💬 LLMs - sworddish · Scour

MechLens: Late Crystallization of Factual Knowledge Explains Intervention Effectiveness in Language Models

🃏Imperfect Information Games Academic

TrustMargin: Training-Free Arbitration between Parametric Memory and Retrieved Evidence in Large Language Models

🃏Imperfect Information Games Academic

Operationalizing Linguistic Methods through Prompt-Engineering Skills: An Automatic Chinese Web Neologism Detection Pipeline

📐Formal Languages Academic

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

🧩Neural-Symbolic AI Academic

LoRi: Low-Rank Distillation for Implicit Reasoning

🃏Imperfect Information Games Academic

NGram-MoSE: Efficient Remote Sensing Super-Resolution via N-Gram Context and Mixture-of-Experts

📐Formal Languages Academic

How Small Can You Go? LoRA Fine-Tuning 270M-8B Models for Merchant Information Extraction in Financial Transactions

🧪Agent Evaluation Academic

AISC deployment in dynamic UAV-assisted MEC network: a reinforcement learning method based on heterogeneous graph attention neural network

🌳Decision-Time Planning Academic

APEX4: Efficient Pure W4A4 LLM Inference via Intra-SM Compute Rebalancing

🧩Neural-Symbolic AI Academic

Less-relevant results

LoomVideo: Unifying Multimodal Inputs into Video Generation and Editing

🃏Imperfect Information Games Academic

Principled Agent Debate: Adversarial Arbitration for Sycophancy Reduction in Large Language Models

🧪Agent Evaluation Academic

AttentionCap: Transformer Based Capacitance Matrix Learning Toward Full-Chip Extraction

🧩Neural-Symbolic AI Academic

Reconstructing Multi-Decadal Forest Disturbances: A Spatio-Temporal Transformer Approach

🃏Imperfect Information Games Academic

A Mechanistic Analysis of Adversarial Fine-tuning of Vision Transformers

🧪Agent Evaluation Academic

Pre-Intervention Prediction of Sparse Autoencoder Steering Side Effects

🃏Imperfect Information Games Academic

Optimal Post-Training Quantization Scales and Where to Find Them

🧩Neural-Symbolic AI Academic

Learned Subspace Compression for Communication-Efficient Pipeline Parallelism

🧩Neural-Symbolic AI Academic

Phantom transitions in language model fine-tuning

📐Formal Languages Academic

AQIFormer: A Transformer-Based Multi-View Architecture for Cross-City Air Quality Classification

🧪Agent Evaluation Academic

Hidden Consensus:Preference-Validity Compression in Human Feedback

🧪Agent Evaluation Academic

No more posts from sworddish's subscribed feeds.

Scour all 25258 feeds Learn more about Feeds

Sign up or log in to see more results

Log in to enable infinite scrolling