Knowledge catalogue
arXiv:2609.24626v1 Announce Type: new Abstract: Latent world models learn predictive representations for autonomous driving, but the relational semantics these states preserve often remain implicit. W
arXiv:2609.22234v1 Announce Type: new Abstract: Instruction hierarchy (IH) alignment teaches language models to prioritize higher-level instructions when inputs conflict. While studied primarily in te
arXiv:2507.00236v4 Announce Type: replace Abstract: Simulation-based design, optimization, and validation of autonomous vehicles have proven to be crucial for their improvement over the years. Neverth
arXiv:2609.24198v1 Announce Type: cross Abstract: This paper describes the SKstars submission to SHROOM-Visions 2026, a shared task on fine-grained hallucination detection in large vision-language mod
arXiv:2609.22750v1 Announce Type: new Abstract: Manual attendance methods, such as paper or register-based systems, take a lot of time, can lead to errors, and are easy to falsify. Face recognition is
arXiv:2609.21677v1 Announce Type: new Abstract: Recent advances in large reasoning models (LRMs) have made machine unlearning more challenging, as protected facts or unsafe rationales may surface in i
arXiv:2609.21246v1 Announce Type: cross Abstract: Vision-language-action (VLA) models map visual observations and natural-language instructions to robotic actions, but distribution shifts can compromi
I think there are lots of good reasons to worry about whether AI is giving correct answers (especially free models), but, given the contradiction with other recent research suggesting AI is now doing
We tested Jev against LLM judges on accuracy, repeatability, latency, and cost to see whether System One models could offer a new approach to agent evaluation. https://x.com/i/article/2101448785255907
arXiv:2609.19334v1 Announce Type: new Abstract: Full-duplex speech-to-speech (S2S) models provide natural, low-latency conversational interaction and would benefit from the ability to use external too
arXiv:2609.20139v1 Announce Type: cross Abstract: Vision-language models (VLMs) are fragile under image corruption. We find that the wording of the question affects VLMs in two opposite ways. Verbose
arXiv:2609.20051v1 Announce Type: new Abstract: Step distillation reduces the cost of video generation, but reusing a LoRA trained for a longer trajectory can alter its functional effect or degrade ta
arXiv:2609.19596v1 Announce Type: new Abstract: Full-duplex speech models listen and speak at once, promising always-on assistants. Yet they must also decide when they should speak. Human listeners sp
arXiv:2609.19385v1 Announce Type: cross Abstract: Cardiovascular disease (CVD) remains the leading cause of death among women, yet cardiovascular risk assessment often relies on clinical variables tha
arXiv:2609.19203v1 Announce Type: new Abstract: AI applications have shifted from single, monolithic foundation models (FM) to compound agentic systems. Yet today's stacks remain fragmented: even as p
arXiv:2609.18489v1 Announce Type: cross Abstract: This study analyses kinetic energy (KE) spectra, difference kinetic energy (DKE) spectra, and signatures of KE transfer across spatial scales in four
arXiv:2609.18473v1 Announce Type: new Abstract: We present CADSplat, a framework that reconstructs photorealistic, geometrically accurate digital twins from sparse (<15 views), wide-baseline posed ima
arXiv:2609.18718v1 Announce Type: new Abstract: Retrieving a target from clutter requires deciding whether to grasp the target, remove a blocker, or defer. Existing methods typically commit to a singl
arXiv:2609.17620v1 Announce Type: cross Abstract: Whole genome sequencing (WGS) is essential for precision oncology, yet its clinical adoption remains limited by prohibitive computational costs and mu
arXiv:2609.18471v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) exhibit strong problem-solving abilities, yet their safety alignment often degrades when handling harmful queries. Existin
arXiv:2609.16237v1 Announce Type: cross Abstract: Rotating detonation engines (RDEs) exhibit strongly nonlinear, multiscale wave dynamics that set the observed thermal field. High-fidelity simulations
arXiv:2609.16779v1 Announce Type: new Abstract: LLMs are increasingly employed in a wide range of decision-making tasks. However, the opacity of their internal reasoning makes it difficult to validate
arXiv:2609.16847v1 Announce Type: cross Abstract: Region-level retrieval aims to align user-specified image regions with relevant regions or textual descriptions, playing a crucial role in realworld a
arXiv:2609.16641v1 Announce Type: new Abstract: Vision-language-action (VLA) models have become the dominant paradigm for language-conditioned robot manipulation. However, although images and language
arXiv:2602.02132v2 Announce Type: replace Abstract: Prior work argues that refusal in large language models is mediated by a single direction, enabling steering and abliteration. We show that this acc
arXiv:2609.14578v1 Announce Type: new Abstract: Autonomous agents that author building information models need more than access to a host API. They need a representation of what they intended, what a
Artificial intelligence agent certification startup Artificial Intelligence Underwriting Company today announced it has raised 40 million in new funding to begin auditing frontier AI models. Until now
arXiv:2602.00377v3 Announce Type: replace Abstract: Existing knowledge probing methods rely on pre-defined queries, limiting extraction to known concepts. We introduce DecompressionLM, a stateless fra
arXiv:2609.13773v1 Announce Type: cross Abstract: LLM-as-a-Judge evaluators are increasingly used to score open-ended generation, yet a judge's correlation with human ratings on its development set ma
arXiv:2609.15338v1 Announce Type: cross Abstract: Large Language Models (LLMs) primarily perform inference at the token level, resulting in substantial memory overhead and compromised computational ef
