All entries

arXiv:2607.19633v1 Announce Type: new Abstract: Despite recent advances in general-purpose robotic manipulation, real-world multi-object clutter remains challenging to handle for today's prevalent app

applicationsarxiv-cs-ro

Research

Leveraging ChatGPT's Multimodal Vision Capabilities to Rank Satellite Images by Poverty Level: Advancing Tools for Social Science Research

DGX agent

arXiv:2501.14546v2 Announce Type: replace-cross Abstract: This paper investigates the novel application of Large Language Models (LLMs) with vision capabilities to analyze satellite imagery for villag

researcharxiv-cs-ai

23 Jul 2026

Leveraging ECRAM for Edge Continual Learning

arXiv:2607.19661v1 Announce Type: cross Abstract: Several edge computing platforms, such as autonomous vehicles and smart sensing devices, need to adapt to dynamic environments in real time by learnin

hardwarearxiv-cs-lg

Leveraging Offline Supervision for Efficient and Generalizable Reinforcement Learning in Large-Scale Vision-Language-Action Models

model-releasesarxiv-cs-ai

arXiv:2607.19399v1 Announce Type: cross Abstract: It is commonly observed that online reinforcement learning (RL) produces better-performing strategies than offline methods across a broad range of per

Lifted Representation Hypothesis in Language Models

arXiv:2607.19360v1 Announce Type: new Abstract: Large language models (LLMs) often answer queries by mapping individual observations to more general rule-like structures. However, it remains unclear h

researcharxiv-cs-ai

Tutorials

Lightweight Person-Place Relation Extraction from Historical Newspapers with Dependency Graphs and Proximity Features

arXiv:2607.19718v1 Announce Type: new Abstract: The HIPE-2026 shared task introduces person-place relation extraction from multilingual historical newspapers as a new evaluation track, classifying the

tutorialsarxiv-cs-cl

Agents

Ling-3.0-flash, the new MoE model from @AntLingAGI, is now free in Nous Portal for the next week! At 124B parameters and 5.1B active, it's q…

Ling-3.0-flash, the new MoE model from @AntLingAGI, is now free in Nous Portal for the next week! At 124B parameters and 5.1B active, it's quick to run and built for agent workloads: coding, search, r

agentsnous-research--x

Local Ai

Lipschitzian SLLNs for random functions

arXiv:2607.20411v1 Announce Type: cross Abstract: We prove strong laws of large numbers for locally Lipschitz functions in the Lipschitz pseudometric. Our results hold under either a topological or a

local-aiarxiv-cs-lg

LISA: Linear-Indexed Sparse Attention for Efficient Long-Context Reasoning

model-releasesarxiv-cs-ai

arXiv:2607.19358v1 Announce Type: new Abstract: Recent advances in long chain-of-thought reasoning models such as DeepSeek-R1 have led to increasingly longer inference context lengths under the test-t

LKValues: Aligning Large Language Models with Sri Lankan Societal Values

model-releasesarxiv-cs-cl

arXiv:2607.20410v1 Announce Type: new Abstract: Value alignment of Large Language Models (LLMs) has been shown to be culturally biased toward Western norms. This results in the mishandling of local va

Agents

LlamaParse can't solve a conjecture, but it can parse this as a PDF 🫡

LlamaParse can't solve a conjecture, but it can parse this as a PDF 🫡 Dinitz-Garg-Goemans conjecture is false. This graph theory problem was open for ~30 years. The graph below has fractional flow cos

agentsjerry-liu--x

Local Causal Structure Learning in the Presence of Latent Variables and Selection Bias

arXiv:2607.19866v1 Announce Type: new Abstract: Discovering the direct causes and effects of a target variable from observational data is a fundamental problem in causal discovery, with broad applicat

safetyarxiv-cs-lg

Local Label-Informed Feature Transfer for Generating Ground-Truth Medical Images: A Comparison of GAN- and Diffusion-Based Approaches

arXiv:2607.18882v1 Announce Type: new Abstract: Validating Explainable Artificial Intelligence (XAI) methods in medical imaging requires ground-truth data with known locations of informative features.

Local Ai

Local Stability and Gaussian Smoothing of Quantized Neural Networks

arXiv:2607.20153v1 Announce Type: new Abstract: We study Gaussian averaging as a smooth surrogate for quantized neural models. Under bounded local oscillation, we derive a local dimension-dependent bo

local-aiarxiv-cs-lg

Tutorials

Logic-Guided Data Extraction with Answer Set Programming and Large Language Models

arXiv:2607.19365v1 Announce Type: new Abstract: When Large Language Models (LLMs) are used for semantic data extraction from unstructured text, producing candidate relational facts from natural langua

tutorialsarxiv-cs-ai

Long-Term Sequential Decision Making under Risk

model-releasesarxiv-cs-ai

arXiv:2607.19914v1 Announce Type: new Abstract: We study finite-horizon MDP planning under root-based (resolute) risk objectives that apply a rank-dependent functional to the distribution of total ret

