Knowledge catalogue
arXiv:2609.29106v1 Announce Type: cross Abstract: 3D foundation models recover video cameras and geometry in one forward pass, but some of the strongest are up to scale. Joint people-scene reconstruct
arXiv:2609.27333v1 Announce Type: new Abstract: Platform operators increasingly rely on system prompts and fine-tuning to govern model behavior, yet it remains unclear how reliably these interventions
arXiv:2609.27607v1 Announce Type: cross Abstract: An AI-generated radiology report can resemble a physician's report while omitting an abnormality, adding an unsupported finding, or reversing its pres
arXiv:2609.28177v1 Announce Type: cross Abstract: LLM leaderboard gains can reflect selection among privately evaluated model variants, yet neither the number of variants nor their dependence is publi
arXiv:2609.28322v1 Announce Type: new Abstract: Benchmarking and routing platforms increasingly act as intermediaries connecting large language model providers with end-users. However, providers on th
arXiv:2609.27024v1 Announce Type: cross Abstract: Volatility forecasts play a central role in financial risk management because their overall level and day-to-day movements affect downstream decisions
arXiv:2609.27041v1 Announce Type: new Abstract: Mathematical reasoning benchmarks are typically organized by topic, but language models may organize their internal computation by reusable reasoning ap
arXiv:2607.10669v2 Announce Type: replace Abstract: Bayesian optimization (BO) is widely used for expensive black-box problems, yet practical performance depends not only on high-level algorithmic cho
arXiv:2609.28312v1 Announce Type: cross Abstract: We present VGM-VS, a visual servoing method built on a pretrained feed-forward visual geometry model. Given the current view and a reference image cap
arXiv:2609.27411v1 Announce Type: new Abstract: Machine fault diagnosis from vibration requires learning from scarce labelled fault recordings while meeting the computational constraints of edge devic
arXiv:2602.01163v2 Announce Type: replace Abstract: Safe UAV emergency landing requires more than just identifying flat terrain; it demands understanding complex semantic risks (e.g., crowds, temporar
arXiv:2609.25264v1 Announce Type: new Abstract: Cosserat rod models for soft robots usually construct sectional stiffness by summing material properties over a common cross-section. This assumption be
arXiv:2609.26733v1 Announce Type: new Abstract: The rapidly advancing capabilities of vision-language models (VLMs) present a systemic challenge to academic integrity. VLMs now allow students to bypas
arXiv:2609.26605v1 Announce Type: cross Abstract: Foundation model embeddings of screening mammograms may encode pre-diagnostic tissue change without task-specific adaptation. We tested whether embedd
arXiv:2609.25567v1 Announce Type: cross Abstract: A lack of high-throughput phenotyping solutions for root traits in field-grown crops has severely constrained understanding and improvement of below-g
arXiv:2609.25569v1 Announce Type: new Abstract: Soccer tactics are interactive: an attacking action changes the opponent's defensive problem, and the observed response depends on the multi-agent match
arXiv:2609.22939v1 Announce Type: cross Abstract: Long-context models read a novel the way a person reads a printout: one token after another, in narrative order, with the whole history competing for
arXiv:2609.23184v1 Announce Type: new Abstract: Embodied world models learn to predict future physical dynamics from visual observations and control signals, where physical knowledge is implicitly ent
arXiv:2609.22896v1 Announce Type: new Abstract: Autonomous vehicles operating in open-world scenarios are inevitably confronted with previously unknown objects, such as exotic animals or loose cargo.
arXiv:2609.22317v1 Announce Type: new Abstract: World models support autonomous driving by predicting the scene evolution associated with candidate trajectories. Driving dynamics differ in predictabil
arXiv:2609.22103v1 Announce Type: cross Abstract: Electroencephalography (EEG) provides a noninvasive means of capturing emotion-related neural dynamics, yet reliable EEG emotion decoding lacks models
arXiv:2609.22173v1 Announce Type: new Abstract: Mobility simulation supports logistics, safety, and communications planning in industrial environments such as ports, mines, and airports. Existing traj
arXiv:2506.07044v5 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in understanding common visual elements, largely due to their lar
arXiv:2609.24504v1 Announce Type: new Abstract: Fine-tuned checkpoints and adapters now fill public repositories, and the most common operation applied to these artifacts is model merging: arithmetic
arXiv:2609.22858v1 Announce Type: new Abstract: World models allow robots to anticipate action consequences before execution. This capability is especially valuable in excavation, where each scoop res
arXiv:2609.22283v1 Announce Type: new Abstract: Understanding the design space of streaming video diffusion is essential to exploring its potential for generation quality and computational efficiency.
