Search: “research”

Decoupled Similarity for Task-Aware Token Pruning in Large Vision-Language Models

arXiv:2604.11240v1 Announce Type: new Abstract: Token pruning has emerged as an effective approach to reduce the substantial computational overhead of Large Vision-Language Models (LVLMs) by discardin

Research

DeCoVec: Building Decoding Space based Task Vector for Large Language Models via In-Context Learning

DGX agent

arXiv:2604.11129v1 Announce Type: new Abstract: Task vectors, representing directions in model or activation spaces that encode task-specific behaviors, have emerged as a promising tool for steering l

researcharxiv-cs-cl

14 Apr 2026

DeepShapeMatchingKit: Accelerated Functional Map Solver and Shape Matching Pipelines Revisited

arXiv:2604.10377v1 Announce Type: new Abstract: Deep functional maps, leveraging learned feature extractors and spectral correspondence solvers, are fundamental to non-rigid 3D shape matching. Based o

DeepSketcher: Internalizing Visual Manipulation for Multimodal Reasoning

arXiv:2509.25866v2 Announce Type: replace Abstract: The 'thinking with images' paradigm represents a pivotal shift in the reasoning of Vision Language Models (VLMs), moving from text-dominant chain-of

Defending against Backdoor Attacks via Module Switching

arXiv:2504.05902v2 Announce Type: replace-cross Abstract: Backdoor attacks pose a serious threat to deep neural networks (DNNs), allowing adversaries to implant triggers for hidden behaviors in infere

Safety

Designing Adaptive Digital Nudging Systems with LLM-Driven Reasoning

arXiv:2604.11206v1 Announce Type: cross Abstract: Digital nudging systems lack architectural guidance for translating behavioral science into software design. While research identifies nudge strategie

safetyarxiv-cs-ai

Detecting Invariant Manifolds in ReLU-Based RNNs

arXiv:2510.03814v4 Announce Type: replace-cross Abstract: Recurrent Neural Networks (RNNs) have found widespread applications in machine learning for time series prediction and dynamical systems recon

Detecting RAG Extraction Attack via Dual-Path Runtime Integrity Game

arXiv:2604.10717v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems augment large language models with external knowledge, yet introduce a critical security vulnerability: R

Diagnosing Failure Modes of Neural Operators Across Diverse PDE Families

arXiv:2601.11428v4 Announce Type: replace Abstract: Neural PDE solvers have shown strong performance on standard benchmarks, but their robustness under deployment-relevant distribution shifts remains

DIB-OD: Preserving the Invariant Core for Robust Heterogeneous Graph Adaptation via Decoupled Information Bottleneck and Online Distillation

arXiv:2604.10882v1 Announce Type: cross Abstract: Graph Neural Network pretraining is pivotal for leveraging unlabeled graph data. However, generalizing across heterogeneous domains remains a major ch

Differentiable Vector Quantization for Rate-Distortion Optimization of Generative Image Compression

arXiv:2604.10546v1 Announce Type: new Abstract: The rapid growth of visual data under stringent storage and bandwidth constraints makes extremely low-bitrate image compression increasingly important.

Diffusion-CAM: Faithful Visual Explanations for dMLLMs

arXiv:2604.11005v1 Announce Type: new Abstract: While diffusion Multimodal Large Language Models (dMLLMs) have recently achieved remarkable strides in multimodal generation, the development of interpr

Diffusion Denoiser Achievable Analysis for Finite Blocklength Unsourced Random Access

arXiv:2604.09904v1 Announce Type: cross Abstract: Polyanskiy proposed a framework for the unsourced multiple access channel (MAC) problem where users employ a common codebook in the finite blocklength

Digital hybridity and relics in cultural heritage: using corpus linguistics to inform design in emerging technologies from AI to VR

arXiv:2604.09669v1 Announce Type: cross Abstract: Hybrid technologies enable the blending of physical and digital elements, creating new ways to experience and interact with the world. Such technologi

DINO_4D: Semantic-Aware 4D Reconstruction

arXiv:2604.09877v1 Announce Type: cross Abstract: In the intersection of computer vision and robotic perception, 4D reconstruction of dynamic scenes serve as the critical bridge connecting low-level g

