Knowledge catalogue
arXiv:2609.18009v1 Announce Type: cross Abstract: Lightweight audio-visual speech enhancement (AVSE) models face a critical trade-off between computational efficiency and cross-modal alignment accurac
Romeo Lupascu has criticized the prevailing AI agency framework, which relies on repeatedly looping an LLM core with identical context. He calls this strategy “deeply flawed” and argues that it should
arXiv:2609.18763v1 Announce Type: new Abstract: Whole-body humanoid teleoperation commonly combines a motion-tracking policy with a separate dexterous-hand retargeter. However, independently generated
arXiv:2609.18011v1 Announce Type: new Abstract: In collaborative tasks with asymmetric information, participants coordinate their understanding through interaction. We ask whether gaze provides eviden
arXiv:2609.17814v1 Announce Type: new Abstract: Diffusion models are increasingly used to generate synthetic training data, but precise label control remains difficult when the conditioning signal is
arXiv:2609.18688v1 Announce Type: cross Abstract: AI models for multimodal medical imaging must balance modality-specific specialization with cross-modal shared representations, a trade-off that pure
arXiv:2507.05952v2 Announce Type: replace Abstract: Neural implicit representations have recently achieved impressive results in novel view synthesis and multi-view 3D reconstruction, yet both NeRF- a
arXiv:2305.16901v5 Announce Type: replace Abstract: One of the primary reasons behind the success of neural networks has been the emergence of an array of new, highly-successful optimizers, perhaps mo
arXiv:2609.17578v1 Announce Type: cross Abstract: Let a_1,ldots,a_m be distinct elements of a field K, and let Z(X)=prod_{i=1}^m (X-a_i). We study the arithmetic complexity of computing the unique nor
arXiv:2609.18634v1 Announce Type: cross Abstract: Video streaming dominates global internet traffic, yet conventional pipelines remain inefficient for structured, human-centric content such as sports,
arXiv:2609.18465v1 Announce Type: new Abstract: Feed-forward 3D foundation models such as VGGT predict cameras, depth, and point maps in a single pass, but can fail silently under low overlap, low par
arXiv:2609.18069v1 Announce Type: new Abstract: Underwater semantic segmentation is essential for marine ecosystem monitoring, yet remains challenging due to severe visual degradation. Light absorptio
arXiv:2609.18050v1 Announce Type: new Abstract: How do elephant trunks generate complex postures without relying solely on fine segmental activation? We propose that part of this complexity arises fro
arXiv:2609.18737v1 Announce Type: new Abstract: Underwater 3D reconstruction supports applications ranging from marine ecosystem monitoring and subsea inspection to underwater archaeology, education,
arXiv:2609.17740v1 Announce Type: new Abstract: Face swapping and face compositing pipelines routinely produce a face that is geometrically well aligned but photometrically implausible: the donor face
Good implementation of agent shared memory from the NVIDIA team. Banger paper from NVIDIA on shared memory for research agents. (bookmark it) If you run several coding agents on the same research prob
Google announced “CC,” an experimental AI agent that extends the Gemini‑powered personalization available in Google’s ecosystem to whole families of up to six members. Each family can grant limited ac
Google LLC today opened its experimental artificial intelligence agent CC to families, with as many as six people in a household able to share one. Each member picks what the agent is allowed to see,
At Google, we see firsthand how the speed, scale, and sophistication of cyber threats continue to challenge traditional enterprise defenses. Today’s defenders can’t rely on reactive triage or fragment
Amy Harder / Axios: Google, Nvidia, and Emerald AI launch the AI Energy Management Alliance to advance data centers that dynamically adjust electricity use based on grid conditions — A new coalition l
arXiv:2609.18416v1 Announce Type: cross Abstract: Stochastic subspace methods have gained popularity as gradient descent based techniques for large scale optimisation problems, especially in distribut
arXiv:2609.18856v1 Announce Type: cross Abstract: Compact acoustic models face a challenging quality-capacity trade-off. We investigate two factors in this regime: encoder context and Mel-spectrogram
arXiv:2609.17695v1 Announce Type: new Abstract: A large language model (LLM) agent can follow more graph paths without acquiring more independent evidence. GraphEcho tests whether agents mistake these
arXiv:2609.18358v1 Announce Type: new Abstract: Robot manipulation policies often struggle to generalize beyond their demonstrations, even when new instructions involve familiar objects and behaviors.
