Knowledge catalogue
arXiv:2608.23347v1 Announce Type: new Abstract: Deep learning models for electrocardiogram (ECG) classification often suffer from significant performance degradation when deployed in unseen domains du
arXiv:2507.12295v2 Announce Type: replace-cross Abstract: Text anomaly detection is a critical task in natural language processing (NLP), with applications spanning fraud detection, misinformation ide
arXiv:2608.22312v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable progress in vision-language interaction, yet their safety alignment remains vulnerable
arXiv:2608.21443v1 Announce Type: new Abstract: Estimating interpretable conditional-dependence structures from multimodal visual-linguistic features remains largely unexplored. We propose CM-GLasso (
arXiv:2608.21412v1 Announce Type: new Abstract: Root cause analysis (RCA) in large datacenter networks is challenging because telemetry is noisy, partial, and asynchronous. Score-based approaches degr
arXiv:2608.23416v1 Announce Type: new Abstract: Systematic trading rests on one article of faith: that regularities found in the past persist. We state it as a time-invariant mechanism driven by an un
arXiv:2608.21871v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards has become the dominant recipe for improving large language model reasoning, yet it presumes large human-
arXiv:2608.22152v1 Announce Type: new Abstract: Multi-agent systems built from large language models are deployed widely, yet how much performance is lost when two LLMs must coordinate rather than act
arXiv:2608.22007v1 Announce Type: cross Abstract: The components of a transformer communicate by writing to and reading from a shared residual stream, and mechanistic interpretability has mapped these
arXiv:2608.22752v1 Announce Type: new Abstract: A safety rule and an episodic log compete for the same tokens in an AI agent's context. When the budget overflows, both are summarized at the same rate;
This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. How to encourage smarter AI use in the classroom Chatbots took
arXiv:2608.23338v1 Announce Type: cross Abstract: LoRA fine-tuning is standard for adapting LLMs to reranking, but it remains unclear where in the network task-specific relevance behavior is learned a
We've closed our Series B, bringing total funding to $232M under new leadership. This round welcomes entertainment titans Electronic Arts, Sony Music Group, Universal Music Group, Warner Music Group,
arXiv:2602.21910v2 Announce Type: replace Abstract: Operator learning has the potential to strongly impact scientific computing by learning solution operators for differential equations, potentially a
arXiv:2608.21496v1 Announce Type: new Abstract: AI systems increasingly generate alternatives, inspect evidence, and deploy a selected output. Validation is therefore target-relative: evidence certifi
arXiv:2608.23358v1 Announce Type: new Abstract: The performance gap between low- and high-resource languages in LLMs is widely known, but it remains unclear which internal model factors drive these di
arXiv:2608.22956v1 Announce Type: new Abstract: Concept-bottleneck controllable generation routes multi-attribute control through a low-dimensional concept code that, at deployment, must be synthesise
arXiv:2608.22301v1 Announce Type: cross Abstract: Humans imitate at the level of intent: given a demonstration, we infer its goal and carry it out with whatever tools, objects, and layouts are at hand
arXiv:2608.23541v1 Announce Type: cross Abstract: Does multi-agent LLM interaction help or hurt? Some work reports gains from debate (Du et al., 2024), critique loops (Chen et al., 2025), and mixture-
arXiv:2608.23252v1 Announce Type: cross Abstract: As Retrieval-Augmented Generation (RAG) shifts toward diverse portfolio generation, it is stymied by two critical bottlenecks: flawed measurement of e
arXiv:2608.22876v1 Announce Type: cross Abstract: We formalize prefix invariance: representations at position t must not depend on future inputs. We give a lightweight audit, two forward passes, no tr
arXiv:2608.23524v1 Announce Type: cross Abstract: Artificial intelligence (AI) is transforming measurement in economics. AI models convert unstructured data, such as text and images, into structured v
arXiv:2608.23037v1 Announce Type: cross Abstract: This paper introduces the Multilingual FrameNet Corpus (mFNC), a novel resource that extends the English Berkeley FrameNet corpus by collecting and ha
arXiv:2608.21713v1 Announce Type: cross Abstract: Reasoning-augmented text-to-image models such as GoT-R1 emit an explicit textual plan - object names, attributes, and bounding boxes - before generati
arXiv:2608.22120v1 Announce Type: new Abstract: Cooperative teams often need to agree on the best few options rather than simply accumulate reward, and they must do so while each member sees only a fr
arXiv:2608.22767v1 Announce Type: new Abstract: Long-term language-model agents accumulate memories across interactions, but their retrievers typically do not accumulate retrieval experience. Semantic
arXiv:2608.21433v1 Announce Type: new Abstract: The setting or tuning of specifications for the inertial measurement unit (IMU) is tricky in sensor fusion. The underneath conundrum is caused by the fa
arXiv:2608.22293v1 Announce Type: cross Abstract: Urban wildfire resilience depends on interactions among built form, vegetation condition, and extreme fire weather, yet city-scale risk models often o
arXiv:2608.22467v1 Announce Type: new Abstract: Long-horizon language-model tasks --- multi-step reasoning and tool-using agents alike --- are limited by credit assignment. We analyze it through the p
There is a child with a rare disease who is currently suffering and struggling to manage his symptoms. Rare as this is, you can directly help him. Today we are launching the 'Rare Disease, Real Kid' H