arXiv:2609.13627v1 Announce Type: new Abstract: Many labor-intensive tasks in fruit production such as pruning require physically interacting with the plant (e.g., pushing, pulling, bending limbs, etc
arXiv:2609.13257v1 Announce Type: cross Abstract: Test-time scaling (TTS) can improve generation only when additional compute produces better candidates and the system can reliably identify them. This
arXiv:2609.14284v1 Announce Type: new Abstract: Criterion-level grading connects examination performance to learning outcomes, but manual marking introduces workload and variation between markers. Thi
arXiv:2609.12163v1 Announce Type: new Abstract: Existing evaluations of concept unlearning in text-to-image (T2I) diffusion models primarily rely on attack success rates obtained through automated adv
Daniel Kokotajlo / @dkokotajlo: OpenAI researcher: top models are becoming so situationally aware humans “are losing the ability to evaluate them” while humans rely more on AI to lead research — Dan S
arXiv:2609.12658v1 Announce Type: new Abstract: Streaming video understanding requires models to process continuous multimodal input while maintaining temporal context. Existing evaluations are predom
2019: “GPT2 is groundbreaking in two ways. One is its size, says Dario Amodei, OpenAI’s research director. The models “were 12 times bigger, and the dataset was 15 times bigger and much broader” than
Not sure if anyone out there is working on this, don't see any on huggingface to try out. It might be too new at the moment, but it would be cool to see the difference between a tiny model trained wit
Bloomberg: Amodei says pacing does not mean halting training or progress, but giving companies time to align and safeguard models and third-party evaluators time to verify — Leaders of the world's big
arXiv:2609.11315v1 Announce Type: new Abstract: Diffusion vision-language models generate answers through iterative refinement, exposing intermediate answer trajectories that can be inspected and cont
arXiv:2606.20041v2 Announce Type: replace-cross Abstract: We propose an AI economist agent for economic and financial scenario analysis. Scenario design often requires analysts to assess emerging risk
arXiv:2603.27325v2 Announce Type: replace Abstract: Accurate wound classification (WC) and boundary segmentation are essential for guiding clinical decisions in chronic and acute wound management. How
arXiv:2609.10993v1 Announce Type: new Abstract: Multilingual large language models (mLLMs) contain a small fraction of feed-forward neurons that are sensitive to particular languages, commonly termed
Fugu Max is now live on @OpenRouter! 🐡 Our learned multi-agent orchestration engine routes tasks across open-weights and specialized models for Pareto-frontier efficiency. • 2/6 per 1M tokens • Multim
arXiv:2609.09547v1 Announce Type: new Abstract: Sample size determination for machine learning (ML) prediction models is challenging because conventional power analysis typically requires the predicto
arXiv:2603.08275v2 Announce Type: replace-cross Abstract: With the global proliferation of Large Language Models (LLMs), cultural safety, defined as the ability to generate respectful and appropriate
arXiv:2601.12723v3 Announce Type: replace-cross Abstract: Optimization benchmarks play a fundamental role in assessing algorithm performance; however, existing artificial benchmarks often fail to capt
arXiv:2508.05427v2 Announce Type: replace Abstract: Large language models (LLMs) are beginning to reshape how organic-synthesis workflows are represented, queried, planned, and connected to experiment
arXiv:2609.07663v1 Announce Type: cross Abstract: A wrong number is worse than no answer. Across factuality-critical domains -- audience metrics, scheduling and rights in media; dosages and lab values
arXiv:2609.09070v1 Announce Type: cross Abstract: Clinical AI evaluation should encompass diagnosis and management after adaptive information gathering. We compared Doctorina, eight physicians and fou
arXiv:2609.09163v1 Announce Type: new Abstract: LLMs generalize across a domain only after seeing many real, labeled examples, which most domains lack. We study a way to manufacture it cheaply. When a
arXiv:2609.08230v1 Announce Type: new Abstract: Chunk-autoregressive video world models typically condition each generated chunk on one action. An action received during sampling must therefore wait f
arXiv:2607.10655v2 Announce Type: replace Abstract: Robotic foundation models still need task-specific fine-tuning before deployment, and the fine-tuned policies often break under modest changes in sc
arXiv:2609.07838v1 Announce Type: new Abstract: Connected robotics is an emerging 6G application where mobile robots follow natural-language instructions to manipulate physical objects. The Vision-Lan
arXiv:2609.05821v1 Announce Type: cross Abstract: Vision-language models (VLMs) often answer new questions about recurring visual content, where reusing the key-value (KV) cache can avoid re-encoding
arXiv:2606.13877v2 Announce Type: replace Abstract: Contact-rich manipulation requires world models to capture complex interaction dynamics from heterogeneous visual and tactile observations, yet the
arXiv:2609.07756v1 Announce Type: new Abstract: Inertial confinement fusion (ICF) is a leading pathway toward clean energy, but each shot at the National Ignition Facility costs on the order of one mi
arXiv:2607.17138v2 Announce Type: replace Abstract: Deep neural networks trained on natural images are shown to produce outputs consistent with human observers for brightness illusions. While this phe
arXiv:2609.06820v1 Announce Type: cross Abstract: Active mapping requires a robot to select camera viewpoints that efficiently reconstruct an unknown 3D scene. To reason about unobserved regions, rece
arXiv:2609.06491v1 Announce Type: new Abstract: Open-world entity segmentation aims to predict masks for arbitrary objects across domains and at multiple granularities, from parts to whole objects. In