Directional Mollification for Knot-Preserving C^{infty} Smoothing of Polygonal Chains with Explicit Curvature Bounds

arXiv:2603.21831v2 Announce Type: replace Abstract: Starting from a polygonal chain (a first-order polynomial spline) through prescribed knots (vertices), we introduce the extit{directional mollificat

researcharxiv-cs-ro

DisCo-FLoc: Using Dual-Level Visual-Geometric Contrasts to Disambiguate Depth-Aware Visual Floorplan Localization

arXiv:2601.01822v2 Announce Type: replace-cross Abstract: Since floorplan data is readily available, long-term persistent, and robust to changes in visual appearance, visual Floorplan Localization (FL

Discourse Diversity in Multi-Turn Empathic Dialogue

arXiv:2604.11742v1 Announce Type: cross Abstract: Large language models (LLMs) produce responses rated as highly empathic in single-turn settings (Ayers et al., 2023; Lee et al., 2024), yet they are a

Discrete Bayesian Sample Inference for Graph Generation

arXiv:2511.03015v2 Announce Type: replace Abstract: Generating graph-structured data is crucial in applications such as molecular generation, knowledge graphs, and network analysis. However, their dis

Distributionally Robust K-Means Clustering

arXiv:2604.11118v1 Announce Type: new Abstract: K-means clustering is a workhorse of unsupervised learning, but it is notoriously brittle to outliers, distribution shifts, and limited sample sizes. Vi

Do BERT Embeddings Encode Narrative Dimensions? A Token-Level Probing Analysis of Time, Space, Causality, and Character in Fiction

arXiv:2604.10786v1 Announce Type: cross Abstract: Narrative understanding requires multidimensional semantic structures. This study investigates whether BERT embeddings encode dimensions of fictional

Do Instance Priors Help Weakly Supervised Semantic Segmentation?

arXiv:2604.11170v1 Announce Type: new Abstract: Semantic segmentation requires dense pixel-level annotations, which are costly and time-consuming to acquire. To address this, we present SeSAM, a frame

Do Neurons Dream of Primitive Operators? Wake-Sleep Compression Rediscovers Schank's Event Semantics

arXiv:2603.25975v2 Announce Type: replace-cross Abstract: We show that they do. Roger Schank's conceptual dependency theory proposed that all human events decompose into primitive operations -- ATRANS

DreamKG: A KG-Augmented Conversational System for People Experiencing Homelessness

arXiv:2604.11703v1 Announce Type: new Abstract: People experiencing homelessness (PEH) face substantial barriers to accessing timely, accurate information about community services. DreamKG addresses t

Dual-R-DETR: Resolving Query Competition with Pairwise Routing in Transformer Decoders

arXiv:2512.13876v2 Announce Type: replace Abstract: Detection Transformers (DETR) formulate object detection as a set prediction problem and enable end-to-end training without post-processing. However

DuET: Dual Execution for Test Output Prediction with Generated Code and Pseudocode

arXiv:2604.11514v1 Announce Type: cross Abstract: This work addresses test output prediction, a key challenge in test case generation. To improve the reliability of predicted outputs by LLMs, prior ap

Duration-Informed Workload Scheduler

arXiv:2604.09599v1 Announce Type: cross Abstract: High-performance computing systems are complex machines whose behaviour is governed by the correct functioning of its many subsystems. Among these, th

Dyadic Partnership(DP): A Missing Link Towards Full Autonomy in Medical Robotics

arXiv:2604.11423v1 Announce Type: new Abstract: For the past decades medical robotic solutions were mostly based on the concept of tele-manipulation. While their design was extremely intelligent, allo

researcharxiv-cs-ro

Dynamic Adaptive Attention and Supervised Contrastive Learning: A Novel Hybrid Framework for Text Sentiment Classification

arXiv:2604.10459v1 Announce Type: new Abstract: The exponential growth of user-generated movie reviews on digital platforms has made accurate text sentiment classification a cornerstone task in natura

EditCrafter: Tuning-free High-Resolution Image Editing via Pretrained Diffusion Model

arXiv:2604.10268v1 Announce Type: new Abstract: We propose EditCrafter, a high-resolution image editing method that operates without tuning, leveraging pretrained text-to-image (T2I) diffusion models

EEG-based AI-BCI Wheelchair Advancement: Hybrid Deep Learning with Motor Imagery for Brain Computer Interface

arXiv:2509.25667v2 Announce Type: replace-cross Abstract: This paper presents an Artificial Intelligence (AI) integrated approach to Brain-Computer Interface (BCI)-based wheelchair development, utiliz

Efficient Emotion-Aware Iconic Gesture Prediction for Robot Co-Speech

arXiv:2604.11417v1 Announce Type: cross Abstract: Co-speech gestures increase engagement and improve speech understanding. Most data-driven robot systems generate rhythmic beat-like motion, yet few in

