Planet AI Developer Filter
From Detection to Refusal: Safer LLMs via Circuit-Guided Weight Scaling
Abstract page for arXiv paper 2609.00051: From Detection to Refusal: Safer LLMs via Circuit-Guided Weight Scaling
Community feed
doyaken.ai
A focused stream of recent stories from the sources curated for this community. Latest: From Detection to Refusal: Safer LLMs via Circuit-Guided Weight Scaling, GUI-CC: Benchmarking Contextual Consistency of GUI World Models as Agent Environments, and trajectory-judge: What Outcome-Only LLM Judges Miss on Agent Trajectories. Page 176.
Search
Planet AI Developer Filter
GUI-CC: Benchmarking Contextual Consistency of GUI World Models as Agent Environments
Abstract page for arXiv paper 2609.00048: GUI-CC: Benchmarking Contextual Consistency of GUI World Models as Agent Environments
Planet AI Developer Filter
trajectory-judge: What Outcome-Only LLM Judges Miss on Agent Trajectories
Abstract page for arXiv paper 2609.00038: trajectory-judge: What Outcome-Only LLM Judges Miss on Agent Trajectories
Planet AI Developer Filter
Behaviorally Grounded User Profiles from the Wild for Personalized Alignment and Multi-Perspective Reasoning
Abstract page for arXiv paper 2609.00014: Behaviorally Grounded User Profiles from the Wild for Personalized Alignment and Multi-Perspective Reasoning
Planet AI Developer Filter
Assessing Alignment and Stability of Feature Importance Explanations via Weight of Evidence
Abstract page for arXiv paper 2609.00090: Assessing Alignment and Stability of Feature Importance Explanations via Weight of Evidence
Planet AI Developer Filter
Foundation models for electricity price forecasting and battery arbitrage: Can they replace market-specific forecasting models?
Abstract page for arXiv paper 2609.00089: Foundation models for electricity price forecasting and battery arbitrage: Can they replace market-specific forecasting models?
Planet AI Developer Filter
Stochastic complexity of vectors containing cluster structure
Abstract page for arXiv paper 2609.00084: Stochastic complexity of vectors containing cluster structure
Planet AI Developer Filter
RW-LoRA: Communication-Efficient Decentralized LoRA Fine-Tuning via Random Walks
Abstract page for arXiv paper 2609.00078: RW-LoRA: Communication-Efficient Decentralized LoRA Fine-Tuning via Random Walks
Planet AI Developer Filter
Attention Sensitivity Is Not Enough: Dissociating Attention-Level and Behavioural In-Context Learning under Fine-Tuning
Abstract page for arXiv paper 2609.00064: Attention Sensitivity Is Not Enough: Dissociating Attention-Level and Behavioural In-Context Learning under Fine-Tuning
Planet AI Developer Filter
DISTAL: Distillation and Self-Supervised Pretraining for Structure-Agnostic Materials Property Prediction
Abstract page for arXiv paper 2609.00059: DISTAL: Distillation and Self-Supervised Pretraining for Structure-Agnostic Materials Property Prediction
Planet AI Developer Filter
REAL-Q: E2E LLM Quantization via Dynamic Gradient Descent
Abstract page for arXiv paper 2609.00049: REAL-Q: E2E LLM Quantization via Dynamic Gradient Descent
Planet AI Developer Filter
Task-Specific Prompt with Global Context for Multi-Task Graph Pre-Training
Abstract page for arXiv paper 2609.00047: Task-Specific Prompt with Global Context for Multi-Task Graph Pre-Training