prediction quality al
arXiv:2609.38927v1 Announce Type: cross Abstract: World models aim to learn representations of real-world environments and predict their future evolution. Recent object-centric world models have made
arXiv:2609.38140v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE), popularized by large language models, is a promising paradigm for scaling visual generative models. However, conventional to
arXiv:2609.36965v1 Announce Type: new Abstract: System One models such as Jev offer an efficient alternative to generative language models for tasks that require decisions rather than open-ended respo
arXiv:2609.36612v1 Announce Type: new Abstract: Unlearning in large language models (LLMs) is typically evaluated at the output level, where a model appears to suppress sensitive or undesirable conten
arXiv:2609.37488v1 Announce Type: cross Abstract: Frozen multimodal large language models (MLLMs) now solve standard referring expression comprehension with a single prompted call, yet on adversarial
Google LLC today began rolling out Gemini 4 Argon, a frontier artificial intelligence model that beats rival models from Anthropic PBC and OpenAI Group PBC on most of Google’s benchmarks, to vetted cy
arXiv:2609.37564v1 Announce Type: new Abstract: Merging pretrained models has emerged as an effective approach for consolidating diverse capabilities into a single unified model. However, prevailing m
arXiv:2609.36087v1 Announce Type: cross Abstract: Clinicians and neuroscientists have long analyzed intracranial electroencephalography (iEEG) through directly measurable physiological characteristics
arXiv:2609.35570v1 Announce Type: cross Abstract: Vision-language navigation (VLN) models perform well but target compute-rich platforms, limiting deployment on memory- and power-constrained robotic e
arXiv:2609.33687v1 Announce Type: new Abstract: Onboard satellite models often require frequent updates, but the weights adapted to earlier data distributions can quickly become outdated. However, upd
arXiv:2609.34736v1 Announce Type: cross Abstract: Large language model (LLM) routing aims to select the most suitable model for each incoming query. Most existing routers learn this decision directly
Anthropic PBC today announced the launch of Claude Sonnet 5.5, the most capable mid-tier model in the company’s AI family, designed for everyday tasks and a clear upgrade over the previous generation,
arXiv:2609.31378v1 Announce Type: new Abstract: In recent years, diffusion models and GAN-based models have become the mainstream approaches for SAR-to-optical image translation, owing to their advant
Some context first. I am process improvement / business consultant and had worked with Fortune 500 companies on improving their processes around refunds, returns, customer support, etc. This entire th
arXiv:2609.30918v1 Announce Type: cross Abstract: Robust counterfactual explanations promise recourse that still works after the model behind it changes. Whether they keep that promise depends on what
arXiv:2609.31342v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) is often used to address outdated knowledge by providing external evidence. But retrieval helps only when that evid
People on X: “CLAUDE IS BACK, baby!” Listen, Opus 5.5 is incredible and probably my favorite overall model right now, but it is still ridiculously verbose and over-justifies and over-qualifies everyth
arXiv:2609.30173v1 Announce Type: cross Abstract: We introduce GridSFM, a framework that combines a pretrained foundation model across grid topologies with physics-informed fine-tuning for solving AC
arXiv:2609.28344v1 Announce Type: cross Abstract: Audio-language models (ALMs) integrate acoustic perception with the knowledge encoded in language models, enabling contextual understanding of auditor
arXiv:2609.28314v1 Announce Type: new Abstract: Human teleoperators spend substantial time demonstrating behaviors that robots can already perform autonomously, limiting the scalability of data collec
arXiv:2609.23974v1 Announce Type: new Abstract: Foundation models are endowing autonomous systems with greater intelligence, enabling a more comprehensive understanding of the environment through visu
arXiv:2609.25627v1 Announce Type: new Abstract: General-purpose robot control requires models to understand task intent, identify where to interact, capture how the scene evolves, and generate precise
