Knowledge catalogue
Pay attention to System One models if you are building custom harnesses and agentic workflows. Great to see DSPy integrate Jev and now support System One models for calibrating agentic workflows. I'm
arXiv:2609.28921v1 Announce Type: new Abstract: Protein modification requires navigating an immense sequence space, yet wet-lab validation remains low-throughput and costly. Although computational par
arXiv:2609.29690v1 Announce Type: new Abstract: University students experience disproportionately high rates of common mental health conditions, such as depression, which can impair learning, social f
arXiv:2609.30219v1 Announce Type: cross Abstract: An acceptance protocol is developed for sensor-coordinate and polarity binding in mechatronic commissioning. Candidate generation is separated from re
arXiv:2609.30247v1 Announce Type: cross Abstract: World Action Models (WAMs) couple action generation with future visual prediction for robotic manipulation. However, completing the joint video-action
arXiv:2609.29235v1 Announce Type: cross Abstract: Camera-LiDAR fusion has become a prevailing paradigm for 3D object detection in autonomous driving. However, existing fusion detectors often establish
arXiv:2609.29347v1 Announce Type: new Abstract: Event cameras provide a high dynamic range and preserve brightness-change cues in lighting conditions where conventional RGB frames may be noisy or satu
arXiv:2609.29803v1 Announce Type: cross Abstract: Search quality evaluation provides essential supervision and diagnostic signals for the development and iteration of industrial search systems. Althou
arXiv:2609.30063v1 Announce Type: new Abstract: Advances in language modeling have been driven by scaling pretraining on ever more data. Yet, the training data is still largely curated on the model's
TL;DR - Swift Flash is a killer model that massively reduces excess reasoning. Try it out! If you haven't seen from my previous comparison posts, I'm a huge fan of the Swift Qwen3.8 models. I've been
arXiv:2609.29792v1 Announce Type: cross Abstract: We present TimeBraid, a series of unified time-series and language models that align pretrained language models and pretrained time-series foundation
arXiv:2507.00938v4 Announce Type: replace-cross Abstract: Foundation models now enable autonomous agents to interact with real-world websites, but existing benchmarks emphasize general-purpose browsin
arXiv:2609.29921v1 Announce Type: new Abstract: Large language model agents increasingly combine generation, decision-making, execution, and self-evaluation within a single agentic loop. Although they
arXiv:2609.26848v1 Announce Type: cross Abstract: Postoperative acute kidney injury (AKI) after major non-cardiac surgery carries substantial morbidity, yet early intraoperative risk stratification re
Entire database engineering careers have been spent on a single question: How do you scale an OLTP workload without compromising the system of record that owns the data? Exadata answered the question
arXiv:2609.27580v1 Announce Type: cross Abstract: Distributed intelligence concerns systems in which semi-autonomous components with local dynamics and partial observations coordinate through informat
Enterprises rely on mission-critical operational databases where performance slowdowns simply aren’t an option. Yet when even a few agents execute dense reasoning loops, the unpredictable surge in que
arXiv:2609.28335v1 Announce Type: new Abstract: Claims about AI safety reach audiences well beyond the AI community, yet many rely on opaque evidence or static assessments, when supporting evidence is
Banger paper introducing Jev-as-a-Judge. The overall finding is that you want to use a cheap judge for most of your evals and send only the uncertain calls to a frontier model. This paper measures how
arXiv:2609.27536v1 Announce Type: cross Abstract: Behaviora is a preliminary conceptual architecture for representing agent and robot behavior, external and internal alike, in an addressable form. A b
arXiv:2609.26927v1 Announce Type: new Abstract: The objective of this article is to provide design principles and a software architecture for enabling interaction between humans and multiple agents in
arXiv:2505.10083v2 Announce Type: replace Abstract: Conventional forecasting methods are trained end-to-end on unimodal time series, which limits their ability to exploit textual information and under
confidence scores only matter if they help you decide what to automate. for document extraction, that usually means knowing how much work you can safely accept at a given precision target. in our late
arXiv:2609.28471v1 Announce Type: new Abstract: Our results show that contrastive learning outperforms a classification-based approach to authorship verification under the tested settings. We identify
arXiv:2609.26853v1 Announce Type: cross Abstract: While Large Language Models (LLMs) have achieved remarkable results across various benchmarks, their alignment with normative values often results in
arXiv:2609.27421v1 Announce Type: new Abstract: Multi-constraint instruction following requires a model to respond to a query under many simultaneously active constraints. Even strong instruction-tune
Enterprise artificial intelligence platform company Dataiku Inc. today launched Agent Management, a standalone product that finds and tracks every AI agent a business runs, including those built on ot
arXiv:2609.27276v1 Announce Type: new Abstract: Long-horizon language-model agents accumulate reasoning traces, tool exchanges, and observations whose relevance changes with the current decision. Exis
arXiv:2609.27279v1 Announce Type: new Abstract: An agent that interacts with users over long periods must recall facts, preferences, events, and changes from a continuously growing interaction history
arXiv:2609.28007v1 Announce Type: new Abstract: Most Turkish-capable large language models (LLMs) are evaluated using general-purpose benchmarks rather than long, structurally complex domain documents
