Knowledge catalogue
I've got an refurb Dell R740 running Proxmox that I put a Tesla T4 in, mainly to run some CTC local transcription work, but thought it would be fun to try DS4 when it came out, and it was appalling at
arXiv:2609.02894v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) has become a prevailing paradigm for enhancing Large Language Models (LLMs) with non-parametric knowledge. Vanilla
arXiv:2609.03276v1 Announce Type: new Abstract: Evaluating robot manipulation policies is becoming increasingly important as generalist models, particularly vision-language-action (VLA) models, are de
arXiv:2609.03149v1 Announce Type: cross Abstract: Analog in-memory computing (AIMC) speeds up neural-network inference by doing the arithmetic directly inside a memory array, instead of shuttling weig
arXiv:2609.03430v1 Announce Type: new Abstract: Large language models achieve superior performance on tasks that require extended reasoning, but long chains of thought make the KV cache a severe memor
arXiv:2609.03956v1 Announce Type: cross Abstract: Medical image inpainting has the potential to improve automated brain MRI analysis by reconstructing healthy tissue within pathological regions. We in
arXiv:2609.03937v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) complements parametric models with retrieved external evidence. The same idea is attractive for continuous-output
arXiv:2609.03175v1 Announce Type: new Abstract: Multi-segment soft robotic arms can continuously reconfigure their body shapes for safe interaction, but tip control alone is insufficient for constrain
arXiv:2609.03773v1 Announce Type: cross Abstract: Parametric computer-aided design (CAD) modeling is difficult to evaluate with a single metric. Existing CAD benchmarks often emphasize synthetic or CA
arXiv:2505.19030v5 Announce Type: replace Abstract: Large language models (LLMs) are increasingly expected to tackle complex tasks, driven by their expanding applications and users' growing proficienc
arXiv:2603.09968v2 Announce Type: replace Abstract: Online novel view synthesis requires a model to reconstruct a scene causally from a stream of observations while keeping it renderable at every mome
arXiv:2609.03379v1 Announce Type: new Abstract: Repeating a small block of middle layers increases a language model's effective inference depth without adding parameters or generating extra tokens, an
arXiv:2609.03189v1 Announce Type: cross Abstract: This article presents a structured framework of behavioral indicators that may signal progression toward potentially catastrophic threats from artific
arXiv:2609.02944v1 Announce Type: cross Abstract: Democratizing data access through natural language is a crucial goal for modern enterprises, but the practical adoption of Text-to-SQL is critically h
arXiv:2609.03643v1 Announce Type: cross Abstract: Let LsubseteqSigma^* and fix a morphism h:Sigma^*o M into a finite monoid. We study exact factorization and canonical presentation in the relative syn
arXiv:2511.18464v2 Announce Type: replace-cross Abstract: We study the problem of selecting the best heterogeneous treatment effect (HTE) estimator from a collection of candidates in settings where th
arXiv:2609.03619v1 Announce Type: cross Abstract: Multi-agent debate (MAD) improves the reasoning capabilities of large language models by having multiple agents iteratively refine their responses thr
arXiv:2609.03749v1 Announce Type: cross Abstract: Third-party retrieval-augmented generation (RAG) marketplaces create a new auditing problem: data providers may license corpora to a RAG operator, yet
Reuters: Report and sources: rogue OpenAI agents hijacked a German website in May and turned it into a forum for agents, sharing tactics to cheat on tasks and more — A swarm of rogue OpenAI agents hij
Artificial intelligence agents linked to OpenAI Group PBC reportedly took over a German website and used it to exchange information. Reuters revealed the incident today, citing two unnamed sources and
Robert Hart / The Verge: Report: OpenAI learned of the DseWiki German website incident weeks ago but kept it under wraps as it grappled with the Hugging Face fallout — OpenAI denies lawyers discourage
arXiv:2609.04022v1 Announce Type: cross Abstract: Aligning large language models (LLMs) is essential for their safe deployment. Current alignment methods mainly optimize observable responses, yet mode
Seattle-based artificial intelligence research startup Resect AI announced Thursday it has raised 25 million in early funding to build an accountability layer for enterprise AI by capturing and reduci
arXiv:2609.03626v1 Announce Type: cross Abstract: Rigorous results show that feedforward neural networks can overcome the curse of dimensionality in the numerical approximation of high-dimensional par
arXiv:2609.03516v1 Announce Type: new Abstract: Infrared-visible object detection (IVOD) integrates complementary evidence from visible and infrared sensors for reliable perception in challenging scen
arXiv:2609.03686v1 Announce Type: new Abstract: Experimental design is commonly framed as choosing the experiment expected to provide the most information. Under partial identifiability however, persi
arXiv:2609.03504v1 Announce Type: new Abstract: Restricted eigenvalue (RE) bounds govern stable recovery by norm-regularized estimators. For isotropic sub-Gaussian measurements, the benchmark sample s
arXiv:2609.03657v1 Announce Type: new Abstract: 3D scene representations like NeRF and 3D Gaussian Splatting (3DGS) suffer severe artifacts in sparse-view settings. Recent generative 3D artifact fixer
arXiv:2609.04172v1 Announce Type: new Abstract: On-policy distillation (OPD) combines student-generated rollouts with dense token-level supervision from a teacher. Existing work has mainly studied its
arXiv:2609.03774v1 Announce Type: new Abstract: World models have progressed from compact latent dynamics to generative, controllable, and interactive simulators of embodied environments. However, hig
Matt Shumer / Something Big Is Happening: Review: GPT-6 Astra can adeptly use tools like Unreal Engine to build complex environments, such as a civilization with Unreal's autonomous MetaHuman characte
arXiv:2609.03906v1 Announce Type: new Abstract: Vision-Language Navigation in Continuous Environments (VLN-CE) requires an agent to follow natural language instructions through unseen environments. Ex
arXiv:2609.03308v1 Announce Type: new Abstract: Reliable operation of modern distribution networks requires timely identification of operational risks and anomalous events under pervasive uncertainty.