Local Ai

Look Before You Edit: Attention-Guided Camera Placement and Multi-View Alignment for 3D Gaussian Splatting Editing

arXiv:2607.19777v1 Announce Type: new Abstract: Text-driven 3D scene editing with 3D Gaussian Splatting (3DGS) typically applies a 2D diffusion editor to views rendered from fixed training cameras, li

local-aiarxiv-cs-cv

Tutorials

Look Less, Think Faster: Joint Token-Compute Adaptation for Multimodal LLMs

arXiv:2607.20357v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have recently demonstrated strong performance across vision-language tasks. However, their high inference cost,

tutorialsarxiv-cs-cv

LoRFT: Benchmarking Long-Range Vehicle Trajectory Reconstruction from Fixed Highway Cameras

arXiv:2607.19911v1 Announce Type: new Abstract: Long-range vehicle trajectories provide important spatio-temporal evidence for traffic safety analysis, autonomous driving evaluation, and data-driven t

LTX Desktop v1.1.0 is out: local generation on Apple Silicon, a built-in LoRA library, video extend, and more

model-releasesr-stablediffusion

LTX Desktop v1.1.0 just shipped with some big updates. Apple Silicon Macs can generate video locally now, there's a built-in LoRA/IC-LoRA library you can browse and apply from inside the app with per-

Machine Can Automatically Discover Parametric Functions to Model HEP Data

arXiv:2607.19750v1 Announce Type: cross Abstract: In HEP data analyses, finding an adequate function to model binned data has largely relied on a manual process: guess a functional form by intuition,

researcharxiv-cs-lg

Machine-learned syndrome post-selection for reliable quantum error correction

arXiv:2607.19563v1 Announce Type: cross Abstract: Quantum error correction can be enhanced by post-selecting out runs that are likely to produce a logical failure, but the most accurate measures for t

researcharxiv-cs-lg

Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing

arXiv:2607.19064v2 Announce Type: replace-cross Abstract: Large-scale visual generators are increasingly capable but costly to train, fine-tune, and deploy. We introduce Mage-Flow, a compact 4B-scale

hardwarearxiv-cs-ai

MagicPrompt: Ultra-Lightweight Prompt Tuning for Video Generation

arXiv:2607.14595v2 Announce Type: replace Abstract: Large-scale video diffusion models deliver strong generation performance, but full fine-tuning for downstream tasks incurs prohibitive computational

Making Single-Cell Data Distillation Auditable: Traceable Real-Cell Coresets via Discrete Min-Max Selection

arXiv:2607.19426v1 Announce Type: cross Abstract: Single-cell datasets are increasingly costly to store, audit, and reuse for model training. Dimensionality reduction and dataset distillation can redu

hardwarearxiv-cs-ai

Many still debate open vs closed, and compare cost per token (accounting metric). Better to shift attention to cost per successful task. @se…

model-releasesfireworks-ai--x

Many still debate open vs closed, and compare cost per token (accounting metric). Better to shift attention to cost per successful task. @seldo and the team at @arizeai did so across 2,400 runs. Concl

Marine Engine Fault Dataset: Open-Access Data under Controlled Reference and Fault Scenario Conditions

model-releasesarxiv-cs-lg

arXiv:2607.19444v1 Announce Type: new Abstract: Open-access datasets for marine-engine predictive maintenance remain scarce, particularly those from controlled fault experiments with documented operat

Mark Zuckerberg launches a media campaign positioning the company's AI development as an optimistic, pro-human alternative to its competitors' 'dystopian' ideas (Sara Fischer/Axios)

Sara Fischer / Axios: Mark Zuckerberg launches a media campaign positioning the company's AI development as an optimistic, pro-human alternative to its competitors' “dystopian” ideas — Meta CEO Mark Z

model-releasestechmeme

Masked Visual Actions for Unified World Modeling

arXiv:2607.19343v1 Announce Type: new Abstract: Video models absorb rich priors over how the visual world moves, interacts, and responds to contact, making them promising substrates for robotic world

safetyarxiv-cs-cv

Matching Ranks Over Probability Yields Truly Deep Safety Alignment

arXiv:2512.05518v2 Announce Type: replace-cross Abstract: Open-source Large Language Models (LLMs) play a critical role in the democratization of AI, yet their 'open' nature introduces more avenues fo

safetyarxiv-cs-ai

MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators

arXiv:2607.15273v2 Announce Type: replace Abstract: MeanFlow generators achieve fast few-step sampling by predicting average velocities over time intervals, making them attractive for efficient genera

safetyarxiv-cs-cv

Applications

Measuring LLM Trust Allocation Across Conflicting Software Artifacts

arXiv:2604.03447v2 Announce Type: replace-cross Abstract: LLM-based software engineering assistants often reason over multiple artifacts, including code, documentation, signatures, and tests, even whe

applicationsarxiv-cs-ai

MeetingToM: Evaluating Multimodal LLMs on Theory-of-Mind Reasoning in Multi-Party Meetings

arXiv:2607.19235v1 Announce Type: cross Abstract: Theory of Mind (ToM), the ability to infer other's beliefs, intentions, and states of knowledge, is central to social interaction, yet remains challen

