Knowledge catalogue
arXiv:2609.32529v1 Announce Type: new Abstract: Open-prompt detectors allow users to specify targets with text, visual exemplars, or both. We argue that existing designs underuse the visual modality i
arXiv:2609.32493v1 Announce Type: new Abstract: Distillation enables student language models to acquire new capabilities from expert teachers. However, integrating knowledge from multi-teacher, multi-
arXiv:2609.34598v1 Announce Type: new Abstract: Video temporal grounding (VTG) aims to localize the video interval corresponding to a language query. Recent large vision-language models (LVLMs) show g
arXiv:2609.33685v1 Announce Type: new Abstract: Artificial Intelligence (AI) models for temporal multimodal data have potential in healthcare and agriculture, but their opacity can limit trust and ado
arXiv:2609.33548v1 Announce Type: new Abstract: Fine-tuning anguage models (LLMs) with first-order optimizers requires a memory several times larger than that required for inference. Memory-efficient
arXiv:2609.35035v1 Announce Type: new Abstract: The integration of artificial intelligence into computer-aided design frameworks has sparked a shift in the design of analog integrated circuits (ICs),
arXiv:2609.32939v1 Announce Type: new Abstract: Multi-agent systems built on large language models (LLMs) are largely homogeneous, as their agents behave alike even across distinct LLMs. We show that
arXiv:2609.32591v1 Announce Type: cross Abstract: Data-driven model predictive control (MPC) combines learned world models with online trajectory optimization, achieving strong performance in continuo
arXiv:2609.33109v1 Announce Type: new Abstract: Grounding is a core capability of spatial vision-language models, yet most existing work focuses only on where a referred object is. Many 3D tasks also
arXiv:2306.00206v3 Announce Type: replace Abstract: Embedding models, often obtained via self-supervised learning, extract general-purpose representations from data. Quantifying the reliability of the
arXiv:2609.32573v1 Announce Type: new Abstract: On-policy distillation (OPD) is a promising approach to language-model adaptation, aligning teacher supervision with the student's own generated traject
arXiv:2609.32244v1 Announce Type: new Abstract: Gait recognition always remains challenging due to severe overfitting and the rigid view constraints common in single-stage approaches. We propose a two
arXiv:2609.31900v1 Announce Type: new Abstract: Modern LLM post-training composes supervised fine-tuning (SFT), reinforcement learning with verifiable rewards (RLVR), and on-policy distillation (OPD)
arXiv:2609.34639v1 Announce Type: new Abstract: We study approximate sampling: given N independent samples from a proposal distribution mu, the goal is to select one whose distribution is close to a t
arXiv:2609.35134v1 Announce Type: new Abstract: Video editing has advanced substantially in recent years, with methods increasingly accounting for the visual consequences of edits, such as changes to
arXiv:2609.32918v1 Announce Type: cross Abstract: Vision-language models (VLMs) are increasingly being used in scientific workflows, but their ability as agents to directly control laboratory experime
arXiv:2609.32002v1 Announce Type: cross Abstract: The rank r in LoRA is widely treated as a capacity control: a smaller rank is assumed to yield a simpler model that generalizes better. We show that,
arXiv:2606.16353v2 Announce Type: replace Abstract: Streaming video understanding models must answer queries at any moment during an ongoing stream, using only what they have observed so far and under
arXiv:2609.33220v1 Announce Type: new Abstract: Outcome-based reinforcement learning can produce models with similar task performance but very different ways of communicating about their mistakes. We
arXiv:2609.32489v1 Announce Type: cross Abstract: In tri-modal visual question answering (VQA), auxiliary text is commonly used to complement visual and textual inputs, yet its reliability is often un
arXiv:2609.34861v1 Announce Type: new Abstract: Visual token pruning has been widely studied as a practical approach to reducing the computational cost of large vision-language models. However, it str
arXiv:2609.35630v1 Announce Type: cross Abstract: Massive activation features (MAs) in Transformers are extreme-value residual-stream features that persist across layers despite the model's ability to
arXiv:2609.34159v1 Announce Type: cross Abstract: World models infer latent states of an environment to capture its underlying dynamics and predict future evolution. Many real-world environments, howe
arXiv:2609.32457v1 Announce Type: new Abstract: Transformers process information strictly forward through depth, preventing deeper computation from revisiting and refining earlier representations. To
Hello everyone! A little while back I posted about LlamAmpere, a fork of Llama.cpp with Ampere-specific improvements (though it is caught up to main and will support other hardware, too). Thank you to
arXiv:2609.30642v1 Announce Type: cross Abstract: As Large Language Models (LLMs) become integrated into software development workflows, concerns regarding unintentional biases in AI-generated code. A
arXiv:2609.31358v1 Announce Type: cross Abstract: The Model Context Protocol (MCP) provides a common interface through which AI applications discover and use external resources and tools. It allows la
arXiv:2609.30733v1 Announce Type: new Abstract: Text-to-image generation has advanced in controlling what, where, and how objects appear, yet how visual attention is distributed among objects remains
