Papers
-
Skip to the Good Part: Representation Structure & Inference-Time Layer Skipping in Diffusion vs. Autoregressive LLMs
-
EVLF: Early Vision-Language Fusion for Generative Dataset Distillation
-
Interpretable-by-Design Transformers via Architectural Stream Independence
-
Multi-Modal Decouple and Recouple Network for Robust 3D Object Detection
-
A Joint Neural Baseline for Concept, Assertion, and Relation Extraction from Clinical Text
-
RobustSCI: Beyond Reconstruction to Restoration for Snapshot Compressive Imaging under Real-World Degradations
-
Pushing Bistatic Wireless Sensing toward High Accuracy at the Sub-Wavelength Scale
-
RayD3D: Distilling Depth Knowledge Along the Ray for Robust Multi-View 3D Object Detection
-
DocCogito: Aligning Layout Cognition and Step-Level Grounded Reasoning for Document Understanding
-
From Thinker to Society: Security in Hierarchical Autonomy Evolution of AI Agents
-
AMR-CCR: Anchored Modular Retrieval for Continual Chinese Character Recognition
-
Enhanced Random Subspace Local Projections for High-Dimensional Time Series Analysis
-
SeDa: A Unified System for Dataset Discovery and Multi-Entity Augmented Semantic Exploration
-
High-Fidelity Medical Shape Generation via Skeletal Latent Diffusion
-
A Unified Framework for Knowledge Transfer in Bidirectional Model Scaling
-
Online Continual Learning for Anomaly Detection in IoT under Data Distribution Shifts
-
Bolbosh: Script-Aware Flow Matching for Kashmiri Text-to-Speech
-
A Unified View of Drifting and Score-Based Models
-
EvolveReason: Self-Evolving Reasoning Paradigm for Explainable Deepfake Facial Image Identification
-
InterReal: A Unified Physics-Based Imitation Framework for Learning Human-Object Interaction Skills
-
Reinforcement learning-based dynamic cleaning scheduling framework for solar energy system
-
SketchGraphNet: A Memory-Efficient Hybrid Graph Transformer for Large-Scale Sketch Corpora Recognition
-
Beyond Data Splitting: Full-Data Conformal Prediction by Differential Privacy
-
One-for-All Model Initialization with Frequency-Domain Knowledge
-
Neural Dynamics-Informed Pre-trained Framework for Personalized Brain Functional Network Construction
-
Generative prediction of laser-induced rocket ignition with dynamic latent space representations
-
TableMind++: An Uncertainty-Aware Programmatic Agent for Tool-Augmented Table Reasoning
-
Obliviator Reveals the Cost of Nonlinear Guardedness in Concept Erasure
-
ACCURATE: Arbitrary-shaped Continuum Reconstruction Under Robust Adaptive Two-view Estimation
-
Accent Vector: Controllable Accent Manipulation for Multilingual TTS Without Accented Data
-
Scale-Aware UAV-to-Satellite Cross-View Geo-Localization: A Semantic Geometric Approach
-
MAWARITH: A Dataset and Benchmark for Legal Inheritance Reasoning with LLMs
-
How Long Can Unified Multimodal Models Generate Images Reliably? Taming Long-Horizon Interleaved Image Generation via Context Curation
-
CONSTANT: Towards High-Quality One-Shot Handwriting Generation with Patch Contrastive Enhancement and Style-Aware Quantization
-
DreamSAC: Learning Hamiltonian World Models via Symmetry Exploration
-
COOL-MC: Verifying and Explaining RL Policies for Multi-bridge Network Maintenance
-
Learning-free L2-Accented Speech Generation using Phonological Rules
-
Targeted Speaker Poisoning Framework in Zero-Shot Text-to-Speech
-
Nwāchā Munā: A Devanagari Speech Corpus and Proximal Transfer Benchmark for Nepal Bhasha ASR
-
ECG Classification on PTB-XL: A Data-Centric Approach with Simplified CNN-VAE
-
Active Inference for Micro-Gesture Recognition: EFE-Guided Temporal Sampling and Adaptive Learning
-
PureCC: Pure Learning for Text-to-Image Concept Customization
-
Brain-WM: Brain Glioblastoma World Model
-
SiamGM: Siamese Geometry-Aware and Motion-Guided Network for Real-Time Satellite Video Object Tracking
-
GRD-Net: Generative-Reconstructive-Discriminative Anomaly Detection with Region of Interest Attention Module
-
Revisiting the LiRA Membership Inference Attack Under Realistic Assumptions
-
Constraints Matrix Diffusion based Generative Neural Solver for Vehicle Routing Problems
-
Efficient RGB-D Scene Understanding via Multi-task Adaptive Learning and Cross-dimensional Feature Guidance
-
A Systematic Comparison of Training Objectives for Out-of-Distribution Detection in Image Classification
-
TS-MLLM: A Multi-Modal Large Language Model-based Framework for Industrial Time-Series Big Data Analysis