Membership Inference Attacks for Unseen Classes

arXiv:2506.06488v3 Announce Type: replace Abstract: A key tool in developing safe AI models is data auditing, i.e., using statistical tools to determine whether harmful content may have been used in t

safetyarxiv-cs-lg

Memo2496: Expert-Annotated Dataset and Dual-view Adaptive Framework for Music Emotion Recognition

arXiv:2512.13998v4 Announce Type: replace-cross Abstract: Music Emotion Recognition (MER) is constrained by limited expert annotations and the need to establish robustness across heterogeneous corpora

researcharxiv-cs-ai

Memory-Augmented Multimodal Large Language Models for Small Object Understanding in Streaming Aerial Videos

arXiv:2607.19857v1 Announce Type: cross Abstract: Language-guided aerial perception aims to understand user-specified tiny targets in complex unmanned aerial vehicle (UAV) scenes. In real UAV deployme

researcharxiv-cs-ai

Memory Merge DQN: Sensitivity Weighted Target Updates for Stable Value Learning

model-releasesarxiv-cs-lg

arXiv:2607.19397v1 Announce Type: new Abstract: Deep Q-networks use target networks to stabilise bootstrapped value learning, but the standard hard copy update also introduces a tradeoff. Holding the

Meta-Learning Preferences for Multilingual LLM Alignment

arXiv:2607.13315v2 Announce Type: replace Abstract: Unequal availability of human preference data across languages poses a significant challenge for aligning large language models in multilingual sett

safetyarxiv-cs-cl

Milo, a Fully Autonomous Indoor/Outdoor Robotic Guide Dog

arXiv:2607.19530v1 Announce Type: new Abstract: Many Blind and Low-Vision (BLV) people rely on guide dogs for moment-to-moment navigation, such as staying on path and avoiding obstacles and pedestrian

safetyarxiv-cs-ro

Minimize idle accelerators: Native RL job interleaving with co-operative time-slicing in llm-d

The math behind reinforcement learning (RL) post-training for large language models (LLMs) is notoriously unforgiving. As frontier AI labs push the boundaries of reasoning and coding models using RL p

safetygoogle-cloud-ai

MissingBench-Verified: Probing Vision-Language Models' Inability to Detect Missing Object Parts

arXiv:2607.18673v2 Announce Type: new Abstract: Vision Language Models (VLMs) are well known for hallucinating non-existent objects in images. Objects with missing parts present a unique challenge for

Mitigating Modality and Language-Style Gaps for Zero-Shot Video Moment Retrieval

arXiv:2607.19027v1 Announce Type: new Abstract: Zero-shot video moment retrieval aims to overcome the limitations of traditional approaches that require large-scale datasets annotated with text and it

safetyarxiv-cs-cv

Mitigating Scaffolding Collapse in Socratic Tutors via Representation Alignment

arXiv:2607.19371v1 Announce Type: new Abstract: Large language model (LLM)-based Socratic tutors increasingly guide students through multi-turn questioning, but they can suffer from scaffolding collap

safetyarxiv-cs-ai

MoA-Structured Decode Attention DNF Derivation, KV-Cache Accumulation, GQA/MQA, and OpenACC Kernel

arXiv:2607.19456v1 Announce Type: cross Abstract: We derive four memory-optimal inference artifacts for transformer attention using the Mathematics of Arrays (MoA), each following directly from the fo

hardwarearxiv-cs-ai

Applications

MoAKE: Toward Unified All-in-One Action Quality Assessment via Mixture of Action Knowledge Experts

arXiv:2607.19826v1 Announce Type: new Abstract: Action Quality Assessment (AQA) aims to objectively evaluate performance quality from action videos. Most existing methods follow a ``one-by-one'' parad

applicationsarxiv-cs-cv

Model 'distillation' accusations are getting way overblown at this point

model-releasesr-localllama

The news about Anthropic settling a class action lawsuit for 1.5B over training data isn't just a legal headache for them, it's a massive warning sign for engineering teams relying entirely on closed

Model Gateway: Management Platform for Model-Driven Drug Discovery

model-releasesarxiv-cs-lg

arXiv:2512.05462v2 Announce Type: replace-cross Abstract: Pharmaceutical drug discovery demands machine learning (ML) infrastructure that goes beyond general-purpose Machine Learning Operations (MLOps

ModPack: An Extensible Teleoperation Interface for Bimanual Mobile Manipulation

arXiv:2607.19479v1 Announce Type: cross Abstract: Existing teleoperation systems are often tailored to specific robot hardware and task domains, limiting their scalability and adaptability. We present

safetyarxiv-cs-ai