All entries

Nous Research is hosting a livestream featuring team members Karan and Yoni speaking from NVIDIA, likely discussing AI research, model development, or collaboration between Nous Research and NVIDIA. T

hardwarenous-research--x

Safety

Joint Agent Memory and Exploration Learning via Novelty Signals

DGX agent

arXiv:2606.01528v1 Announce Type: new Abstract: In open-ended environments, exploration is fundamental for autonomous agents, yet current language model agents struggle with this. Effective exploratio

safetyarxiv-cs-ai

2 Jun 2026

Jointly Optimizing Debiased CTR and Uplift for Coupons Marketing: A Unified Causal Framework

arXiv:2602.12972v2 Announce Type: replace-cross Abstract: In online advertising, marketing interventions such as coupons introduce significant confounding bias into Click-Through Rate (CTR) prediction

safetyarxiv-cs-lg

JupiterOne launches Continuous Controls Monitoring to test security controls against live asset data

model-releasessiliconangle

Artificial intelligence risk management platform provider JupiterOne Inc. today announced the launch of JupiterOne Continuous Controls Monitoring, a new product that tests whether security and complia

K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts

model-releasesarxiv-cs-cl

arXiv:2606.02404v1 Announce Type: new Abstract: Frontier model evaluations are shifting from foundational capabilities (e.g., instruction following and reasoning) toward compositional, agentic ones, b

KACE: Knowledge-Adaptive Context Engineering for Mathematical Reasoning

arXiv:2606.00532v1 Announce Type: new Abstract: Context engineering can improve large language models without updating their weights, but mathematical reasoning exposes a key limitation: feedback accu

researcharxiv-cs-ai

KDH-CAD: Knowledge-data hybrid CAD learning under data scarcity

arXiv:2606.01702v1 Announce Type: cross Abstract: Deep learning in computer-aided design (CAD) remains fundamentally constrained by the data scarcity challenge: authentic CAD data is difficult to coll

applicationsarxiv-cs-lg

Keeping sensitive data on device while cloud AI adds scale and context, @perplexity_ai @AravSrinivas demonstrates hybrid local server infere…

Perplexity AI demonstrates a hybrid approach to AI inference that combines on-device processing for sensitive data with cloud-based AI services to achieve scalability and contextual understanding. Thi

local-aiperplexity--x

KG-FairDiff: Knowledge Graph-Guided Prompt Refinement for Demographically Fair Text-to-Image Generation

arXiv:2606.01282v1 Announce Type: new Abstract: Text-to-Image (TTI) systems are now everyday infrastructure for journalism, education, advertising, and public communication, and the demographic and cu

safetyarxiv-cs-cv

KG-Guard: Graph-Based Hallucination Detection for Knowledge Base Question Answering

arXiv:2606.00328v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for knowledge base question answering (KBQA), where answering requires selecting entities from a ques

applicationsarxiv-cs-lg

KISS: Keeping it Simple and Slotted when Learning to Communicate over Wireless

arXiv:2606.00266v1 Announce Type: cross Abstract: A long-standing challenge in distributed wireless systems is ensuring efficient and fair random channel access. Existing solutions often address speci

safetyarxiv-cs-lg

KliniskVestBERT: BERT Model Specialised to Norwegian Clinical Texts

arXiv:2606.01904v1 Announce Type: cross Abstract: The increasing application of Natural Language Processing (NLP) in healthcare demands language models specifically attuned to the complexities of clin

Agents

Knowing Isn't Understanding: Re-grounding Generative Proactivity with Epistemic and Behavioral Insight

arXiv:2602.15259v2 Announce Type: replace-cross Abstract: Generative AI agents equate understanding with resolving explicit queries, an assumption that confines interaction to what users can articulat

agentsarxiv-cs-ai

Knowledge-Informed Kernel State Reconstruction from Heterogeneous Partial Observations

arXiv:2601.22328v2 Announce Type: replace Abstract: Real-world scientific systems are rarely observed through complete, regularly sampled state trajectories. Instead, measurements are often partial, n

applicationsarxiv-cs-lg

Knowledge-Intensive Video Generation

arXiv:2606.01285v1 Announce Type: cross Abstract: Text-to-video generation has advanced rapidly in visual quality, but remains under-evaluated for factuality and practical usefulness. We introduce kno

KnowledgeBerg: Evaluating Systematic Knowledge Coverage and Compositional Reasoning in Large Language Models

arXiv:2604.17621v2 Announce Type: replace Abstract: Many real-world questions appear deceptively simple yet implicitly demand two capabilities: (i) systematic coverage of a bounded knowledge universe

