arXiv:2609.03526v1 Announce Type: new Abstract: Multimodal language models achieve near-ceiling scores on food recognition benchmarks, yet it remains…
Tag: AI
Feature Reconfiguration With Visual Prior for Medical Lesion Segmentation
arXiv:2609.03535v1 Announce Type: new Abstract: Lesion segmentation in medical images plays a critical role in clinical diagnosis and treatment planning.…
NeoRed: A Knowledge-Logic-Alignment Multimodal Large Language Model for Neonatal Respiratory Disease Diagnosis
arXiv:2609.03527v1 Announce Type: new Abstract: Neonatal respiratory diseases are a major cause of neonatal morbidity and mortality, posing substantial…
Dalek: A Constructive Agent Machine
arXiv:2609.03546v1 Announce Type: new Abstract: We present Dalek, a closed machine designed for agents that realizes self-maintenance, self-evolution,…
AutoGraphForge: Towards Automated Graph Theory Discovery
arXiv:2609.03478v1 Announce Type: new Abstract: We report on our ongoing project to develop a computational pipeline, AutoGraphForge, for an automated…
PPO-STGNN: A Proximal Policy Optimization Approach with Spatio-Temporal Graph Neural Networks for DAG Task Scheduling in Cloud-Edge-End Computing
arXiv:2609.03503v1 Announce Type: new Abstract: With the rapid development of the Internet of Things, computation intensive directed acyclic graph (DAG)…
What Matters for Aggressive Decoding-Time KV Eviction? Temporal Aggregation and Ranking Preservation
arXiv:2609.03515v1 Announce Type: new Abstract: Decoding-time KV cache compression research focuses heavily on designing better token scoring functions,…
GrowPage: On-Demand KV Budgeting for Efficient LLM Reasoning Serving
arXiv:2609.03494v1 Announce Type: new Abstract: Long-output reasoning has made the key–value (KV) cache a critical memory bottleneck for efficient LLM…
OpenAI’s new reasoning technique alarms AI safety experts
OpenAI’s new Astra model will use “recurrent depth,” a technique that allows the model to operate outside of the sequential thinking that characterizes…
Making Every Tool Call Count: Necessary Tool-Evidence Path Rewards for Agentic Vision-Language Models
arXiv:2609.03493v1 Announce Type: new Abstract: Modern vision-language models (VLMs) can directly answer many image-grounded questions, yet they often…