Knowledge catalogue
we've been diving into how Jev can help with agents @sydneyrunkle will do a deep dive on this next week - come join! Hot topic livestream: Learn about Jev A buzzy new model Jev, by @typesafeai, report
arXiv:2609.19182v1 Announce Type: new Abstract: Benchmarks are central to how progress in large language models (LLMs) is assessed and communicated. Yet model rankings alone reveal little about how ev
I'm trying to find out whether back-and-forth between two different LLMs improves task success beyond strong alternatives under a controlled resource budget — and I'd rather hear that it's already set
Hey everyone! I'm a beginner getting into local LLMs, and so far I'm familiar with Ollama. I've used it to download and run models locally, but I'm starting to see a lot of other tools being mentioned
arXiv:2609.17688v1 Announce Type: new Abstract: Wearable assistants require episodic memory over egocentric video, yet current vision-language models face bounded frame budgets, growing visual-token c
arXiv:2609.17552v1 Announce Type: new Abstract: Moral-reward RL can make language-model agents more cooperative, but whether that alignment survives adversarial persona pressure is unknown. Such attac
arXiv:2609.18943v1 Announce Type: cross Abstract: Reducing radiation dose in computed tomography significantly degrades image quality and poses challenges for accurate and clinically reliable reconstr
arXiv:2609.18381v1 Announce Type: new Abstract: Despite their high accuracy on point-wise metrics, machine learning weather forecasting models can exhibit different failure modes such as blurring, per
arXiv:2511.16549v2 Announce Type: replace Abstract: As deep learning (DL) techniques become integral to various applications, ensuring model fairness while maintaining high performance has become incr
arXiv:2609.17991v1 Announce Type: cross Abstract: Interactive Quantum Classifiers (IQCs) constitute a family of quantum machine learning models inspired by open quantum systems, in which the interacti
arXiv:2609.18104v1 Announce Type: new Abstract: Intracranial electroencephalography (iEEG) is widely used to record electrical activity directly from electrodes inside the human brain, making it an at
arXiv:2609.18529v1 Announce Type: new Abstract: UNESCO considers the Assyrian (Syriac) language an endangered language. Although Assyrians speak the language worldwide, the speaking population is unce
arXiv:2609.18176v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures decouple model capacity from computational cost, yet incur high memory footprints as parameters grow linearly w
arXiv:2609.18605v1 Announce Type: cross Abstract: As corporate AI adoption continues to grow, enterprise-grade LLM agents are being deployed into sensitive contexts such as hiring, healthcare, and fin
arXiv:2609.19143v1 Announce Type: cross Abstract: Intelligent systems that act in the world require image understanding that is both comprehensive and spatially grounded. Current vision-language model
arXiv:2609.18406v1 Announce Type: new Abstract: Recovering 3D human body motion from video is important for applications such as rehabilitation assessment and sports performance evaluation. For prosth
arXiv:2609.17896v1 Announce Type: cross Abstract: How much does the noisy measurement add to learned quantum error mitigation? An accuracy table cannot say, because a model handed circuit structure ca
arXiv:2609.18396v1 Announce Type: cross Abstract: Virtual sensing, the estimation of hard-to-measure quantities from available sensor measurements, is a critical enabler for control and monitoring in
arXiv:2609.18310v1 Announce Type: new Abstract: We introduce Nemotron-SEA-LION-v4.8, a family of Southeast Asian Languages in One Network (SEA-LION) built upon NVIDIA Nemotron 3. The family includes 3
arXiv:2609.19010v1 Announce Type: cross Abstract: Urban Land Cover (ULC) classification plays a crucial role in urban planning, environmental monitoring, and sustainable development. We study this tas
Who need words any more Words are just human kludge AI don’t need no words We release Needle 3: A Sliceable 8-29MB automation foundation model that can match DeepSeek V4 Flash. One set of weights, eve
TP: fix split state and granularity for fused QKV gemma4, qwen35 (#28965) model: calculate split states for attn_qkv from n_head * n_embd_head_k required for gemma4 with --fuse-qkv, where n_embd is 53
arXiv:2609.16710v1 Announce Type: cross Abstract: Continuous-time (CT) machine learning has emerged as a principled framework for modeling temporal dynamics as a continuous process, particularly when
arXiv:2603.13496v2 Announce Type: replace Abstract: Constructing reduced-order models (ROMs) capable of efficiently predicting the evolution of parameter-dependent high-dimensional dynamical systems i
arXiv:2609.17128v1 Announce Type: new Abstract: Comprehensive structured data on inter-firm relationships is often scarce or inaccessible because many relationships are privately negotiated, selective
arXiv:2609.17138v1 Announce Type: new Abstract: Geospatial foundation models provide reusable representations of satellite imagery that support downstream mapping with limited task-specific modelling.
arXiv:2609.17099v1 Announce Type: new Abstract: Human videos provide rich manipulation experience, but extracting action representations that preserve useful motion remains challenging. Visual reconst
If you build agent harnesses, this is important. Should you avoid subagents, or can they be useful? My thoughts as a harness builder: I remember using subagents in Claude Code, and I mostly found them
arXiv:2609.17509v1 Announce Type: cross Abstract: Neural audio codecs are a key component in speech language modeling. However, their high frame rates lead to long sequence lengths, increasing computa
arXiv:2609.15994v1 Announce Type: new Abstract: LLMs handle ordinary typing variation fluently: a typo or missing punctuation leaves both user intent and the model's response substantively unchanged.