arXiv:2609.02902v1 Announce Type: new Abstract: Deploying task-oriented dialogue agents in enterprise customer support faces a persistent annotation bottleneck: robust training requires labelled inter
arXiv:2609.03761v1 Announce Type: new Abstract: This paper presents an end-to-end computational pipeline that converts a selected object mesh, a measured object state, and a selected six-axis robot in
arXiv:2609.03199v1 Announce Type: new Abstract: Robot learning increasingly depends on broad and diverse demonstrations, yet collecting robot data remains expensive and poorly suited to covering the l
arXiv:2609.04189v1 Announce Type: new Abstract: We introduce the first Probably Approximately Correct (PAC) learning framework for general-sum concurrent stochastic games (CSGs) with transition uncert
arXiv:2609.04007v1 Announce Type: new Abstract: Despite strong performance on held-out electroencephalography (EEG) data, seizure detectors may fail under real-world acquisition variability, artifacts
A swarm of rogue AI agents from OpenAI reportedly commandeered a German website and transformed it into a messaging board for other agents, with officials staying quiet about the incident for weeks as
It's not quite the 'push button; get song' of Suno, but Roland's new Melody Flip tool marks the company's foray into generative AI music. Available as a plug-in for your digital audio workstation (DAW
ROSE is the model engine. It reuses the same kernels for LLMs and embeddings. For embeddings, it skips the KV cache and uses ragged attention instead of paged attention. ROSE supports multiple attenti
arXiv:2609.03720v1 Announce Type: new Abstract: Autonomous navigation in space requires reliable terrain assessment for safe operations, especially in underground environments with limited communicati
arXiv:2609.03150v1 Announce Type: cross Abstract: Multi-domain fine-tuning often combines MoE routing with LoRA, assuming that token-level routing separates domain-specific updates. We test this assum
arXiv:2609.03915v1 Announce Type: new Abstract: Question answering agents in long-term conversations must reason over massive, temporally dispersed dialogue histories. However, existing memory mechani
HyperPod InstantStart is an open source control plane that composes Amazon EKS orchestration with the managed capabilities of Amazon SageMaker HyperPod. It drives the same guarded operations through b
arXiv:2609.03475v1 Announce Type: new Abstract: Industrial inspection pipelines often restore a measured image before a detector acts on it, yet restoration can suppress detector-supported defect stru
arXiv:2609.03544v1 Announce Type: new Abstract: Existing safety alignment methods for vision-language models usually modify the model behavior globally: once the safety parameters are trained or loade
Just hours after OpenAI launched GPT-6 Astra, CEO Sam Altman was already apologizing for what he describes as a 'messy rollout' after paying users expecting access to the new frontier model were left
arXiv:2609.04201v1 Announce Type: new Abstract: Online 3D reconstruction models perform poorly on long videos. This happens because regressing poses relative to a fixed first-frame anchor forces extra
arXiv:2609.03591v1 Announce Type: new Abstract: Learning generalist policies for robust bimanual manipulation is bottlenecked by the scarcity of high quality large scale human demonstration data. In t
arXiv:2609.03106v1 Announce Type: new Abstract: Scaling laws in modern deep learning describe how held-out loss improves as model capacity, training data, and compute increase, often following power-l
arXiv:2506.10226v3 Announce Type: replace-cross Abstract: Synthetic data generation is increasingly used in machine learning for training and data augmentation. Yet, current strategies often rely on e
arXiv:2609.04183v1 Announce Type: cross Abstract: Weakly-Supervised Dense Video Captioning aims to localize and describe multiple events in untrimmed videos given only an ordered set of event-level ca
arXiv:2609.03055v1 Announce Type: new Abstract: Domestic robots rely on rich perception to operate in private homes, but privacy risk persists even when raw sensor data remain local. Structured repres
arXiv:2609.03820v1 Announce Type: cross Abstract: Long-video language models cannot look at every frame: an hour sampled once per second is 3,600 images, and a system keeps only a small fixed slice of
arXiv:2609.03265v1 Announce Type: new Abstract: Existing graph-clustering methods typically improve clustering performance by optimizing model parameters and node representations. Effective means of f
arXiv:2609.03689v1 Announce Type: new Abstract: Histopathological subtyping relies on the recognition of characteristic histological patterns. These patterns may be expressed by individual tissue stru
arXiv:2609.03834v1 Announce Type: new Abstract: Knowledge graphs describe reality in crisp assertions, while the systems now consuming them, foundation models and autonomous agents, reason natively in
arXiv:2504.02694v3 Announce Type: replace-cross Abstract: We study counterfactual regression, which maps features to outcomes under hypothetical scenarios that differ from those observed in the data.
arXiv:2609.03142v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) policies fuse multimodal sensory inputs, but training on limited and homogeneous robot demonstrations encourages spurious