⚡ Transformers - jhcha.oyo · Scour

Selective Coupling of Decoupled Informative Regions: Masked Attention Alignment for Data-Free Quantization of Vision Transformers

🤖AI Academic

Instruction Finetuning DeepSeek-R1-8B Model Using LoRA and NEFTune

🎯Fine-Tuning Academic

Chiaroscuro Attention: Spending Compute in the Dark

⚡Flash Attention Academic

Dynamic Linear Attention

🤖AI Academic

LazyAttention: Efficient Retrieval-Augmented Generation with Deferred Positional Encoding

🤖AI Academic

Look Less, Reason More: Block-wise Attention Skipping for Efficient Multimodal LLMs

👁️Computer Vision Academic

InA-Probe: Instruction-Aware Active Probing for Time Series Forecasting with LLMs

📈Time Series Analysis Academic

Query-based Cross-Modal Projector Bolstering Mamba Multimodal LLM

🤖AI Academic

FuseFSS: Efficient Secure LLM Inference with Function Secret Sharing

💬LLMs Academic

Less-relevant results

Inside the Latent Flow: Causal Deciphering of Attention Dynamics in Audio Separation Foundation Models

📈Optimization Academic

Signed Dual Attention: Capturing Signed Dependencies in Time Series Forecasting

🤖AI Academic

When Vision Misleads, Let Location Speak: A Worldwide Image Geo-Localization Method via Location Attention Mechanism and Large Multimodal Models

🤖AI Academic

Inside the LLM Word Factory

💬Natural Language Processing Academic

Transformer-Enhanced Reinforcement Learning: Fundamentals and Applications in Communication Networks

🤖AI Academic

TextEconomizer: Enhancing Lossy Text Compression with Denoising Transformers and Entropy Coding

🤖AI Academic

ATT-CR: Adaptive Triangular Transformer for Cloud Removal

🧮Complexity Theory Academic

Towards Tight Bounds for Streaming Attention

🤖AI Academic

Depth-Attention: Cross-Layer Value Mixing for Language Models

📈Optimization Academic

Beyond Item IDs: Scaling Short-Form-Video Recommendation via Semantic-Native Long Sequence Modeling

🧮Complexity Theory Academic

Attention at the Theoretical Minimum: A Mathematics of Arrays Framework for Memory-Optimal Transformer Kernels

🤖AI Academic

Log in to enable infinite scrolling