research

FLASH: Efficient Impact Fall Detection with Unified Hypergraph State-Space Model

arXiv:2607.25791v1 Announce Type: new Abstract: Falls represent a critical public health challenge, and accurate detection of the impact moment when an individual hits the ground is crucial for timely

Research

FORGE: Frame Orthogonality in Relevance Geometry for Long-Form Video Understanding

DGX agent

arXiv:2607.25266v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have enabled long-form video understanding at a scale that was not previously possible. However, the density of

researcharxiv-cs-cv

29 Jul 2026

Forgetting Is Not a Fix: Path Dependence in Sequential Engram Editing

arXiv:2607.24805v1 Announce Type: cross Abstract: AI Engram (Kwon et al., 2026) formalizes the four engram criteria of neuroscience as a constrained inverse problem in weight space and solves it close

Foundation Models for EEG Are Blind to Long-Range Temporal Correlations: A Spectral-Temporal Dissociation Behind Their Cross-Population Fragility

arXiv:2607.24834v1 Announce Type: cross Abstract: Objective. Electroencephalography (EEG) foundation models (FMs) are trained to reconstruct or contrastively align short patches, then pooled into a fi

FREPix: Frequency-Heterogeneous Flow Matching for Pixel-Space Image Generation

arXiv:2605.06421v2 Announce Type: replace Abstract: Pixel-space diffusion has re-emerged as a promising alternative to latent-space generation because it avoids the representation bottleneck introduce

Freq-RemoteVAR: Next-Frequency Autoregressive Modeling for Remote Sensing Change Detection

arXiv:2607.25815v1 Announce Type: new Abstract: Remote sensing change detection aims to identify land-cover changes from bi-temporal images. Most existing methods follow a one-shot dense prediction pa

From Training to Deployment: Post-Hoc Causal Feature Identification via Sensitivity Ratios

arXiv:2607.25546v1 Announce Type: new Abstract: Given a model that is already trained, which features does it rely on causally versus spuriously? Existing methods require access to the training proced

Fundamental Recovery Bounds for SPAD Signals under Stationary Flux

arXiv:2601.07599v4 Announce Type: replace Abstract: Single-photon avalanche diodes (SPADs) record light as a discrete stream of individual detections. The signal is stochastic. Its statistical structu

FunnelAL: Retrieve-then-Rank Active Learning for Single-Class Discovery

arXiv:2607.25276v1 Announce Type: new Abstract: We present FunnelAL, a retrieve-then-rank active learning system for single-class discovery, which adapts the multi-stage funnel architecture of industr

Game AI Not Fun? A Scoping Review and Meta-Analysis on the Differences in Enjoyment between Human and Computer Opponents

arXiv:2607.24749v1 Announce Type: cross Abstract: Although advancements in game character AI aim to enhance player engagement, evidence suggests that perceiving an opponent as artificial can diminish

Generative Distributionally Robust Optimization

arXiv:2607.24983v1 Announce Type: cross Abstract: Generative models are increasingly adopted in distributionally robust optimization (DRO), but existing approaches trade off model compatibility and ad

Generator-Aligned Representation Interfaces for Diagnostic Soft Equivariance

arXiv:2607.25988v1 Announce Type: new Abstract: Exact-equivariant architectures typically encode prescribed group actions in specialized operators, which can complicate their reuse with generic backbo

GLIDE: Guided Layerwise Hybrid Attention for Efficient LLM Inference

arXiv:2607.24788v1 Announce Type: new Abstract: As Large Language Models scale to increasingly long contexts, the memory I/O and computational overhead of the Key-Value (KV) cache during decoding emer

Gradient-Based Latent Decomposition Reveals Mechanisms of Feature Degradation in Weakly Supervised Mammography

arXiv:2607.24835v1 Announce Type: new Abstract: Weakly supervised hierarchical models exhibit a persistent asymmetry: coarse lesion-type features are preserved under reconstruction while fine-grained

Grounded in Consensus, In Step With Emerging Science: A Consensus-Anchored Multi-Corpus Clinical Chatbot for Long COVID

arXiv:2607.25038v1 Announce Type: cross Abstract: Long COVID (LC) poses a challenge for clinical decision support because relevant evidence is distributed across sources with different update cycles,

Guiding Posterior Exploration with Optimizer-Derived Geometry

arXiv:2607.25312v1 Announce Type: new Abstract: Sampling-based methods offer a principled approach to uncertainty quantification in Bayesian neural networks. Their practical use, however, is often cha

