Search: “research”

Fast-SegSim: Real-Time Open-Vocabulary Segmentation for Robotics in Simulation

arXiv:2604.10951v1 Announce Type: new Abstract: Open-vocabulary panoptic reconstruction is crucial for advanced robotics and simulation. However, existing 3D reconstruction methods, such as NeRF or Ga

researcharxiv-cs-ro

FatigueFusion: Latent Space Fusion for Fatigue-Driven Motion Synthesis

DGX agent

arXiv:2604.10199v1 Announce Type: cross Abstract: Investigating the impact of fatigue on human physiological function and motor behavior is crucial for developing biomechanics and medical applications

researcharxiv-cs-lg

14 Apr 2026

FF3R: Feedforward Feature 3D Reconstruction from Unconstrained views

arXiv:2604.09862v1 Announce Type: new Abstract: Recent advances in vision foundation models have revolutionized geometry reconstruction and semantic understanding. Yet, most of the existing approaches

FlowBind: Efficient Any-to-Any Generation with Bidirectional Flows

arXiv:2512.15420v2 Announce Type: replace Abstract: Any-to-any generation seeks to translate between arbitrary subsets of modalities, enabling flexible cross-modal synthesis. Despite recent success, e

FlowHijack: A Dynamics-Aware Backdoor Attack on Flow-Matching Vision-Language-Action Models

arXiv:2604.09651v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models are emerging as a cornerstone for robotics, with flow-matching policies like pi_0 showing great promise in generatin

FM-SIREN & FM-FINER: Implicit Neural Representation Using Nyquist-based Orthogonality

arXiv:2509.23438v3 Announce Type: replace Abstract: Existing periodic activation-based implicit neural representation (INR) networks, such as SIREN and FINER, suffer from hidden feature redundancy, wh

From Attribution to Action: A Human-Centered Application of Activation Steering

arXiv:2604.11467v1 Announce Type: new Abstract: Explainable AI (XAI) methods reveal which features influence model predictions, yet provide limited means for practitioners to act on these explanations

From Perception to Planning: Evolving Ego-Centric Task-Oriented Spatiotemporal Reasoning via Curriculum Learning

arXiv:2604.10517v1 Announce Type: new Abstract: Modern vision-language models achieve strong performance in static perception, but remain limited in the complex spatiotemporal reasoning required for e

From Pixels to Digital Agents: An Empirical Study on the Taxonomy and Technological Trends of Reinforcement Learning Environments

arXiv:2603.23964v2 Announce Type: replace Abstract: The remarkable progress of reinforcement learning (RL) is intrinsically tied to the environments used to train and evaluate artificial agents. Movin

From Redaction to Restoration: Deep Learning for Medical Image Anonymization and Reconstruction

arXiv:2604.11376v1 Announce Type: cross Abstract: Removing patient-specific information from medical images is crucial to enable sharing and open science without compromising patient identities. Howev

From Speech-to-Spatial: Grounding Utterances on A Live Shared View with Augmented Reality

arXiv:2602.03059v2 Announce Type: replace-cross Abstract: We introduce Speech-to-Spatial, a referent disambiguation framework that converts verbal remote-assistance instructions into spatially grounde

GaNI: Global and Near Field Illumination Aware Neural Inverse Rendering

arXiv:2403.15651v5 Announce Type: replace Abstract: In this paper, we present GaNI, a Global and Near-field Illumination-aware neural inverse rendering technique that can reconstruct geometry, albedo,

GanitLLM: Difficulty-Aware Bengali Mathematical Reasoning through Curriculum-GRPO

arXiv:2601.06767v2 Announce Type: replace-cross Abstract: We present a Bengali mathematical reasoning model called GanitLLM (named after the Bangla word for mathematics, 'Ganit'), together with a new

Generating Hadamard matrices with transformers

arXiv:2604.11101v1 Announce Type: cross Abstract: We present a new method for constructing Hadamard matrices that combines transformer neural networks with local search in the PatternBoost framework.

