downstream task

Adaptive Dynamic Dehazing via Instruction-Driven and Task-Feedback Closed-Loop Optimization for Diverse Downstream Task Adaptation AAAI 2026 CaptionQA: Is Your Caption as Useful as the Image Itself? CVPR 2026 EEG-DLite: Dataset Distillation for Efficient Large EEG Model Training AAAI 2026 Understanding and Mitigating Bias Inheritance in LLM-based Data Augmentation on Downstream Tasks ACL 2026 A Context-Aware Approach for Enhancing Data Imputation with Pre-trained Language Models COLING 2025 AdaDHP: Fine-Grained Fine-Tuning via Dual Hadamard Product and Adaptive Parameter Selection ACL 2025 All Roads Lead to Rome: Graph-Based Confidence Estimation for Large Language Model Reasoning EMNLP 2025 A Pipeline to Assess Merging Methods via Behavior and Internals EMNLP 2025 Are Language Models Agnostic to Linguistically Grounded Perturbations? A Case Study of Indic Languages NAACL 2025 Are Sparse Autoencoders Useful? A Case Study in Sparse Probing ICML 2025 A Simple and Comprehensive Benchmark for Single-Cell Transcriptomics AAAI 2025 A Survey on Foundation Language Models for Single-cell Biology ACL 2025 A Survey on Temporal Interaction Graph Representation Learning: Progress, Challenges, and Opportunities IJCAI 2025 Attribute-based Visual Reprogramming for Vision-Language Models ICLR 2025 Auto Cherry-Picker: Learning from High-quality Generative Data Driven by Language CVPR 2025 Bridging the Faithfulness Gap in Prototypical Models NAACL 2025 Can Perplexity Predict Finetuning Performance? An Investigation of Tokenization Effects on Sequential Language Models for Nepali ACL 2025 Capability Salience Vector: Fine-grained Alignment of Loss and Capabilities for Downstream Task Scaling Law ACL 2025 DIDS: Domain Impact-aware Data Sampling for Large Language Model Training EMNLP 2025 EmbedLLM: Learning Compact Representations of Large Language Models ICLR 2025 Error-driven Data-efficient Large Multimodal Model Tuning ACL 2025 Explanations explained. Influence of Free-text Explanations on LLMs and the Role of Implicit Knowledge EMNLP 2025 Exploring Learning Complexity for Efficient Downstream Dataset Pruning ICLR 2025 Exploring the Effectiveness of Object-Centric Representations in Visual Question Answering: Comparative Insights with Foundation Models ICLR 2025 Flexora: Flexible Low-Rank Adaptation for Large Language Models ACL 2025