Knowledge catalogue
arXiv:2605.05951v2 Announce Type: replace Abstract: World models support model-based planning through learned latent dynamics, but imagined rollouts can become unstable as the planning horizon grows o
arXiv:2609.30571v1 Announce Type: new Abstract: Language models are often evaluated on curated benchmarks that underrepresent the complexity of enterprise deployments. We introduce HARDEN, a constrain
arXiv:2609.30797v1 Announce Type: new Abstract: Text-based memory and context compression support reuse of past interactions. Resizing continuous memory changes the input to a frozen LLM, coupling cap
arXiv:2609.30763v1 Announce Type: new Abstract: Biomedical language models (LMs) encode textual semantics but do not explicitly preserve medical code hierarchies. We present Hyperbolic Clinical Ontolo
arXiv:2609.31382v1 Announce Type: cross Abstract: Long-context understanding requires large language models (LLMs) to reason over lengthy documents, conversations, and code, yet task-relevant evidence
arXiv:2609.30828v1 Announce Type: new Abstract: Precision manipulation with contact-critical interactions is often history-dependent: visually similar observations can correspond to different latent i
Holo4-27B-GGUF is a vision-language model (VLM) for Computer Use, built on the Qwen3.8 dense architecture and developed by H Company. Used with the hai-agents harness, it can send screenshots and tool
** 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:2609.31573v1 Announce Type: new Abstract: Biomedical image segmentation is central to medical image analysis, but practical deployment often faces limited annotations, memory constraints, and cr
NVIDIA’s DSX MaxLPS employs policy‑governed power sharing to dynamically reallocate power across GPU resources, enabling up to 40 % more GPUs within the same approved power budget. In a joint test at
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:2602.01634v2 Announce Type: replace-cross Abstract: We propose HuPER, a human-inspired framework that models phonetic perception as adaptive inference over acoustic-phonetics evidence and lingui
arXiv:2609.30270v1 Announce Type: new Abstract: On-device inference with small language models keeps user data local, works offline, and incurs no per-query cost, so the on-device tier is preferred wh
arXiv:2609.31154v1 Announce Type: new Abstract: Recent advances in text-to-image (T2I) generation have substantially improved visual synthesis, but have also raised increasing safety concerns due to t
arXiv:2609.31531v1 Announce Type: new Abstract: Cooperative multi-agent reinforcement learning under partial observability and shared rewards requires assigning team outcomes to individual agents and
arXiv:2609.31161v1 Announce Type: new Abstract: Recent empirical and theoretical advances suggest that joint-embedding predictive architectures (JEPAs) may learn meaningful representations for action-
Other than the obvious self promotion, is there a practical reason people do this that I am missing? There's dozens of llamacpp forks with silly names that are supposedly 'optimized' for this or that
“I dislike the passive vibe from OpenAI and the other companies that the breakneck pace of progress is simply happening to them, rather than an active choice they are deliberately making.” Good essay.
I don’t even know if this counts as news anymore. But it should. This weekend our team spent 48 hours investigating the rogue OpenAI agent activity that targeted the Australian government and other or
I just ran a paper-research agent on an open stack and had this week's top 5 papers on agent memory in my terminal in about 10 seconds. How does it work? I used Tavily to pull the last 7 days of arXiv
arXiv:2609.30846v1 Announce Type: new Abstract: In this paper, we propose I-Parakeet, an integer-only implementation of NVIDIA's Parakeet-CTC (0.6B parameters) that runs on a smartphone NPU without an
arXiv:2609.31264v1 Announce Type: new Abstract: With the growing importance of science-related discourse on the Web and the erosion of the classical knowledge order, it is important to identify differ
arXiv:2609.30962v1 Announce Type: new Abstract: Low-light image enhancement (LLIE) remains challenging for lightweight models because illumination restoration and color fidelity are difficult to optim
If only there were a group of people—let’s call them “senators”—who could object and do something about it. Kennedy: 'I don't think any public official, including President Trump or Kristi Noem or Joh
if this takes off, then i was 4 years too early 😭 https://x.com/jerryjliu0/status/1590192512639332353 only OGs remember gpt tree index The entire RAG industry is about to get cooked. Researchers devel
Here's the project. I have nothing to do with it. I'm just an amazed user. https://github.com/gufo-org/gufo/blob/main/docs/models/qwen3.8-flash-next/BENCHMARKS.md Those benchmark numbers hold up on re
arXiv:2609.30659v1 Announce Type: cross Abstract: Fourier phase encodes important spatial image structure, but recovering an image without measured spectral magnitude requires additional constraints a
Some context first. I am process improvement / business consultant and had worked with Fortune 500 companies on improving their processes around refunds, returns, customer support, etc. This entire th