arXiv:2609.18581v1 Announce Type: new Abstract: Although vision-language models (VLMs) possess strong visual understanding and reasoning capabilities, existing vision-and-language navigation (VLN) age
arXiv:2609.17573v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) are emerging as a promising generative paradigm that complements autoregressive decoding. In long-context sett
arXiv:2609.17696v1 Announce Type: new Abstract: Document repositories evolve continuously. Guidelines and policies are revised, superseded, and re-uploaded, so the same content recurs in different wor
arXiv:2609.18384v1 Announce Type: cross Abstract: We present a robust benchmark for measuring cultural value orientation in large language models on the two Inglehart-Welzel axes over several domains
arXiv:2602.02888v2 Announce Type: replace-cross Abstract: Hallucinations remain a major obstacle for large language models (LLMs), especially in safety-critical domains. We present HALT (Hallucination
arXiv:2609.18548v1 Announce Type: cross Abstract: Egocentric motion forecasting has primarily focused on hands and manipulated objects, leaving future human head motion comparatively underexplored. Du
arXiv:2609.18434v1 Announce Type: new Abstract: Teaching robotics relies on screen-based simulation, showing robot motion in an abstract coordinate frame rather than at real scale in the learner's own
arXiv:2609.18680v1 Announce Type: new Abstract: Contextual ASR can benefit from semantic cues or from target words explicitly provided in the context. We introduce HearInContext, a Mandarin--English b
arXiv:2609.18916v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) language models suffer from large parameter counts, which create a significant memory bottleneck. Expert pruning is the most
arXiv:2609.18419v1 Announce Type: cross Abstract: Latent neural operators improve the efficiency of operator learning for partial differential equations (PDEs) by performing the main computation on co
arXiv:2609.17771v1 Announce Type: cross Abstract: Approaches to incorporating human awareness into mobile robot decision-making mainly focus on collision avoidance in low-level motion planning, often
Editor's note: Lucius AI, a tender-intelligence startup covering markets across five continents, runs its entire data platform on AlloyDB for PostgreSQL with a single operator. By migrating semantic s
arXiv:2609.17547v1 Announce Type: new Abstract: AI assistants are expected to remain useful during difficult interactions, but little is known about how repeated verbal abuse changes their engagement
arXiv:2609.17764v1 Announce Type: new Abstract: Attention-based rerankers score documents by aggregating query-to-document attention and subtracting a null-query calibration pass to remove positional
David Streitfeld / New York Times: How Dario Amodei's essays on AI safety and ethics help explain some AI fears; his regulatory stance evolved from wariness in January to embracing safety reviews — Da
What I want to know is how your daily interaction routine looks like. Do you wake up, take your coffee/tea/drinkname.txt, have a nice morning, then click a button and somethings starts and creates som
arXiv:2609.18622v1 Announce Type: new Abstract: Classifiers can make identical predictions yet require labels to compare their selective performance: confidence ranks weight the same errors differentl
arXiv:2609.19107v1 Announce Type: new Abstract: Scaling laws predict how loss decreases with increases in computation. We show, contrary to conventional wisdom, that architectural interventions can mo
Learn how MRH Trowe, one of Germany's leading commercial and industrial insurance brokers, gave about 400 employees secure, self-service access to AI agents in its first month of production - using St
arXiv:2609.18908v1 Announce Type: new Abstract: Existing legal benchmarks cover diverse tasks, while continuous monetary remedies remain comparatively underexplored. We introduce ECtHR-NPD, to the bes
Evals measure failures you know how to name. Arize Signal continuously reviews production traces to find recurring trajectory failures you do not, then turns them into evidence for tests and fixes. Th
arXiv:2609.17749v1 Announce Type: new Abstract: A lot of expectations have been put for years on integrating domain expert knowledge in image classification models. Several approaches have been explor
How To Write With An LLM Thomas Ptacek on using LLMs as copyeditors, not as writing assistants: Rule Number One: You may not use a single word an LLM suggests to you. [...] I think that as a form of i
arXiv:2609.18431v1 Announce Type: new Abstract: More than 300 million people worldwide are affected by one of over 7,000 known rare diseases, yet diagnosis remains difficult because patients initially
arXiv:2609.17540v1 Announce Type: new Abstract: We propose a framework that transfers tacit human subjective criteria to robotic systems for the appropriate grasping of deformable objects. Achieving s
arXiv:2510.25218v2 Announce Type: replace-cross Abstract: AI is changing work and decision making faster than many institutions can adapt their operating practices. We argue that this adaptation gap m
“HUMANZS LAUNCHED THE JOB” Ok, I don’t like the spelling here, but the gist of this Mozilla cybersecurity researcher rings true. The six new incidents aren’t about the second coming of Skynet, they ar
We compared 20 model versions on 360 frozen joke prompts, with four jokes requested per prompt and model names hidden from our humor-trained judge. Fable 5 had the highest estimated score: 66.8 points
arXiv:2609.17841v1 Announce Type: new Abstract: We develop a hybrid modeling framework for coupling pre-trained numerics-informed neural networks (NINNs) with classical full order models (FOMs) using
arXiv:2609.18481v1 Announce Type: new Abstract: Biomedical knowledge graphs combine ontology-derived hierarchies with transversal associations among heterogeneous entities such as phenotypes, diseases
arXiv:2609.18598v1 Announce Type: cross Abstract: Self-driving laboratories can explore synthesis conditions autonomously, but their decision-making layer is typically a black-box optimizer, and the o
arXiv:2608.27875v3 Announce Type: replace Abstract: Quantization has been widely adopted in LLM training and inference to reduce cost and improve efficiency. However, low-bit quantization of the atten
arXiv:2609.18274v1 Announce Type: cross Abstract: Classroom observations are widely recognized as a key tool for establishing benchmarks of education quality and guiding pedagogical improvement, yet t
I developed https://lora-hunt.info/ for finding LoRA/PEFT adapters that might work with local LLM setups. The site collects public model metadata from Hugging Face and tries to make base-model compati
Everyone now talks about the architecture that's not auto regressive and does lightning fast probability prediction with a json schema. I worked on this literally one year back in March 2025, publishe
arXiv:2609.18729v1 Announce Type: cross Abstract: Consumers increasingly use AI chatbots for advice on what to buy. With companies like OpenAI and Google monetising their AI through advertising, this