Knowledge catalogue
arXiv:2609.03577v1 Announce Type: new Abstract: Language models are commonly discussed as technical artefacts, but they are obviously shaped by the linguistic worlds conveyed by data during their trai
arXiv:2609.04194v1 Announce Type: new Abstract: Reasoning traces from chain-of-thought models appear to offer a legible window into how a model arrives at its answer. A growing body of work treats the
arXiv:2609.03330v1 Announce Type: new Abstract: Moral language plays a central role in shaping online endorsement and the diffusion of information, yet existing moral foundation detection systems ofte
arXiv:2609.03426v1 Announce Type: new Abstract: Transformers lack a native lookup mechanism, requiring repeated dense computation to recognize and reuse local static patterns. Lngram v1 introduces tok
arXiv:2508.00935v3 Announce Type: replace-cross Abstract: Computer-using agents (CUAs), which can autonomously control computers to perform multi-step actions, might pose significant safety risks if m
arXiv:2609.03261v1 Announce Type: cross Abstract: A benchmark score credits final answers, but not the route by which an item can be answered. In medical multimodal multiple-choice questions (MCQs), t
arXiv:2609.03026v1 Announce Type: cross Abstract: Mechanistic interpretability is increasingly used to guide interventions such as activation steering, circuit removal, and safety monitoring. Yet an i
arXiv:2609.03293v1 Announce Type: new Abstract: Personalized assistants should not only comply with user requests but also assess whether those requests are appropriate given the user's current circum
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:2609.04022v1 Announce Type: cross Abstract: Aligning large language models (LLMs) is essential for their safe deployment. Current alignment methods mainly optimize observable responses, yet mode
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:2609.03235v1 Announce Type: new Abstract: Large language models (LLMs) face severe memory bottlenecks in long-context inference due to the linearly growing size of key-value (KV) caches. Existin
arXiv:2609.04167v1 Announce Type: cross Abstract: Repository-level software engineering benchmarks have significantly advanced the evaluation of coding agents, but existing benchmarks primarily measur
I got access to GPT-6 Astra this afternoon, so naturally I used it to generate SVGs of pelicans riding bicycles - at low, medium, high, xhigh and max reasoning levels (Astra doesn't support reasoning=
arXiv:2609.03410v1 Announce Type: new Abstract: Idiomatic expressions are an integral part of natural language, reflecting cultural nuances and posing unique challenges for computational models, parti
arXiv:2609.03938v1 Announce Type: new Abstract: While HTN planning has received significant attention in recent years, support for numerical reasoning remains very limited. In this paper, we investiga
arXiv:2609.03797v1 Announce Type: new Abstract: Long-term human-AI interaction is difficult because the information that guides inference is updated implicitly by the model and is not directly inspect
I'm one of the developers. We said in August it would go open source in September and it did last night. MIT or Apache-2.0, pick one. The repo you see is our internal repo, kernels included, so from n
arXiv:2609.04061v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to edit existing code, but correctness alone is not enough: useful repairs should also be minimal,
arXiv:2410.15184v2 Announce Type: replace-cross Abstract: As trajectories sampled by policies used by reinforcement learning (RL) and generative flow networks (GFlowNets) grow longer, credit assignmen
arXiv:2505.22451v2 Announce Type: replace Abstract: Large Reasoning Models (LRMs) have made significant progress in mathematical capabilities in recent times. However, these successes have been primar
arXiv:2609.02414v1 Announce Type: cross Abstract: Multi-turn jailbreak attacks demonstrate that harmful intent can be distributed across dialogue, yet existing methods obscure what conversational mech
arXiv:2410.10136v2 Announce Type: replace-cross Abstract: In customer contact centers, human agents often struggle with long average handling times (AHT) due to the need to manually interpret queries
arXiv:2609.02172v1 Announce Type: new Abstract: Optimization-based jailbreak attacks such as Greedy Coordinate Gradient (GCG) achieve strong effectiveness and transferability by optimizing adversarial
arXiv:2609.02131v1 Announce Type: cross Abstract: Sentiment in social-media threads does not only vary across posts; it shifts as users react to claims, corrections, evidence, and hostility within a b
arXiv:2609.02459v1 Announce Type: new Abstract: We present CivBench, an open-source benchmark for evaluating language model agents in long-horizon, tool-mediated environments through the Model Context
arXiv:2609.02496v1 Announce Type: new Abstract: Model compression techniques such as pruning and quantization facilitate the efficient deployment and acceleration of Large Language Models (LLMs). Howe
arXiv:2609.02885v1 Announce Type: new Abstract: Recent web agents use world models for test-time action selection by sampling candidate actions, predicting the resulting web states, and ranking them w
arXiv:2606.17350v2 Announce Type: replace-cross Abstract: Recent advances in large language models (LLMs) have enabled the generation of high-quality prose, yet whether these models are capable of gen
arXiv:2609.01873v1 Announce Type: new Abstract: Multi-agent AI systems improve inference by spawning agents and synthesizing reports. But another agent is not another observation: apparently independe
arXiv:2609.01878v1 Announce Type: new Abstract: Activation steering suppresses undesired behaviors in language models by adding a steering vector to the hidden state during generation. Recent conditio
