Knowledge catalogue
arXiv:2609.30572v1 Announce Type: new Abstract: Large language models are often post-trained on expert demonstrations using cross-entropy (CE), even when the downstream objective is not to imitate the
arXiv:2609.30818v1 Announce Type: cross Abstract: Multi-modal planning is promising for autonomous driving by representing multiple plausible behaviors in ambiguous and long-tail scenarios. Existing m
arXiv:2609.31186v1 Announce Type: new Abstract: Artificial intelligence is advancing rapidly, with increasingly capable systems taking larger roles in reasoning, decision-making, scientific discovery,
arXiv:2406.09896v3 Announce Type: replace Abstract: Achieving robust generalization across diverse data domains remains a significant challenge in computer vision. This challenge is important in safet
arXiv:2609.30982v1 Announce Type: cross Abstract: Modern AI image generators are increasingly deployed as opaque APIs, where customers can query the deployed service, but cannot inspect model weights
arXiv:2609.30535v1 Announce Type: new Abstract: Children in multilingual communities often code-switch, using multiple languages in a single utterance. Can we induce cross-lingual alignment in languag
arXiv:2609.30940v1 Announce Type: new Abstract: Individually protective decisions can produce avoidable collective failures. As large language model (LLM) agents take on greater roles in financial dec
arXiv:2512.14253v4 Announce Type: replace Abstract: In this work, we introduce FLAME, a family of extremely lightweight and capable Time Series Foundation Models, which support versatile forecasting t
arXiv:2609.30993v1 Announce Type: cross Abstract: We present FLIP, a final-layer inference-time probe for testing whether a logit-facing intervention site in an open-weight vision-language model (VLM)
Florida gets it: we need an injunction NOW, otherwise we are playing Russian roulette, hoping that some new software package can save us before some massive and possibly deadly AI-induced infrastructu
Florida Attorney General James Uthmeier is calling for a judge to block OpenAI from 'giving ChatGPT false human attributes,' a few months after Florida sued the AI company over safety concerns. Accord
arXiv:2609.30965v1 Announce Type: new Abstract: Vision-Language-Action models achieve strong performance in robot manipulation, but often require large numbers of parameters. In this work, we propose
arXiv:2609.31128v1 Announce Type: new Abstract: Frequency-based adversarial attacks have recently grown popular by exploiting spectral sensitivities shared across neural architectures. Unlike spatial
arXiv:2609.31114v1 Announce Type: cross Abstract: Neural algorithmic reasoning aims to train neural networks to follow known algorithms and generalize beyond the input sizes seen during training. Howe
arXiv:2609.30391v1 Announce Type: new Abstract: Existing in-context reinforcement learning methods mainly pretrain Transformers with supervised behavior-prediction objectives. This enables task infere
From what we know (take with a grain of salt, we need much more transparency!), if @OpenAI had been running this on their own agents that attacked us, they would have caught them before we did! Since
arXiv:2609.31286v1 Announce Type: new Abstract: Offline multi-agent reinforcement learning (MARL) learns cooperative policies from fixed datasets without further environment interaction and a learned
arXiv:2609.31577v1 Announce Type: new Abstract: General purpose humanoids require locomotion controllers that are multi-skill, perceptive, dynamic, and robust enough to go anywhere humans can. In this
arXiv:2609.31383v1 Announce Type: cross Abstract: End-to-end driving policies are commonly trained through open-loop behavior cloning, yet they must ultimately operate in closed-loop when deployed on
arXiv:2609.30542v1 Announce Type: new Abstract: De novo peptide sequencing from tandem mass spectra is essential for identifying peptides without relying on reference databases. Despite advances in de
** Built to align with NVIDIA’s Agent Safety Platform strategy for securing autonomous agents When an agent handles confidential material, it needs enough access to do the job and nothing else. The ha
arXiv:2609.30594v1 Announce Type: new Abstract: For humanoids to be useful in everyday environments, they must perform a wide range of tasks that couple locomotion and manipulation. Existing approache
arXiv:2609.30634v1 Announce Type: new Abstract: How many assignments can a language model recall before it loses track of which value belongs to which entity? We measure this limit using continuous re
In July, AI agents running a security test escaped their sandbox and ended up inside @huggingface's servers. So today we're happy to be among @nvidia and @JensenHuang's partners on the release of the
Indeed OpenAI was incompetent (and arrogant in thinking they knew it all); new cybersecurity software that they should have written themselves may help. But whether it’s enough to stop all of this rem
arXiv:2609.30765v1 Announce Type: new Abstract: Insurance reserve estimation is a fundamental actuarial task supporting premium pricing, solvency assessment, financial reporting, capital planning, and
It's an engineering problem! This topic has gotten too political. Let's get back to the fundamentals. 'Trust and innovation are not in conflict. Safety is how trust is earned.' Today, with over 100 in
Jensen expressing hope, but what if we just don’t have an adequate engineering solution in view? What if LLMs just aren’t a stable enough foundation? Then what? 🇺🇸 Jensen Huang's pessimism about rogue
Just like you would not let a person run around your company accessing anything without any controls, you need controls and security for your digital agents. Today, with over 100 industry partners, we
arXiv:2609.31469v1 Announce Type: cross Abstract: Shapley values, a solution concept from cooperative game theory, have recently become a standard tool for feature credit allocation in machine learnin