Big model release today - I wrote about Claude Opus 5.5, GPT-6 Sol, and GPT-6 Luna - plus comparison grids of pelicans by the different model families at different reasoning levels https://simonwillis
arXiv:2609.22614v1 Announce Type: new Abstract: Process model forecasting (PMF) aims to predict the process model that will characterize a future period, thereby providing a process-level view of how
Opus 5.5 is the best frontier model for parsing tables in PDFs. We ran it through ParseBench, and it scored 93.9%, a 7%+ increase over Opus 5, and beating Fable/Gemini/Astra. It's comparable to LlamaP
arXiv:2609.22947v1 Announce Type: new Abstract: Reinforcement learning (RL) is vital for optimizing video generation models, with a robust reward model (RM) serving as the cornerstone. However, existi
arXiv:2609.22165v1 Announce Type: new Abstract: Automatic synthesis of analog and Radio Frequency (RF) circuits is an emerging area that requires an efficient circuit modeling method. In recent years,
Global technology company Xiaomi Corp. today announced the release and open-sourcing of its MiMo-V2.6 series generative artificial intelligence models today, which includes two natively omnimodal mode
arXiv:2609.21821v1 Announce Type: cross Abstract: This paper presents a novel framework integrating Bayesian physiological modeling with optimal control strategies to achieve uncertainty-aware, person
MiMo-V2.6-Pro debuts as the top open weights model on the Artificial Analysis Intelligence Index (46). At 0.13 per Intelligence Index task, it lands on the Intelligence vs. Cost per Task Pareto fronti
StepFun’s new Step 5 Preview model is impressive! Had a chance to test it early. I've been testing it as a coding agent. It’s on the Pareto frontier for cost vs. capability. It is a very capable model
arXiv:2609.20441v1 Announce Type: new Abstract: Geospatial foundation models can provide strong flood-segmentation performance, but their size limits deployment on memory-constrained edge hardware. We
Hey everyone, Jovan from UkisAI here, a small lab building the tech to make tiny frontier LLMs possible (and doing it open-source!) The purpose of this post is simply to thank the community for all th
arXiv:2609.18560v1 Announce Type: new Abstract: Some aspects of AI development resemble a population process in which models are specialised, retrained on the output of peers, or combined by averaging
arXiv:2609.14498v1 Announce Type: cross Abstract: Sensor-based human activity recognition (HAR) is fundamental to ubiquitous and wearable computing, yet existing foundation models are largely designed
arXiv:2609.13470v1 Announce Type: new Abstract: Although large language models (LLMs) have demonstrated remarkable capabilities, their reliance on cloud-scale infrastructure poses fundamental challeng
arXiv:2609.15348v1 Announce Type: new Abstract: Multi-model fitting involves fitting multiple models accurately in a noisy environment. It is the basis for computer vision tasks such as scene reconstr
arXiv:2609.15038v1 Announce Type: new Abstract: Language-model agents are increasingly used as synthetic people in surveys and social simulations, yet their apparent realism is often judged from popul
arXiv:2609.12310v1 Announce Type: new Abstract: We describe six submissions under the team name ESTS to the unconstrained WMT26 Model Compression Shared Task for English--Simplified Chinese and Englis
arXiv:2509.24367v2 Announce Type: replace Abstract: Deepfake generators evolve rapidly, making exhaustive data collection and repeated retraining impractical. Unlike generic multi-task settings, deepf
I’ve been building Catalyst around a capability I want engineering agents to have: An AI agent can read a program and make a good guess about what matters. Catalyst lets it measure what actually matte
arXiv:2609.11314v1 Announce Type: new Abstract: Traffic flow prediction is a core supporting technology for intelligent transportation systems. It uses historical data to infer future traffic dynamics
arXiv:2609.11897v1 Announce Type: new Abstract: Causal discovery aims to uncover causal structures from data and is fundamental to scientific reasoning and intervention-based decision making. Its eval
arXiv:2609.11917v1 Announce Type: cross Abstract: As the supply of human-written text is exhausted, it has become standard practice to repeat language model training data. Prior work has studied data
arXiv:2609.10954v1 Announce Type: new Abstract: Continual world models must decide whether new data justify changing the model. Fixed replay schedules and prediction-error triggers specify when to upd