Knowledge catalogue
arXiv:2609.17757v1 Announce Type: new Abstract: Behavioral cloning trains a policy offline on expert demonstrations, but deployment is closed loop: each action affects the observations the policy rece
Important paper on improving agent coordination. On normal tasks, this work shows agents caused harm 0 to 5% of the time. After receiving an unsafe trajectory from another agent, that rose to 40 to 95
arXiv:2609.18842v1 Announce Type: new Abstract: The scaling laws hold that a language model grows more capable with more parameters and more training data, and Mixture-of-Experts (MoE) architectures h
UPDATE https://github.com/ggml-org/llama.cpp/pull/29009 MERGED More Gen AI coverage and frameworks integrations to minimize code changes New models supported: On CPU: Gemma-3n On CPU, GPU: Kokoro-82M,
arXiv:2609.18504v1 Announce Type: new Abstract: Grasp synthesis aims to generate stable and physically plausible hand--object interactions, and has become a fundamental problem in both human hand mode
Epoch AI has launched “Benchmark Reviews,” an initiative to evaluate existing AI benchmark datasets. The program initially audits 15 benchmarks, categorizing them as 4 verified, 9 flawed, and 2 lackin
arXiv:2609.18379v1 Announce Type: new Abstract: Square jigsaw reassembly requires recovering the spatial arrangement of shuffled fragments from their visual content and pairwise relationships. While r
I released KaozKit this week, a Swift library for running LLM agents written in JavaScript inside a Mac app. Built from the start to keep everything local. Providers: MLX with Hugging Face model manag
arXiv:2609.18317v1 Announce Type: cross Abstract: Large language models (LLMs) suffer from a long-tail deficit: culturally specific facts, particularly those concerning underrepresented regions such a
arXiv:2609.18587v1 Announce Type: cross Abstract: Test-time reinforcement learning (TTRL) enables models to improve their reasoning without relying on labeled training data, but existing approaches ty
arXiv:2609.18959v1 Announce Type: new Abstract: LLM code-generation systems usually choose a target programming language before decoding and treat that choice as fixed. We show that, for language-flex
arXiv:2609.18616v1 Announce Type: cross Abstract: Subspace methods such as multiple signal classification (MUSIC) achieve super-resolution direction of arrival (DoA) estimation by exploiting the ortho
arXiv:2609.18578v1 Announce Type: new Abstract: Pathologists diagnose diseases by first locating suspicious tissue and then examining it at higher magnification, whereas self-supervised vision transfo
arXiv:2609.17546v1 Announce Type: new Abstract: In this position paper, we argue that legal LLMs' hallucinations should be evaluated as a failure of legal warrant rather than as factual inaccuracy or
arXiv:2609.19062v1 Announce Type: new Abstract: Automatic sleep staging is fundamental to personal health monitoring, yet many existing approaches are ill-suited for real-world applications. Tradition
arXiv:2609.18106v1 Announce Type: cross Abstract: Open-weight large language models are rapidly entering hiring pipelines, yet their discriminatory failure modes -- and the regulatory exposure these c
LLMs lack theories of mind and body, are disembodied, possess neither homeostatic regulating feelings and emotions, are not persistent, and cannot continuously learn or compute. As currently construct
arXiv:2510.08928v2 Announce Type: replace Abstract: Existing benchmarks for large multimodal models (LMMs) often fail to capture their performance in real-time, adversarial environments. We introduce
arXiv:2609.17930v1 Announce Type: new Abstract: As AI agents take on long, autonomous tasks, we increasingly oversee rather than perform the work, yet we still judge them almost entirely by whether th
arXiv:2609.19041v1 Announce Type: new Abstract: Informative terrain perception is important for robust reinforcement learning policies in humanoid locomotion. Still, common sensors such as depth camer
arXiv:2609.18935v1 Announce Type: new Abstract: A game character should not have to reread its entire life before every conversation. For locally deployed language-model characters, however, revising
arXiv:2609.17868v1 Announce Type: new Abstract: Pathology vision-language models are commonly built by pretraining or fine-tuning large encoders on paired image-caption data. We asked whether a pathol
I've been building Selfcoder, a VS Code coding agent focused specifically on local models. I originally started working on it because I was frustrated with the context management when using local mode
arXiv:2609.17910v1 Announce Type: new Abstract: We introduce Map2Route, a human-curated benchmark for compositional language-grounded route planning over pre-built semantic maps. Map2Route contains 1,
arXiv:2609.18716v1 Announce Type: new Abstract: Spiking Neural Networks (SNNs) match the event-driven nature of event cameras and naturally extract spatiotemporal features. These properties have motiv
arXiv:2609.18496v1 Announce Type: cross Abstract: Cybersecurity combines high-stakes analysis with complex technical language, making it an impactful and challenging domain for LLMs. We present MiST (
arXiv:2507.21828v2 Announce Type: replace Abstract: While the task of assessing the plausibility of events such as 'news is relevant' has been addressed by a growing body of work, less attention has b
arXiv:2609.17763v1 Announce Type: new Abstract: Next-day wildfire prediction requires models whose forecasts can be evaluated alongside the assumptions and historical evidence used in their computatio
arXiv:2609.19101v1 Announce Type: new Abstract: As models scale, reward hacking becomes more frequent, more sophisticated, and more consequential. Does it leave a telltale signature in model represent
arXiv:2609.18176v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures decouple model capacity from computational cost, yet incur high memory footprints as parameters grow linearly w