Generating High Quality Synthetic Data for Dutch Medical Conversations

arXiv:2604.09645v1 Announce Type: cross Abstract: Medical conversations offer insights into clinical communication often absent from Electronic Health Records. However, developing reliable clinical Na

Generative Path-Finding Method for Wasserstein Gradient Flow

arXiv:2604.11519v1 Announce Type: new Abstract: Wasserstein gradient flows (WGFs) describe the evolution of probability distributions in Wasserstein space as steepest descent dynamics for a free energ

Generative UI: LLMs are Effective UI Generators

arXiv:2604.09577v1 Announce Type: cross Abstract: AI models excel at creating content, but typically render it with static, predefined interfaces. Specifically, the output of LLMs is often a markdown

GeomPrompt: Geometric Prompt Learning for RGB-D Semantic Segmentation Under Missing and Degraded Depth

arXiv:2604.11585v1 Announce Type: new Abstract: Multimodal perception systems for robotics and embodied AI often assume reliable RGB-D sensing, but in practice, depth is frequently missing, noisy, or

GIST: Gauge-Invariant Spectral Transformers for Scalable Graph Neural Operators

arXiv:2603.16849v2 Announce Type: replace Abstract: Adapting transformer positional encodings to graphs and meshes faces a fundamental tension: exact spectral methods require cubic-complexity eigendec

Global Geometry of Orthogonal Foliations of Signed-Quadratic Systems

arXiv:2604.01912v2 Announce Type: replace-cross Abstract: This work formalizes the differential topology of redundancy resolution for systems governed by signed-quadratic actuation maps. By analyzing

researcharxiv-cs-ro

Graph-Coarsening Approach for the Capacitated Vehicle Routing Problem with Time Windows

arXiv:2510.22329v2 Announce Type: replace Abstract: The Capacitated Vehicle Routing Problem with Time Windows (CVRPTW) is a fundamental NP-hard optimization problem in logistics. Solving large-scale i

Graph-RHO: Critical-path-aware Heterogeneous Graph Network for Long-Horizon Flexible Job-Shop Scheduling

arXiv:2604.10073v1 Announce Type: cross Abstract: Long-horizon Flexible Job-Shop Scheduling~(FJSP) presents a formidable combinatorial challenge due to complex, interdependent decisions spanning exten

GrOCE:Graph-Guided Online Concept Erasure for Text-to-Image Diffusion Models

arXiv:2511.12968v2 Announce Type: replace Abstract: Concept erasure aims to remove harmful, inappropriate, or copyrighted content from text-to-image diffusion models while preserving non-target semant

Grounded Forcing: Bridging Time-Independent Semantics and Proximal Dynamics in Autoregressive Video Synthesis

arXiv:2604.06939v2 Announce Type: replace Abstract: Autoregressive video synthesis offers a promising pathway for infinite-horizon generation but is fundamentally hindered by three intertwined challen

GS4City: Hierarchical Semantic Gaussian Splatting via City-Model Priors

arXiv:2604.11401v1 Announce Type: new Abstract: Recent semantic 3D Gaussian Splatting (3DGS) methods primarily rely on 2D foundation models, often yielding ambiguous boundaries and limited support for

Gypscie: A Cross-Platform AI Artifact Management System

arXiv:2604.10311v1 Announce Type: new Abstract: Artificial Intelligence (AI) models, encompassing both traditional machine learning (ML) and more advanced approaches such as deep learning and large la

H-SPAM: Hierarchical Superpixel Anything Model

arXiv:2604.11218v1 Announce Type: new Abstract: Superpixels offer a compact image representation by grouping pixels into coherent regions. Recent methods have reached a plateau in terms of segmentatio

HFI: A unified framework for training-free detection and implicit watermarking of latent diffusion model generated images

arXiv:2412.20704v2 Announce Type: replace Abstract: Dramatic advances in the quality of the latent diffusion models (LDMs) also led to the malicious use of AI-generated images. While current AI-genera

Hidden Failures in Robustness: Why Supervised Uncertainty Quantification Needs Better Evaluation

arXiv:2604.11662v1 Announce Type: new Abstract: Recent work has shown that the hidden states of large language models contain signals useful for uncertainty estimation and hallucination detection, mot

Hide-and-Seek Attribution: Weakly Supervised Segmentation of Vertebral Metastases in CT

arXiv:2512.06849v2 Announce Type: replace Abstract: Accurate segmentation of vertebral metastasis in CT is clinically important yet difficult to scale, as voxel-level annotations are scarce and both l

Hijacking Text Heritage: Hiding the Human Signature through Homoglyphic Substitution

arXiv:2604.10271v1 Announce Type: cross Abstract: In what way could a data breach involving government-issued IDs such as passports, driver's licenses, etc., rival a random voluntary disclosure on a n

HistLens: Mapping Idea Change across Concepts and Corpora

arXiv:2604.11749v1 Announce Type: new Abstract: Language change both reflects and shapes social processes, and the semantic evolution of foundational concepts provides a measurable trace of historical