HeAD-CP: Heterophily-Aware Diffused Conformal Prediction Sets for Graph Neural Networks

arXiv:2607.25273v1 Announce Type: new Abstract: Conformal prediction (CP) provides distribution-free uncertainty quantification, and its extension to graphs is an active research direction. Diffused A

HeatACO: A Heatmap-Guided Max--Min Ant System for Large-Scale Travelling Salesman Problems

arXiv:2601.19041v2 Announce Type: replace-cross Abstract: Non-autoregressive neural solvers predict an edge-confidence heatmap for the Travelling Salesman Problem (TSP) in one forward pass, but a deco

HOLODECK 2.0: Vision-Language-Guided 3D World Generation with Editing

arXiv:2508.05899v3 Announce Type: replace Abstract: 3D scene generation plays a crucial role in gaming, artistic creation, virtual reality, and many other domains. However, current 3D scene design sti

HOME: Robust Hough-space Matching Method for Structured and Textureless Videos

arXiv:2607.25389v1 Announce Type: new Abstract: Visual front-ends for robotic localization typically rely on point-based features such as Oriented FAST and Rotated BRIEF (ORB), which frequently fail i

Human-in-the-Loop Signature Bootstrapping for UAV Hyperspectral PFM-1 Mine Detection

arXiv:2607.25310v1 Announce Type: new Abstract: Hyperspectral imaging (HSI) is useful for material discrimination, but operational mine screening also depends on how many false alarms must be inspecte

Image Quality Dependent Degradation for AI Systems

arXiv:2607.25736v1 Announce Type: cross Abstract: Perception is one of the primary applications where neural networks outperform conventional algorithms. One example is AI systems for automated drivin

Improving Human-Robot Teamwork in Urban Search and Rescue Through Episodic Memory of Prior Collaboration

arXiv:2606.18836v2 Announce Type: replace-cross Abstract: Effective human-robot teamwork requires robots to adapt to partners, situations, and task dynamics from the start of an interaction. In the MA

Input-Aware Dynamic Backdoor Attack Against Quantum Neural Networks

arXiv:2607.11843v2 Announce Type: replace-cross Abstract: Quantum Neural Networks (QNNs) are a promising framework for quantum machine learning on near-term quantum devices, but their security risks r

Input Shaping for Point-to-Point Motion with a Continuum Robot Arm

arXiv:2607.25071v1 Announce Type: new Abstract: A cable-driven continuum robot arm is an underactuated mechanism and may suffer residual vibration at the end of a rest-to-rest maneuver. In this work,

researcharxiv-cs-ro

Intrinsic and Triangulation-Agnostic Attention: A Simple and Powerful Approach for Learning on Meshes

arXiv:2607.24954v1 Announce Type: cross Abstract: This work proposes an adaptation of the attention mechanism for triangle meshes. The core observation is that endowing the attention mechanism with cr

JKO-RAG: Distributional Retrieval as Wasserstein Free-Energy Gradient Flow

arXiv:2607.24776v1 Announce Type: cross Abstract: RAG pipelines return a ranked list of passages. We argue this is a mismatch: the downstream language model conditions on a set, and the selection prob

Knowledge-Guided Multimodal Reasoning over Interacting Streams for Video-Level Ambivalence and Hesitancy Recognition

arXiv:2607.25961v1 Announce Type: cross Abstract: Ambivalence and hesitancy (A/H) are conflicting affective states that precede the delay or abandonment of health behaviour change. Recognition of A/H

KQFuzz: Knowledge-Guided Fuzzing for Quantum Libraries via Large Language Models

arXiv:2607.25647v1 Announce Type: cross Abstract: As quantum computing continually improves, ensuring the reliability and correctness of quantum libraries has become increasingly critical. To this end

Language as a Material Interface for Creative LLM Interaction

arXiv:2607.24753v1 Announce Type: cross Abstract: Although directive prompting is the predominant way to interact with Large Language Models (LLMs), many creative practices rely on language that is op

researcharxiv-cs-cl

Lantern: Conflict-Aware Gradient Blending for Physics-Guided Diffusion Models in Calorimeter Simulation

arXiv:2607.25060v1 Announce Type: cross Abstract: Monte Carlo simulation of calorimeter showers is a principal bottleneck for the High-Luminosity LHC, and diffusion models have emerged as fast, high-f

Latent Stability Analysis of Malware Representations Under Feature-Space Perturbations

arXiv:2607.24896v1 Announce Type: cross Abstract: Static malware detectors are commonly evaluated using clean-sample metrics such as accuracy, F1, ROC AUC, and PR AUC. However, these metrics provide l

