Learning Theory

Long-Term Individual Causal Effect Estimation via Identifiable Latent Representation Learning IJCAI 2025 Loss Gradient Gaussian Width based Generalization and Optimization Guarantees AISTATS 2025 Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions COLT 2025 Low-Dimension-to-High-Dimension Generalization and Its Implications for Length Generalization ICML 2025 Lower Bounds for Chain-of-Thought Reasoning in Hard-Attention Transformers ICML 2025 Lower Bounds for Greedy Teaching Set Constructions COLT 2025 Lower Bounds for Time-Varying Kernelized Bandits AISTATS 2025 Lower Bounds on the Size of Markov Equivalence Classes UAI 2025 Low-Perplexity LLM-Generated Sequences and Where To Find Them ACL 2025 Low-rank fine-tuning lies between lazy training and feature learning COLT 2025 LR²Bench: Evaluating Long-chain Reflective Reasoning Capabilities of Large Language Models via Constraint Satisfaction Problems ACL 2025 MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces ICML 2025 Make Haste Slowly: A Theory of Emergent Structured Mixed Selectivity in Feature Learning ReLU Networks ICLR 2025 Marginal Benefit Driven RL Teacher for Unsupervised Environment Design AAAI 2025 Mastering Multiple-Expert Routing: Realizable H-Consistency and Strong Guarantees for Learning to Defer ICML 2025 MathGAP: Out-of-Distribution Evaluation on Problems with Arbitrarily Complex Proofs ICLR 2025 Matrix Completion with Incomplete Side Information via Orthogonal Complement Projection ICML 2025 MC-Bench: A Benchmark for Multi-Context Visual Grounding in the Era of MLLMs ICCV 2025 Mean-field analysis of polynomial-width two-layer neural network beyond finite time horizon COLT 2025 Measuring Representational Shifts in Continual Learning: A Linear Transformation Perspective ICML 2025 Measuring Social Biases in Masked Language Models by Proxy of Prediction Quality ACL 2025 Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning NAACL 2025 Memorization in Language Models through the Lens of Intrinsic Dimension ACL 2025 MEReQ: Max-Ent Residual-Q Inverse RL for Sample-Efficient Alignment from Intervention CoRL 2025 Meta-Learning Neural Mechanisms rather than Bayesian Priors ACL 2025