HOG-Layout: Hierarchical 3D Scene Generation, Optimization and Editing via Vision-Language Models

arXiv:2604.10772v1 Announce Type: new Abstract: 3D layout generation and editing play a crucial role in Embodied AI and immersive VR interaction. However, manual creation requires tedious labor, while

How LLMs Might Think

arXiv:2604.09674v1 Announce Type: new Abstract: Do large language models (LLMs) think? Daniel Stoljar and Zhihe Vincent Zhang have recently developed an argument from rationality for the claim that LL

Human-like Working Memory Interference in Large Language Models

arXiv:2604.09670v1 Announce Type: cross Abstract: Intelligent systems must maintain and manipulate task-relevant information online to adapt to dynamic environments and changing goals. This capacity,

Human vs. Machine Deception: Distinguishing AI-Generated and Human-Written Fake News Using Ensemble Learning

arXiv:2604.09960v1 Announce Type: new Abstract: The rapid adoption of large language models has introduced a new class of AI-generated fake news that coexists with traditional human-written misinforma

Industry

I just updated our license. For personal use, you’re free to run the software on your own servers for coding, building applications, agents,…

I just updated our license. For personal use, you’re free to run the software on your own servers for coding, building applications, agents, tools, or integrations, as well as for research, experiment

industryclem-delangue--x

I Walk the Line: Examining the Role of Gestalt Continuity in Object Binding for Vision Transformers

arXiv:2604.09942v1 Announce Type: cross Abstract: Object binding is a foundational process in visual cognition, during which low-level perceptual features are joined into object representations. Bindi

Immune2V: Image Immunization Against Dual-Stream Image-to-Video Generation

arXiv:2604.10837v1 Announce Type: new Abstract: Image-to-video (I2V) generation has the potential for societal harm because it enables the unauthorized animation of static images to create realistic d

Improving Deep Learning-Based Target Volume Auto-Delineation for Adaptive MR-Guided Radiotherapy in Head and Neck Cancer: Impact of a Volume-Aware Dice Loss

arXiv:2604.10130v1 Announce Type: new Abstract: Background: Manual delineation of target volumes in head and neck cancer (HNC) remains a significant bottleneck in radiotherapy planning, characterized

Improving DNS Exfiltration Detection via Transformer Pretraining

arXiv:2604.09849v1 Announce Type: cross Abstract: We study whether in-domain pretraining of Bidirectional Encoder Representations from Transformer (BERT) model improves subdomain-level detection of ex

Improving Pediatric Emergency Department Triage with Modality Dropout in Late Fusion Multimodal EHR Models

arXiv:2604.09905v1 Announce Type: new Abstract: Emergency department triage relies heavily on both quantitative vital signs and qualitative clinical notes, yet multimodal machine learning models predi

Improving understanding and trust in AI: How users benefit from interval-based counterfactual explanations

arXiv:2604.09573v1 Announce Type: cross Abstract: Experimental user studies evaluating the effectiveness of different subtypes of post-hoc explanations for black-box models are largely nonexistent. Th

In order to make sure ARC-AGI-3 games were solvable by humans we tested over 450 people If a game was too hard we either revised it or tosse…

researchfrancois-chollet--x

In order to make sure ARC-AGI-3 games were solvable by humans we tested over 450 people If a game was too hard we either revised it or tossed it completely For maximum transparency we just open source

Inductive Reasoning for Temporal Knowledge Graphs with Emerging Entities

arXiv:2604.10164v1 Announce Type: new Abstract: Reasoning on Temporal Knowledge Graphs (TKGs) is essential for predicting future events and time-aware facts. While existing methods are effective at ca

Inflation was coming down in the United States—and then Trump’s tariffs happened.

Inflation in the United States had been on a downward trajectory following its post-pandemic peak, but the implementation of tariffs under President Trump introduced new upward pressure on consumer pr

researchyann-lecun--x

Instruction Data Selection via Answer Divergence

arXiv:2604.10448v1 Announce Type: new Abstract: Instruction tuning relies on large instruction-response corpora whose quality and composition strongly affect downstream performance. We propose Answer

Inter-Layer Hessian Analysis of Neural Networks with DAG Architectures

arXiv:2604.11639v1 Announce Type: new Abstract: Modern automatic differentiation frameworks (JAX, PyTorch) return the Hessian of the loss function as a monolithic tensor, without exposing the internal