11 posts published in the last hour
- 09:33AtomWorld-Mem: Memory-Restored World States for Long-Horizon Atomistic Evolution
- 09:33Externalized CPDAG Summaries Improve LLM Causal Deduction
- 09:33Up and Down the Abstraction Ladder: Code-Based Skills for Language Agents
- 09:32Monitor Jailbreaking: Evading Chain-of-Thought Monitoring Without Encoded Reasoning
- 09:32OmouAI: Argumentative Human-AI Policy Deliberation with Simulated Personas
- 09:04Governed Deduction: Policy-Grounded Premise Authorization Beyond Relevance
- 09:03Factorized axis convolutional gated recurrent unit with dynamic adaptive pooling for remaining useful life prediction of rolling bearings
- 09:03Cheap, open agents make LLM pollution harder to mitigate
- 09:03Neuralyzing the Trace: Selective Representation-Level Unlearning with Contrastive Sparse Autoencoders
- 09:03Who’s liable when AI agents go rogue?
- 09:03Same Text, Different Numbers: The Divergence of LLM-Based Measures