Neural Network Optimization

A Training-Free Length Extrapolation Approach for LLMs: Greedy Attention Logit Interpolation EMNLP 2025 Attention Entropy is a Key Factor: An Analysis of Parallel Context Encoding with Full-attention-based Pre-trained Language Models ACL 2025 Autocorrelation Matters: Understanding the Role of Initialization Schemes for State Space Models ICLR 2025 Automatic Expert Discovery in LLM Upcycling via Sparse Interpolated Mixture-of-Experts ACL 2025 AutoMMLab: Automatically Generating Deployable Models from Language Instructions for Computer Vision Tasks AAAI 2025 Avoiding spurious sharpness minimization broadens applicability of SAM ICML 2025 B2Opt: Learning to Optimize Black-box Optimization with Little Budget AAAI 2025 Balancing Model Efficiency and Performance: Adaptive Pruner for Long-tailed Data ICML 2025 Balcony: A Lightweight Approach to Dynamic Inference of Generative Language Models EMNLP 2025 BeamLoRA: Beam-Constraint Low-Rank Adaptation ACL 2025 Better Embeddings with Coupled Adam ACL 2025 Beyond Linear Steering: Unified Multi-Attribute Control for Language Models EMNLP 2025 Beyond Losses Reweighting: Empowering Multi-Task Learning via the Generalization Perspective ICCV 2025 Beyond Zero Initialization: Investigating the Impact of Non-Zero Initialization on LoRA Fine-Tuning Dynamics ICML 2025 Boosting Adversarial Transferability via Residual Perturbation Attack ICCV 2025 Boosting Policy and Process Reward Models with Monte Carlo Tree Search in Open-Domain QA ACL 2025 Breaking Neural Network Scaling Laws with Modularity ICLR 2025 Breaking the Attention Trap in Code LLMs: A Rejection Sampling Approach to Enhance Code Execution Prediction EMNLP 2025 Breaking the Stage Barrier: A Novel Single-Stage Approach to Long Context Extension for Large Language Models COLING 2025 BSFA: Leveraging the Subspace Dichotomy to Accelerate Neural Network Training EMNLP 2025 BUINUS at IWSLT: Evaluating the Impact of Data Augmentation and QLoRA-based Fine-Tuning for Maltese to English Speech Translation ACL 2025 Cacheback: Speculative Decoding With Nothing But Cache EMNLP 2025 Capacity Matters: a Proof-of-Concept for Transformer Memorization on Real-World Data ACL 2025 CARFT: Boosting LLM Reasoning via Contrastive Learning with Annotated Chain-of-Thought-based Reinforced Fine-Tuning EMNLP 2025 CARP: Visuomotor Policy Learning via Coarse-to-Fine Autoregressive Prediction ICCV 2025