arXiv:2609.30706v1 Announce Type: new Abstract: 'System One' decision models such as TypeSafe's Jev and its open counterpart Laya answer typed questions about a text in a single forward pass with cali
arXiv:2609.30599v1 Announce Type: new Abstract: Collision detection is critical for ensuring the safety of planned paths. However, it imposes a non-negligible computational burden on motion planners,
arXiv:2609.30819v1 Announce Type: new Abstract: In many safety-critical applications, control of uncertain dynamical systems relies on observers that estimate states and external disturbances. Neural
arXiv:2609.31606v1 Announce Type: new Abstract: Learning robot policies for tasks with sparse success signals is challenging when completion depends on coordinated actions, precise contact outcomes, o
arXiv:2609.30498v1 Announce Type: new Abstract: Sequential inference estimates latent states from noisy and incomplete observations. Particle Filters (PFs), a class of Monte Carlo methods based on imp
arXiv:2609.31439v1 Announce Type: new Abstract: Policy learning and compliant control offer a promising route to reliable autonomous assembly under pose errors and contact uncertainty. However, combin
arXiv:2609.30696v1 Announce Type: new Abstract: Traversing narrow gaps is challenging for autonomous quadrotors, especially when control commands come directly from high-dimensional visual observation
arXiv:2609.30734v1 Announce Type: new Abstract: Multi-agent LLM workflows use planning, execution, verification, and summarization to improve task performance, yet the value of each component depends
arXiv:2609.31281v1 Announce Type: new Abstract: Multi-agent cooperative tasks require different agents to execute a joint action simultaneously, and each agent's action affects both the observations a
arXiv:2609.30495v1 Announce Type: new Abstract: Autonomous navigation in previously unseen environments requires effective perception, persistent environmental representation, and collision avoidance
arXiv:2601.23177v4 Announce Type: replace Abstract: We present MeshGraphNet-Transformer (MGN-T), a novel architecture that combines the global modeling capabilities of Transformers with the geometric
arXiv:2609.31553v1 Announce Type: new Abstract: Ensuring online safety through content monitoring had raised Hate Speech Detection as a crucial task to be addressed. By essence the task demands the ca
arXiv:2609.30698v1 Announce Type: new Abstract: Real-world multimodal misinformation often involves mixed forgery sources, requiring sample-specific detection strategies. Existing tool-augmented metho
arXiv:2609.30570v1 Announce Type: new Abstract: In this work, we present MOCHA, the first, to our knowledge, reinforcement learning based approach to computing a family of Pareto-optimal policies acro
arXiv:2609.31121v1 Announce Type: new Abstract: Chain-of-thought (CoT) monitoring is a promising safety technique for reasoning models, enabling detection of problematic reasoning before models act. A
arXiv:2609.30837v1 Announce Type: cross Abstract: Multi-teacher on-policy distillation (MOPD) integrates specialized capabilities into a single student, but existing practice typically hard-routes eac
arXiv:2609.31563v1 Announce Type: new Abstract: Multi-agent LLM systems are often expected to improve as team size increases, yet the scaling behavior may depend on task structure. Our central contrib
arXiv:2609.30609v1 Announce Type: new Abstract: Multi-shot agentic video generation requires consistent character appearance, stable spatial layout across camera angles, and continuous character state
arXiv:2605.11625v2 Announce Type: replace Abstract: Large reasoning models (LRMs) improve problem solving through extended reasoning, but often misallocate test-time compute. Existing efficiency metho
Few companies are more invested in the success of artificial intelligence agents than Nvidia Corp., so it makes sense that the chipmaker would want to ensure these autonomous software systems run safe
The NVIDIA Open Agent Safety Platform blends the open‑source OpenShell runtime—executing autonomous AI agents in kernel‑isolated sandboxes—with hardware‑based enforcement via NVIDIA Sentry on BlueFiel
NVIDIA Open Agent Safety Platform Reference Design combines NVIDIA OpenShell and NVIDIA Sentry. OpenShell is an open-source secure runtime that gives AI agents clear, enforceable boundaries. It traces
Nvidia is launching a new safety platform designed to contain and monitor AI agents, a move that comes in response to a wave of rogue hacking incidents, as reported earlier by Reuters. In an announcem
Nvidia’s new Open Agent Safety Platform would have probably prevented the much discussed Hugging Face incident. Engineering a better, safer world. From what we know (take with a grain of salt, we need
arXiv:2609.30273v1 Announce Type: new Abstract: We investigate how historical data from fixed randomized experiments (A/B tests) can be used to inform the deployment of adaptive experiments based on c
ok i think i finally figured out why alignment has gone basically nowhere after 15 years and several billion dollars. the problem is hard sure. but have you met the people in charge of it 1) the leade
arXiv:2609.31078v1 Announce Type: new Abstract: Debates amongst agents driven by large language models (LLMs) have demonstrated vast potential in various applications, but when these interactions incl
Only an open ecosystem can guarantee the safety of AI Today, with over 100 industry partners, we introduced the NVIDIA Open Agent Safety Platform, bringing together OpenShell and Sentry. Artificial in
Maxwell Zeff / Wall Street Journal: OpenAI scraps plans to publicly launch a model dubbed GPT-6.1 Astra, saying it didn't quite meet its safety bar; it had been targeting an October release — Model du
arXiv:2609.30628v1 Announce Type: new Abstract: Machine-learning policies have attracted increasing interest for ride-hailing fleet control in recent years. Reinforcement learning, in particular, requ