Theory

Exploit Gradient Skewness to Circumvent Byzantine Defenses for Federated Learning AAAI 2025 Exploring Backdoor Vulnerabilities of Chat Models COLING 2025 Exploring channel distinguishability in local neighborhoods of the model space in quantum neural networks ICLR 2025 Exploring Response Uncertainty in MLLMs: An Empirical Evaluation under Misleading Scenarios EMNLP 2025 Exploring the Limitations of Mamba in COPY and CoT Reasoning EMNLP 2025 Exploring The Loss Landscape Of Regularized Neural Networks Via Convex Duality ICLR 2025 Exploring Topological Properties in Artificial Neural Networks AAAI 2025 Exposing the Achilles’ Heel: Evaluating LLMs Ability to Handle Mistakes in Mathematical Reasoning ACL 2025 Expressive Power of Temporal Message Passing AAAI 2025 Expressivity of Neural Networks with Random Weights and Learned Biases ICLR 2025 Extending Mercer's expansion to indefinite and asymmetric kernels ICLR 2025 Extracting PAC Decision Trees from Black Box Binary Classifiers: The Gender Bias Study Case on BERT-based Language Models AAAI 2025 Factual Knowledge Assessment of Language Models Using Distractors COLING 2025 Factual Knowledge in Language Models: Robustness and Anomalies under Simple Temporal Context Variations ACL 2025 FADE: Why Bad Descriptions Happen to Good Features ACL 2025 Fast and Synchronous Crash Consistency with Metadata Write-Once File System OSDI 2025 F-Fidelity: A Robust Framework for Faithfulness Evaluation of Explainable AI ICLR 2025 FinanceReasoning: Benchmarking Financial Numerical Reasoning More Credible, Comprehensive and Challenging ACL 2025 Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency ACL 2025 Fingerprinting LLMs through Survey Item Factor Correlation: A Case Study on Humor Style Questionnaire EMNLP 2025 Finite State Automata Inside Transformers with Chain-of-Thought: A Mechanistic Study on State Tracking ACL 2025 Flavors of Margin: Implicit Bias of Steepest Descent in Homogeneous Neural Networks ICLR 2025 FLEX: Expert-level False-Less EXecution Metric for Text-to-SQL Benchmark NAACL 2025 Flow matching achieves almost minimax optimal convergence ICLR 2025 ForecastBench: A Dynamic Benchmark of AI Forecasting Capabilities ICLR 2025