Optimization & Theory

TAP: A Token-Adaptive Predictor Framework for Training-Free Diffusion Acceleration CVPR 2026 TARE: Lightweight Token-Aware Representation Editing for Fine-tuning Transformer-like Models ACL 2026 TaskIT: Memory-Efficient Fine-Tuning of Multi-LoRA LLMs via Cross-Task Importance Transfer CVPR 2026 TC-Pade: Trajectory-Consistent Pade Approximation for Diffusion Acceleration CVPR 2026 Teacher-Guided Routing for Sparse Vision Mixture-of-Experts CVPR 2026 Teaching the Old Dog New Tricks: Building Efficient Data Pipelines for Large-Scale LLM Pre-Training (Operational Systems) OSDI 2026 Team faisalm3at SemEval-2026 Task 3: From Standard Regression to Distributional Alignment in Dimensional Sentiment Analysis SemEval 2026 Team Habib Disambiguators at SemEval-2026 Task 5: Assessing Semantic Plausibility using Regularized Transformer Fine-Tuning SemEval 2026 TensorLens: End-to-End Transformer Analysis via High-Order Attention Tensors ACL 2026 Tessera: A Holistic Pipeline Parallelism Framework for Trillion-Parameter Heterogeneous MoE Training (Operational Systems) OSDI 2026 Test-Time Alignment of Text-to-Image Diffusion Models via Null-Text Embedding Optimisation CVPR 2026 Test-time Sparsity for Extreme Fast Action Diffusion CVPR 2026 The Convergence Behavior of Adam under Heavy-Tailed Noise UAI 2026 The Devil Is in Gradient Entanglement: Energy-Aware Gradient Coordinator for Robust Generalized Category Discovery CVPR 2026 The Drift Kernel: Why Diffusion Models Change Even When Told Not To CVPR 2026 The Median is Easier than it Looks: Approximation with a Constant-Depth, Linear-Width ReLU Network COLT 2026 Theoretical Compression Bounds for Wide Multilayer Perceptrons COLT 2026 Theory-optimal Quantization Based on Flatness ACL 2026 The Power of Decaying Steps: Enhancing Attack Stability and Transferability for Sign-based Optimizers CVPR 2026 The Retrieval Bottleneck: Scaling Laws for Reinforcement Learning in RAG ACL 2026 The Silence of the Facts: Popularity as a Barrier to Machine Unlearning ACL 2026 ThinkBooster: A Unified Framework for Seamless Test-Time Scaling of LLM Reasoning ACL 2026 ThinkingViT: Matryoshka Thinking Vision Transformer for Elastic Inference CVPR 2026 Think Less, Code Better: Probing When Chain-of-Thought Hurts and How to Route Around It ACL 2026 TileLoom: Automatic Dataflow Planning for Tile-Based Languages on Spatial Dataflow Accelerators OSDI 2026