AITOPIC / AI NewsAI NewsACCT: Asymmetric Cross-LLM Context Transfer Enables Efficient KV Cache Reuse Across Models
AITOPIC / AI NewsAI NewsAudit Finds LLM Health Advice Varies by User Persona, Factual Floor Helps but Not Uniformly
AITOPIC / AI NewsAI NewsSecPO: Adversarial Training and New Loss Cut Prompt Injection Attack Success Rates Dramatically
AITOPIC / AI NewsAI NewsDAMI: Dual-Axis Memory Initialization Boosts Long-Context Retrieval in Gated Linear Attention
AITOPIC / AI NewsAI NewsETAPS: Gradual Pruning with Sparse Adaptation Achieves High Quality at Extreme Sparsity
AITOPIC / AI NewsAI NewsGeneral-purpose foundation models outperform specialized chemical FMs on property prediction with scarce data
AITOPIC / AI NewsAI NewsAI evaluators favor job applications written by certain AI models, independent of candidate quality
AITOPIC / AI NewsAI NewsDynamical Memory Transformer: Selective Recurrent Memories with Constant Cost Attention
AITOPIC / AI NewsAI NewsLatent-Lens: Enabling Visual Perception in Small Language Models via Latent Communication
AITOPIC / AI NewsAI NewsVLA Policies Do Not Know When Not to Act: Unintended Task Execution and Start Suppression