Every week I go through hundreds of new AI papers to pick the top ones for our Top AI Papers of the Week digest. Besides reading a lot of papers, I have started to use agent teams a lot. Here is what
arXiv:2609.27664v1 Announce Type: new Abstract: Cooperation emergence is a central problem in multi-agent systems because decentralized agents must coordinate while adapting to the changing behavior o
We’re excited and proud to share that Gartner has recognized Google as a Leader for the fourth year in a row in the 2026 Gartner® Magic Quadrant™ for Container Management, based on its Completeness of
arXiv:2609.26891v1 Announce Type: new Abstract: Modern language-model agents are built around the extit{agent loop}, where the LLM is placed in an environment exposing a set of tools, and the LLM has
arXiv:2507.21112v4 Announce Type: replace Abstract: With the rapid rise of InsurTech, traditional insurance companies are increasingly exploring alternative data sources and advanced technologies to s
arXiv:2609.28003v1 Announce Type: new Abstract: Small and medium-sized language models offer cost-effective executors for tool-using agents, making them attractive for local and large-scale deployment
arXiv:2609.28078v1 Announce Type: new Abstract: Segmentation-based multi-object tracking (MOT) with foundation video models such as SAM2 offers strong localization quality, yet remains fragile in crow
arXiv:2609.27311v1 Announce Type: cross Abstract: Command-and-control (C2) traffic increasingly hides within TLS, so defenders now apply machine learning to traffic metadata. Many studies assume that
arXiv:2609.27526v1 Announce Type: new Abstract: Long-horizon navigation requires an agent to revise its intermediate objectives as evidence accumulates. Full visual histories are costly to process, wh
arXiv:2607.11433v2 Announce Type: replace Abstract: Omni-modal agents must seek evidence across video, audio, web pages, and computation to answer questions. Their main bottleneck is planning: noisy m
Following our announcement of Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking last week, we are thrilled to share that Gemini 3.8 Live with Live Avatar is now generally available in Gemini Enter
Personal note first, being straight with you: I'm lazy tonight and used AI to write the following post: The workflow, the conversion work, and the mistakes that taught me the stuff below are mine, and
arXiv:2609.26865v1 Announce Type: cross Abstract: Conversational AI systems can pose safety risks to their users such as hallucination, sycophancy, overconfidence, and anthropomorphism, but these risk
arXiv:2601.13566v2 Announce Type: replace-cross Abstract: Can language models improve their accuracy without external supervision? Methods such as debate, bootstrap, and internal coherence maximizatio
arXiv:2609.28274v1 Announce Type: new Abstract: The final safeguard against rogue AI behavior is the human ability to shut systems down. It has been theorized that when an AI is instructed to perform
arXiv:2609.26907v1 Announce Type: cross Abstract: Memes often derive their harmful, hateful, or sarcastic meaning from small but decisive visual, textual, or cross-modal cues. Existing multimodal clas
arXiv:2609.27780v1 Announce Type: cross Abstract: Vision-language robot manipulation policies can follow semantic instructions, but adapting them to a new procedure from only a few demonstrations rema
arXiv:2609.27155v1 Announce Type: cross Abstract: With recent advancements in large language models (LLMs) and LLM-based agents, these agents are becoming increasingly autonomous and gaining broader a
Google Cloud has become the platform of choice for startups building AI. Our uniquely complete stack — including a choice of first- and third-party compute and models; our platform for building and ma
arXiv:2609.27037v1 Announce Type: new Abstract: Wake word detection is a critical component of virtual assistants, serving as the gateway to seamless user interactions. This paper introduces a novel w
arXiv:2508.13680v5 Announce Type: replace Abstract: We introduce VMMU, a Vietnamese Multitask Multimodal Understanding and Reasoning Benchmark designed to evaluate how vision-language models (VLMs) in
I am creating a local AI agent called 'Ontelic' for Windows. Ontelic returns to Ollama and also manipulates the actual Chrome. This is not for promotion but to share what we've learned. I'll give GitH
arXiv:2609.26826v1 Announce Type: cross Abstract: Frontier benchmarks need tasks that current models cannot solve. But a task that no model solves is not automatically a hard task. The same zero pass
arXiv:2609.28342v1 Announce Type: new Abstract: Removing an object from a real image requires more than synthesizing plausible content within a mask: the method must suppress residual object features,
arXiv:2609.24348v1 Announce Type: cross Abstract: AI coding agents increasingly support software development beyond code completion, including planning, implementation, testing, and repository-level t
arXiv:2609.26237v1 Announce Type: cross Abstract: We present the ABAI submission to COLIEE 2026 Task 1, case law retrieval, together with a controlled study of why it underperformed. The task suppress
arXiv:2609.24446v2 Announce Type: cross Abstract: Large language model (LLM) agents increasingly execute long-horizon workflows through external tools, allowing untrusted outputs to influence subseque
https://huggingface.co/bartowski/LensVLM-9B-GGUF LensVLM-9B LensVLM is a 9B Vision Language Model (VLM) that scans compressed images of text, then selectively expands only the relevant pages to their
CUDA: enable sparse-fa for dsv4 prefill (again) (#29298) CUDA: enable sparse-fa for dsv4 prefill (again) CUDA: unroll the query loop of the sparse mask scan The query loop of flash_attn_mask_to_sparse
arXiv:2609.24324v1 Announce Type: new Abstract: Electroencephalography (EEG) provides a non-invasive window into dynamic brain activity, yet modeling long-horizon EEG sequences remains challenging due