Planet AI Developer Filter
BCMT: Blockwise Causal Memory Transformer
Abstract page for arXiv paper 2608.13578: BCMT: Blockwise Causal Memory Transformer
Community feed
doyaken.ai
A focused stream of recent stories from the sources curated for this community. Latest: BCMT: Blockwise Causal Memory Transformer, Not All Tokens Are Equal: Inflation-Aware Routing for Agentic LLM Systems, and Does a Language Server Save Tokens for Coding Agents? A Measurement Methodology and Preliminary Study. Page 334.
Search
Planet AI Developer Filter
Not All Tokens Are Equal: Inflation-Aware Routing for Agentic LLM Systems
Abstract page for arXiv paper 2608.13571: Not All Tokens Are Equal: Inflation-Aware Routing for Agentic LLM Systems
Planet AI Developer Filter
Does a Language Server Save Tokens for Coding Agents? A Measurement Methodology and Preliminary Study
Abstract page for arXiv paper 2608.13568: Does a Language Server Save Tokens for Coding Agents? A Measurement Methodology and Preliminary Study
Topics: Coding Agents
Entities: Coding Agents
Planet AI Developer Filter
EEG-PRISM: Physiologically-Grounded Interpretability of Predictions by EEG Foundation Models
Abstract page for arXiv paper 2608.13676: EEG-PRISM: Physiologically-Grounded Interpretability of Predictions by EEG Foundation Models
Planet AI Developer Filter
From BERT to Frontier Agents: Eight Years of Language-Model Progress, the Collapse of the Capability-Cost Curve, and the Rise of Task-Targeted Models
Abstract page for arXiv paper 2608.13675: From BERT to Frontier Agents: Eight Years of Language-Model Progress, the Collapse of the Capability-Cost Curve, and the Rise of Task-Targeted Models
Planet AI Developer Filter
The Query Knows What to Forget: A Second Erase Direction for Linear Attention
Abstract page for arXiv paper 2608.13668: The Query Knows What to Forget: A Second Erase Direction for Linear Attention
Planet AI Developer Filter
Contrastive Learning for Interpretable Anomaly Detection at Collider Experiments
Abstract page for arXiv paper 2608.13652: Contrastive Learning for Interpretable Anomaly Detection at Collider Experiments
Planet AI Developer Filter
Robust Dual-Model Collaborative Random Vector Functional Link Network
Abstract page for arXiv paper 2608.13628: Robust Dual-Model Collaborative Random Vector Functional Link Network
Planet AI Developer Filter
Training-Free Knowledge Transfer Across Model Scales through Activation-Guided Pruning
Abstract page for arXiv paper 2608.13596: Training-Free Knowledge Transfer Across Model Scales through Activation-Guided Pruning
Planet AI Developer Filter
Don't Claim Benchmark-Oriented Optimization Improves General Coding Capability -- Diverse Evaluation Is Required
Abstract page for arXiv paper 2608.13566: Don't Claim Benchmark-Oriented Optimization Improves General Coding Capability -- Diverse Evaluation Is Required
Planet AI Developer Filter
Measuring Cross-Task Behavioral Consistency in Language Model Agents
Abstract page for arXiv paper 2608.13598: Measuring Cross-Task Behavioral Consistency in Language Model Agents
Planet AI Developer Filter
Agentao: A Governed Local-First Runtime for Tool-Using LLM Agents
Abstract page for arXiv paper 2608.13574: Agentao: A Governed Local-First Runtime for Tool-Using LLM Agents