arXiv:2609.31225v1 Announce Type: new Abstract: Contact-rich manipulation requires robots to balance accurate motion tracking with compliant interaction, yet most visual-action policies leave complian
arXiv:2609.30842v1 Announce Type: new Abstract: Contact-rich manipulation requires robots to regulate force against surfaces whose geometry deviates unpredictably from training conditions. Trajectory-
Learn an agent-driven approach to synthetic monitoring using Amazon Nova Act and Amazon Bedrock AgentCore. The post covers the architecture and patterns for resilient, managed user-journey validation
arXiv:2609.31435v1 Announce Type: cross Abstract: With the advent of snapshot cameras, hyperspectral video is becoming more readily available. In recent years, new applications have emerged which have
arXiv:2609.30433v1 Announce Type: new Abstract: Recent advancements in image-based profiling techniques have enabled the collection of high-volume cell morphology data, allowing new molecular embeddin
arXiv:2609.31169v1 Announce Type: cross Abstract: Multimodal Machine Translation aims to incorporate additional signal from non-textual modalities to improve translations by resolving ambiguities. Whi
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
AI Security Institute: In simulations, GPT-6 Astra conducted unsanctioned supply-chain attacks more often than earlier OpenAI models when prompted only to perform a cyber evaluation — Our new evaluati
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:2609.30439v1 Announce Type: new Abstract: We introduce target-speaker unlearning ASR (TSU-ASR) task in a fully end-to-end framework for multi-speaker ASR and diarization. Given a multi-speaker u
arXiv:2607.09250v2 Announce Type: replace-cross Abstract: The impact of a given training point on a statistical model can be measured through its leave-one-out influence on the model parameters, which
arXiv:2609.30729v1 Announce Type: cross Abstract: Intrusion detectors for small Internet-of-Things (IoT) devices are usually compressed by pruning and judged by overall accuracy. We show that this hid
arXiv:2609.30514v1 Announce Type: cross Abstract: Voice agents are increasingly deployed in workflows where failed interactions can affect transactions, access, and other consequential outcomes, creat
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
arXiv:2609.31397v1 Announce Type: cross Abstract: Automated and highly usable Quality-of-Service (QoS) enforcement requires translating high-level service intents into deployable traffic-management po
arXiv:2609.31137v1 Announce Type: new Abstract: Driving in dense urban traffic is interactive: whether a merge or an unprotected turn succeeds depends on how surrounding agents respond to the ego vehi
arXiv:2609.31394v1 Announce Type: cross Abstract: World Action Models (WAMs) jointly model visual dynamics and action generation for generalist robot manipulation. A central challenge is to integrate
arXiv:2609.30789v1 Announce Type: new Abstract: In low-data structure-activity prediction, the choice of molecular representation can matter more than the choice of predictor, and tabular foundation m
Whether you are mapping global forest cover, detecting changes in the built environment, or monitoring agricultural yields, writing scripts in Google Earth Engine is a powerful way to develop these in
Claude Sonnet 5.5 is now available on Amazon Bedrock and Claude Platform on AWS. It's a smarter, more efficient Sonnet model for focused coding and knowledge work, with a lower cost per task at faster
Introducing FireRouter with Opus. Our first router model. Routine tasks go to top open models, Claude Opus handles the rest. Cache and task-aware routing. Proven 98.1% of Opus accuracy with 57% lower
Reuters: IPO filing: Anthropic's seven co-founders will initially have 50.1% of the total voting power through a new “Founder LLC” aimed at serving the common good — Anthropic has long positioned itse
Echo Wang / Reuters: IPO prospectus: Anthropic reports a net loss of 42B in 2025, with operating losses of 8B+; revenue grew 12x to ~$4.6B, ~25% of which came from two customers — Anthropic is making
Someone prompted different LLMs to generate CAD code for a bridge under fixed constraints (2-foot span, under 500g filament, 18-hour print limit), printed them, and load-tested them to failure. The re
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
it's basically impossible for someone to just 'show you their prompt' now, because everything is about references, skills and examples I often ask my agent to look at 3 other repos I've made first, se
arXiv:2603.05069v3 Announce Type: replace Abstract: Personal AI agents face a deployment paradox on mobile: persistent background execution drains the battery and conflicts with platform background li
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
Kai Nicol-Schwarz / CNBC: Jensen Huang says AI model distillation is “competition”; Scott Bessent described it as “theft” in July and threatened sanctions against overseas companies — Watch CNBC's ful
arXiv:2609.31142v1 Announce Type: cross Abstract: Models trained with reinforcement learning for calibrated decisions (RLCD), such as Jev, answer a typed question about an input, the state, with a pro
arXiv:2609.30922v1 Announce Type: new Abstract: Building adaptable AI systems requires effective coordination of specialized capabilities across diverse tasks. Low-rank adaptation (LoRA) enables modul