Efficient Matrix Implementation for Rotary Position Embedding

arXiv:2604.09742v1 Announce Type: cross Abstract: Rotary Position Embedding (RoPE) has become a core component of modern Transformer architectures across language, vision, and 3D domains. However, exi

Efficient Personalization of Generative User Interfaces

arXiv:2604.09876v1 Announce Type: cross Abstract: Generative user interfaces (UIs) create new opportunities to adapt interfaces to individual users on demand, but personalization remains difficult bec

Embedding of Low-Dimensional Sensory Dynamics in Recurrent Networks: Implications for the Geometry of Neural Representation

arXiv:2601.19019v2 Announce Type: replace-cross Abstract: Neural population activity in sensory cortex is organized on low-dimensional manifolds, but why such manifolds arise and what determines their

Model Releases

Enhancing Multimodal Large Language Models for Ancient Chinese Character Evolution Analysis via Glyph-Driven Fine-Tuning

model-releasesarxiv-cs-ai

arXiv:2604.11299v1 Announce Type: cross Abstract: In recent years, rapid advances in Multimodal Large Language Models (MLLMs) have increasingly stimulated research on ancient Chinese scripts. As the e

Evaluating Visual Prompts with Eye-Tracking Data for MLLM-Based Human Activity Recognition

arXiv:2604.09585v1 Announce Type: cross Abstract: Large Language Models (LLMs) have emerged as foundation models for IoT applications such as human activity recognition (HAR). However, directly applyi

'Every truck on the road is generating data that nobody's capturing today. It happens, and it disappears.' Nexar CEO @ZMGreenb on the 'What …

'Every truck on the road is generating data that nobody's capturing today. It happens, and it disappears.' Nexar CEO @ZMGreenb on the 'What The Truck' podcast from @FreightWaves. The data was always o

researchyann-lecun--x

EvoESAP: Non-Uniform Expert Pruning for Sparse MoE

arXiv:2603.06003v2 Announce Type: replace Abstract: Sparse Mixture-of-Experts (SMoE) language models achieve strong capability at low per-token compute, yet deployment remains constrained by memory fo

Evolutionary Profiles for Protein Fitness Prediction

arXiv:2510.07286v3 Announce Type: replace-cross Abstract: Predicting the fitness impact of mutations is central to protein engineering but constrained by limited assays relative to the size of sequenc

Exact Certification of Neural Networks and Partition Aggregation Ensembles against Label Poisoning

arXiv:2604.11416v1 Announce Type: new Abstract: Label-flipping attacks, which corrupt training labels to induce misclassifications at inference, remain a major threat to supervised learning models. Th

Exact Finite-Sample Variance Decomposition of Subagging: A Spectral Filtering Perspective

arXiv:2604.10469v1 Announce Type: new Abstract: Standard resampling ratios (e.g., alpha approx 0.632) are widely used as default baselines in ensemble learning for three decades. However, how these ra

ExPath: Targeted Pathway Inference for Biological Knowledge Bases via Graph Learning and Explanation

arXiv:2502.18026v3 Announce Type: replace-cross Abstract: Retrieving targeted pathways in biological knowledge bases, particularly when incorporating wet-lab experimental data, remains a challenging t

Expect the Unexpected? Testing the Surprisal of Salient Entities

arXiv:2604.10724v1 Announce Type: new Abstract: Previous work examining the Uniform Information Density (UID) hypothesis has shown that while information as measured by surprisal metrics is distribute

ExpertEdit: Learning Skill-Aware Motion Editing from Expert Videos

arXiv:2604.10466v1 Announce Type: new Abstract: Visual feedback is critical for motor skill acquisition in sports and rehabilitation, and psychological studies show that observing near-perfect version

Exploring Knowledge Purification in Multi-Teacher Knowledge Distillation for LLMs

arXiv:2602.01064v2 Announce Type: replace Abstract: Knowledge distillation has emerged as a pivotal technique for transferring knowledge from stronger large language models (LLMs) to smaller, more eff

F3G-Avatar : Face Focused Full-body Gaussian Avatar

arXiv:2604.09835v1 Announce Type: cross Abstract: Existing full-body Gaussian avatar methods primarily optimize global reconstruction quality and often fail to preserve fine-grained facial geometry an

Factorizing formal contexts from closures of necessity operators

arXiv:2604.09582v1 Announce Type: new Abstract: Factorizing datasets is an interesting process in a multitude of approaches, but many times it is not possible or efficient the computation of a factori