Papers
-
The Spillover Effects of Peer AI Rinsing on Corporate Green Innovation
-
Self-Tuning Sparse Attention: Multi-Fidelity Hyperparameter Optimization for Transformer Acceleration
-
Mind the Rarities: Can Rare Skin Diseases Be Reliably Diagnosed via Diagnostic Reasoning?
-
From Topic to Transition Structure: Unsupervised Concept Discovery at Corpus Scale via Predictive Associative Memory
-
The Impact of Corporate AI Washing on Farmers' Digital Financial Behavior Response -- An Analysis from the Perspective of Digital Financial Exclusion
-
SynQ: Accurate Zero-shot Quantization by Synthesis-aware Fine-tuning
-
Multimodal Task Interference: A Benchmark and Analysis of History-Target Mismatch in Multimodal LLMs
-
Prune-then-Quantize or Quantize-then-Prune? Understanding the Impact of Compression Order in Joint Model Compression
-
R&D: Balancing Reliability and Diversity in Synthetic Data Augmentation for Semantic Segmentation
-
Adaptive Decoding via Test-Time Policy Learning for Self-Improving Generation
-
AndroTMem: From Interaction Trajectories to Anchored Memory in Long-Horizon GUI Agents
-
Towards Noise-Resilient Quantum Multi-Armed and Stochastic Linear Bandits
-
LLM-Enhanced Energy Contrastive Learning for Out-of-Distribution Detection in Text-Attributed Graphs
-
MLOW: Interpretable Low-Rank Frequency Magnitude Decomposition of Multiple Effects for Time Series Forecasting
-
AS2 -- Attention-Based Soft Answer Sets: An End-to-End Differentiable Neuro-Soft-Symbolic Reasoning Architecture
-
MARLIN: Multi-Agent Reinforcement Learning for Incremental DAG Discovery
-
SR-Nav: Spatial Relationships Matter for Zero-shot Object Goal Navigation
-
Discounted Beta--Bernoulli Reward Estimation for Sample-Efficient Reinforcement Learning with Verifiable Rewards
-
UT-ACA: Uncertainty-Triggered Adaptive Context Allocation for Long-Context Inference
-
SODIUM: From Open Web Data to Queryable Databases
-
Seeking Universal Shot Language Understanding Solutions
-
POET: Power-Oriented Evolutionary Tuning for LLM-Based RTL PPA Optimization
-
Learning Consistent Temporal Grounding between Related Tasks in Sports Coaching
-
HypeMed: Enhancing Medication Recommendations with Hypergraph-Based Patient Relationships
-
Interpretable Prostate Cancer Detection using a Small Cohort of MRI Images
-
Cell-Type Prototype-Informed Neural Network for Gene Expression Estimation from Pathology Images
-
AlignMamba-2: Enhancing Multimodal Fusion and Sentiment Analysis with Modality-Aware Mamba
-
AcceRL: A Distributed Asynchronous Reinforcement Learning and World Model Framework for Vision-Language-Action Models
-
MedQ-UNI: Toward Unified Medical Image Quality Assessment and Restoration via Vision-Language Modeling
-
Recolour What Matters: Region-Aware Colour Editing via Token-Level Diffusion
-
GAIN: A Benchmark for Goal-Aligned Decision-Making of Large Language Models under Imperfect Norms
-
Cognitive Mismatch in Multimodal Large Language Models for Discrete Symbol Understanding
-
Do Post-Training Algorithms Actually Differ? A Controlled Study Across Model Scales Uncovers Scale-Dependent Ranking Inversions
-
WASD: Locating Critical Neurons as Sufficient Conditions for Explaining and Controlling LLM Behavior
-
UniFluids: Unified Neural Operator Learning with Conditional Flow-matching
-
Do Vision Language Models Understand Human Engagement in Games?
-
T-QPM: Enabling Temporal Out-Of-Distribution Detection and Domain Generalization for Vision-Language Models in Open-World
-
The Truncation Blind Spot: How Decoding Strategies Systematically Exclude Human-Like Token Choices
-
Precise Performance of Linear Denoisers in the Proportional Regime
-
Diffusion-Guided Semantic Consistency for Multimodal Heterogeneity
-
Collaborative Adaptive Curriculum for Progressive Knowledge Distillation
-
TexEditor: Structure-Preserving Text-Driven Texture Editing
-
EntropyCache: Decoded Token Entropy Guided KV Caching for Diffusion Language Models
-
AIMER: Calibration-Free Task-Agnostic MoE Pruning
-
FILT3R: Latent State Adaptive Kalman Filter for Streaming 3D Reconstruction
-
Cross-Domain Demo-to-Code via Neurosymbolic Counterfactual Reasoning
-
NymeriaPlus: Enriching Nymeria Dataset with Additional Annotations and Data
-
Recovering Sparse Neural Connectivity from Partial Measurements: A Covariance-Based Approach with Granger-Causality Refinement
-
Efficient Video Diffusion with Sparse Information Transmission for Video Compression
-
HOMEY: Heuristic Object Masking with Enhanced YOLO for Property Insurance Risk Detection
MongoDB - Build AI That Scales