arXiv:2602.24208v2 Announce Type: replace Abstract: Diffusion models achieve state-of-the-art video generation quality, but their inference remains expensive due to the large number of sequential deno
arXiv:2609.23118v1 Announce Type: new Abstract: Reinforcement learning for off-road navigation requires extensive vehicle-terrain interaction data, which are costly to collect in high-fidelity simulat
arXiv:2605.15418v2 Announce Type: cross Abstract: Hybrid optical systems combining refractive and diffractive optical responses have the potential to support new types of optical behavior, but they ar
arXiv:2609.21455v1 Announce Type: new Abstract: While diffusion-based text-to-video (T2V) models have demonstrated impressive capability in generating realistic and temporally coherent videos, they of
arXiv:2609.21941v1 Announce Type: cross Abstract: The importance of deep neural networks (DNNs) is widely recognized, and the parameters obtained through training are regarded as valuable assets. Rece
arXiv:2601.06848v2 Announce Type: replace Abstract: Multimodal aspect-based sentiment analysis (MABSA) aims to identify aspect-level sentiments by jointly modeling textual and visual information, whic
Jev and the System One Model: RLCD, intelligence/, reliable AI, & the end of chat-first AI https://www.latent.space/p/jev @typesafeai CEO @CompleteSkeptic explains why AI can solve extraordinarily har
arXiv:2609.21280v1 Announce Type: new Abstract: Drug mechanism-of-action (MoA) modeling commonly relies on perturbational transcriptomes, but matched microRNA (miRNA) measurements are often unavailabl
arXiv:2402.04013v3 Announce Type: replace Abstract: Deep Neural Networks (DNNs) have revolutionized various domains with their exceptional performance across numerous applications. However, Model Inve
When running modern AI workloads, there’s often a conflict between performance and cost. Workloads like large language models (LLMs) load massive files, and may serve thousands of AI agents that need
arXiv:2609.21983v1 Announce Type: new Abstract: Reusing manipulation experience across robot embodiments is important for scaling robot learning and reducing repeated task-specific data collection. Ho
arXiv:2609.21187v1 Announce Type: new Abstract: Agent models are frequently evaluated one decision at a time, where the model predicts the next action based on the gold interaction history, which is s
arXiv:2602.03128v2 Announce Type: replace Abstract: Multi-agent LLM frameworks are data-intensive systems that govern how agents orchestrate tasks, manage state, and coordinate decisions. These archit
arXiv:2609.19242v1 Announce Type: new Abstract: Block diffusion language models (BDLMs) combine autoregressive dependencies across blocks with parallel denoising within blocks, but long-context traini
According to people familiar with the matter, Naive AI, an AI startup founded in February this year by Tsinghua University professor Dai Jifeng, has completed three funding rounds totaling 400 million
arXiv:2609.20535v1 Announce Type: new Abstract: Deep learning predictive maintenance models suffer from poor transferability across machines and operating conditions, especially when labelled data are
arXiv:2609.19683v1 Announce Type: cross Abstract: The deployment of Vision-Language Models (VLMs) on edge devices is severely bottlenecked by memory bandwidth, necessitating aggressive sub-8-bit quant
arXiv:2609.19378v1 Announce Type: new Abstract: Online residual learning can reduce model mismatch in predictive control, but passive data collection may fail to adequately cover states that become im
arXiv:2609.18514v1 Announce Type: cross Abstract: Active perception is essential for robotic manipulation when fixed viewpoints leave task-relevant information occluded or unobserved. However, enablin
arXiv:2609.17572v1 Announce Type: new Abstract: Auditing vision-language models (VLMs) for societal bias requires distinguishing direct algorithmic valuation disparities from confounders embedded with
arXiv:2609.17538v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for structured information extraction from documents, yet their behavior under realistic OCR noise re
arXiv:2609.18442v1 Announce Type: new Abstract: Safe motion planning in automated driving requires anticipating evolving traffic risks and deciding when to revise the current planned trajectory. We in
Self-generated prompt injections in compaction summaries In Our framework for reporting model misalignment OpenAI provide 'six reports on unexpected or concerning model behavior we’ve observed in the
arXiv:2609.18759v1 Announce Type: cross Abstract: Generating signals on graphs requires permutation-equivariant models that exhibit stability with respect to relative structural perturbations. While r
The difference with using VLMs for OCR vs. other tasks is that the ratio of output/input tokens is quite high - meaning the model can spend a lot of time writing markdown. Speculative decoding offers
Anyone else trying out the new Union stealth model on openrouter? It’s pretty good for a free model, and of course I had to run tokenizer tests and training cutoff tests which established it’s the 99%
arXiv:2609.16597v1 Announce Type: cross Abstract: Background Non-invasive presurgical diagnosis of brain tumor types from Magnetic Resonance Imaging (MRI) is essential but challenging due to overlappi
arXiv:2609.16890v1 Announce Type: new Abstract: Large Language Model (LLM) unlearning is essential for removing sensitive or copyrighted knowledge while preserving general utility. Existing methods of
We gave two small LLMs a real customer-service task. One got 100/100. The other stopped with the job half-done. I wanted to test something more meaningful than benchmark scores: can a small model actu
arXiv:2609.16129v1 Announce Type: new Abstract: A new scheme for parameter pruning is introduced, derived from the differential-geometric distance in model space. Pruning a parameter sets its value to
Our framework for reporting model misalignment https://openai.com/index/model-misalignment-reporting-framework/ // if you scrape away all the anthropomorphic language, all the nonsense about thinking,
arXiv:2609.16527v1 Announce Type: cross Abstract: Exploring the chemical space of flexible molecules remains challenging because the vast number of possible compounds and conformations, together with
Saw the new Introducing System One Models & Jev - TypeSafe AI Blog Jev model which just outputs probabilities given choices and I thought it sounded a something the Qwen reranker models could do? Then
arXiv:2609.16660v1 Announce Type: new Abstract: Test-time reinforcement learning adapts a model on its own unlabeled test set using majority-vote pseudo-labels and has shown strong results in mathemat