Papers
-
DataProphet: Demystifying Supervision Data Generalization in Multimodal LLMs
-
A Unified Phase-native Computational Principle Governs Hippocampal Spike Timing and Neural Coding
-
Demographic-Aware Self-Supervised Anomaly Detection Pretraining for Equitable Rare Cardiac Diagnosis
-
Regret Analysis of Sleeping Competing Bandits
-
Minimax and Adaptive Covariance Matrix Estimation under Differential Privacy
-
WorldAgents: Can Foundation Image Models be Agents for 3D World Models?
-
Bounded Coupled AI Learning Dynamics in Tri-Hierarchical Drone Swarms
-
AIGQ: An End-to-End Hybrid Generative Architecture for E-commerce Query Recommendation
-
EvoTaxo: Building and Evolving Taxonomy from Social Media Streams
-
TAB-AUDIT: Detecting AI-Fabricated Scientific Tables via Multi-View Likelihood Mismatch
-
Learning from Similarity/Dissimilarity and Pairwise Comparison
-
LoopRPT: Reinforcement Pre-Training for Looped Language Models
-
Stepwise: Neuro-Symbolic Proof Search for Automated Systems Verification
-
BALM: A Model-Agnostic Framework for Balanced Multimodal Learning under Imbalanced Missing Rates
-
FedRG: Unleashing the Representation Geometry for Federated Learning with Noisy Clients
-
PerformRecast: Expression and Head Pose Disentanglement for Portrait Video Editing
-
Procedural Refinement by LLM-driven Algorithmic Debugging for ARC-AGI-2
-
PoC: Performance-oriented Context Compression for Large Language Models via Performance Prediction
-
A two-step sequential approach for hyperparameter selection in finite context models
-
MOSS-TTSD: Text to Spoken Dialogue Generation
-
FedPDPO: Federated Personalized Direct Preference Optimization for Large Language Model Alignment
-
Hybrid Autoencoder-Isolation Forest approach for time series anomaly detection in C70XP cyclotron operation data at ARRONAX
-
Dual Path Attribution: Efficient Attribution for SwiGLU-Transformers through Layer-Wise Target Propagation
-
Rethinking Ground Truth: A Case Study on Human Label Variation in MLLM Benchmarking
-
PhysNeXt: Next-Generation Dual-Branch Structured Attention Fusion Network for Remote Photoplethysmography Measurement
-
ReLi3D: Relightable Multi-view 3D Reconstruction with Disentangled Illumination
-
Uncertainty-aware Prototype Learning with Variational Inference for Few-shot Point Cloud Segmentation
-
GEM: A Native Graph-based Index for Multi-Vector Retrieval
-
Growing Networks with Autonomous Pruning
-
PCSTracker: Long-Term Scene Flow Estimation for Point Cloud Sequences
-
Adapting a Pre-trained Single-Cell Foundation Model to Spatial Gene Expression Generation from Histology Images
-
FREAK: A Fine-grained Hallucination Evaluation Benchmark for Advanced MLLMs
-
High-fidelity Multi-view Normal Integration with Scale-encoded Neural Surface Representation
-
FlashCap: Millisecond-Accurate Human Motion Capture via Flashing LEDs and Event-Based Vision
-
Low-pass Personalized Subgraph Federated Recommendation
-
Neither Here Nor There: Cross-Lingual Representation Dynamics of Code-Mixed Text in Multilingual Encoders
-
Template-based Object Detection Using a Foundation Model
-
Evaluating Image Editing with LLMs: A Comprehensive Benchmark and Intermediate-Layer Probing Approach
-
ReManNet: A Riemannian Manifold Network for Monocular 3D Lane Detection
-
Graph-Aware Text-Only Backdoor Poisoning for Text-Attributed Graphs
-
One Model, Two Minds: Task-Conditioned Reasoning for Unified Image Quality and Aesthetic Assessment
-
Decoupled Sensitivity-Consistency Learning for Weakly Supervised Video Anomaly Detection
-
Embodied Science: Closing the Discovery Loop with Agentic Embodied AI
-
Learning Hierarchical Orthogonal Prototypes for Generalized Few-Shot 3D Point Cloud Segmentation
-
ContractSkill: Repairable Contract-Based Skills for Multimodal Web Agents
-
From Plausibility to Verifiability: Risk-Controlled Generative OCR for Vision-Language Models
-
Scalable Learning of Multivariate Distributions via Coresets
-
Interpretable Multiple Myeloma Prognosis with Observational Medical Outcomes Partnership Data
-
Controllable Text-to-Motion Generation via Modular Body-Part Phase Control
-
Borderless Long Speech Synthesis
MongoDB - Build AI That Scales
