Anthropic’s AI biolab finds ‘CRISPR-like’ DNA in viruses. What’s next?
Post Content
Backdoors Leave Structural Traces: FedMAST for Backdoor Detection and Containment in Federated Learning
arXiv:2609.27760v1 Announce Type: cross Abstract: Federated learning enables distributed training of a shared model without requiring clients to share their…
SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue
arXiv:2609.26780v2 Announce Type: replace-cross Abstract: Long-term conversational memory in multi-party settings requires more than retrieving relevant content from long-term conversations:…
Silent Failures in Agent-Tool Interaction: An Audit of ToolUniverse
arXiv:2609.26836v1 Announce Type: new Abstract: Agentic AI systems are increasingly adopting automated pipelines that integrate multiple tools. While prior research…
QuantWM: Temporally Consistent 2-Bit KV Cache Quantization for World Models and Video Generation
arXiv:2609.26425v2 Announce Type: replace-cross Abstract: KV cache memory has become a major deployment bottleneck for video generation and world models,…
Hard Negatives Reveal What Easy Negatives Hide: Cross-Lingual Harmfulness Representations Degrade with Resource Tier Under Hard Negatives
arXiv:2609.27758v1 Announce Type: cross Abstract: Safety alignment in large language models is trained primarily in English, and recent work reports…