conftrace_

Optimization & Theory

7,804 papers (27 classified directly here)

Subtopics · a paper can sit in several, so these overlap

Optimization (1,960) Model Compression (1,896) Efficient Computing (1,780) Theory (1,239) Neural Network Optimization (1,004) Evaluation (533) Regularization (177) Loss Functions (157) Interpretability (128) Stochastic Methods (119) Generalization (115) Sparse Optimization (25)

Papers per year

8

7

12

6

16

9

25

48

45

60

94

150

295

436

675

803

1,010

944

1,346

1,352

463

'10

'15

'20

'25

Papers (including subtopics)

Boosting Vision State Space Model with Fractal Scanning AAAI 2025 Boost Your Human Image Generation Model via Direct Preference Optimization CVPR 2025 Both Asymptotic and Non-Asymptotic Convergence of Quasi-Hyperbolic Momentum using Increasing Batch Size ACML 2025 Boundary-Conscious Pruning: Hard Set-Aware Model Compression for Efficient Speaker Recognition Interspeech 2025 Breaking the Encoder Barrier for Seamless Video-Language Understanding ICCV 2025 Bridging the Gap Between Hyperdimensional Computing and Kernel Methods via the Nyström Method AAAI 2025 Bringing Interpretability to Neural Audio Codecs Interspeech 2025 Bringing RNNs Back to Efficient Open-Ended Video Understanding ICCV 2025 BSDB-Net: Band-Split Dual-Branch Network with Selective State Spaces Mechanism for Monaural Speech Enhancement AAAI 2025 Building Vision Models upon Heat Conduction CVPR 2025 Bypass Back-propagation: Optimization-based Structural Pruning for Large Language Models via Policy Gradient ACL 2025 C3oT: Generating Shorter Chain-of-Thought Without Compromising Effectiveness AAAI 2025 Cacheback: Speculative Decoding With Nothing But Cache EMNLP 2025 CalibraEval: Calibrating Prediction Distribution to Mitigate Selection Bias in LLMs-as-Judges ACL 2025 Calibration Across Layers: Understanding Calibration Evolution in LLMs EMNLP 2025 Calm Composite Losses: Being Improper Yet Proper Composite AISTATS 2025 Can Transformers Do Enumerative Geometry? ICLR 2025 Can We Achieve Efficient Diffusion Without Self-Attention? Distilling Self-Attention into Convolutions ICCV 2025 CARE Transformer: Mobile-Friendly Linear Visual Transformer via Decoupled Dual Interaction CVPR 2025 CASP: Compression of Large Multimodal Models Based on Attention Sparsity CVPR 2025 Cauchy-Schwarz Regularizers ICLR 2025 CENTAUR: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference ACL 2025 Certifiably Quantisation-Robust training and inference of Neural Networks AISTATS 2025 Certified Mitigation of Worst-Case LLM Copyright Infringement EMNLP 2025 Channel Merging: Preserving Specialization for Merged Experts AAAI 2025