arXiv:2609.30454v1 Announce Type: new Abstract: Non-generative 'System-1' models return structured probabilistic decisions in a single forward pass, without autoregressive decoding, at a small fractio
arXiv:2609.31546v1 Announce Type: new Abstract: Electrocardiogram (ECG) foundation models typically tokenize the signal into fixed-length patches that ignore cardiac structure, so a patch may split a
arXiv:2609.30341v1 Announce Type: new Abstract: Data Spaces enable sovereign and governed data sharing across organizational boundaries, but their integration with AI agents remains challenging due to
arXiv:2609.30884v1 Announce Type: new Abstract: Large language models rely on KV caching to reduce repeated prefill computation in long context and interactive applications. As lightweight adapters ev
arXiv:2609.30650v1 Announce Type: cross Abstract: Task performance need not determine which intervention mechanism an agent retains. We study causal retention: whether a frozen learned state answers a
arXiv:2609.30345v1 Announce Type: cross Abstract: Cloud-security investigation is dominated by population tasks: which identities can read a data store, how many resources fail a control, which assets
arXiv:2609.31272v1 Announce Type: cross Abstract: AI is becoming increasingly integrated into daily workflows, especially in computing. We are gradually shifting towards an AI-rich future, an impendin
arXiv:2609.31568v1 Announce Type: new Abstract: AI tutoring could markedly improve learning outcomes for students in developing regions such as Vietnam, yet the two obvious paths both fall short. Clou
arXiv:2605.05725v2 Announce Type: replace Abstract: Time-series anomaly detection often returns scores or intervals, while analysts need to understand the abnormal behavior and the evidence supporting
arXiv:2607.11347v2 Announce Type: replace Abstract: Neural networks increasingly inform consequential decisions, making their reliability increasingly important. Yet their internal mechanisms provide
arXiv:2608.00008v2 Announce Type: replace Abstract: The local deployment of large language models (LLMs) is gaining traction due to privacy concerns and the desire for on-premise inference. However, t
arXiv:2609.31071v1 Announce Type: new Abstract: Corr2Cause asks whether a causal claim holds in every DAG compatible with observed correlations and conditional independencies. We frame this as latent-
arXiv:2602.09163v2 Announce Type: replace Abstract: Scientific knowledge bases accelerate discovery by curating findings from primary literature into structured, queryable formats for both human resea
arXiv:2609.31450v1 Announce Type: cross Abstract: Medical vision-language model (VLM) post-training is commonly evaluated through answer accuracy. We examine how changes in accuracy and training objec
** 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:2609.30270v1 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
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
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
I've liked how Muse-Glimmer worked, so I wanted to see if I could produce a smaller 'kid' out of it. Ornith's sharp decisions on when to think and which tool to call were the other thing I liked, so O
arXiv:2609.31122v1 Announce Type: new Abstract: Activation steering is a powerful training-free paradigm for controlling large language models at inference time. However, standard approaches estimate
arXiv:2609.30939v1 Announce Type: new Abstract: Cognitive behavioral therapy (CBT) is an evidence-based first-line treatment for depression, yet its scale is constrained by the time clinicians spend o
Apple Silicon Macs on macOS 26+ come with a small LLM built in. No download, no API key, and nothing leaves your Mac. Why I built it I was making a tool that writes API docs from code, and I didn't wa
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:2609.30837v1 Announce Type: cross Abstract: Multi-teacher on-policy distillation (MOPD) integrates specialized capabilities into a single student, but existing practice typically hard-routes eac
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
Model Developer: NVIDIA Corporation Model Development: Fine-tuned from NVIDIA-Nemotron-3-Ultra-550B-A55B What is Nemotron? NVIDIA Nemotron™ is a family of open models with open weights, training data,
arXiv:2609.31364v1 Announce Type: new Abstract: Predicting human gaze is a core capability for applications ranging from web/UI design analysis to robotics and human-computer interaction. Yet, most vi
arXiv:2506.02015v4 Announce Type: replace Abstract: Recent advances in Multimodal Large Language Models (MLLMs) have enabled unified multimodal understanding and generation. However, they still strugg
arXiv:2609.30337v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) mitigates knowledge obsolescence and factual hallucination in large language models by introducing external context
arXiv:2609.30661v1 Announce Type: new Abstract: The main result presented is a formula for the population loss in the student-teacher kernel model that is applicable to shallow ReLU networks with bias
arXiv:2609.30554v1 Announce Type: new Abstract: Large language models (LLMs) have recently demonstrated promising capabilities as in-context policy optimizers for Reinforcement Learning (RL), enabling
https://preview.redd.it/23cumykhabsh1.png?width=944&format=png&auto=webp&s=0b1d1c437fc845169f521b31793e2b1325dab0dd Reminder that you can put Qwen 3.8 27B as a subagent and its a workhorse. Pic: using