All entries

Injecting Hallucinations in Autonomous Vehicles: A Component-Agnostic Safety Evaluation Framework

arXiv:2510.07749v2 Announce Type: replace Abstract: Perception failures in autonomous vehicles (AV) remain a major safety concern because they are the basis for many accidents. To study how these fail

safetyarxiv-cs-ro

Safety

INSIDE the Student's Mind: Jointly Modeling Latent Reasoning and Action in LLM Student Simulators

DGX agent

arXiv:2608.10492v1 Announce Type: new Abstract: Large Language Model (LLM)-based simulators often reproduce observable actions but fail to capture the underlying reasoning behind them. In education, w

safetyarxiv-cs-ai

12 Aug 2026

InSight-doc: Agentic Visual Perception for Long-Document Understanding

model-releasesarxiv-cs-cl

arXiv:2608.10628v1 Announce Type: cross Abstract: Long-document understanding often requires reasoning over many visually rich pages, making inference costly and prone to context rot. In this work, we

Interesting research suggests caution in determining which AI company is winning by looking at any one source.. OpenRouter seems to show ope…

model-releasesethan-mollick--x

Interesting research suggests caution in determining which AI company is winning by looking at any one source.. OpenRouter seems to show open weights winning over time, but work submitted to Pangram i

Interpreting Language Model Hidden States at Scale

arXiv:2608.10260v1 Announce Type: new Abstract: Lens methods interpret large language models (LLMs) by mapping intermediate activations to the output vocabulary, revealing how next-token predictions d

InterPruner: Interactive Structured Pruning via Taylor-Implicit Criterion and Language-Prior Modulator for Multimodal Object Detection

arXiv:2608.10724v1 Announce Type: new Abstract: Multimodal object detection proves effective in remote sensing, especially the RGB-Infrared paradigm. The parallel feature extractors provide rich multi

Intrinsic Structure: Spectral Identifiability for Mechanistic Interpretability

arXiv:2608.10172v1 Announce Type: new Abstract: Mechanistic interpretability explains models by identifying circuits inside them, but has no way to tell whether a circuit is a property of the model or

Introspective Attention Modulation for Safe Text-to-Image Generation

model-releasesarxiv-cs-cv

arXiv:2607.14945v2 Announce Type: replace Abstract: State-of-the-art flow based text-to-image (T2I) models exhibit remarkable generative abilities but remain vulnerable to producing unsafe content. Pr

Invertible Logits Transformation for Accuracy-Preserving Post-Hoc Uncertainty Calibration

arXiv:2608.10372v1 Announce Type: new Abstract: Post-hoc calibration aligns a classifier's predicted confidences with its empirical accuracy without retraining. An ideal calibrator should correct nonl

IO Factory: Simulating AI-Enabled Influence Campaigns at Scale

arXiv:2608.10920v1 Announce Type: new Abstract: We introduce IO Factory, an AI-driven framework for simulating information and influence campaigns as fully integrated, traceable processes. The threat

safetyarxiv-cs-ai

Hardware

Is the future of AI selling hardware for Open Source/Models?

I’m not super knowledgeable of the entire AI industry, but as we see this industry grow and the Cold War that is happening between the US and China on AI development, I can’t help but notice what US c

hardwarer-localllama

Is There Really a Camouflaged Object? Towards Realistic Camouflaged Object Detection

model-releasesarxiv-cs-cv

arXiv:2608.11135v1 Announce Type: new Abstract: Camouflaged object detection (COD) aims to segment objects that are visually concealed in their surroundings and has attracted increasing attention in r

Is This Your Final Answer? Cross-Contextual Consistency as a Measure of LLM Credibility

arXiv:2608.10315v1 Announce Type: cross Abstract: Large language models (LLMs) are powerful black-box systems, making it difficult to discern whether their answers reflect stable internal beliefs or s

Iterative Erasure Count Is Not an Affine-Invariant Concept Dimension

arXiv:2608.10566v1 Announce Type: cross Abstract: How many directions does a neural representation use to encode a concept? A common answer repeatedly erases probe directions and reports the stopping

JEPA-WAM: Stage-Level Joint-Embedding Prediction for World-Action Models in Robot Manipulation

arXiv:2608.10780v1 Announce Type: new Abstract: Generalist robot policies aim to map multimodal observations and linguistic task instructions to actions across diverse tasks. However, existing methods

local-aiarxiv-cs-ro

Applications

JitTrack: Onboard Multi-Object Tracking Against Viewpoint Jitter for Agile UAVs

arXiv:2608.10485v1 Announce Type: new Abstract: Multi-object tracking (MOT) onboard agile unmanned aerial vehicles (UAVs) remains challenging due to severe viewpoint jitter induced by camera ego-motio

applicationsarxiv-cs-ro

KKL Observer Synthesis for Nonlinear Systems via Physics-Informed Learning

arXiv:2501.11655v3 Announce Type: replace-cross Abstract: This paper proposes a novel learning approach for designing Kazantzis-Kravaris or nonlinear Luenberger (KKL) observers for autonomous nonlinea