// There Is No Neutral Harness // Great work discussing some of the issues in harness evaluation. Twelve open-weight models answer the same 3,679 items from ARC, HellaSwag, MMLU, and TruthfulQA under
arXiv:2608.21382v1 Announce Type: new Abstract: Multiple-choice benchmarks fix the questions and the correct answers, but not the harness: the order of the options, the wording of the prompt, and whet
arXiv:2608.21887v1 Announce Type: cross Abstract: Runtime thermal management of high-performance chips depends on fast and accurate full-chip thermal maps. Conventional simulators typically estimate p
arXiv:2608.23224v1 Announce Type: cross Abstract: Retrieval can efficiently and effectively augment a frozen vision--language--action (VLA) policy without retraining, yet retrieved text becomes a cont
arXiv:2608.22429v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) capable of thinking with images often rely on external tools for fine-grained perception. However, this relianc
arXiv:2608.22854v1 Announce Type: new Abstract: Practical deployment of large language models (LLMs) requires families of post-trained variants---instruction-tuned, reasoning-tuned, and chat-style mod
arXiv:2608.23329v1 Announce Type: cross Abstract: Open-world video understanding often requires a model to locate sparse visual evidence and acquire external knowledge that is absent from the video an
this is a practical guide (+ updated skill) on how we use real world data like traces + human feedback to make synthetic environments + evals so we can measure, harness engineer, and post-train our ag
This summer, we brought in two first-year Waterloo interns (‘rising sophomores’ in 🇺🇸) and tasked them with shipping complex production features that help push the frontier of our document processing
arXiv:2608.22096v1 Announce Type: new Abstract: This report describes Libo Zhang's algorithmic solution to autoPETV Grand Challenge on interactive lesion segmentation in whole-body PET/CT. Interaction
arXiv:2608.21813v1 Announce Type: new Abstract: Forensic histopathology, essential for determining cause of death and disease diagnosis, is severely impeded by postmortem autolysis, i.e., an irreversi
arXiv:2605.21622v2 Announce Type: replace Abstract: Topology optimization can generate efficient structures, but designers often must manually translate qualitative intent, such as desired visual styl
arXiv:2411.06039v2 Announce Type: replace Abstract: Despite obesity being widely discussed in the social sciences, the effect of a robot's perceived obesity level on trust is not covered by the field
Today we are launching the 'Rare Disease, Real Kid' Hackathon together with @sagebio in which you can literally save a life if you’re interested in AI and genome 🧬 (and incidentally win 50,000 in priz
Today we’re launching Portable Computer on @NVIDIA DGX Spark. Portable Computer is a fully local version of Perplexity Computer, where the entire runtime: orchestrator LLM, subagent LLM, agent harness
arXiv:2608.22179v1 Announce Type: cross Abstract: Membership inference asks whether a text was used to train a language model, whereas AI-generated text detection asks whether it was generated by a la
Upgraded ollama from .32.6 to .32.15 ran a test on my qwen3:30b and it went from 90+ t/s down to 45+t/s System has 4 and v620 pro and one rtx3090 Before it was only using the amd, now it's using all 5
arXiv:2608.21404v1 Announce Type: new Abstract: Fixed coordinate measuring machines (CMMs) and portable articulated-arm CMMs are often assigned to the same inspection task, but their nominal accuracy
arXiv:2608.21455v1 Announce Type: new Abstract: Face presentation attack detection (PAD) is traditionally formulated as a face-specific problem, although many of the visual artifacts introduced by pri
arXiv:2608.22296v1 Announce Type: cross Abstract: Quadruped mobile manipulation requires two tightly coupled capabilities: reaching manipulation-ready configurations and maintaining stable contact thr
Top open models by use case 👇 chat - Kimi K3, Qwen3.8 2.4T A95B reasoning - Kimi K3, DeepSeek V4 Pro coding agents - Kimi K3, DeepSeek V4 Flash, GLM 5.2 small + fast - Qwen3.8 27B, gpt-oss 20B mid-siz
arXiv:2608.21422v1 Announce Type: new Abstract: CBCT (Cone Beam Computed Tomography) scans provide detailed three-dimensional images, widely used in dentistry for diagnostic and treatment planning tas
arXiv:2608.21969v1 Announce Type: new Abstract: Humans have multiple levels of temporal abstractions on daily interaction and thinking, such as concept perception and strategic planning. Inspired by t
arXiv:2608.22253v1 Announce Type: new Abstract: We study the language-model head and softmax as a single module, deriving an update geometry from their composition rather than from the weight matrix i
arXiv:2608.23190v1 Announce Type: new Abstract: Computed tomography (CT) throughput is limited by scan time, which grows with both the number of projections acquired and the detector integration time
arXiv:2608.22974v1 Announce Type: new Abstract: Large language model (LLM) agents rely heavily on knowledge encoded in model parameters or presented as unstructured context. In domain-specific tasks,
arXiv:2608.22866v1 Announce Type: new Abstract: Storing face images under a hard sub-kilobyte budget, as required for identity documents, smart-card biometrics and bandwidth-constrained verification,
arXiv:2608.23392v1 Announce Type: cross Abstract: User representation learning in real-world industrial scenarios is commonly scaled by increasing user amount, behavioral sequence length and model siz
arXiv:2011.03783v3 Announce Type: replace-cross Abstract: In this work, we introduce the construction of a machine translation (MT) assisted and human-in-the-loop multilingual parallel corpus with ann
arXiv:2608.23344v1 Announce Type: new Abstract: Modeling team interactions in high-stakes environments such as operating rooms is critical for understanding how coordination, communication, and indivi