Papers
-
AgentSLR: Automating Systematic Literature Reviews in Epidemiology with Agentic AI
-
Synergistic Perception and Generative Recomposition: A Multi-Agent Orchestration for Expert-Level Building Inspection
-
Can Large Multimodal Models Inspect Buildings? A Hierarchical Benchmark for Structural Pathology Reasoning
-
Enhancing Hyperspace Analogue to Language (HAL) Representations via Attention-Based Pooling for Text Classification
-
Design-OS: A Specification-Driven Framework for Engineering System Design with a Control-Systems Design Case
-
Beyond Single Tokens: Distilling Discrete Diffusion Models via Discrete MMD
-
Semantic Token Clustering for Efficient Uncertainty Quantification in Large Language Models
-
Evaluating Evidence Grounding Under User Pressure in Instruction-Tuned Language Models
-
The Robot's Inner Critic: Self-Refinement of Social Behaviors through VLM-based Replanning
-
Comprehensive Description of Uncertainty in Measurement for Representation and Propagation with Scalable Precision
-
EgoForge: Goal-Directed Egocentric World Simulator
-
Learning Dynamic Belief Graphs for Theory-of-mind Reasoning
-
WebNavigator: Global Web Navigation via Interaction Graph Retrieval
-
Measuring Faithfulness Depends on How You Measure: Classifier Sensitivity in LLM Chain-of-Thought Evaluation
-
TinyML Enhances CubeSat Mission Capabilities
-
LagerNVS: Latent Geometry for Fully Neural Real-time Novel View Synthesis
-
Adaptive Greedy Frame Selection for Long Video Understanding
-
Improving Generalization on Cybersecurity Tasks with Multi-Modal Contrastive Learning
-
Kolmogorov-Arnold causal generative models
-
VideoSeek: Long-Horizon Video Agent with Tool-Guided Seeking
-
Improving Image-to-Image Translation via a Rectified Flow Reformulation
-
MuSteerNet: Human Reaction Generation from Videos via Observation-Reaction Mutual Steering
-
Wildfire Spread Scenarios: Increasing Sample Diversity of Segmentation Diffusion Models with Training-Free Methods
-
MeanFlow Meets Control: Scaling Sampled-Data Control for Swarms
-
CoVR-R:Reason-Aware Composed Video Retrieval
-
Deterministic Mode Proposals: An Efficient Alternative to Generative Sampling for Ambiguous Segmentation
-
LumosX: Relate Any Identities with Their Attributes for Personalized Video Generation
-
From Masks to Pixels and Meaning: A New Taxonomy, Benchmark, and Metrics for VLM Image Tampering
-
MME-CoF-Pro: Evaluating Reasoning Coherence in Video Generative Models with Text and Visual Hints
-
ALARA for Agents: Least-Privilege Context Engineering Through Portable Composable Multi-Agent Teams
-
The production of meaning in the processing of natural language
-
Uni-Classifier: Leveraging Video Diffusion Priors for Universal Guidance Classifier
-
Multi-Stage Fine-Tuning of Pathology Foundation Models with Head-Diverse Ensembling for White Blood Cell Classification
-
Jigsaw Regularization in Whole-Slide Image Classification
-
From Cross-Validation to SURE: Asymptotic Risk of Tuned Regularized Estimators
-
A chemical language model for reticular materials design
-
CAMA: Exploring Collusive Adversarial Attacks in c-MARL
-
Monocular Models are Strong Learners for Multi-View Human Mesh Recovery
-
SymCircuit: Bayesian Structure Inference for Tractable Probabilistic Circuits via Entropy-Regularized Reinforcement Learning
-
Compression is all you need: Modeling Mathematics
-
KV Cache Optimization Strategies for Scalable and Efficient LLM Inference
-
FAAR: Efficient Frequency-Aware Multi-Task Fine-Tuning via Automatic Rank Selection
-
Hetero-Net: An Energy-Efficient Resource Allocation and 3D Placement in Heterogeneous LoRa Networks via Multi-Agent Optimization
-
Putnam 2025 Problems in Rocq using Opus 4.6 and Rocq-MCP
-
Thinking in Different Spaces: Domain-Specific Latent Geometry Survives Cross-Architecture Translation
-
Meta-Learning for Repeated Bayesian Persuasion
-
SLE-FNO: Single-Layer Extensions for Task-Agnostic Continual Learning in Fourier Neural Operators
-
Beyond the Mean: Distribution-Aware Loss Functions for Bimodal Regression
-
Data-driven discovery of roughness descriptors for surface characterization and intimate contact modeling of unidirectional composite tapes
-
CERN: Correcting Errors in Raw Nanopore Signals Using Hidden Markov Models
MongoDB - Build AI That Scales