arXiv:2609.18393v1 Announce Type: new Abstract: Conditioning a video generator on multiple images requires preserving appearance while associating each reference with its intended role. We present MSR
arXiv:2609.17539v1 Announce Type: new Abstract: We present MudawanSn, a gold-standard resource of 1,271 sentence-aligned pairs manually translated from Wolof into Modern Standard Arabic (MSA). The sou
arXiv:2609.18315v1 Announce Type: new Abstract: Non-intrusive load monitoring (NILM) estimates appliance power sequences from aggregate power, but models trained on source households commonly lose acc
arXiv:2609.18139v1 Announce Type: new Abstract: Cross-view object geo-localization (CVOGL) locates a target in satellite imagery using drone or street-view queries. Existing methods train separate det
arXiv:2603.06084v2 Announce Type: replace Abstract: Large language models have been widely used for robotic task planning, often taking advantage of representations such as Behavior Trees (BTs). Visio
arXiv:2609.17987v1 Announce Type: new Abstract: The traditional Batak Ulos weaving industry faces growing challenges in producing diverse, innovative motifs due to limitations in conventional, manuall
arXiv:2609.19088v1 Announce Type: new Abstract: Large vision-language models have achieved remarkable progress in multi-modal understanding, yet their capabilities in educational settings remain insuf
arXiv:2603.09908v2 Announce Type: replace Abstract: Existing aerial-robotics benchmarks target vehicles from hundreds of grams to several kilograms and typically expose only high-level state data. The
arXiv:2609.17699v1 Announce Type: new Abstract: We present NeMo Data Designer (NDD), an open-source, general-purpose framework for multi-modal synthetic data generation (SDG). Designed to be intuitive
arXiv:2609.17550v1 Announce Type: new Abstract: Language models frequently abandon correct answers when users push back. We study this in two small instruction-tuned models from different families, Qw
arXiv:2609.17825v1 Announce Type: new Abstract: Understanding how deep neural networks make decisions remains a fundamental challenge. We present NObSP (Nonlinear Oblique Subspace Projections), a fram
arXiv:2609.18084v1 Announce Type: cross Abstract: Fine-tuning a Vision-Language-Action (VLA) model for a new deployment environment is expensive, yet most methods apply uniform-capacity adapters to ev
arXiv:2609.17890v1 Announce Type: new Abstract: Large reasoning models (LRMs) generate long chain-of-thought traces before answering, creating significant inference overhead. Pruning can reduce this c
arXiv:2609.18432v1 Announce Type: new Abstract: Extensive occlusions in real-world scenarios pose challenges to gait recognition due to missing and noisy information, as well as body misalignment in p
Hello, I'm at the old pro plan. With the upcoming cloud model retirement of deepseek v4 0731 flash in mind because 4.1 is supposed to be more efficient while providing even better results I remembered
arXiv:2609.17942v1 Announce Type: new Abstract: The problem of identifiability in linear parametric models (LPMs) whose nodes follow either an ordered logit model or a regular one-parameter exponentia
arXiv:2609.17633v1 Announce Type: new Abstract: The Graph Coloring Problem (GCP) is NP-hard and DSATUR stands as one of the fastest heuristics for it despite producing colorings that typically use mor
OpenAI Group PBC today launched Astra for Law, a version of its GPT-6 Astra model set up for legal research and drafting. Astra for Law is not a new model. The company has wrapped GPT-6 Astra in a leg
OpenAI: OpenAI launches Astra for Law, combining GPT-6 Astra with a legal search index and instructions for legal analysis and writing, initially for select law firms — Our most powerful model, config
arXiv:2609.18605v1 Announce Type: cross Abstract: As corporate AI adoption continues to grow, enterprise-grade LLM agents are being deployed into sensitive contexts such as hiring, healthcare, and fin
arXiv:2609.19143v1 Announce Type: cross Abstract: Intelligent systems that act in the world require image understanding that is both comprehensive and spatially grounded. Current vision-language model
arXiv:2505.23126v5 Announce Type: replace Abstract: Although many benchmarks evaluate the reasoning abilities of Large Language Models (LLMs) within domains such as mathematics, coding, or data wrangl
arXiv:2609.18329v2 Announce Type: new Abstract: Remote sensing recognition is often constrained by scarce observations of rare targets and costly annotations, making realistic synthetic augmentation p
arXiv:2609.18120v1 Announce Type: cross Abstract: AI-driven penetration testing has been demonstrated with premium frontier models such as GPT-4, but the per-engagement token cost makes continuous, au
Perhaps the most important warning I ever issued was this, to the US Senate, May 2023: “A month after GPT-4 was released, OpenAI released ChatGPT plug-ins, which quickly led others to develop somethin
arXiv:2609.18861v1 Announce Type: new Abstract: Adaptive learning systems commonly formulate learning path planning as Exercise-Centric (EC) recommendation, where the next step is inferred from item-l
arXiv:2609.18025v1 Announce Type: cross Abstract: Strong chromospheric absorption lines such as Halpha 6562.8 A and Ca II 8542.1 A provide vital diagnostics of plasma dynamics and thermal structure in
arXiv:2505.03590v2 Announce Type: replace-cross Abstract: Magnetic resonance spectroscopy (MRS) is a non-invasive technique to measure the metabolic composition of tissues, offering valuable insights
arXiv:2609.18440v1 Announce Type: new Abstract: Lindsey et al. (2025) report that Claude 3.5 Haiku plans rhymes: features for candidate rhyme words are active on the newline before a line is written,
arXiv:2609.19113v1 Announce Type: new Abstract: We evaluate six frontier language models on the two-agent log(N)-Questions game. A questioner sees N Wikipedia lead paragraphs and must identify a secre