Leak-Free Cross-Validated Stacking with Per-Architecture Calibration for Sand-Boil Segmentation in Earthen Levees

arXiv:2607.25367v1 Announce Type: new Abstract: Sand boils, points where water seeping beneath an earthen levee re-emerges at the surface, are early warnings of internal erosion, and deep segmentation

LENS: Adaptive Spatio-Temporal Zooming for Keyframe Sampling in Long-Form Videos

arXiv:2607.25125v1 Announce Type: new Abstract: Despite rapid progress in Multi-modal Large Language Models (MLLMs), understanding long-form videos is still bottlenecked by limited context windows. Wh

Less is More: Modality-Decoupling for General AIGC Audio-Video Detection

arXiv:2607.25543v1 Announce Type: cross Abstract: Generative AI has rapidly expanded audio-visual forgery beyond human-centric deepfakes into general scenes. Existing AIGC detection methods assume aud

Leveraging Semantic Maps for City-Scale Cross-View Localization

arXiv:2607.25215v1 Announce Type: cross Abstract: We want robots to localize in previously untraversed environments against commonly available prior data. Rich semantic data available from OpenStreetM

LivingArena: Do LLMs Know What Other LLMs Don't? Peer-Probing as Scalable Evaluation

arXiv:2607.24780v1 Announce Type: new Abstract: Evaluating frontier LLMs is challenging: static benchmarks suffer from contamination and saturation -- leaving users unable to distinguish top models an

Localizing Persona Representations in LLMs

arXiv:2505.24539v4 Announce Type: replace-cross Abstract: We present a study on how and where personas -- defined by distinct sets of human characteristics, values, and beliefs -- are encoded in the r

Long-Term PM2.5 Forecasting Using a DTW-Enhanced CNN-GRU Model

arXiv:2510.22863v2 Announce Type: replace-cross Abstract: Reliable long-term forecasting of PM2.5 concentrations is critical for public health early-warning systems, yet existing deep learning approac

Loss Invariance Determines What Concept Layers Encode: Volume Grounding in Echocardiography

arXiv:2607.25748v1 Announce Type: new Abstract: Objective: Concept bottleneck models route prediction through interpretable intermediate variables, and their validity is normally judged by how accurat

Machine Learning the H-theorem

arXiv:2508.14003v4 Announce Type: replace-cross Abstract: The H-theorem provides a microscopic foundation for the Second Law of Thermodynamics and therefore occupies a central place in statistical phy

Matrix-Free Photoacoustic Image Reconstruction via Sensor-Token Self-Attention

arXiv:2607.25576v1 Announce Type: new Abstract: Photoacoustic tomography (PAT) combines the optical absorption contrast of biological tissue with the spatial resolution of ultrasound, yet recovering t

Measuring and Improving Behavioral Consistency in Large Language Models through Fact-Heuristic-Emotion State Enforcement

arXiv:2607.24765v1 Announce Type: cross Abstract: Large language models (LLMs) can give different answers to the same decision problem across runs, and reverse a decision when their own prior answer r

Measuring the State of Open Science in Transportation Using Large Language Models

arXiv:2601.14429v2 Announce Type: replace-cross Abstract: Open science initiatives have strengthened scientific integrity and accelerated research progress across many fields, but the state of their p

MemLens: A Value-Aware Memory Management System with Interactive Analytics for LLM-based Agents

arXiv:2607.25992v1 Announce Type: cross Abstract: Recently, memory management has become a key infrastructure for LLM-based agents, as it directly affects long-horizon reasoning, personalized response

Modular Robotic Catheters for Endovascular Aneurysm Repair

arXiv:2607.25807v1 Announce Type: new Abstract: Fenestrated/Branched endovascular aneurysm repair (FEVAR/BEVAR) require surgeons to navigate catheters and guidewires into various branches of the abdom

researcharxiv-cs-ro

MODUS: Decoder-Only Any-to-Any Modeling of Diverse Modalities

arXiv:2607.25948v1 Announce Type: cross Abstract: Any-to-any models predict any modality from any combination of others within a single network, a formulation used in multimodal vision and vision-lang

Multi-Objective Kinodynamic Motion Planning with Asymptotic Pareto Optimality

arXiv:2607.15508v2 Announce Type: replace Abstract: In this paper, we address the challenge of multi-objective motion planning for systems under kinodynamic constraints. We consider three problem clas

researcharxiv-cs-ro