Knowledge-Guided 3D CT Generation: A Conditioning-Centric Taxonomy

arXiv:2608.09992v1 Announce Type: cross Abstract: Controllable generation guided by external knowledge is a key requirement in modern generative deep learning applications, enabling the synthesis of s

LaViT: Aligning Latent Visual Thoughts for Multi-modal Reasoning

arXiv:2601.10129v2 Announce Type: replace-cross Abstract: Current multimodal latent reasoning often relies on external supervision (e.g., auxiliary images), ignoring intrinsic visual attention dynamic

Learning Disease-Sensitive Latent Interaction Graphs From Noisy Cardiac Flow Measurements

arXiv:2602.23035v2 Announce Type: replace Abstract: Cardiac blood flow patterns contain rich information about disease severity and clinical interventions, yet current imaging and computational method

researcharxiv-cs-lg

Learning Gaussian Structure: Intervention-Guided Density Control for Feed-Forward Driving Reconstruction

arXiv:2608.11077v1 Announce Type: new Abstract: Feed-forward Gaussian reconstruction has recently emerged as an efficient approach for driving scene reconstruction. However, prevailing LiDAR-based met

local-aiarxiv-cs-cv

Learning in ImaginationLand: Omnidirectional Policies through 3D Generative Models (OP-Gen)

arXiv:2509.06191v2 Announce Type: replace-cross Abstract: Recent 3D generative models, which are capable of generating full object shapes from just a few images, now open up new opportunities in robot

safetyarxiv-cs-cv

Tutorials

Learning Representations from Incomplete EHR Data with Dual-Masked Autoencoding

arXiv:2602.15159v2 Announce Type: replace Abstract: Electronic health records (EHR) arrive masked. Clinicians order measurements selectively, and any patient table thus contains only a subset of the v

tutorialsarxiv-cs-lg

LEGO: Leveled Language Gaussian Splatting

arXiv:2608.10057v1 Announce Type: new Abstract: We introduce LEGO for advanced open-vocabulary scene understanding. Beyond basic concept recognition, its core innovation lies in capturing the intrinsi

Lesion-Aware Adaptive Fourier Neural Operator for CT-to-PSMA PET Synthesis in Prostate Cancer

arXiv:2608.10429v1 Announce Type: new Abstract: Deep learning models that synthesize PET from CT or MRI can reduce patient dose and scanner demand, but are typically optimized with global losses such

local-aiarxiv-cs-cv

Leveraging Human Reading Behavior for Keyphrase Extraction: A Webcam-based Eye-tracking Corpus

arXiv:2608.10688v1 Announce Type: new Abstract: Purpose: Keyphrases are statistically and semantically important textual units that can also attract readers' attention during comprehension. However, e

researcharxiv-cs-cl

Leveraging Large Language Models for Causal Discovery: a Constraint-based, Argumentation-driven Approach

arXiv:2602.16481v2 Announce Type: replace Abstract: Causal discovery seeks to uncover causal relations from data, typically represented as causal graphs, and is essential for predicting the effects of

safetyarxiv-cs-ai

Applications

Lights, inference, action… I’m so happy to share that @sequoia has led the Seed in @previewio. Developers are flying in magical AI-nat…

applicationssonya-huang--x

***Lights, inference, action…*** I’m so happy to share that @sequoia has led the Seed in @previewio. Developers are flying in magical AI-native editors. But creative tooling is still stuck in the pre-

Tutorials

Link-adaptive digital twin for robust physical-layer modeling in hybrid-amplified ultra-wideband optical networks

arXiv:2608.10517v1 Announce Type: cross Abstract: Accurate physical-layer modeling is increasingly essential for reliable ultra-wideband operation and capacity optimization, especially under the inten

tutorialsarxiv-cs-lg

Lipschitz Dueling Bandits over Continuous Action Spaces

arXiv:2604.00523v2 Announce Type: replace Abstract: We study for the first time, stochastic dueling bandits over continuous action spaces with Lipschitz structure, where feedback is purely comparative

researcharxiv-cs-lg

LiquidAI/LFM2.5-VL-3B · Hugging Face

LFM2.5-VL-3B is a multimodal variant of LFM2.5, a family of hybrid models designed for on-device deployment. It builds on LFM2-VL-3B with further mid- and post-training. LFM2.5-VL-3B can process both

local-air-localllama

Agents

LLM Agents Factory: Retrieval of Domain-Specific LLM Agents

arXiv:2608.09934v1 Announce Type: cross Abstract: Large language model (LLM) agents improve task performance by decomposing problems into role-specialized behaviors. However, their practical deploymen

agentsarxiv-cs-ai

LLMs Encode Their Failures: Predicting Success from Pre-Generation Activations

arXiv:2602.09924v4 Announce Type: replace-cross Abstract: Running LLMs with extended reasoning on every problem is expensive, but determining which inputs actually require additional compute remains c

safetyarxiv-cs-ai

Local AI is exploding! Transformers.js, that we've been building @huggingface for the past three years has now become the most popular open-…