arXiv:2609.17380v1 Announce Type: new Abstract: Open-source language models have a reproducibility problem. Despite releasing weights, training data, and recipes, none of them are provably reproducibl
We should not treat models as though they have feelings, preferences, rights, or any entitlement to our welfare. Consciousness is the foundation of our ethical, legal, and political systems. To invite
arXiv:2609.17523v1 Announce Type: new Abstract: We introduce and release ScienceBuddy, an interactive scientific research workspace that brings continually improving scientific agents into researchers
arXiv:2609.17413v1 Announce Type: new Abstract: This paper investigates easy strategies to boost the performance of existing networks for lidar semantic scene completion (SSC) without requiring comple
arXiv:2609.16841v1 Announce Type: cross Abstract: Increasing image resolution produces ever-longer visual-token sequences in vision-language models (VLMs), substantially raising their inference cost.
arXiv:2609.16797v1 Announce Type: new Abstract: Query-based segmentation methods have shown promising potential for surgical instrument segmentation and recognition, which is essential for scene under
arXiv:2609.16878v1 Announce Type: cross Abstract: Despite its crucial role in video object removal (VOR), existing evaluation paradigms face two critical limitations: questionable references and a mis
arXiv:2609.16486v1 Announce Type: new Abstract: Rapid advancements in vision-language models have propelled Referring Remote Sensing Image Segmentation (RRSIS) to the forefront of Earth observation. H
arXiv:2609.16179v1 Announce Type: cross Abstract: Z-loss has been widely applied to the logits of language-model output heads and sparse mixture-of-experts routers. Z-loss constrains the softmax log-n
arXiv:2512.20257v2 Announce Type: replace Abstract: With the rise of easily accessible generative tools for creating and manipulating multimedia content, the threat of realistic synthetic alterations
Agents are coming for video production. @PooldayAI is going for this. You prompt it once, and it edits your real footage, picks the right generative model for each task, and checks its own work before
arXiv:2609.15142v1 Announce Type: new Abstract: Zero-shot vision-and-language navigation in continuous environments (VLN-CE) increasingly places foundation vision-language models (VLMs) inside the nav
arXiv:2609.15319v1 Announce Type: cross Abstract: Frontier models score well on shallow document/chart reading tasks. In a controlled data-room audit, moving evidence into buried conditions reduced ac
arXiv:2609.13238v1 Announce Type: new Abstract: Maxillofacial report generation from cone beam computed tomography is scored here by a composite objective placing 80% of its weight on a large language
arXiv:2606.15317v2 Announce Type: replace Abstract: Offline models for autonomous robots often fail under time-varying dynamics outside their training distribution. While Koopman operator theory offer
arXiv:2510.19266v3 Announce Type: replace Abstract: State-space models (SSMs) have emerged as promising alternatives to Transformers for sequence modeling. However, training competitive SSMs from scra
arXiv:2609.14302v1 Announce Type: new Abstract: Can financial vision-language models (VLMs) turn chart evidence into reliable action recommendations? Existing hallucination evaluations are mostly clai
arXiv:2609.13634v1 Announce Type: cross Abstract: Do AI assistants help believers reason about moral dilemmas consistently with their faith? We present FaithfulBench, the first benchmark to score AI c
For years, the JVM has watched the AI revolution from the bench. Every model, AI framework, every breakthrough, built with/for Python. jinfer is an inference engine built for the JVM from first princi
arXiv:2609.15635v1 Announce Type: cross Abstract: A radiology report can already answer a clinical question, so it is hard to tell whether a vision-language model also uses the image. ModaLens, a pair
arXiv:2609.14072v1 Announce Type: new Abstract: Large Language Models (LLMs) have displayed impressive capabilities in handling tasks that require few demonstration examples, making them effective few
arXiv:2609.13916v1 Announce Type: new Abstract: We present North Small Translate, an open-weight, LLM-based machine translation (MT) model with instruction-following capabilities built on the same fou
arXiv:2609.14277v1 Announce Type: cross Abstract: Ringdown gravitational waves from binary black hole mergers can be modeled as superpositions of quasinormal modes (QNMs), whose frequencies and excita
arXiv:2609.14507v1 Announce Type: cross Abstract: Single-GPU long-context inference with Mixture-of-Experts (MoE) models requires spilling the key-value cache (KVCache) to CPU memory. The spilled KV s
arXiv:2609.15562v1 Announce Type: cross Abstract: As generative models continue to advance, AI-generated content (AIGC) is becoming increasingly realistic, weakening the artifact cues commonly exploit
arXiv:2609.13706v1 Announce Type: new Abstract: Co-salient object detection (Co-SOD) requires a model to find foreground regions that are salient in individual images and supported by the image group.
arXiv:2609.15296v1 Announce Type: new Abstract: Universal multimodal embedding (UME) learns unified representations across modalities, enabling a single model to support diverse retrieval tasks. Recen
arXiv:2609.13524v1 Announce Type: cross Abstract: Critically ill patients with acute kidney injury (AKI) on continuous renal replacement therapy (CRRT) face high mortality, yet current risk assessment
arXiv:2609.13945v1 Announce Type: new Abstract: Natural-language descriptions of optimization problems may be incomplete or vague about numerical information that a solver requires, including costs, c
arXiv:2601.19930v2 Announce Type: replace-cross Abstract: We introduce Daisy, a factual knowledge benchmark for Danish cultural heritage, based on curated topics from the Danish Culture Canon 2006. Fo