Theory

Logarithmic Regret for Linear Markov Decision Processes with Adversarial Corruptions AAAI 2025 Logical forms complement probability in understanding language model (and human) performance ACL 2025 Long-Context Linear System Identification ICLR 2025 Looped ReLU MLPs May Be All You Need as Practical Programmable Computers AISTATS 2025 Loss Landscape of Shallow ReLU-like Neural Networks: Stationary Points, Saddle Escape, and Network Embedding ICLR 2025 M2RC-EVAL: Massively Multilingual Repository-level Code Completion Evaluation ACL 2025 Machine-generated text detection prevents language model collapse EMNLP 2025 MambaOut: Do We Really Need Mamba for Vision? CVPR 2025 Mapping from Meaning: Addressing the Miscalibration of Prompt-Sensitive Language Models AAAI 2025 MARS-Bench: A Multi-turn Athletic Real-world Scenario Benchmark for Dialogue Evaluation EMNLP 2025 Mastering Task Arithmetic: τJp as a Key Indicator for Weight Disentanglement ICLR 2025 Matérn Kernels for Tunable Implicit Surface Reconstruction ICLR 2025 Matrix Completion with Incomplete Side Information via Orthogonal Complement Projection ICML 2025 Maximin Share Guarantees for Few Agents with Subadditive Valuations IJCAI 2025 MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models EMNLP 2025 MDSEval: A Meta-Evaluation Benchmark for Multimodal Dialogue Summarization EMNLP 2025 Mechanism and Emergence of Stacked Attention Heads in Multi-Layer Transformers ICLR 2025 Memorization in Language Models through the Lens of Intrinsic Dimension ACL 2025 Metric Calculating Benchmark: Code-Verifiable Complicate Instruction Following Benchmark for Large Language Models EMNLP 2025 (Mis)Fitting Scaling Laws: A Survey of Scaling Law Fitting Techniques in Deep Learning ICLR 2025 MixEval-X: Any-to-any Evaluations from Real-world Data Mixture ICLR 2025 MMEvalPro: Calibrating Multimodal Benchmarks Towards Trustworthy and Efficient Evaluation NAACL 2025 MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models ICLR 2025 Model Consistency as a Cheap yet Predictive Proxy for LLM Elo Scores EMNLP 2025 More Efforts Towards Fixed-Parameter Approximability of Multiwinner Rules IJCAI 2025