KromHC: Manifold-Constrained Hyper-Connections with Kronecker-Product Residual Matrices

model-releasesarxiv-cs-cl

arXiv:2601.21579v2 Announce Type: replace Abstract: The success of Hyper-Connections (HC) in neural networks (NN) has also highlighted issues related to training instability and restricted scalability

LagerNVS: Latent Geometry for Fully Neural Real-time Novel View Synthesis

arXiv:2603.20176v3 Announce Type: replace Abstract: Recent work has shown that neural networks can perform 3D tasks such as Novel View Synthesis (NVS) without explicit 3D reconstruction. Even so, we a

Lagrangian Perturbation Diffusion Steering: Latent Reinforcement Learning for Generative Policies

arXiv:2606.01151v1 Announce Type: new Abstract: Behavior cloning with high-capacity generative policies achieves strong imitation performance, but is often limited by demonstration coverage and distri

safetyarxiv-cs-lg

LALE: Lightweight-Transformer Architecture for Land-Cover Estimation

arXiv:2606.02092v1 Announce Type: cross Abstract: Semantic segmentation of remote sensing imagery requires models that capture both global context and local detail under tight computational budgets. P

Tutorials

{lambda}Split: Self-Supervised Content-Aware Spectral Unmixing for Fluorescence Microscopy

arXiv:2603.23647v2 Announce Type: replace-cross Abstract: In fluorescence microscopy, spectral unmixing aims to recover individual fluorophore concentrations from spectral images that capture mixed fl

tutorialsarxiv-cs-ai

Language-Native Materials Processing Design by Lightly Structured Text Database and Reasoning Large Language Model

arXiv:2509.06093v4 Announce Type: replace-cross Abstract: Materials synthesis procedures are predominantly documented as narrative text in papers, protocols, and laboratory records, placing them beyon

LAP: Fast LAtent Diffusion Planner for Autonomous Driving

model-releasesarxiv-cs-ro

arXiv:2512.00470v4 Announce Type: replace Abstract: Diffusion models have demonstrated strong capabilities for modeling human-like driving behaviors in autonomous driving, but their iterative sampling

Large Electron Model: A Universal Ground State Predictor

arXiv:2603.02346v2 Announce Type: replace-cross Abstract: We introduce Large Electron Model, a single neural network model that produces variational wavefunctions of interacting electrons over the ent

Large Language Model Guided Incentive Aware Reward Design for Cooperative Multi-Agent Reinforcement Learning

arXiv:2603.24324v4 Announce Type: replace-cross Abstract: Designing effective auxiliary rewards for cooperative multi-agent systems remains challenging, as misaligned incentives can induce suboptimal

safetyarxiv-cs-ai

Large Language Models in Transportation Systems Management and Operations: From Text Reasoning to Multi-modal Decision Support

arXiv:2606.00991v1 Announce Type: new Abstract: Transportation systems management and operations (TSMO) increasingly depends on timely interpretation of heterogeneous data, from various sensor streams

local-aiarxiv-cs-ai

Large-scale Uncertainty Quantification for Latent Variable Models Using Subsampling Markov Chain Monte Carlo

arXiv:2606.00309v1 Announce Type: new Abstract: Stochastic gradient Langevin dynamics combined with Gibbs updates (SGLD--Gibbs) provides a highly scalable approach to approximate Bayesian inference in

LASER: Loss-Aware Singular-value Decomposition and Rank Allocation for Efficient Low-Precision Vision-Language Models

arXiv:2606.00573v1 Announce Type: new Abstract: Vision-language models (VLMs) deliver strong multimodal reasoning capabilities, but their large computational cost and high parameter counts make deploy

LaSR: Context-Aware Speech Recognition via Latent Reasoning

model-releasesarxiv-cs-cl

arXiv:2606.00507v1 Announce Type: new Abstract: Recent advances in Speech Large Language Models (Speech LLMs) have significantly enhanced spoken language understanding and reasoning. However, their co

Tutorials

Last Layer Logits to Logic: Empowering LLMs with Logic-Consistent Structured Knowledge Reasoning

arXiv:2511.07910v2 Announce Type: replace Abstract: Large Language Models (LLMs) achieve excellent performance in natural language reasoning tasks through pre-training on vast unstructured text, enabl

tutorialsarxiv-cs-cl

LastAct: Trajectory-Guided Latest-Activity Localization for Real-Time Smart-Home Activity Recognition

arXiv:2606.00260v1 Announce Type: new Abstract: Human Activity Recognition (HAR) from ambient sensors enables smart-home applications such as health monitoring and assisted living. In realistic deploy

