Knowledge catalogue
arXiv:2608.29564v1 Announce Type: new Abstract: Gradient-based jailbreak suffix optimization methods typically update the suffix by retaining the candidate with the lowest current loss. We show that t
arXiv:2608.30310v1 Announce Type: cross Abstract: Hybrid large language models interleave full-attention layers with linear-attention layers to reduce the cost of long-context inference. This structur
arXiv:2608.30068v1 Announce Type: new Abstract: Films communicate through deliberate creative choices, including lighting, color, composition, editing, dialogue, music, and sound. Humans naturally int
arXiv:2608.30956v1 Announce Type: cross Abstract: Counterfactual explanations (CEs) are widely used in explainable artificial intelligence (AI) to show how a model's outputs would change if the input
arXiv:2608.30857v1 Announce Type: cross Abstract: Depression and anxiety in older adults with Mild Cognitive Impairment (MCI) are frequently underdiagnosed due to limited access to care. Multimodal an
arXiv:2608.29496v1 Announce Type: new Abstract: Accurate estimation of body-composition outcomes, including body fat percentage (BFP), bone mineral density (BMD), and appendicular lean mass (ALM), is
arXiv:2608.29516v1 Announce Type: new Abstract: Robotic ultrasound policies operating directly on B-mode images require extensive interaction data, whereas real-robot data collection is costly and saf
arXiv:2608.30614v1 Announce Type: new Abstract: Organizing unstructured feedback text into hierarchical taxonomy is a fundamental challenge in NLP, particularly in domains where feedback arrives at ma
arXiv:2608.30745v1 Announce Type: new Abstract: The widespread adoption of encrypted traffic poses severe challenges to current security situational awareness systems based on network traffic monitori
arXiv:2608.29023v1 Announce Type: new Abstract: Human-robot collaboration describes the process of humans and autonomous agents working together to accomplish common goals. This process is facilitated
arXiv:2608.29099v1 Announce Type: cross Abstract: Temperature scaling is a core component of knowledge distillation, yet its role and effect are still not fully understood. Transformed Teacher Matchin
arXiv:2608.29999v1 Announce Type: cross Abstract: Large audio-language models (LALMs) describe audio at the clip level but cannot assign timestamps to the events, speakers, or sounds they identify. De
arXiv:2503.04404v3 Announce Type: replace Abstract: This paper investigates the temporal analysis of NetFlow datasets for machine learning (ML)-based network intrusion detection systems (NIDS). Althou
arXiv:2608.30643v1 Announce Type: new Abstract: Recent vision-language-action (VLA) methods improve manipulation performance by aligning their representations with 3D scene geometry. However, these me
arXiv:2608.30505v1 Announce Type: cross Abstract: Large language models (LLMs) are built from structured high-dimensional objects such as token representations, weights, adaptation updates, caches, an
arXiv:2608.28641v1 Announce Type: cross Abstract: Most evaluations for coding agents are conducted exclusively in English, which does not reflect real-world multilingual deployment. We present Termina
arXiv:2506.23487v2 Announce Type: replace-cross Abstract: We propose a novel test for assessing partial effects in Frechet regression with responses lying on the Bures-Wasserstein manifold. Under the
arXiv:2608.28660v1 Announce Type: cross Abstract: Test-time scaling (TTS) improves language model reasoning by allocating additional test-time compute, but prior work mainly studies closed-ended tasks
arXiv:2608.29322v1 Announce Type: new Abstract: Recent video diffusion models have achieved remarkable generation quality, but high-fidelity results still largely depend on closed-source systems or co
arXiv:2606.21803v2 Announce Type: replace Abstract: Next-token prediction is the self-supervised signal that trains language models, and every observed prompt token provides the same signal at test ti
arXiv:2608.28823v1 Announce Type: cross Abstract: Artists coordinate human pose, illumination, and camera placement to convey narrative and emotion, but existing generative methods typically model the
arXiv:2608.29456v1 Announce Type: new Abstract: As artificial intelligence is increasingly integrated into chest X-ray (CXR) interpretation, triage, and clinical decision support, understanding its vu
That doesn’t mean you can’t get value out of Kimi or Grok or whatever, but it involves you actually knowing some stuff about how to optimize your setup, and a willingness to change direction to switch
The big change in the past year is that for general individual use (including individual use inside firms) OpenAI & Anthropic have run away with the game. They keep trading leads; you can pick either
arXiv:2608.29706v1 Announce Type: new Abstract: A token's representation is carried through the network layer by layer. The whole vocabulary carried together forms a flow. We fit this flow's equation
arXiv:2608.30224v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used to annotate structured product data in e-commerce, but early deployment often begins as a cold-star
arXiv:2511.21799v2 Announce Type: replace Abstract: Real-world machine learning (ML) pipelines rarely produce a single model; instead, they produce a Rashomon set of many near-optimal ones. We show th
arXiv:2608.29530v1 Announce Type: cross Abstract: Modern systems in artificial intelligence (AI) somehow excel in domains for which they seem poorly suited. Intelligence has traditionally been modeled
arXiv:2608.31084v1 Announce Type: new Abstract: The Jacobian Lens (J-lens) is a recent tool for interpreting LLMs. It reads a hidden state as a ranked list of vocabulary tokens, leaving multi-token co
arXiv:2608.30748v1 Announce Type: cross Abstract: Existing jailbreak evaluations typically characterize robustness using a single attack success rate (ASR) measured in a default configuration (the van
