Cs-Ai
EoRA: Fine-tuning-free Compensation for Compressed LLM with Eigenspace Low-Rank Approximation
Efficient Mixture-of-Expert for Video-based Driver State and Physiological Multi-task Estimation in Conditional Autonomous Driving
Working Paper: Active Causal Structure Learning with Latent Variables: Towards Learning to Detour in Autonomous Robots
Estimating Causal Effects of Text Interventions Leveraging LLMs
A-UTE: Advection Informed, Uncertainty Aware Temperature Emulator
Deconfounded Time Series Forecasting: A Causal Inference Approach
Angel or Devil: Discriminating Hard Samples and Anomaly Contaminations for Unsupervised Time Series Anomaly Detection
Intrinsic Stability Limits of Autoregressive Reasoning: Structural Consequences for Long-Horizon Execution
TFusionOcc: Student's t-Distribution Based Object-Centric Multi-Sensor Fusion Framework for 3D Occupancy Prediction
Revisiting Salient Object Detection from an Observer-Centric Perspective
Improve Large Language Model Systems with User Logs
CORE: Comprehensive Ontological Relation Evaluation for Large Language Models
Generating High-quality Privacy-preserving Synthetic Data
Unlocking Noisy Real-World Corpora for Foundation Model Pre-Training via Quality-Aware Tokenization
Difficulty-Estimated Policy Optimization
Revisiting the Shape Convention of Transformer Language Models
TrajAD: Trajectory Anomaly Detection for Trustworthy LLM Agents
Principle-Evolvable Scientific Discovery via Uncertainty Minimization
Empirical Analysis of Adversarial Robustness and Explainability Drift in Cybersecurity Classifiers
Error Bounds for Physics-Informed Neural Networks in Fokker-Planck PDEs
RealCQA-V2: A Diagnostic Benchmark for Structured Visual Entailment over Scientific Charts
Target noise: A pre-training based neural network initialization for efficient high resolution learning
