LLaVA-MORE: A Comparative Study of LLMs and Visual Backbones for Enhanced Visual Instruction Tuning
"模型性能" 相关文章
FLOSS: Federated Learning with Opt-Out and Straggler Support
Causal Reasoning in Pieces: Modular In-Context Learning for Causal Discovery
VL-Cogito: Progressive Curriculum Reinforcement Learning for Advanced Multimodal Reasoning
Too Much Thinking Can Break LLMs: Inverse Scaling in Test-Time Compute
Detection Transformers Under the Knife: A Neuroscience-Inspired Approach to Ablations
ToolACE: Winning the Points of LLM Function Calling
Neural Corrective Machine Unranking
Sticking to the Mean: Detecting Sticky Tokens in Text Embedding Models
NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database
On the Performance of Concept Probing: The Influence of the Data (Extended Version)
AQuilt: Weaving Logic and Self-Inspection into Low-Cost, High-Relevance Data Synthesis for Specialist LLMs
Benchmarking Amazon Nova: A comprehensive analysis through MT-Bench and Arena-Hard-Auto
Constructing Ophthalmic MLLM for Positioning-diagnosis Collaboration Through Clinical Cognitive Chain Reasoning
LLM Data Selection and Utilization via Dynamic Bi-level Optimization
最新爆料揭露苹果顶级AI开发者接连离开的幕后秘辛
最新爆料揭露蘋果頂級AI開發者接連離開的幕後秘辛
DFQ-ViT: Data-Free Quantization for Vision Transformers without Fine-tuning
It's Not That Simple. An Analysis of Simple Test-Time Scaling
SMART: Relation-Aware Learning of Geometric Representations for Knowledge Graphs