Local AI is exploding! Transformers.js, that we've been building @huggingface for the past three years has now become the most popular open-source library to run AI models directly in your browser and

local-aiclem-delangue--x

Locally Deployable Small Language Models for Emergency Department Decision Support: A Systematic Benchmark of Fine-Tuning Strategies

arXiv:2608.10273v1 Announce Type: cross Abstract: Deploying large language models (LLMs) for decision support in emergency departments (EDs) faces two major challenges: privacy risks of transmitting p

Logit-Boundary Geometric Belief Interfaces and Sparse Sheaf-Enclave Protocols: A Self-Contained Substrate for Secure Network Electronic Health Record (EHR) Interoperability

arXiv:2608.10300v1 Announce Type: new Abstract: Electronic health-record interoperability is a boundary problem: legacy systems, generative models, terminology services, identity systems, and human re

Logit Lens Supervision for Patch-Level Explanations in Vision-Language Models

arXiv:2602.01530v2 Announce Type: replace Abstract: Modern autoregressive Vision-Language Models (VLMs) can generate fluent answers while their visual-token representations become weakly tied to the i

Tutorials

Long-Horizon AI Research for Grothendieck Constant: A Case Study in Human-AI Mathematical Collaboration

arXiv:2608.11195v1 Announce Type: new Abstract: AI agents are increasingly used in mathematics research, but it is often unclear how to use them effectively. Towards this, we present an extensive case

tutorialsarxiv-cs-ai

Long-Time Trajectory Approximation via SA-NODEs: Model Predictive and Floquet Strategies

arXiv:2608.10738v1 Announce Type: new Abstract: We study the approximation of dynamical systems by semi-autonomous neural ordinary differential equations (SA-NODEs) over long time horizons. For a sing

Longitudinal 3D Foundation Modeling for Neoadjuvant Breast Cancer Response Prediction from Serial DCE-MRI

arXiv:2608.09991v1 Announce Type: cross Abstract: Pathologic complete response (pCR) is an important endpoint in neoadjuvant chemotherapy (NAC) for breast cancer, and predicting pCR from imaging durin

Longitudinal Evidence That General-Purpose Chatbots Actively Foster Relational Engagement

arXiv:2608.10672v1 Announce Type: cross Abstract: Social interaction has become one of the most common uses of LLMs, yet research on emotional bonds with AI has focused largely on how users experience

LoRCA: LoRA Cycle Adaptation for Histology to HiP-CT Translation with DINOv3

arXiv:2608.10002v1 Announce Type: cross Abstract: Hierarchical Phase-Contrast Tomography (HiP-CT) is a synchrotron based X-ray imaging technique that enables non-destructive, volumetric imaging of int

safetyarxiv-cs-cv

Lost in Reconstruction: Aligning Action Representations with Language in Vision-Language-Action Models

arXiv:2608.10484v1 Announce Type: cross Abstract: Action verbs describe not only the physical outcomes of actions, but also how those actions are performed. Yet action representations in vision-langua

MAD-HOI: Masked Autoregressive Diffusion for Generating Articulated Hand Object Interactions from Text

model-releasesarxiv-cs-cv

arXiv:2608.10162v1 Announce Type: new Abstract: Methods for text-based generation of hand-object interaction (HOI) sequences primarily focus on producing smooth, physically plausible trajectories. A t

Applications

MammoMix: Leveraging Mixture of Experts for Robust Mammogram Breast Detection

arXiv:2608.10437v1 Announce Type: new Abstract: Breast lesion detection in mammography remains a challenging task due to variations in image quality, lesion appearance, and population demographics acr

applicationsarxiv-cs-cv

MAP-Graph: Provenance-Aware Shared Memory for Multi-Agent Workflows

arXiv:2608.10509v1 Announce Type: new Abstract: Shared memory helps language-model agents reuse information across long workflows, yet relevant evidence may not be admissible for a particular agent or

Mapping and Measuring the Behavioral Evolution of Large Language Models

model-releasesarxiv-cs-cl

arXiv:2608.11027v1 Announce Type: cross Abstract: Benchmark leaderboards summarize how well a language model performs, but not how its behavior relates to that of other models or changes across genera

MARCO: Click-Intent Decomposition for Calibrated Ads Conversion Prediction

arXiv:2608.10562v1 Announce Type: new Abstract: Not all clicks are equal. Industrial ads ranking decouples conversion probability into click-through rate (CTR) and post-click conversion rate (CVR), ye

safetyarxiv-cs-lg