Optimization & Theory

TRAIL: Trust-Aware Client Scheduling for Semi-Decentralized Federated Learning AAAI 2025 Trained Transformer Classifiers Generalize and Exhibit Benign Overfitting In-Context ICLR 2025 Training compute-optimal transformer encoder models EMNLP 2025 Training Deep Neural Networks with Virtual Smoothing Classes AAAI 2025 Training Dynamics Underlying Language Model Scaling Laws: Loss Deceleration and Zero-Sum Learning ACL 2025 Training-free and Adaptive Sparse Attention for Efficient Long Video Generation ICCV 2025 Training-Free and Hardware-Friendly Acceleration for Diffusion Models via Similarity-based Token Pruning AAAI 2025 Training-free LLM Merging for Multi-task Learning ACL 2025 Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights CVPR 2025 Training LLMs with MXFP4 AISTATS 2025 Training Long-Context LLMs Efficiently via Chunk-wise Optimization ACL 2025 Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization Analysis ICLR 2025 Training on the Benchmark Is Not All You Need AAAI 2025 Training Verification-Friendly Neural Networks via Neuron Behavior Consistency AAAI 2025 Training with Fewer Bits: Unlocking Edge LLMs Training with Stochastic Rounding EMNLP 2025 Train It and Forget It: Merge Lists are Unnecessary for BPE Inference in Language Models EMNLP 2025 Transformed Low-rank Adaptation via Tensor Decomposition and Its Applications to Text-to-image Models ICCV 2025 Transformers without Normalization CVPR 2025 Translate Smart, not Hard: Cascaded Translation Systems with Quality-Aware Deferral EMNLP 2025 TREAD: Token Routing for Efficient Architecture-agnostic Diffusion Training ICCV 2025 Treasures in Discarded Weights for LLM Quantization AAAI 2025 TreeKV: Smooth Key-Value Cache Compression with Tree Structures IJCAI 2025 TrimLLM: Progressive Layer Dropping for Domain-Specific LLMs ACL 2025 TripleFact: Defending Data Contamination in the Evaluation of LLM-driven Fake News Detection ACL 2025 TRNAS: A Training-Free Robust Neural Architecture Search ICCV 2025