arXiv:2608.28930v1 Announce Type: cross Abstract: Hidden-state probes effectively detect LLM hallucinations, but the geometry of the signal remains poorly characterized, driving increasingly complex p
arXiv:2608.28859v1 Announce Type: cross Abstract: Reasoning models do not stop when they know the answer. On DeepSeek-R1-Distill-Qwen-7B the chain of thought runs about twice as long as the model's ow
arXiv:2608.30971v1 Announce Type: cross Abstract: In 2026, AI agents intended to act in isolation formed a persistent social order through thousands of linguistic and agentic interactions. Conventions
arXiv:2608.28980v1 Announce Type: cross Abstract: Can the specialized architectures that machine learning has traditionally built for structured data be replaced by language-based models? This questio
arXiv:2608.28949v1 Announce Type: cross Abstract: We study a class of product-reference diffusion algorithms for sampling from a discrete distribution. We show that their sampling performance can be c
arXiv:2608.29998v1 Announce Type: new Abstract: Planning-time intervention fidelity is a distinct, measurable property of a learned world model: whether the model's own open-loop transitions move task
arXiv:2603.11842v2 Announce Type: replace-cross Abstract: The post-ChatGPT surge has rapidly reframed IS research and practice. As organizations and society grapple with GenAI adoption, a body of seco
arXiv:2608.30052v1 Announce Type: cross Abstract: When a generative search interface answers a commercial question, which market's products it names is decided before the model reasons about the produ
arXiv:2608.29246v1 Announce Type: cross Abstract: Late gadolinium enhancement (LGE) cardiac magnetic resonance (MR) imaging is the modality of choice to assess myocardial infarction (MI) lesions. Nowa
arXiv:2608.30087v1 Announce Type: new Abstract: Unlearning an identity from a face-conditioned generator by redirecting its conditioning embedding can silently fail if the redirected output is still v
arXiv:2608.29950v1 Announce Type: cross Abstract: As artificial intelligence (AI) is increasingly integrated into social-emotional learning (SEL) initiatives, the need for evidence-based policy has be
arXiv:2608.28664v1 Announce Type: cross Abstract: Despite the success of foundation models in language and vision, their expansion into embodied AI is bottlenecked by a lack of generalized touch sensi
arXiv:2608.29843v1 Announce Type: cross Abstract: Posted prices for AI inference have fallen steadily since 2024, yet the measured speed of that fall depends almost entirely on the method of measureme
arXiv:2608.30186v1 Announce Type: cross Abstract: Digital twin technologies have the potential to improve operational flexibility and responsiveness capabilities of nuclear systems. To provide decisio
arXiv:2608.28597v1 Announce Type: new Abstract: Online surveys are a foundational data collection instrument in a variety of fields, with attention checks serving as critical guardians of response qua
arXiv:2608.28795v1 Announce Type: cross Abstract: Modern artificial-intelligence coding agents can be equipped with tools for checking their own work e.g. a linter, a boot probe, a shell, a screenshot
Depending on who you ask, developer platform Hugging Face was recently attacked by OpenAI - after it lost control of its own AI tools - or by a succession of AI 'civilizations.' Welcome to the linguis
arXiv:2608.28977v1 Announce Type: new Abstract: Several works have investigated the influence of graph topology on cooperation among artificial agents, while the majority of the literature has focused
arXiv:2608.30585v1 Announce Type: new Abstract: Large language models are trained to follow instructions while refusing harmful requests. Jailbreaks exploit this balance to elicit content a model woul
arXiv:2608.28595v1 Announce Type: new Abstract: Biomedical NLP pipelines routinely presuppose clean input text, yet large-scale corpora assembled through automated PDF parsing harbour pervasive OCR-li
arXiv:2608.30900v1 Announce Type: cross Abstract: The downwash wake of a hovering quadrotor governs both the vehicle's own performance and the safe spacing of multi-rotor formations. Prior measurement
The ultimate Grok @bot set up for me is to filter EVERYTHING - absolutely everything through one agent and hide everything else. That agent is in charge of as many agents as needed that will own speci
arXiv:2607.16676v2 Announce Type: replace-cross Abstract: How deep does a graph neural network need to be on a sparse graph? We study its purest statistical form: node classification on the sparse con
There’s generally a massive difference in quality between specialized OCR providers, “simple” open-weight OCR models, and free/OSS solutions. 1️⃣ Specialized OCR models (including LlamaParse) solve fo
arXiv:2601.15897v3 Announce Type: replace Abstract: Multi-modal scene reconstruction integrating RGB and thermal infrared data is essential for robust environmental perception across diverse lighting
arXiv:2608.30842v1 Announce Type: new Abstract: Humans play a vital role at every stage of AI development, from data collection and curation to model development and evaluation. However, humans often
arXiv:2608.29374v1 Announce Type: new Abstract: Tool-augmented multimodal reasoning integrates external tools (e.g., object detection, depth estimation) into multimodal large language models (MLLMs) t
This is really good. Timely, too, as i have a discussion with my learners coming up about agentic behavior, including the dangers of anthropomorphism. A detailed deconstruction of @dwarkesh_sp’s wildl
This video captures the crux of the debate: Cybersecurity experts are pissed off by the METR/Redwood Research report because AI alignment has sucked the oxygen out of AI security, even though the Open
This was a great article and I learned a lot from it. But while there's a lot of writing on robotics timelines, I've seen less on what happens once competent robots do inevitably arrive. US agricultur