arXiv:2609.02015v1 Announce Type: new Abstract: Instruction-tuning data are judged by quality metrics, and tuned models are judged by benchmarks, but both judgments pass through an output interface: t
arXiv:2609.01687v1 Announce Type: new Abstract: Grounded question answering systems should answer only when the supplied evidence supports the answer. In multi-hop QA, this requirement is difficult be
Meet E-Commerce Bench, a new benchmark for long-horizon autonomous business operations. 🚀 Agents start with ¥100,000 to run online stores for 365 days, handling sourcing, negotiation, pricing, promoti
arXiv:2609.01612v1 Announce Type: cross Abstract: We introduce MESSY STREETS, a benchmark for evaluating geocoders on verbatim web addresses, with existence verification and controlled measurement of
arXiv:2609.02060v1 Announce Type: new Abstract: Mineral exploration requires integrating heterogeneous geochemical, geophysical, and geological evidence, yet existing prospectivity systems often provi
arXiv:2609.02057v1 Announce Type: new Abstract: Reliable web-agent monitoring is difficult when model-internal uncertainty signals such as token logits are unavailable. In this work, we study prefix-l
Nvidia is announcing its new Personal AI Router (PAIR), a free tool that syncs up your home computers for tackling local AI inference tasks with tools like Ollama and LM Studio. Let's get the obvious
arXiv:2609.02158v1 Announce Type: cross Abstract: Legal Judgment Prediction (LJP) models are typically trained on documents that describe facts from a prosecutorial perspective. Existing datasets furt
Portable Computer is now available on Linux for @NVIDIA RTX GPUs with 24GB of VRAM or higher. Today we’re launching Portable Computer on @NVIDIA DGX Spark. Portable Computer is a fully local version o
arXiv:2609.02480v1 Announce Type: new Abstract: Synthetic dialogue generation can support research in privacy-restricted service settings, but generated conversations must preserve communicative inten
arXiv:2609.01671v1 Announce Type: cross Abstract: Security teams and researchers choose knowledge-graph extraction tooling for threat reports on the strength of published triple-F1 scores, yet those s
arXiv:2609.02292v1 Announce Type: new Abstract: The rapid proliferation of large language models (LLMs) and the growing diversity of their applications presents a unique optimization opportunity: sele
arXiv:2609.02011v1 Announce Type: cross Abstract: Large language model question answering over power-grid models must respect a fixed context budget. We introduce seed-anchored graph rendering, a dete
arXiv:2609.02203v1 Announce Type: cross Abstract: Time series representation learning (TSRL) has attracted growing research interests in recent years. Two recent explorations in TSRL are: i) exploitin
arXiv:2609.02440v1 Announce Type: cross Abstract: Adversarially robust models often overfit to a specific attack budget, necessitating multiple specialized models for diverse and dynamic adversarial e
arXiv:2609.02861v1 Announce Type: cross Abstract: Autonomous robots powered by deep learning face a fundamental auditability challenge: when incidents occur, investigators cannot reconstruct why the s
arXiv:2607.17952v2 Announce Type: replace Abstract: Climate disclosure classification is a fundamental task for analysing corporate climate disclosures, yet such disclosures appear in many different s
arXiv:2609.01315v1 Announce Type: new Abstract: Building an omni-modal foundation model means evaluating it across text, image, video, and audio. Excellent evaluation toolkits exist for each modality,
arXiv:2609.00322v1 Announce Type: cross Abstract: Can an artificial intelligence (AI) generate a scientific hypothesis outside a human collaborator's active hypothesis space (AHS), and can human-AI re
arXiv:2609.00572v1 Announce Type: cross Abstract: Enterprise artificial intelligence is increasingly embedded in decisions that must remain lawful, explainable, adaptable, and accountable despite pers
arXiv:2609.01045v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities as powerful components in agentic systems, enabling sophisticated reasoning and c
arXiv:2609.00818v1 Announce Type: new Abstract: We argue that financial report generation should operate at the analytical rather than structural level, composing content from data-derived insights ra
arXiv:2609.01187v1 Announce Type: cross Abstract: A single vulnerability in a widely used library can cascade through millions of dependent applications, yet more than half of vulnerability database e
arXiv:2609.00763v1 Announce Type: new Abstract: Hierarchical Knowledge graph (KG)-based retrieval augmented generation (RAG) has emerged as a powerful approach for supporting large language models wit
arXiv:2609.01209v1 Announce Type: cross Abstract: Crystal generators and tool-using agents propose structures faster than density functional theory (DFT) energy and phonon calculations or experiments
arXiv:2609.00874v1 Announce Type: new Abstract: As agentic systems become compound systems, increasingly important decisions move above task execution itself: when should a higher-level controller pre
arXiv:2512.11199v2 Announce Type: replace Abstract: Computer-aided design (CAD) defines 3D models as compact, precise, and editable representations, making it directly useful for several fields. Recen
arXiv:2609.01352v1 Announce Type: cross Abstract: Role-playing large language models (LLMs) are expected to adopt a character's style while also respecting that character's knowledge boundaries. Prior
arXiv:2609.00967v1 Announce Type: new Abstract: As large language models increasingly act through external tools, deciding when to call a tool has become a central problem alongside deciding how to us