💬 NLP - dungngo · Scour

LLMCodec: Adapting Video Codecs for Efficient Weight Compression of Large Language Models

🧠Neural Architecture Academic

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

🧠Neural Architecture Academic

SpikeDecoder: Realizing the GPT Architecture with Spiking Neural Networks

🧠Neural Architecture Academic

SafeRun: Enabling Determinism in LLM Planning for Running

🔄MLOps Academic

Dual-Stance Evaluation of Sycophancy: The Structure of Agreement and the Limits of Intervention

🧠Neural Architecture Academic

Auditing Training Data in Domain-adapted LLMs: LoRA-MINT

🔄MLOps Academic

A retrieval conditioned rebinding circuit for dynamic entity tracking in large language models

📊Embeddings Academic

MODF-SIR: A Multi-agent Omni-modal Distilled Framework for Social Intelligence Reasoning

📱Edge AI Academic

Reducing Hallucinations in Complex Question Answering using Simple Graph-based Retrieval-Augmented Generation (long version)

📊Embeddings Academic

Automatic Extraction of Structured Information from Brain MRI Reports Using an Open-Weight Large Language Model

📊Embeddings Academic

Post-training is (Massive) Supervised Learning

🧠AI Academic

The Structural Attention Tax: How Retrieval Format Hijacks In-Context Learning Independent of Content

📊Embeddings Academic

Minimizing the Hidden Cost of Scales: Graph-Guided Ultra-Low-Bit Quantization for Large Language Models

🧠Neural Architecture Academic

LLM-Based Code Documentation Generation and Multi-Judge Evaluation

⚙️LLVM Academic

When Roleplaying, Do Models Believe What They Say?

🔄MLOps Academic

Shared Latent Structures Enable Unified Backdoor Detection and Mitigation in LLMs

📱Edge AI Academic

Ten Headache Specialists versus Artificial Intelligence for Clinical Literature Summarization: A Critical Evaluation and Comparison

📱Edge AI Academic

Steganography Without Modification: Hidden Communication via LLM Seeds

📊Embeddings Academic

arxiv.org··Hacker News

Augmenting Molecular Language Models with Local $n$-gram Memory

📊Embeddings Academic

FuseFSS: Efficient Secure LLM Inference with Function Secret Sharing

⚙️LLVM Academic

Log in to enable infinite scrolling