Agents

Latent Collaboration in Multi-Agent Systems

arXiv:2511.20639v3 Announce Type: replace-cross Abstract: Multi-agent systems (MAS) extend large language models (LLMs) from independent single-model reasoning to coordinative system-level intelligenc

agentsarxiv-cs-ai

Latent Diffusion Pretraining for Crystal Property Prediction

arXiv:2606.00776v1 Announce Type: new Abstract: Fast and accurate prediction of crystal properties is a central challenge in new materials design. Graph neural networks and Transformer-based models ha

local-aiarxiv-cs-lg

Latent Reasoning in TRMs is Secretly a Policy Improvement Operator

arXiv:2511.16886v5 Announce Type: replace-cross Abstract: Recently, small models with latent recursion have obtained promising results on complex reasoning tasks. These results are typically explained

safetyarxiv-cs-ai

Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs

arXiv:2606.00726v1 Announce Type: new Abstract: Strong reasoning depends not only on model knowledge but also on how effectively cognitive behaviors are deployed during generation. Existing methods of

researcharxiv-cs-ai

Law professors wrote questions they were asked during office hours. Gemini 2.5 & humans answered them then other law professors blindly judg…

model-releasesethan-mollick--x

Law professors wrote questions they were asked during office hours. Gemini 2.5 & humans answered them then other law professors blindly judged the results: -Gemini had a 75% win rate vs. professors -G

Hardware

LayerRoute: Input-Conditioned Adaptive Layer Skipping via LoRA Fine-Tuning for Agentic Language Models

arXiv:2606.01838v1 Announce Type: cross Abstract: Agentic language model systems alternate between two structurally distinct step types: structured tool calls (short, deterministic, low perplexity) an

hardwarearxiv-cs-ai

Leaf Spectral Reflectance Prediction Using Multi-Head Attention Neural Networks

arXiv:2606.01432v1 Announce Type: new Abstract: Accurate modeling of leaf spectral reflectance from physiological and biochemical traits is essential for advancing remote sensing applications in plant

researcharxiv-cs-lg

LeAP: Learnable Adaptive Permutation for Feature Selection in Heterogeneous and Sparse Recommender Systems

arXiv:2606.01111v1 Announce Type: new Abstract: Modern industrial recommender systems rely on thousands of heterogeneous features -- ranging from low-dimensional scalars (e.g., statistical value) to h

Agents

LeARN: Learnable and Adaptive Representations for Nonlinear Dynamics in System Identification

arXiv:2412.12036v2 Announce Type: replace Abstract: System identification, the process of deriving mathematical models of dynamical systems from observed input-output data, has undergone a paradigm sh

agentsarxiv-cs-lg

Learning Action-Conditional and Object-Centric Gaussian Splatting World Models for Rigid Objects

arXiv:2606.01950v1 Announce Type: cross Abstract: World models enable intelligent agents to predict the consequences of their actions on the environment. In this paper, we propose Multi Rigid Object G

Learning-based Directed Graph Abstraction of Combinatorial Spaces for Order-Preserving Search in Mixed-Combinatorial Nonlinear Optimization

arXiv:2606.01425v1 Announce Type: new Abstract: Mixed-combinatorial nonlinear programming (MCNLP) problems arise in many engineering design and planning applications, e.g., due to categorical, compone

Learning Chaotic Dynamics through Second-Order Geometric Supervision

arXiv:2606.01596v1 Announce Type: cross Abstract: Learning chaotic dynamical systems from data requires more than short-term predictive accuracy: the learned model must preserve the attractor geometry

local-aiarxiv-cs-lg

Learning Discriminative and Generalizable Anomaly Detector for Dynamic Graph with Limited Supervision

arXiv:2602.20019v2 Announce Type: replace-cross Abstract: Dynamic graph anomaly detection is critical for many real-world applications but remains challenging due to the scarcity of labeled anomalies.

applicationsarxiv-cs-ai

Learning from Saturated Data: Signals Beyond Correctness for LLM Training

arXiv:2606.01436v1 Announce Type: new Abstract: The growing capabilities of large language models (LLMs) have led to the saturation of many benchmarks and training datasets used to improve them. Motiv

researcharxiv-cs-cl

Learning Hamiltonian Dynamics at Scale: A Differential-Geometric Approach

arXiv:2509.24627v2 Announce Type: replace Abstract: Embedding physical intuition into network architectures allows the learning of dynamics that enforce fundamental properties, such as energy conserva

researcharxiv-cs-lg

Learning Implicit Bias in Generative Spaces for Accelerating Protein Dynamics Emulation

arXiv:2606.01833v1 Announce Type: cross Abstract: Generative emulators of protein dynamics produce plausible trajectories at a fraction of the cost of molecular dynamics, but they inherit their traini

Learning Label-Efficient Interpretable Medical Image Diagnosis via Semi-supervised Hypergraph Concept Bottleneck Model

arXiv:2606.01698v1 Announce Type: new Abstract: Deep learning has revolutionized medical image analysis, delivering exceptional diagnostic accuracy across diverse applications. Yet, the lack of interp