2025

• 25 Oct FLAME: Frozen Large Language Models Enable Data-Efficient Language-Image Pre-training
• 22 Oct Randomly Removing 50% of Dimensions in Text Embeddings has Minimal Impact on Retrieval and Classification Tasks
• 20 Oct LoSiA: Efficient High-Rank Fine-Tuning via Subnet Localization and Optimization
• 06 Oct Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels
• 04 Oct Training LLMs to be Better Text Embedders through Bidirectional Reconstruction
• 28 Sep Boosting Data Utilization for Multilingual Dense Retrieval
• 25 Sep Conan-Embedding-v2: Training an LLM from Scratch for Text Embeddings
• 21 Sep Differential-informed Sample Selection Accelerates Multimodal Contrastive Learning
• 20 Sep Aligning Information Capacity Between Vision and Language via Dense-to-Sparse Feature Distillation for Image-Text Matching
• 13 Sep Negative Matters: Multi-Granularity Hard-Negative Synthesis and Anchor-Token-Aware Pooling for Enhanced Text Embeddings
• 08 Sep Fixing Data That Hurts Performance: Cascading LLMs to Relabel Hard Negatives for Robust Information Retrieval
• 07 Sep SyNeg: LLM-Driven Synthetic Hard-Negatives for Dense Retrieval
• 31 Aug OG-RAG: Ontology-Grounded Retrieval-Augmented Generation for Large Language Models
• 28 Aug SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs
• 27 Aug FinLoRA : Benchmarking LoRA Methods for Fine-Tuning LLMs on Financial Datasets
• 24 Aug Quantifying Uncertainty in Answers from Any Language Model and Enhancing Their Trustworthiness
• 23 Aug Chain-of-Thought Prompting Obscures Hallucination Cues in Large Language Models: An Empirical Evaluation
• 19 Aug SCAR: Data Selection via Style Consistency-Aware Response Ranking for Efficient Instruction-Tuning of Large Language Models
• 17 Aug Smurfs: Multi-Agent System using Context-Efficient DFSDT for Tool Planning
• 16 Aug Re-Invoke: Tool Invocation Rewriting for Zero-Shot Tool Retrieval